```
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/05 08:44:01 ===> Configurations
thomas 04/05 08:44:01     model: Res16UNet34C
thomas 04/05 08:44:01     conv1_kernel_size: 3
thomas 04/05 08:44:01     weights: None
thomas 04/05 08:44:01     weights_for_inner_model: False
thomas 04/05 08:44:01     dilations: [1, 1, 1, 1]
thomas 04/05 08:44:01     wrapper_type: None
thomas 04/05 08:44:01     wrapper_region_type: 1
thomas 04/05 08:44:01     wrapper_kernel_size: 3
thomas 04/05 08:44:01     wrapper_lr: 0.1
thomas 04/05 08:44:01     meanfield_iterations: 10
thomas 04/05 08:44:01     crf_spatial_sigma: 1
thomas 04/05 08:44:01     crf_chromatic_sigma: 12
thomas 04/05 08:44:01     optimizer: SGD
thomas 04/05 08:44:01     lr: 0.1
thomas 04/05 08:44:01     sgd_momentum: 0.9
thomas 04/05 08:44:01     sgd_dampening: 0.1
thomas 04/05 08:44:01     adam_beta1: 0.9
thomas 04/05 08:44:01     adam_beta2: 0.999
thomas 04/05 08:44:01     weight_decay: 0.0001
thomas 04/05 08:44:01     param_histogram_freq: 100
thomas 04/05 08:44:01     save_param_histogram: False
thomas 04/05 08:44:01     iter_size: 1
thomas 04/05 08:44:01     bn_momentum: 0.02
thomas 04/05 08:44:01     scheduler: PolyLR
thomas 04/05 08:44:01     max_iter: 120000
thomas 04/05 08:44:01     step_size: 20000.0
thomas 04/05 08:44:01     step_gamma: 0.1
thomas 04/05 08:44:01     poly_power: 0.9
thomas 04/05 08:44:01     exp_gamma: 0.95
thomas 04/05 08:44:01     exp_step_size: 445
thomas 04/05 08:44:01     log_dir: ./outputs/ScanNet-default/2020-04-05_08-43-59
thomas 04/05 08:44:01     data_dir: data
thomas 04/05 08:44:01     dataset: ScannetVoxelization2cmDataset
thomas 04/05 08:44:01     temporal_dilation: 30
thomas 04/05 08:44:01     temporal_numseq: 3
thomas 04/05 08:44:01     point_lim: -1
thomas 04/05 08:44:01     pre_point_lim: -1
thomas 04/05 08:44:01     batch_size: 4
thomas 04/05 08:44:01     val_batch_size: 1
thomas 04/05 08:44:01     test_batch_size: 1
thomas 04/05 08:44:01     cache_data: False
thomas 04/05 08:44:01     num_workers: 0
thomas 04/05 08:44:01     num_val_workers: 1
thomas 04/05 08:44:01     ignore_label: 255
thomas 04/05 08:44:01     return_transformation: False
thomas 04/05 08:44:01     ignore_duplicate_class: False
thomas 04/05 08:44:01     partial_crop: 0.0
thomas 04/05 08:44:01     train_limit_numpoints: 120000000
thomas 04/05 08:44:01     synthia_path: /home/chrischoy/datasets/Synthia/Synthia4D
thomas 04/05 08:44:01     synthia_camera_path: /home/chrischoy/datasets/Synthia/%s/CameraParams/
thomas 04/05 08:44:01     synthia_camera_intrinsic_file: intrinsics.txt
thomas 04/05 08:44:01     synthia_camera_extrinsics_file: Stereo_Right/Omni_F/%s.txt
thomas 04/05 08:44:01     temporal_rand_dilation: False
thomas 04/05 08:44:01     temporal_rand_numseq: False
thomas 04/05 08:44:01     scannet_path: /home/tcn02/SpatioTemporalSegmentation/data/scannet/processed/train
thomas 04/05 08:44:01     stanford3d_path: /home/chrischoy/datasets/Stanford3D
thomas 04/05 08:44:01     is_train: True
thomas 04/05 08:44:01     stat_freq: 40
thomas 04/05 08:44:01     test_stat_freq: 100
thomas 04/05 08:44:01     save_freq: 1000
thomas 04/05 08:44:01     val_freq: 1000
thomas 04/05 08:44:01     empty_cache_freq: 1
thomas 04/05 08:44:01     train_phase: train
thomas 04/05 08:44:01     val_phase: val
thomas 04/05 08:44:01     overwrite_weights: True
thomas 04/05 08:44:01     resume: None
thomas 04/05 08:44:01     resume_optimizer: True
thomas 04/05 08:44:01     eval_upsample: False
thomas 04/05 08:44:01     lenient_weight_loading: False
thomas 04/05 08:44:01     use_feat_aug: True
thomas 04/05 08:44:01     data_aug_color_trans_ratio: 0.1
thomas 04/05 08:44:01     data_aug_color_jitter_std: 0.05
thomas 04/05 08:44:01     normalize_color: True
thomas 04/05 08:44:01     data_aug_scale_min: 0.9
thomas 04/05 08:44:01     data_aug_scale_max: 1.1
thomas 04/05 08:44:01     data_aug_hue_max: 0.5
thomas 04/05 08:44:01     data_aug_saturation_max: 0.2
thomas 04/05 08:44:01     visualize: False
thomas 04/05 08:44:01     test_temporal_average: False
thomas 04/05 08:44:01     visualize_path: outputs/visualize
thomas 04/05 08:44:01     save_prediction: False
thomas 04/05 08:44:01     save_pred_dir: outputs/pred
thomas 04/05 08:44:01     test_phase: test
thomas 04/05 08:44:01     evaluate_original_pointcloud: False
thomas 04/05 08:44:01     test_original_pointcloud: False
thomas 04/05 08:44:01     is_cuda: True
thomas 04/05 08:44:01     load_path: 
thomas 04/05 08:44:01     log_step: 50
thomas 04/05 08:44:01     log_level: INFO
thomas 04/05 08:44:01     num_gpu: 1
thomas 04/05 08:44:01     seed: 123
thomas 04/05 08:44:01 ===> Initializing dataloader
thomas 04/05 08:44:01 Loading ScannetVoxelization2cmDataset: scannetv2_train.txt
thomas 04/05 08:44:01 Loading ScannetVoxelization2cmDataset: scannetv2_val.txt
thomas 04/05 08:44:01 ===> Building model
thomas 04/05 08:44:01 ===> Number of trainable parameters: Res16UNet34C: 37846644
thomas 04/05 08:44:01 Res16UNet34C(
  (conv0p1s1): MinkowskiConvolution(in=3, out=32, region_type=RegionType.HYPERCUBE, kernel_size=[3, 3, 3], stride=[1, 1, 1], dilation=[1, 1, 1])
  (bn0): MinkowskiBatchNorm(32, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
  (conv1p1s2): MinkowskiConvolution(in=32, out=32, region_type=RegionType.HYPERCUBE, kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1])
  (bn1): MinkowskiBatchNorm(32, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
  (block1): Sequential(
    (0): BasicBlock(
      (conv1): MinkowskiConvolution(in=32, out=32, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=32, out=32, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
    (1): BasicBlock(
      (conv1): MinkowskiConvolution(in=32, out=32, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=32, out=32, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
  )
  (conv2p2s2): MinkowskiConvolution(in=32, out=32, region_type=RegionType.HYPERCUBE, kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1])
  (bn2): MinkowskiBatchNorm(32, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
  (block2): Sequential(
    (0): BasicBlock(
      (conv1): MinkowskiConvolution(in=32, out=64, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=64, out=64, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
      (downsample): Sequential(
        (0): MinkowskiConvolution(in=32, out=64, region_type=RegionType.HYPERCUBE, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): MinkowskiConvolution(in=64, out=64, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=64, out=64, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
    (2): BasicBlock(
      (conv1): MinkowskiConvolution(in=64, out=64, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=64, out=64, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
  )
  (conv3p4s2): MinkowskiConvolution(in=64, out=64, region_type=RegionType.HYPERCUBE, kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1])
  (bn3): MinkowskiBatchNorm(64, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
  (block3): Sequential(
    (0): BasicBlock(
      (conv1): MinkowskiConvolution(in=64, out=128, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=128, out=128, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
      (downsample): Sequential(
        (0): MinkowskiConvolution(in=64, out=128, region_type=RegionType.HYPERCUBE, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): MinkowskiConvolution(in=128, out=128, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=128, out=128, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
    (2): BasicBlock(
      (conv1): MinkowskiConvolution(in=128, out=128, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=128, out=128, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
    (3): BasicBlock(
      (conv1): MinkowskiConvolution(in=128, out=128, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=128, out=128, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
  )
  (conv4p8s2): MinkowskiConvolution(in=128, out=128, region_type=RegionType.HYPERCUBE, kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1])
  (bn4): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
  (block4): Sequential(
    (0): BasicBlock(
      (conv1): MinkowskiConvolution(in=128, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
      (downsample): Sequential(
        (0): MinkowskiConvolution(in=128, out=256, region_type=RegionType.HYPERCUBE, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
    (2): BasicBlock(
      (conv1): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
    (3): BasicBlock(
      (conv1): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
    (4): BasicBlock(
      (conv1): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
    (5): BasicBlock(
      (conv1): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
  )
  (convtr4p16s2): MinkowskiConvolutionTranspose(in=256, out=256, region_type=RegionType.HYPERCUBE, kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1])
  (bntr4): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
  (block5): Sequential(
    (0): BasicBlock(
      (conv1): MinkowskiConvolution(in=384, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
      (downsample): Sequential(
        (0): MinkowskiConvolution(in=384, out=256, region_type=RegionType.HYPERCUBE, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=256, out=256, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
  )
  (convtr5p8s2): MinkowskiConvolutionTranspose(in=256, out=128, region_type=RegionType.HYPERCUBE, kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1])
  (bntr5): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
  (block6): Sequential(
    (0): BasicBlock(
      (conv1): MinkowskiConvolution(in=192, out=128, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=128, out=128, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
      (downsample): Sequential(
        (0): MinkowskiConvolution(in=192, out=128, region_type=RegionType.HYPERCUBE, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): MinkowskiConvolution(in=128, out=128, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=128, out=128, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
  )
  (convtr6p4s2): MinkowskiConvolutionTranspose(in=128, out=96, region_type=RegionType.HYPERCUBE, kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1])
  (bntr6): MinkowskiBatchNorm(96, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
  (block7): Sequential(
    (0): BasicBlock(
      (conv1): MinkowskiConvolution(in=128, out=96, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=96, out=96, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
      (downsample): Sequential(
        (0): MinkowskiConvolution(in=128, out=96, region_type=RegionType.HYPERCUBE, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(96, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): MinkowskiConvolution(in=96, out=96, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=96, out=96, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
  )
  (convtr7p2s2): MinkowskiConvolutionTranspose(in=96, out=96, region_type=RegionType.HYPERCUBE, kernel_size=[2, 2, 2], stride=[2, 2, 2], dilation=[1, 1, 1])
  (bntr7): MinkowskiBatchNorm(96, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
  (block8): Sequential(
    (0): BasicBlock(
      (conv1): MinkowskiConvolution(in=128, out=96, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=96, out=96, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
      (downsample): Sequential(
        (0): MinkowskiConvolution(in=128, out=96, region_type=RegionType.HYPERCUBE, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
        (1): MinkowskiBatchNorm(96, eps=1e-05, momentum=0.02, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): MinkowskiConvolution(in=96, out=96, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm1): MinkowskiBatchNorm(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): MinkowskiConvolution(in=96, out=96, region_type=RegionType.HYBRID, kernel_volume=27, stride=[1, 1, 1], dilation=[1, 1, 1])
      (norm2): MinkowskiBatchNorm(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): MinkowskiReLU()
    )
  )
  (final): MinkowskiConvolution(in=96, out=20, region_type=RegionType.HYPERCUBE, kernel_size=[1, 1, 1], stride=[1, 1, 1], dilation=[1, 1, 1])
  (relu): MinkowskiReLU()
)
thomas 04/05 08:44:04 ===> Start training
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/05 08:44:09 ===> Epoch[1](1/301): Loss 3.2784	LR: 1.000e-01	Score 2.309	Data time: 1.8454, Total iter time: 4.9082
thomas 04/05 08:47:53 ===> Epoch[1](40/301): Loss 1.8782	LR: 9.997e-02	Score 53.877	Data time: 2.2507, Total iter time: 5.6748
thomas 04/05 08:51:58 ===> Epoch[1](80/301): Loss 1.6332	LR: 9.994e-02	Score 57.308	Data time: 2.3812, Total iter time: 6.0507
thomas 04/05 08:55:50 ===> Epoch[1](120/301): Loss 1.5430	LR: 9.991e-02	Score 58.973	Data time: 2.1889, Total iter time: 5.7207
thomas 04/05 08:59:52 ===> Epoch[1](160/301): Loss 1.4221	LR: 9.988e-02	Score 62.160	Data time: 2.3323, Total iter time: 5.9758
thomas 04/05 09:03:41 ===> Epoch[1](200/301): Loss 1.3073	LR: 9.985e-02	Score 63.635	Data time: 2.2323, Total iter time: 5.6586
thomas 04/05 09:07:29 ===> Epoch[1](240/301): Loss 1.3006	LR: 9.982e-02	Score 64.300	Data time: 2.2042, Total iter time: 5.6180
thomas 04/05 09:11:40 ===> Epoch[1](280/301): Loss 1.2764	LR: 9.979e-02	Score 63.855	Data time: 2.4001, Total iter time: 6.1932
thomas 04/05 09:15:29 ===> Epoch[2](320/301): Loss 1.2719	LR: 9.976e-02	Score 64.261	Data time: 2.2204, Total iter time: 5.6490
thomas 04/05 09:19:15 ===> Epoch[2](360/301): Loss 1.3089	LR: 9.973e-02	Score 63.245	Data time: 2.2231, Total iter time: 5.5954
thomas 04/05 09:23:13 ===> Epoch[2](400/301): Loss 1.2654	LR: 9.970e-02	Score 63.663	Data time: 2.2663, Total iter time: 5.8699
thomas 04/05 09:27:23 ===> Epoch[2](440/301): Loss 1.2275	LR: 9.967e-02	Score 64.995	Data time: 2.3759, Total iter time: 6.1595
thomas 04/05 09:31:32 ===> Epoch[2](480/301): Loss 1.2501	LR: 9.964e-02	Score 63.775	Data time: 2.3695, Total iter time: 6.1490
thomas 04/05 09:35:47 ===> Epoch[2](520/301): Loss 1.2418	LR: 9.961e-02	Score 64.512	Data time: 2.4498, Total iter time: 6.3161
thomas 04/05 09:39:31 ===> Epoch[2](560/301): Loss 1.1755	LR: 9.958e-02	Score 66.491	Data time: 2.1174, Total iter time: 5.5105
thomas 04/05 09:43:09 ===> Epoch[2](600/301): Loss 1.1675	LR: 9.955e-02	Score 66.994	Data time: 2.0973, Total iter time: 5.3893
thomas 04/05 09:46:59 ===> Epoch[3](640/301): Loss 1.1624	LR: 9.952e-02	Score 67.238	Data time: 2.2449, Total iter time: 5.6792
thomas 04/05 09:50:49 ===> Epoch[3](680/301): Loss 1.1450	LR: 9.949e-02	Score 66.192	Data time: 2.2493, Total iter time: 5.6659
thomas 04/05 09:54:39 ===> Epoch[3](720/301): Loss 1.1002	LR: 9.946e-02	Score 68.062	Data time: 2.2216, Total iter time: 5.6741
thomas 04/05 09:58:30 ===> Epoch[3](760/301): Loss 1.2009	LR: 9.943e-02	Score 64.716	Data time: 2.2236, Total iter time: 5.7189
thomas 04/05 10:02:31 ===> Epoch[3](800/301): Loss 1.1467	LR: 9.940e-02	Score 66.367	Data time: 2.3583, Total iter time: 5.9433
thomas 04/05 10:06:23 ===> Epoch[3](840/301): Loss 1.1495	LR: 9.937e-02	Score 65.246	Data time: 2.2826, Total iter time: 5.7345
thomas 04/05 10:10:02 ===> Epoch[3](880/301): Loss 1.1395	LR: 9.934e-02	Score 66.991	Data time: 2.1160, Total iter time: 5.4080
thomas 04/05 10:14:04 ===> Epoch[4](920/301): Loss 1.1564	LR: 9.931e-02	Score 65.284	Data time: 2.3252, Total iter time: 5.9589
thomas 04/05 10:18:07 ===> Epoch[4](960/301): Loss 1.1264	LR: 9.928e-02	Score 65.845	Data time: 2.3876, Total iter time: 6.0161
thomas 04/05 10:22:05 ===> Epoch[4](1000/301): Loss 1.0797	LR: 9.925e-02	Score 67.672	Data time: 2.3049, Total iter time: 5.8703
thomas 04/05 10:22:05 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/05 10:22:05 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/05 10:24:04 101/312: Data time: 0.0031, Iter time: 1.2758	Loss 1.354 (AVG: 1.145)	Score 53.142 (AVG: 67.739)	mIOU 17.390 mAP 33.949 mAcc 25.391
IOU: 66.719 94.161 0.007 12.908 55.595 16.099 42.702 1.765 0.004 24.490 0.000 0.000 0.002 17.925 0.000 0.000 0.000 0.000 0.000 15.433
mAP: 66.525 95.824 21.679 43.104 73.190 39.787 54.169 21.246 18.300 30.534 4.324 16.410 23.982 41.758 5.918 36.173 58.433 5.380 4.496 17.757
mAcc: 93.163 98.367 0.007 23.677 59.620 57.971 73.278 1.993 0.004 39.896 0.000 0.000 0.002 24.904 0.000 0.000 0.000 0.000 0.000 34.940

thomas 04/05 10:25:57 201/312: Data time: 0.0027, Iter time: 0.7195	Loss 1.119 (AVG: 1.165)	Score 75.195 (AVG: 67.514)	mIOU 17.660 mAP 34.748 mAcc 25.739
IOU: 66.877 94.544 0.007 11.978 56.304 22.864 39.868 2.012 0.006 25.626 0.000 0.000 0.003 17.076 0.000 0.000 0.000 0.000 0.000 16.044
mAP: 67.258 94.921 23.302 43.175 74.240 45.727 53.397 21.855 21.439 36.263 4.198 19.823 23.681 43.051 5.653 33.833 53.418 4.043 5.562 20.127
mAcc: 92.931 98.569 0.007 24.772 59.981 61.516 71.459 2.272 0.006 39.250 0.000 0.000 0.003 27.507 0.000 0.000 0.000 0.000 0.000 36.506

thomas 04/05 10:27:49 301/312: Data time: 0.0024, Iter time: 0.5095	Loss 1.129 (AVG: 1.158)	Score 62.027 (AVG: 67.364)	mIOU 17.858 mAP 35.157 mAcc 25.878
IOU: 65.255 94.866 0.021 12.421 55.301 24.198 41.542 2.056 0.009 28.755 0.000 0.000 0.003 17.325 0.000 0.000 0.000 0.000 0.000 15.400
mAP: 65.914 95.202 24.930 42.321 74.297 45.651 54.504 22.827 20.591 38.783 4.790 20.689 22.446 44.444 5.779 38.430 51.884 4.938 5.388 19.336
mAcc: 92.565 98.590 0.021 25.639 58.821 61.685 72.078 2.321 0.009 42.492 0.000 0.000 0.003 28.888 0.000 0.000 0.000 0.000 0.000 34.458

thomas 04/05 10:28:01 312/312: Data time: 0.0028, Iter time: 0.7050	Loss 1.508 (AVG: 1.158)	Score 55.619 (AVG: 67.310)	mIOU 17.839 mAP 35.138 mAcc 25.810
IOU: 65.264 94.912 0.022 12.788 54.971 24.097 41.017 2.060 0.009 28.730 0.000 0.000 0.004 17.496 0.000 0.000 0.000 0.000 0.000 15.415
mAP: 65.919 95.245 24.866 42.783 73.448 45.396 54.369 22.838 20.514 38.696 4.714 20.379 22.334 45.057 5.754 38.430 52.483 4.892 5.407 19.245
mAcc: 92.680 98.606 0.022 25.872 58.580 61.291 71.406 2.328 0.009 42.604 0.000 0.000 0.004 28.163 0.000 0.000 0.000 0.000 0.000 34.647

thomas 04/05 10:28:01 Finished test. Elapsed time: 356.0146
thomas 04/05 10:28:01 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/05 10:28:01 Current best mIoU: 17.839 at iter 1000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/05 10:31:36 ===> Epoch[4](1040/301): Loss 1.0302	LR: 9.922e-02	Score 70.237	Data time: 2.1096, Total iter time: 5.2952
thomas 04/05 10:35:32 ===> Epoch[4](1080/301): Loss 1.0577	LR: 9.919e-02	Score 68.692	Data time: 2.2888, Total iter time: 5.8224
thomas 04/05 10:39:20 ===> Epoch[4](1120/301): Loss 1.1285	LR: 9.916e-02	Score 65.422	Data time: 2.2090, Total iter time: 5.6365
thomas 04/05 10:43:07 ===> Epoch[4](1160/301): Loss 1.0705	LR: 9.913e-02	Score 68.311	Data time: 2.1980, Total iter time: 5.6002
thomas 04/05 10:46:58 ===> Epoch[4](1200/301): Loss 1.0615	LR: 9.910e-02	Score 68.489	Data time: 2.2962, Total iter time: 5.6925
thomas 04/05 10:50:56 ===> Epoch[5](1240/301): Loss 1.0239	LR: 9.907e-02	Score 69.178	Data time: 2.3320, Total iter time: 5.8643
thomas 04/05 10:55:11 ===> Epoch[5](1280/301): Loss 1.0180	LR: 9.904e-02	Score 68.777	Data time: 2.4479, Total iter time: 6.2843
thomas 04/05 10:58:44 ===> Epoch[5](1320/301): Loss 1.0504	LR: 9.901e-02	Score 68.547	Data time: 2.0683, Total iter time: 5.2556
thomas 04/05 11:02:48 ===> Epoch[5](1360/301): Loss 1.0391	LR: 9.898e-02	Score 68.635	Data time: 2.3928, Total iter time: 6.0257
thomas 04/05 11:06:29 ===> Epoch[5](1400/301): Loss 0.9856	LR: 9.895e-02	Score 70.176	Data time: 2.1567, Total iter time: 5.4286
thomas 04/05 11:10:18 ===> Epoch[5](1440/301): Loss 1.0202	LR: 9.892e-02	Score 69.038	Data time: 2.2261, Total iter time: 5.6603
thomas 04/05 11:14:00 ===> Epoch[5](1480/301): Loss 1.0312	LR: 9.889e-02	Score 68.299	Data time: 2.1459, Total iter time: 5.4822
thomas 04/05 11:17:56 ===> Epoch[6](1520/301): Loss 1.0369	LR: 9.886e-02	Score 69.138	Data time: 2.3332, Total iter time: 5.8216
thomas 04/05 11:21:27 ===> Epoch[6](1560/301): Loss 1.0242	LR: 9.883e-02	Score 69.354	Data time: 2.0502, Total iter time: 5.2168
thomas 04/05 11:25:17 ===> Epoch[6](1600/301): Loss 0.9737	LR: 9.880e-02	Score 70.474	Data time: 2.1978, Total iter time: 5.6739
thomas 04/05 11:29:21 ===> Epoch[6](1640/301): Loss 0.9785	LR: 9.877e-02	Score 70.282	Data time: 2.3351, Total iter time: 6.0236
thomas 04/05 11:33:14 ===> Epoch[6](1680/301): Loss 0.9162	LR: 9.874e-02	Score 72.186	Data time: 2.3001, Total iter time: 5.7507
thomas 04/05 11:37:04 ===> Epoch[6](1720/301): Loss 0.9213	LR: 9.871e-02	Score 72.006	Data time: 2.2281, Total iter time: 5.6830
thomas 04/05 11:40:53 ===> Epoch[6](1760/301): Loss 0.9532	LR: 9.868e-02	Score 70.798	Data time: 2.2049, Total iter time: 5.6531
thomas 04/05 11:44:46 ===> Epoch[6](1800/301): Loss 0.9415	LR: 9.865e-02	Score 71.234	Data time: 2.2320, Total iter time: 5.7382
thomas 04/05 11:48:43 ===> Epoch[7](1840/301): Loss 0.9355	LR: 9.862e-02	Score 71.428	Data time: 2.3254, Total iter time: 5.8398
thomas 04/05 11:52:23 ===> Epoch[7](1880/301): Loss 0.9188	LR: 9.859e-02	Score 71.779	Data time: 2.1259, Total iter time: 5.4307
thomas 04/05 11:56:23 ===> Epoch[7](1920/301): Loss 0.8686	LR: 9.856e-02	Score 73.071	Data time: 2.3113, Total iter time: 5.9153
thomas 04/05 12:00:34 ===> Epoch[7](1960/301): Loss 0.9329	LR: 9.853e-02	Score 71.225	Data time: 2.3935, Total iter time: 6.1986
thomas 04/05 12:04:48 ===> Epoch[7](2000/301): Loss 0.8948	LR: 9.850e-02	Score 72.969	Data time: 2.4696, Total iter time: 6.2816
thomas 04/05 12:04:50 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/05 12:04:50 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/05 12:06:40 101/312: Data time: 0.0025, Iter time: 0.6128	Loss 1.411 (AVG: 1.031)	Score 56.993 (AVG: 70.179)	mIOU 22.850 mAP 47.791 mAcc 33.808
IOU: 67.603 94.758 3.163 29.257 64.431 39.295 46.594 13.984 2.202 24.739 0.000 5.658 16.444 37.892 0.000 0.000 0.000 0.000 0.000 10.970
mAP: 70.483 96.630 34.771 59.903 79.384 59.881 59.732 29.090 34.559 56.895 9.526 36.390 45.819 65.695 20.090 56.664 54.379 18.915 40.028 26.979
mAcc: 86.321 98.386 3.198 61.145 70.074 81.806 59.728 18.683 2.217 88.200 0.000 6.697 18.906 66.902 0.000 0.000 0.000 0.000 0.000 13.901

thomas 04/05 12:08:39 201/312: Data time: 0.0031, Iter time: 0.4086	Loss 0.906 (AVG: 1.046)	Score 71.180 (AVG: 69.552)	mIOU 23.051 mAP 48.894 mAcc 34.174
IOU: 66.382 95.046 4.282 27.005 65.198 38.000 52.310 16.201 2.089 25.548 0.000 9.352 14.361 33.701 0.000 0.000 0.000 0.000 0.000 11.553
mAP: 69.344 96.575 36.951 61.010 79.227 61.647 60.761 31.153 32.654 60.150 8.656 42.928 41.164 65.342 21.674 62.812 58.212 18.512 43.379 25.735
mAcc: 85.643 98.604 4.322 61.414 71.370 78.380 64.654 21.380 2.107 89.892 0.000 10.258 17.379 63.581 0.000 0.000 0.000 0.000 0.000 14.496

thomas 04/05 12:10:27 301/312: Data time: 0.0028, Iter time: 0.6258	Loss 0.343 (AVG: 1.038)	Score 89.874 (AVG: 69.718)	mIOU 23.225 mAP 48.913 mAcc 34.280
IOU: 66.903 95.063 5.446 26.202 65.034 42.372 51.027 15.187 1.972 24.820 0.000 11.987 13.997 32.925 0.000 0.000 0.000 0.000 0.000 11.569
mAP: 69.707 96.509 39.607 58.566 79.405 64.987 59.226 30.285 31.921 59.123 9.478 45.634 40.219 61.778 19.644 61.037 62.333 19.305 42.926 26.561
mAcc: 85.806 98.566 5.497 60.155 71.881 80.224 62.983 20.588 1.993 91.451 0.000 12.880 17.177 61.550 0.000 0.000 0.000 0.000 0.000 14.845

thomas 04/05 12:10:41 312/312: Data time: 0.0026, Iter time: 0.5065	Loss 0.427 (AVG: 1.033)	Score 88.206 (AVG: 69.794)	mIOU 23.246 mAP 49.080 mAcc 34.341
IOU: 66.800 95.051 5.489 25.609 66.023 42.717 50.847 15.326 2.025 24.748 0.000 11.798 14.646 32.069 0.000 0.000 0.000 0.000 0.000 11.769
mAP: 69.787 96.534 39.215 58.566 79.730 63.623 60.083 30.644 32.393 59.554 9.473 45.150 41.421 61.778 19.723 62.234 62.608 19.099 43.062 26.922
mAcc: 85.580 98.557 5.541 60.155 72.773 80.344 63.240 20.760 2.047 90.489 0.000 12.736 17.807 61.550 0.000 0.000 0.000 0.000 0.000 15.236

thomas 04/05 12:10:41 Finished test. Elapsed time: 350.7428
thomas 04/05 12:10:42 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/05 12:10:42 Current best mIoU: 23.246 at iter 2000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/05 12:14:13 ===> Epoch[7](2040/301): Loss 0.8868	LR: 9.847e-02	Score 72.891	Data time: 2.0151, Total iter time: 5.2057
thomas 04/05 12:17:58 ===> Epoch[7](2080/301): Loss 0.9100	LR: 9.844e-02	Score 72.872	Data time: 2.2228, Total iter time: 5.5521
thomas 04/05 12:21:40 ===> Epoch[8](2120/301): Loss 0.9031	LR: 9.841e-02	Score 72.457	Data time: 2.1932, Total iter time: 5.4719
thomas 04/05 12:25:25 ===> Epoch[8](2160/301): Loss 0.8779	LR: 9.838e-02	Score 72.705	Data time: 2.1811, Total iter time: 5.5605
thomas 04/05 12:29:35 ===> Epoch[8](2200/301): Loss 0.9011	LR: 9.835e-02	Score 71.792	Data time: 2.3894, Total iter time: 6.1790
thomas 04/05 12:33:36 ===> Epoch[8](2240/301): Loss 0.8195	LR: 9.832e-02	Score 74.428	Data time: 2.3471, Total iter time: 5.9191
thomas 04/05 12:37:32 ===> Epoch[8](2280/301): Loss 0.8848	LR: 9.829e-02	Score 73.645	Data time: 2.3018, Total iter time: 5.8341
thomas 04/05 12:41:19 ===> Epoch[8](2320/301): Loss 0.8346	LR: 9.826e-02	Score 74.407	Data time: 2.1974, Total iter time: 5.6063
thomas 04/05 12:45:01 ===> Epoch[8](2360/301): Loss 0.8609	LR: 9.823e-02	Score 73.572	Data time: 2.1357, Total iter time: 5.4782
thomas 04/05 12:48:48 ===> Epoch[8](2400/301): Loss 0.8417	LR: 9.820e-02	Score 73.889	Data time: 2.2503, Total iter time: 5.5936
thomas 04/05 12:52:41 ===> Epoch[9](2440/301): Loss 0.8048	LR: 9.817e-02	Score 76.044	Data time: 2.2399, Total iter time: 5.7517
thomas 04/05 12:56:24 ===> Epoch[9](2480/301): Loss 0.8349	LR: 9.814e-02	Score 74.090	Data time: 2.1211, Total iter time: 5.4912
thomas 04/05 13:00:19 ===> Epoch[9](2520/301): Loss 0.8506	LR: 9.811e-02	Score 73.475	Data time: 2.2802, Total iter time: 5.8022
thomas 04/05 13:04:15 ===> Epoch[9](2560/301): Loss 0.8125	LR: 9.808e-02	Score 74.794	Data time: 2.2975, Total iter time: 5.8371
thomas 04/05 13:08:11 ===> Epoch[9](2600/301): Loss 0.8043	LR: 9.805e-02	Score 75.193	Data time: 2.2757, Total iter time: 5.8024
thomas 04/05 13:12:05 ===> Epoch[9](2640/301): Loss 0.8294	LR: 9.802e-02	Score 74.282	Data time: 2.2622, Total iter time: 5.7729
thomas 04/05 13:16:00 ===> Epoch[9](2680/301): Loss 0.8834	LR: 9.799e-02	Score 73.526	Data time: 2.3013, Total iter time: 5.8115
thomas 04/05 13:19:59 ===> Epoch[10](2720/301): Loss 0.8249	LR: 9.796e-02	Score 74.267	Data time: 2.3919, Total iter time: 5.8785
thomas 04/05 13:24:20 ===> Epoch[10](2760/301): Loss 0.7553	LR: 9.793e-02	Score 76.779	Data time: 2.4885, Total iter time: 6.4332
thomas 04/05 13:28:37 ===> Epoch[10](2800/301): Loss 0.7699	LR: 9.790e-02	Score 75.932	Data time: 2.4883, Total iter time: 6.3600
thomas 04/05 13:32:36 ===> Epoch[10](2840/301): Loss 0.8170	LR: 9.787e-02	Score 75.270	Data time: 2.3643, Total iter time: 5.8851
thomas 04/05 13:36:32 ===> Epoch[10](2880/301): Loss 0.8597	LR: 9.784e-02	Score 73.666	Data time: 2.3023, Total iter time: 5.8290
thomas 04/05 13:40:19 ===> Epoch[10](2920/301): Loss 0.8283	LR: 9.781e-02	Score 75.246	Data time: 2.2082, Total iter time: 5.6026
thomas 04/05 13:44:13 ===> Epoch[10](2960/301): Loss 0.7437	LR: 9.778e-02	Score 76.670	Data time: 2.2583, Total iter time: 5.7755
thomas 04/05 13:48:20 ===> Epoch[10](3000/301): Loss 0.7766	LR: 9.775e-02	Score 75.811	Data time: 2.4358, Total iter time: 6.1053
thomas 04/05 13:48:21 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/05 13:48:22 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/05 13:50:28 101/312: Data time: 0.0025, Iter time: 1.1494	Loss 1.404 (AVG: 0.870)	Score 42.944 (AVG: 74.990)	mIOU 32.036 mAP 56.946 mAcc 42.854
IOU: 66.993 95.590 27.711 45.894 78.338 55.876 61.541 21.567 25.652 51.132 0.033 6.538 29.273 50.535 9.853 0.000 0.000 0.000 0.065 14.133
mAP: 73.931 96.868 49.366 60.804 83.541 73.427 68.143 37.986 43.259 66.328 17.675 53.576 52.694 67.712 39.787 49.000 57.605 41.438 72.241 33.548
mAcc: 81.056 98.702 65.879 63.118 88.613 90.085 66.585 33.293 32.269 71.549 0.033 6.606 41.708 67.246 28.663 0.000 0.000 0.000 0.065 21.612

thomas 04/05 13:52:24 201/312: Data time: 0.1199, Iter time: 0.5425	Loss 1.192 (AVG: 0.896)	Score 55.255 (AVG: 73.487)	mIOU 30.598 mAP 56.536 mAcc 41.813
IOU: 67.226 95.585 28.387 38.416 72.066 56.051 55.701 22.762 24.911 50.804 0.024 5.634 28.429 39.279 13.446 0.000 0.050 0.000 0.233 12.962
mAP: 73.818 96.447 49.799 55.365 80.592 73.428 65.353 38.652 40.809 59.033 16.991 52.666 51.914 68.023 40.676 59.883 64.959 38.622 71.541 32.141
mAcc: 81.311 98.592 66.974 57.654 84.996 87.077 60.517 34.623 33.666 75.950 0.024 5.723 44.188 54.470 32.228 0.000 0.050 0.000 0.233 17.991

thomas 04/05 13:54:20 301/312: Data time: 0.0031, Iter time: 0.4169	Loss 0.626 (AVG: 0.884)	Score 81.946 (AVG: 73.960)	mIOU 30.894 mAP 56.305 mAcc 42.201
IOU: 67.803 95.469 31.068 38.404 71.877 55.951 53.076 21.903 26.742 49.888 0.021 6.797 29.477 38.441 15.601 0.000 0.039 0.000 0.194 15.135
mAP: 73.461 96.452 50.986 54.354 81.665 73.388 63.391 40.067 41.959 59.102 16.055 50.965 52.478 66.938 36.307 62.197 65.242 37.892 70.647 32.547
mAcc: 81.503 98.390 70.329 57.875 84.011 85.335 59.173 32.348 36.114 76.485 0.021 6.905 44.100 54.180 35.480 0.000 0.039 0.000 0.194 21.536

thomas 04/05 13:54:36 312/312: Data time: 0.0027, Iter time: 0.3268	Loss 0.350 (AVG: 0.879)	Score 86.531 (AVG: 74.187)	mIOU 31.014 mAP 56.378 mAcc 42.265
IOU: 67.938 95.468 30.730 41.073 71.989 56.680 53.237 21.645 26.278 49.868 0.020 6.796 29.401 38.626 15.008 0.000 0.038 0.000 0.189 15.288
mAP: 73.495 96.444 50.421 55.759 81.885 73.974 63.459 40.028 41.872 59.736 15.416 50.965 53.024 66.989 35.649 61.148 65.180 38.304 71.047 32.768
mAcc: 81.673 98.430 70.008 60.046 84.108 86.036 59.473 32.062 35.307 76.576 0.020 6.905 43.919 53.884 34.879 0.000 0.038 0.000 0.189 21.739

thomas 04/05 13:54:36 Finished test. Elapsed time: 374.8163
thomas 04/05 13:54:38 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/05 13:54:38 Current best mIoU: 31.014 at iter 3000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/05 13:58:25 ===> Epoch[11](3040/301): Loss 0.7508	LR: 9.772e-02	Score 77.179	Data time: 2.1989, Total iter time: 5.5901
thomas 04/05 14:02:18 ===> Epoch[11](3080/301): Loss 0.7982	LR: 9.769e-02	Score 75.426	Data time: 2.3052, Total iter time: 5.7562
thomas 04/05 14:06:28 ===> Epoch[11](3120/301): Loss 0.7886	LR: 9.766e-02	Score 75.699	Data time: 2.4725, Total iter time: 6.1855
thomas 04/05 14:10:48 ===> Epoch[11](3160/301): Loss 0.7540	LR: 9.763e-02	Score 76.742	Data time: 2.5336, Total iter time: 6.4085
thomas 04/05 14:14:48 ===> Epoch[11](3200/301): Loss 0.7700	LR: 9.760e-02	Score 76.573	Data time: 2.3761, Total iter time: 5.9260
thomas 04/05 14:19:02 ===> Epoch[11](3240/301): Loss 0.7485	LR: 9.757e-02	Score 76.941	Data time: 2.5156, Total iter time: 6.2866
thomas 04/05 14:23:01 ===> Epoch[11](3280/301): Loss 0.7128	LR: 9.754e-02	Score 78.740	Data time: 2.3508, Total iter time: 5.8939
thomas 04/05 14:27:26 ===> Epoch[12](3320/301): Loss 0.6738	LR: 9.751e-02	Score 78.928	Data time: 2.5695, Total iter time: 6.5272
thomas 04/05 14:31:24 ===> Epoch[12](3360/301): Loss 0.7630	LR: 9.748e-02	Score 76.479	Data time: 2.2803, Total iter time: 5.8754
thomas 04/05 14:35:27 ===> Epoch[12](3400/301): Loss 0.7230	LR: 9.745e-02	Score 77.582	Data time: 2.3540, Total iter time: 5.9819
thomas 04/05 14:39:24 ===> Epoch[12](3440/301): Loss 0.7707	LR: 9.742e-02	Score 76.493	Data time: 2.3504, Total iter time: 5.8637
thomas 04/05 14:43:23 ===> Epoch[12](3480/301): Loss 0.7041	LR: 9.739e-02	Score 77.891	Data time: 2.3492, Total iter time: 5.9182
thomas 04/05 14:47:41 ===> Epoch[12](3520/301): Loss 0.7616	LR: 9.736e-02	Score 76.404	Data time: 2.5281, Total iter time: 6.3723
thomas 04/05 14:52:01 ===> Epoch[12](3560/301): Loss 0.7410	LR: 9.733e-02	Score 77.184	Data time: 2.5412, Total iter time: 6.4097
thomas 04/05 14:55:53 ===> Epoch[12](3600/301): Loss 0.6844	LR: 9.730e-02	Score 79.420	Data time: 2.2332, Total iter time: 5.7419
thomas 04/05 14:59:53 ===> Epoch[13](3640/301): Loss 0.7611	LR: 9.727e-02	Score 76.774	Data time: 2.3349, Total iter time: 5.9383
thomas 04/05 15:04:07 ===> Epoch[13](3680/301): Loss 0.7268	LR: 9.724e-02	Score 77.747	Data time: 2.4977, Total iter time: 6.2722
thomas 04/05 15:08:19 ===> Epoch[13](3720/301): Loss 0.6489	LR: 9.721e-02	Score 79.872	Data time: 2.4864, Total iter time: 6.2043
thomas 04/05 15:12:17 ===> Epoch[13](3760/301): Loss 0.7190	LR: 9.718e-02	Score 77.783	Data time: 2.3440, Total iter time: 5.8859
thomas 04/05 15:16:16 ===> Epoch[13](3800/301): Loss 0.7493	LR: 9.715e-02	Score 77.099	Data time: 2.3541, Total iter time: 5.8907
thomas 04/05 15:20:25 ===> Epoch[13](3840/301): Loss 0.7190	LR: 9.712e-02	Score 78.362	Data time: 2.3810, Total iter time: 6.1396
thomas 04/05 15:24:32 ===> Epoch[13](3880/301): Loss 0.6971	LR: 9.709e-02	Score 78.151	Data time: 2.3966, Total iter time: 6.0896
thomas 04/05 15:28:40 ===> Epoch[14](3920/301): Loss 0.7080	LR: 9.706e-02	Score 78.176	Data time: 2.4074, Total iter time: 6.1100
thomas 04/05 15:32:47 ===> Epoch[14](3960/301): Loss 0.6787	LR: 9.703e-02	Score 79.375	Data time: 2.4338, Total iter time: 6.1050
thomas 04/05 15:36:51 ===> Epoch[14](4000/301): Loss 0.7248	LR: 9.699e-02	Score 77.853	Data time: 2.4095, Total iter time: 6.0261
thomas 04/05 15:36:53 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/05 15:36:53 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/05 15:38:55 101/312: Data time: 0.0031, Iter time: 0.4201	Loss 0.572 (AVG: 0.777)	Score 79.162 (AVG: 76.637)	mIOU 36.808 mAP 59.734 mAcc 49.295
IOU: 68.475 93.982 41.589 45.125 76.632 65.266 60.993 22.078 26.225 45.920 0.051 32.730 34.428 47.796 22.196 0.094 20.036 7.764 2.837 21.943
mAP: 77.727 95.408 48.605 62.306 87.317 74.567 62.811 47.139 40.551 60.666 17.538 53.222 52.017 69.380 43.525 67.680 75.958 58.288 64.288 35.683
mAcc: 82.992 98.675 52.967 70.166 94.044 75.635 70.347 30.390 39.497 81.462 0.053 79.222 51.881 49.071 45.341 0.094 20.049 7.899 2.837 33.276

thomas 04/05 15:40:52 201/312: Data time: 0.0029, Iter time: 0.5868	Loss 0.640 (AVG: 0.789)	Score 81.470 (AVG: 76.538)	mIOU 36.853 mAP 60.639 mAcc 48.772
IOU: 68.329 94.211 40.577 43.741 76.100 64.228 61.124 21.382 24.264 51.173 0.025 35.661 36.169 41.839 21.821 0.055 19.181 11.698 3.102 22.375
mAP: 75.544 95.795 51.162 61.967 85.490 72.525 66.971 43.652 40.225 62.468 17.874 55.062 53.895 69.890 41.134 68.114 82.073 62.688 68.733 37.509
mAcc: 83.075 98.691 52.492 70.966 94.241 73.168 70.190 29.624 34.029 86.340 0.028 75.103 54.869 43.092 41.525 0.055 19.318 11.966 3.102 33.565

thomas 04/05 15:43:02 301/312: Data time: 0.0027, Iter time: 0.7757	Loss 0.137 (AVG: 0.792)	Score 98.386 (AVG: 76.343)	mIOU 36.748 mAP 60.211 mAcc 48.600
IOU: 68.150 94.262 42.459 40.231 74.383 64.801 56.616 21.999 24.852 52.295 0.230 42.906 36.331 42.735 20.245 0.046 19.779 10.288 2.974 19.378
mAP: 74.591 95.714 51.678 58.164 85.326 75.507 62.892 44.362 40.200 61.671 16.286 59.950 53.472 68.199 42.868 64.128 81.606 60.862 70.280 36.471
mAcc: 83.104 98.704 55.956 70.026 94.096 71.977 67.299 30.129 35.392 87.452 0.244 78.586 56.743 45.005 37.905 0.046 20.013 10.474 2.974 25.873

thomas 04/05 15:43:14 312/312: Data time: 0.0025, Iter time: 0.7762	Loss 0.882 (AVG: 0.799)	Score 69.847 (AVG: 76.071)	mIOU 36.402 mAP 60.091 mAcc 48.396
IOU: 67.897 94.274 42.163 39.278 74.327 64.684 55.802 21.649 24.242 51.639 0.223 42.638 35.651 42.374 20.099 0.047 19.705 10.007 3.100 18.251
mAP: 74.599 95.804 51.719 58.746 85.481 75.613 62.606 44.307 39.956 61.671 16.554 58.231 53.299 68.376 41.947 64.331 81.656 59.832 70.942 36.152
mAcc: 83.107 98.727 55.944 70.495 93.932 72.281 66.623 29.494 34.774 87.452 0.235 78.235 56.745 45.027 37.728 0.047 19.934 10.183 3.100 23.847

thomas 04/05 15:43:14 Finished test. Elapsed time: 381.3205
thomas 04/05 15:43:16 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/05 15:43:16 Current best mIoU: 36.402 at iter 4000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/05 15:47:25 ===> Epoch[14](4040/301): Loss 0.6983	LR: 9.696e-02	Score 78.088	Data time: 2.4423, Total iter time: 6.1528
thomas 04/05 15:51:30 ===> Epoch[14](4080/301): Loss 0.6620	LR: 9.693e-02	Score 79.688	Data time: 2.4172, Total iter time: 6.0481
thomas 04/05 15:55:50 ===> Epoch[14](4120/301): Loss 0.6725	LR: 9.690e-02	Score 79.295	Data time: 2.5546, Total iter time: 6.4162
thomas 04/05 15:59:59 ===> Epoch[14](4160/301): Loss 0.6669	LR: 9.687e-02	Score 79.489	Data time: 2.4201, Total iter time: 6.1510
thomas 04/05 16:03:49 ===> Epoch[14](4200/301): Loss 0.7143	LR: 9.684e-02	Score 77.935	Data time: 2.2470, Total iter time: 5.6698
thomas 04/05 16:07:45 ===> Epoch[15](4240/301): Loss 0.6652	LR: 9.681e-02	Score 79.431	Data time: 2.2886, Total iter time: 5.8106
thomas 04/05 16:12:23 ===> Epoch[15](4280/301): Loss 0.6785	LR: 9.678e-02	Score 78.836	Data time: 2.6601, Total iter time: 6.8627
thomas 04/05 16:16:22 ===> Epoch[15](4320/301): Loss 0.6726	LR: 9.675e-02	Score 79.537	Data time: 2.3667, Total iter time: 5.9045
thomas 04/05 16:20:29 ===> Epoch[15](4360/301): Loss 0.7103	LR: 9.672e-02	Score 78.900	Data time: 2.4308, Total iter time: 6.0870
thomas 04/05 16:24:33 ===> Epoch[15](4400/301): Loss 0.6381	LR: 9.669e-02	Score 79.647	Data time: 2.3993, Total iter time: 6.0468
thomas 04/05 16:28:26 ===> Epoch[15](4440/301): Loss 0.6673	LR: 9.666e-02	Score 79.497	Data time: 2.2504, Total iter time: 5.7424
thomas 04/05 16:32:25 ===> Epoch[15](4480/301): Loss 0.6767	LR: 9.663e-02	Score 79.418	Data time: 2.2872, Total iter time: 5.9104
thomas 04/05 16:36:23 ===> Epoch[16](4520/301): Loss 0.7178	LR: 9.660e-02	Score 78.121	Data time: 2.3001, Total iter time: 5.8616
thomas 04/05 16:40:46 ===> Epoch[16](4560/301): Loss 0.7039	LR: 9.657e-02	Score 78.236	Data time: 2.5534, Total iter time: 6.4941
thomas 04/05 16:44:45 ===> Epoch[16](4600/301): Loss 0.6486	LR: 9.654e-02	Score 79.682	Data time: 2.3926, Total iter time: 5.8993
thomas 04/05 16:49:01 ===> Epoch[16](4640/301): Loss 0.6607	LR: 9.651e-02	Score 79.564	Data time: 2.4909, Total iter time: 6.3186
thomas 04/05 16:53:02 ===> Epoch[16](4680/301): Loss 0.7141	LR: 9.648e-02	Score 78.011	Data time: 2.3152, Total iter time: 5.9349
thomas 04/05 16:57:08 ===> Epoch[16](4720/301): Loss 0.6153	LR: 9.645e-02	Score 81.263	Data time: 2.3739, Total iter time: 6.0680
thomas 04/05 17:01:06 ===> Epoch[16](4760/301): Loss 0.6505	LR: 9.642e-02	Score 79.859	Data time: 2.3373, Total iter time: 5.8862
thomas 04/05 17:05:30 ===> Epoch[16](4800/301): Loss 0.6464	LR: 9.639e-02	Score 80.268	Data time: 2.6246, Total iter time: 6.5288
thomas 04/05 17:09:33 ===> Epoch[17](4840/301): Loss 0.6740	LR: 9.636e-02	Score 79.420	Data time: 2.3936, Total iter time: 5.9965
thomas 04/05 17:13:22 ===> Epoch[17](4880/301): Loss 0.6136	LR: 9.633e-02	Score 80.982	Data time: 2.2445, Total iter time: 5.6469
thomas 04/05 17:17:12 ===> Epoch[17](4920/301): Loss 0.6422	LR: 9.630e-02	Score 79.973	Data time: 2.1952, Total iter time: 5.6824
thomas 04/05 17:21:05 ===> Epoch[17](4960/301): Loss 0.6639	LR: 9.627e-02	Score 79.204	Data time: 2.2254, Total iter time: 5.7446
thomas 04/05 17:25:19 ===> Epoch[17](5000/301): Loss 0.6594	LR: 9.624e-02	Score 79.850	Data time: 2.4709, Total iter time: 6.2568
thomas 04/05 17:25:20 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/05 17:25:20 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/05 17:27:24 101/312: Data time: 0.0032, Iter time: 0.4434	Loss 0.816 (AVG: 0.774)	Score 70.343 (AVG: 76.263)	mIOU 40.893 mAP 63.724 mAcc 51.264
IOU: 67.358 95.011 41.037 54.841 76.440 67.413 52.551 28.370 31.130 53.251 7.325 17.996 40.959 59.834 21.520 2.654 48.693 3.439 30.262 17.781
mAP: 75.694 95.100 47.370 73.149 85.715 78.776 59.198 42.142 55.170 64.999 21.055 49.001 56.663 75.637 47.061 75.551 86.296 67.021 80.586 38.292
mAcc: 83.776 98.486 67.250 80.155 83.869 92.714 57.635 57.549 36.085 58.597 10.319 18.274 68.505 82.770 22.898 2.709 49.055 3.440 30.294 20.909

thomas 04/05 17:29:30 201/312: Data time: 0.0030, Iter time: 1.2400	Loss 0.344 (AVG: 0.777)	Score 91.043 (AVG: 76.560)	mIOU 39.439 mAP 61.485 mAcc 49.485
IOU: 68.661 95.100 38.837 53.582 78.170 72.392 52.758 30.518 27.916 57.347 5.970 15.423 40.536 46.089 17.143 2.688 42.617 2.025 24.326 16.678
mAP: 75.220 94.783 49.591 67.617 84.850 78.657 60.107 47.235 47.249 61.783 21.382 48.676 58.500 64.838 38.572 72.956 89.219 66.082 66.132 36.243
mAcc: 84.441 98.384 66.222 79.015 86.473 91.270 59.652 60.008 34.153 63.041 8.767 15.759 62.594 70.202 17.962 2.706 42.898 2.025 24.346 19.782

thomas 04/05 17:31:40 301/312: Data time: 0.0027, Iter time: 0.3547	Loss 0.752 (AVG: 0.729)	Score 80.771 (AVG: 78.105)	mIOU 40.231 mAP 62.078 mAcc 50.240
IOU: 70.092 95.447 39.418 53.666 80.821 72.446 55.791 31.415 27.490 62.851 6.735 16.675 38.715 49.926 13.838 2.230 37.799 1.783 30.189 17.294
mAP: 75.529 95.209 50.020 66.239 85.868 79.314 63.740 48.044 46.392 60.448 23.202 52.040 59.661 69.959 38.673 68.129 85.500 65.262 71.353 36.986
mAcc: 84.843 98.457 67.324 81.700 89.397 90.570 62.126 63.043 33.217 68.383 10.244 16.939 59.262 71.944 14.390 2.243 38.113 1.783 30.209 20.619

thomas 04/05 17:31:52 312/312: Data time: 0.0024, Iter time: 0.5505	Loss 0.517 (AVG: 0.728)	Score 81.915 (AVG: 78.163)	mIOU 40.306 mAP 62.318 mAcc 50.264
IOU: 70.260 95.400 39.818 54.033 81.006 72.541 55.979 31.188 26.897 62.452 6.748 17.030 38.980 50.156 14.287 2.230 37.799 1.808 30.189 17.316
mAP: 75.679 95.248 50.929 66.641 86.116 79.383 64.370 48.211 46.059 60.979 23.431 52.723 59.740 69.312 41.006 68.129 85.500 64.849 71.353 36.705
mAcc: 84.946 98.450 67.544 81.777 89.485 90.341 62.232 62.657 32.456 68.094 10.487 17.311 59.455 72.145 14.857 2.243 38.113 1.808 30.209 20.675

thomas 04/05 17:31:52 Finished test. Elapsed time: 391.7184
thomas 04/05 17:31:53 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/05 17:31:53 Current best mIoU: 40.306 at iter 5000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/05 17:35:58 ===> Epoch[17](5040/301): Loss 0.6240	LR: 9.621e-02	Score 81.032	Data time: 2.3887, Total iter time: 6.0494
thomas 04/05 17:39:58 ===> Epoch[17](5080/301): Loss 0.6308	LR: 9.618e-02	Score 80.468	Data time: 2.3056, Total iter time: 5.9232
thomas 04/05 17:43:57 ===> Epoch[18](5120/301): Loss 0.6439	LR: 9.615e-02	Score 79.835	Data time: 2.3070, Total iter time: 5.8958
thomas 04/05 17:48:06 ===> Epoch[18](5160/301): Loss 0.6338	LR: 9.612e-02	Score 80.523	Data time: 2.3958, Total iter time: 6.1540
thomas 04/05 17:52:16 ===> Epoch[18](5200/301): Loss 0.6403	LR: 9.609e-02	Score 80.192	Data time: 2.4325, Total iter time: 6.1656
thomas 04/05 17:56:38 ===> Epoch[18](5240/301): Loss 0.6605	LR: 9.606e-02	Score 79.368	Data time: 2.5909, Total iter time: 6.4676
thomas 04/05 18:00:29 ===> Epoch[18](5280/301): Loss 0.5642	LR: 9.603e-02	Score 82.725	Data time: 2.2612, Total iter time: 5.7030
thomas 04/05 18:04:28 ===> Epoch[18](5320/301): Loss 0.6463	LR: 9.600e-02	Score 80.035	Data time: 2.2952, Total iter time: 5.9121
thomas 04/05 18:08:11 ===> Epoch[18](5360/301): Loss 0.6052	LR: 9.597e-02	Score 81.079	Data time: 2.1702, Total iter time: 5.5070
thomas 04/05 18:11:58 ===> Epoch[18](5400/301): Loss 0.6461	LR: 9.594e-02	Score 80.130	Data time: 2.2121, Total iter time: 5.5896
thomas 04/05 18:15:48 ===> Epoch[19](5440/301): Loss 0.6650	LR: 9.591e-02	Score 79.669	Data time: 2.2782, Total iter time: 5.6717
thomas 04/05 18:19:55 ===> Epoch[19](5480/301): Loss 0.6111	LR: 9.588e-02	Score 81.402	Data time: 2.4448, Total iter time: 6.1017
thomas 04/05 18:23:49 ===> Epoch[19](5520/301): Loss 0.6029	LR: 9.585e-02	Score 81.868	Data time: 2.2837, Total iter time: 5.7863
thomas 04/05 18:27:57 ===> Epoch[19](5560/301): Loss 0.6098	LR: 9.582e-02	Score 80.896	Data time: 2.3858, Total iter time: 6.1115
thomas 04/05 18:32:01 ===> Epoch[19](5600/301): Loss 0.6161	LR: 9.579e-02	Score 80.907	Data time: 2.3645, Total iter time: 6.0173
thomas 04/05 18:36:09 ===> Epoch[19](5640/301): Loss 0.6020	LR: 9.576e-02	Score 81.324	Data time: 2.3927, Total iter time: 6.1423
thomas 04/05 18:40:22 ===> Epoch[19](5680/301): Loss 0.6370	LR: 9.573e-02	Score 80.235	Data time: 2.5218, Total iter time: 6.2414
thomas 04/05 18:44:32 ===> Epoch[20](5720/301): Loss 0.6711	LR: 9.570e-02	Score 79.468	Data time: 2.4845, Total iter time: 6.1630
thomas 04/05 18:48:29 ===> Epoch[20](5760/301): Loss 0.6373	LR: 9.567e-02	Score 80.556	Data time: 2.3172, Total iter time: 5.8456
thomas 04/05 18:52:51 ===> Epoch[20](5800/301): Loss 0.5620	LR: 9.564e-02	Score 82.487	Data time: 2.5298, Total iter time: 6.4846
thomas 04/05 18:56:39 ===> Epoch[20](5840/301): Loss 0.6463	LR: 9.561e-02	Score 80.369	Data time: 2.1977, Total iter time: 5.6241
thomas 04/05 19:00:55 ===> Epoch[20](5880/301): Loss 0.6602	LR: 9.558e-02	Score 79.595	Data time: 2.4518, Total iter time: 6.3125
thomas 04/05 19:05:09 ===> Epoch[20](5920/301): Loss 0.6202	LR: 9.555e-02	Score 80.517	Data time: 2.5118, Total iter time: 6.2766
thomas 04/05 19:09:23 ===> Epoch[20](5960/301): Loss 0.6143	LR: 9.552e-02	Score 81.190	Data time: 2.5039, Total iter time: 6.2517
thomas 04/05 19:13:17 ===> Epoch[20](6000/301): Loss 0.6073	LR: 9.549e-02	Score 81.182	Data time: 2.2607, Total iter time: 5.7669
thomas 04/05 19:13:18 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/05 19:13:18 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/05 19:15:23 101/312: Data time: 0.1177, Iter time: 0.4619	Loss 0.705 (AVG: 0.736)	Score 75.429 (AVG: 77.327)	mIOU 44.289 mAP 64.057 mAcc 56.687
IOU: 71.779 95.005 35.943 62.274 73.402 63.553 44.697 30.926 25.824 32.836 4.971 52.372 30.481 55.347 11.135 30.672 67.691 24.428 47.153 25.295
mAP: 79.116 96.134 54.808 67.733 83.807 80.464 64.457 45.624 45.779 60.805 35.196 63.289 52.293 78.496 30.063 83.891 89.055 64.272 65.266 40.598
mAcc: 83.180 98.714 73.592 76.042 87.312 92.209 47.697 54.091 27.323 46.654 5.594 80.275 40.926 79.897 31.931 31.892 69.145 25.140 48.288 33.826

thomas 04/05 19:17:19 201/312: Data time: 0.0023, Iter time: 0.4546	Loss 0.462 (AVG: 0.716)	Score 87.490 (AVG: 78.192)	mIOU 46.560 mAP 65.408 mAcc 59.227
IOU: 71.688 95.392 37.671 60.601 76.908 61.885 51.891 31.166 22.924 54.410 7.236 46.770 35.680 48.574 20.265 35.442 66.631 30.434 50.005 25.620
mAP: 78.328 96.619 55.059 64.966 85.580 79.866 65.321 48.742 46.651 57.023 33.917 59.805 56.345 71.208 41.347 83.827 91.027 73.941 77.070 41.511
mAcc: 83.231 98.650 73.655 76.130 89.757 92.572 55.244 55.618 24.523 69.512 8.019 71.745 44.391 72.968 47.673 36.752 67.689 31.475 50.886 34.057

thomas 04/05 19:19:27 301/312: Data time: 0.0032, Iter time: 0.8994	Loss 0.399 (AVG: 0.723)	Score 91.420 (AVG: 77.992)	mIOU 46.132 mAP 65.276 mAcc 58.860
IOU: 70.784 95.434 37.440 55.048 78.777 63.015 52.013 32.382 22.453 54.205 5.729 46.315 35.293 55.436 21.062 32.927 67.745 25.352 50.479 20.748
mAP: 76.725 96.980 53.165 64.764 86.079 82.018 65.609 49.906 46.712 55.230 29.837 60.466 57.370 74.292 42.173 83.447 90.628 71.078 77.428 41.608
mAcc: 82.832 98.623 73.375 77.540 90.862 93.148 55.254 58.036 23.862 68.983 6.284 71.282 45.664 78.638 45.009 34.926 68.767 26.147 51.304 26.673

thomas 04/05 19:19:37 312/312: Data time: 0.0036, Iter time: 0.6733	Loss 0.550 (AVG: 0.723)	Score 83.793 (AVG: 77.999)	mIOU 45.986 mAP 65.206 mAcc 58.742
IOU: 70.786 95.362 37.131 55.353 78.369 63.517 51.719 32.482 22.690 54.104 5.714 44.949 35.256 54.968 21.028 32.696 67.107 25.453 50.102 20.926
mAP: 76.548 96.915 53.023 64.980 85.814 81.537 65.915 49.464 46.534 55.990 29.542 59.966 57.371 73.797 42.173 83.302 90.788 71.278 77.836 41.350
mAcc: 82.941 98.547 72.372 77.847 90.337 93.314 54.954 57.952 24.073 68.552 6.268 71.075 45.714 79.051 45.009 34.602 68.103 26.251 50.898 26.975

thomas 04/05 19:19:37 Finished test. Elapsed time: 379.3508
thomas 04/05 19:19:39 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/05 19:19:39 Current best mIoU: 45.986 at iter 6000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/05 19:23:41 ===> Epoch[21](6040/301): Loss 0.6262	LR: 9.546e-02	Score 80.855	Data time: 2.3486, Total iter time: 5.9588
thomas 04/05 19:28:08 ===> Epoch[21](6080/301): Loss 0.6076	LR: 9.543e-02	Score 80.723	Data time: 2.6003, Total iter time: 6.6010
thomas 04/05 19:32:23 ===> Epoch[21](6120/301): Loss 0.6231	LR: 9.540e-02	Score 80.672	Data time: 2.4982, Total iter time: 6.2906
thomas 04/05 19:36:18 ===> Epoch[21](6160/301): Loss 0.6042	LR: 9.537e-02	Score 81.418	Data time: 2.3107, Total iter time: 5.7938
thomas 04/05 19:40:14 ===> Epoch[21](6200/301): Loss 0.5839	LR: 9.534e-02	Score 81.751	Data time: 2.2804, Total iter time: 5.8155
thomas 04/05 19:44:00 ===> Epoch[21](6240/301): Loss 0.5672	LR: 9.531e-02	Score 82.644	Data time: 2.2012, Total iter time: 5.5937
thomas 04/05 19:48:16 ===> Epoch[21](6280/301): Loss 0.5500	LR: 9.528e-02	Score 82.800	Data time: 2.4672, Total iter time: 6.3104
thomas 04/05 19:52:21 ===> Epoch[21](6320/301): Loss 0.5878	LR: 9.525e-02	Score 82.114	Data time: 2.4014, Total iter time: 6.0460
thomas 04/05 19:56:35 ===> Epoch[22](6360/301): Loss 0.5720	LR: 9.522e-02	Score 82.649	Data time: 2.5076, Total iter time: 6.2817
thomas 04/05 20:00:30 ===> Epoch[22](6400/301): Loss 0.6041	LR: 9.519e-02	Score 81.369	Data time: 2.2822, Total iter time: 5.8027
thomas 04/05 20:04:29 ===> Epoch[22](6440/301): Loss 0.6050	LR: 9.516e-02	Score 81.071	Data time: 2.3087, Total iter time: 5.8852
thomas 04/05 20:08:26 ===> Epoch[22](6480/301): Loss 0.6378	LR: 9.513e-02	Score 80.435	Data time: 2.2642, Total iter time: 5.8480
thomas 04/05 20:12:15 ===> Epoch[22](6520/301): Loss 0.5842	LR: 9.510e-02	Score 81.921	Data time: 2.2112, Total iter time: 5.6455
thomas 04/05 20:16:47 ===> Epoch[22](6560/301): Loss 0.5560	LR: 9.507e-02	Score 82.971	Data time: 2.6833, Total iter time: 6.7209
thomas 04/05 20:21:13 ===> Epoch[22](6600/301): Loss 0.5955	LR: 9.504e-02	Score 81.206	Data time: 2.6312, Total iter time: 6.5750
thomas 04/05 20:25:14 ===> Epoch[23](6640/301): Loss 0.5938	LR: 9.501e-02	Score 81.447	Data time: 2.3393, Total iter time: 5.9598
thomas 04/05 20:29:20 ===> Epoch[23](6680/301): Loss 0.6023	LR: 9.498e-02	Score 81.583	Data time: 2.3654, Total iter time: 6.0689
thomas 04/05 20:33:27 ===> Epoch[23](6720/301): Loss 0.5752	LR: 9.495e-02	Score 82.477	Data time: 2.3800, Total iter time: 6.1119
thomas 04/05 20:37:39 ===> Epoch[23](6760/301): Loss 0.6180	LR: 9.492e-02	Score 81.128	Data time: 2.4430, Total iter time: 6.2241
thomas 04/05 20:41:48 ===> Epoch[23](6800/301): Loss 0.5496	LR: 9.489e-02	Score 82.928	Data time: 2.4642, Total iter time: 6.1249
thomas 04/05 20:45:45 ===> Epoch[23](6840/301): Loss 0.6445	LR: 9.486e-02	Score 80.094	Data time: 2.3370, Total iter time: 5.8673
thomas 04/05 20:49:46 ===> Epoch[23](6880/301): Loss 0.5941	LR: 9.482e-02	Score 81.799	Data time: 2.3053, Total iter time: 5.9387
thomas 04/05 20:53:46 ===> Epoch[23](6920/301): Loss 0.5875	LR: 9.479e-02	Score 81.713	Data time: 2.2920, Total iter time: 5.9345
thomas 04/05 20:57:50 ===> Epoch[24](6960/301): Loss 0.5970	LR: 9.476e-02	Score 81.391	Data time: 2.3450, Total iter time: 6.0088
thomas 04/05 21:02:02 ===> Epoch[24](7000/301): Loss 0.6395	LR: 9.473e-02	Score 80.305	Data time: 2.4695, Total iter time: 6.2359
thomas 04/05 21:02:04 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/05 21:02:04 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/05 21:04:20 101/312: Data time: 0.0028, Iter time: 0.7225	Loss 0.698 (AVG: 0.691)	Score 78.447 (AVG: 79.350)	mIOU 45.127 mAP 64.793 mAcc 56.510
IOU: 71.527 95.320 43.564 58.117 77.355 67.613 56.919 30.953 31.509 64.047 1.593 50.739 42.934 51.101 31.200 4.148 64.364 19.741 19.535 20.268
mAP: 76.913 97.178 49.204 63.634 83.568 83.078 66.373 51.441 48.921 61.322 12.374 61.312 66.276 79.523 49.298 75.398 92.939 69.910 68.517 38.682
mAcc: 85.463 97.623 61.734 70.514 82.758 93.620 68.575 64.328 34.361 78.269 2.055 68.875 79.079 67.516 38.794 4.346 65.445 19.921 19.742 27.179

thomas 04/05 21:06:28 201/312: Data time: 0.0066, Iter time: 1.4345	Loss 0.566 (AVG: 0.704)	Score 82.111 (AVG: 79.004)	mIOU 46.028 mAP 65.289 mAcc 57.583
IOU: 71.543 95.324 44.420 56.528 75.326 60.455 56.822 33.215 29.833 66.584 2.910 49.105 42.055 50.468 30.599 10.959 65.035 23.571 34.397 21.412
mAP: 76.333 97.358 52.781 61.891 82.897 83.483 62.266 52.466 44.798 67.881 21.960 59.732 65.826 74.191 44.972 81.102 91.155 71.339 71.142 42.206
mAcc: 84.973 97.873 63.232 69.630 80.861 93.736 64.446 67.138 32.906 84.572 3.599 65.830 77.472 60.505 39.971 11.167 65.878 23.933 34.929 29.003

thomas 04/05 21:08:40 301/312: Data time: 0.0029, Iter time: 0.7644	Loss 0.796 (AVG: 0.685)	Score 76.120 (AVG: 78.972)	mIOU 47.006 mAP 65.811 mAcc 58.529
IOU: 71.091 95.511 46.671 59.874 75.686 58.002 56.852 32.463 33.810 63.267 3.266 51.295 41.933 54.603 30.464 15.023 66.044 25.684 35.457 23.118
mAP: 76.418 97.700 53.810 66.338 83.449 82.298 60.947 50.879 48.573 66.602 22.014 56.124 65.787 73.803 47.653 82.242 91.587 72.712 75.190 42.103
mAcc: 84.480 97.902 64.537 73.191 80.950 94.196 63.603 66.112 38.361 79.716 4.002 68.452 77.198 61.301 40.528 15.547 66.861 26.141 35.847 31.663

thomas 04/05 21:08:53 312/312: Data time: 0.0021, Iter time: 0.4819	Loss 1.335 (AVG: 0.682)	Score 68.538 (AVG: 79.098)	mIOU 47.084 mAP 65.648 mAcc 58.637
IOU: 71.374 95.537 46.422 59.675 75.344 56.694 57.202 32.792 33.156 65.938 3.262 51.206 41.780 55.975 30.319 14.492 66.681 25.757 35.133 22.947
mAP: 76.540 97.610 53.973 66.188 83.507 81.172 61.510 51.147 47.742 66.045 22.120 56.124 65.297 74.331 47.653 82.042 91.812 73.058 72.713 42.369
mAcc: 84.697 97.929 64.156 72.828 80.569 94.203 63.785 66.722 37.555 81.649 3.993 68.452 77.290 62.714 40.528 14.929 67.477 26.219 35.507 31.545

thomas 04/05 21:08:53 Finished test. Elapsed time: 408.8758
thomas 04/05 21:08:54 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/05 21:08:54 Current best mIoU: 47.084 at iter 7000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/05 21:12:57 ===> Epoch[24](7040/301): Loss 0.5815	LR: 9.470e-02	Score 81.891	Data time: 2.3622, Total iter time: 5.9980
thomas 04/05 21:16:48 ===> Epoch[24](7080/301): Loss 0.5716	LR: 9.467e-02	Score 82.436	Data time: 2.2321, Total iter time: 5.7054
thomas 04/05 21:20:35 ===> Epoch[24](7120/301): Loss 0.5349	LR: 9.464e-02	Score 83.703	Data time: 2.1900, Total iter time: 5.6110
thomas 04/05 21:24:44 ===> Epoch[24](7160/301): Loss 0.5521	LR: 9.461e-02	Score 82.851	Data time: 2.4347, Total iter time: 6.1626
thomas 04/05 21:29:02 ===> Epoch[24](7200/301): Loss 0.5519	LR: 9.458e-02	Score 83.414	Data time: 2.6078, Total iter time: 6.3547
thomas 04/05 21:33:13 ===> Epoch[25](7240/301): Loss 0.5766	LR: 9.455e-02	Score 82.539	Data time: 2.4576, Total iter time: 6.2152
thomas 04/05 21:37:18 ===> Epoch[25](7280/301): Loss 0.5876	LR: 9.452e-02	Score 81.854	Data time: 2.3161, Total iter time: 6.0504
thomas 04/05 21:41:22 ===> Epoch[25](7320/301): Loss 0.5453	LR: 9.449e-02	Score 83.340	Data time: 2.3428, Total iter time: 6.0118
thomas 04/05 21:45:24 ===> Epoch[25](7360/301): Loss 0.5522	LR: 9.446e-02	Score 83.063	Data time: 2.3212, Total iter time: 5.9562
thomas 04/05 21:49:39 ===> Epoch[25](7400/301): Loss 0.5128	LR: 9.443e-02	Score 84.079	Data time: 2.5028, Total iter time: 6.2890
thomas 04/05 21:53:50 ===> Epoch[25](7440/301): Loss 0.5675	LR: 9.440e-02	Score 82.387	Data time: 2.5139, Total iter time: 6.1974
thomas 04/05 21:58:01 ===> Epoch[25](7480/301): Loss 0.5615	LR: 9.437e-02	Score 82.936	Data time: 2.4644, Total iter time: 6.1815
thomas 04/05 22:01:44 ===> Epoch[25](7520/301): Loss 0.5861	LR: 9.434e-02	Score 81.555	Data time: 2.1674, Total iter time: 5.4998
thomas 04/05 22:05:57 ===> Epoch[26](7560/301): Loss 0.5805	LR: 9.431e-02	Score 81.864	Data time: 2.4664, Total iter time: 6.2483
thomas 04/05 22:10:00 ===> Epoch[26](7600/301): Loss 0.5498	LR: 9.428e-02	Score 82.543	Data time: 2.3310, Total iter time: 6.0015
thomas 04/05 22:14:12 ===> Epoch[26](7640/301): Loss 0.5177	LR: 9.425e-02	Score 83.819	Data time: 2.4340, Total iter time: 6.2186
thomas 04/05 22:18:19 ===> Epoch[26](7680/301): Loss 0.5487	LR: 9.422e-02	Score 82.912	Data time: 2.4527, Total iter time: 6.1146
thomas 04/05 22:22:25 ===> Epoch[26](7720/301): Loss 0.6059	LR: 9.419e-02	Score 81.238	Data time: 2.3562, Total iter time: 6.0764
thomas 04/05 22:26:28 ===> Epoch[26](7760/301): Loss 0.5287	LR: 9.416e-02	Score 83.401	Data time: 2.3023, Total iter time: 5.9853
thomas 04/05 22:29:59 ===> Epoch[26](7800/301): Loss 0.5588	LR: 9.413e-02	Score 82.739	Data time: 2.0374, Total iter time: 5.2007
thomas 04/05 22:33:38 ===> Epoch[27](7840/301): Loss 0.5716	LR: 9.410e-02	Score 82.522	Data time: 2.0929, Total iter time: 5.4184
thomas 04/05 22:37:53 ===> Epoch[27](7880/301): Loss 0.5466	LR: 9.407e-02	Score 83.038	Data time: 2.5301, Total iter time: 6.3005
thomas 04/05 22:42:10 ===> Epoch[27](7920/301): Loss 0.5902	LR: 9.404e-02	Score 81.911	Data time: 2.5356, Total iter time: 6.3397
thomas 04/05 22:46:14 ===> Epoch[27](7960/301): Loss 0.5351	LR: 9.401e-02	Score 83.539	Data time: 2.3676, Total iter time: 6.0307
thomas 04/05 22:50:05 ===> Epoch[27](8000/301): Loss 0.4951	LR: 9.398e-02	Score 84.729	Data time: 2.2168, Total iter time: 5.7008
thomas 04/05 22:50:07 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/05 22:50:07 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/05 22:52:18 101/312: Data time: 0.0025, Iter time: 0.8422	Loss 0.318 (AVG: 0.695)	Score 91.367 (AVG: 80.547)	mIOU 48.168 mAP 66.246 mAcc 58.903
IOU: 72.256 96.233 48.908 47.560 81.705 58.621 66.623 40.080 21.060 76.341 3.503 33.908 34.935 53.402 37.658 27.854 78.785 18.678 42.175 23.067
mAP: 75.029 97.115 58.226 76.392 84.120 85.160 68.555 52.676 47.445 72.227 34.657 49.141 53.471 60.773 46.376 85.547 92.049 63.182 75.125 47.653
mAcc: 89.327 98.698 69.693 84.029 88.966 97.924 79.189 62.412 21.706 92.234 5.223 36.004 45.118 61.006 43.734 30.912 81.842 19.026 42.223 28.787

thomas 04/05 22:54:08 201/312: Data time: 0.0030, Iter time: 0.5346	Loss 0.658 (AVG: 0.692)	Score 81.369 (AVG: 80.549)	mIOU 48.124 mAP 64.819 mAcc 58.172
IOU: 73.238 95.962 50.019 57.653 77.463 57.880 61.316 36.416 19.827 69.392 4.957 37.192 34.746 53.241 38.458 33.470 76.887 17.912 42.375 24.069
mAP: 76.171 97.210 55.733 68.186 82.512 82.601 64.332 52.154 44.570 71.440 29.089 51.120 51.235 63.672 47.097 81.988 92.911 66.392 72.591 45.383
mAcc: 88.693 98.630 68.170 79.272 86.346 98.425 74.815 58.905 20.435 88.556 6.217 39.901 42.738 60.795 43.548 36.028 79.626 18.205 42.403 31.730

thomas 04/05 22:56:02 301/312: Data time: 0.0028, Iter time: 0.5253	Loss 0.979 (AVG: 0.713)	Score 72.725 (AVG: 79.917)	mIOU 47.470 mAP 65.068 mAcc 57.630
IOU: 72.468 95.556 47.721 57.726 77.528 54.283 60.238 35.407 22.293 67.010 4.986 37.317 33.725 60.252 33.287 36.111 74.917 15.715 40.391 22.471
mAP: 75.546 97.046 54.242 68.337 83.753 82.729 64.384 51.521 44.801 72.051 28.522 52.312 51.750 69.506 44.507 82.630 90.738 66.512 75.866 44.598
mAcc: 88.566 98.444 65.426 78.330 86.498 97.927 74.264 57.066 22.948 86.482 6.004 40.041 42.361 68.252 38.771 39.080 77.047 15.938 40.421 28.736

thomas 04/05 22:56:15 312/312: Data time: 0.0025, Iter time: 0.4474	Loss 1.023 (AVG: 0.708)	Score 69.994 (AVG: 80.097)	mIOU 47.478 mAP 65.052 mAcc 57.561
IOU: 72.634 95.526 47.660 57.395 78.449 54.930 60.828 35.341 21.964 67.318 4.889 37.317 33.465 59.752 33.286 35.091 75.142 15.476 40.391 22.707
mAP: 75.358 97.062 54.144 67.045 84.160 82.911 65.376 51.673 44.989 71.755 28.214 52.312 51.653 69.177 44.507 82.946 90.900 65.963 75.866 45.031
mAcc: 88.700 98.435 65.411 77.762 87.206 98.014 74.904 56.864 22.607 86.615 5.980 40.041 41.889 67.696 38.771 37.888 77.237 15.692 40.421 29.083

thomas 04/05 22:56:15 Finished test. Elapsed time: 368.3164
thomas 04/05 22:56:16 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/05 22:56:17 Current best mIoU: 47.478 at iter 8000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/05 23:00:22 ===> Epoch[27](8040/301): Loss 0.5213	LR: 9.395e-02	Score 83.489	Data time: 2.3371, Total iter time: 6.0719
thomas 04/05 23:04:35 ===> Epoch[27](8080/301): Loss 0.5576	LR: 9.392e-02	Score 82.828	Data time: 2.5240, Total iter time: 6.2516
thomas 04/05 23:08:24 ===> Epoch[27](8120/301): Loss 0.5618	LR: 9.389e-02	Score 82.964	Data time: 2.2655, Total iter time: 5.6363
thomas 04/05 23:12:22 ===> Epoch[28](8160/301): Loss 0.5280	LR: 9.386e-02	Score 83.589	Data time: 2.2819, Total iter time: 5.8825
thomas 04/05 23:16:11 ===> Epoch[28](8200/301): Loss 0.5643	LR: 9.383e-02	Score 82.798	Data time: 2.1677, Total iter time: 5.6500
thomas 04/05 23:20:08 ===> Epoch[28](8240/301): Loss 0.6202	LR: 9.380e-02	Score 80.790	Data time: 2.2665, Total iter time: 5.8565
thomas 04/05 23:24:07 ===> Epoch[28](8280/301): Loss 0.5242	LR: 9.377e-02	Score 84.040	Data time: 2.2978, Total iter time: 5.8830
thomas 04/05 23:28:33 ===> Epoch[28](8320/301): Loss 0.5880	LR: 9.374e-02	Score 81.716	Data time: 2.6246, Total iter time: 6.5747
thomas 04/05 23:32:40 ===> Epoch[28](8360/301): Loss 0.5031	LR: 9.371e-02	Score 84.559	Data time: 2.3995, Total iter time: 6.0909
thomas 04/05 23:36:27 ===> Epoch[28](8400/301): Loss 0.5365	LR: 9.368e-02	Score 83.837	Data time: 2.1798, Total iter time: 5.6169
thomas 04/05 23:40:25 ===> Epoch[29](8440/301): Loss 0.5398	LR: 9.365e-02	Score 83.034	Data time: 2.2633, Total iter time: 5.8691
thomas 04/05 23:44:29 ===> Epoch[29](8480/301): Loss 0.5560	LR: 9.362e-02	Score 82.806	Data time: 2.3200, Total iter time: 6.0332
thomas 04/05 23:48:29 ===> Epoch[29](8520/301): Loss 0.5168	LR: 9.359e-02	Score 83.786	Data time: 2.3465, Total iter time: 5.9151
thomas 04/05 23:52:41 ===> Epoch[29](8560/301): Loss 0.5066	LR: 9.356e-02	Score 84.356	Data time: 2.5072, Total iter time: 6.2101
thomas 04/05 23:57:02 ===> Epoch[29](8600/301): Loss 0.5772	LR: 9.353e-02	Score 82.107	Data time: 2.5343, Total iter time: 6.4353
thomas 04/06 00:00:49 ===> Epoch[29](8640/301): Loss 0.5059	LR: 9.350e-02	Score 84.434	Data time: 2.1766, Total iter time: 5.5952
thomas 04/06 00:04:29 ===> Epoch[29](8680/301): Loss 0.5209	LR: 9.347e-02	Score 83.791	Data time: 2.0980, Total iter time: 5.4306
thomas 04/06 00:08:03 ===> Epoch[29](8720/301): Loss 0.5038	LR: 9.344e-02	Score 84.469	Data time: 2.0453, Total iter time: 5.2778
thomas 04/06 00:12:05 ===> Epoch[30](8760/301): Loss 0.4929	LR: 9.341e-02	Score 85.051	Data time: 2.3487, Total iter time: 5.9739
thomas 04/06 00:16:05 ===> Epoch[30](8800/301): Loss 0.5310	LR: 9.338e-02	Score 83.202	Data time: 2.4055, Total iter time: 5.9067
thomas 04/06 00:20:09 ===> Epoch[30](8840/301): Loss 0.5091	LR: 9.334e-02	Score 83.854	Data time: 2.3862, Total iter time: 6.0308
thomas 04/06 00:24:10 ===> Epoch[30](8880/301): Loss 0.5835	LR: 9.331e-02	Score 82.028	Data time: 2.2893, Total iter time: 5.9422
thomas 04/06 00:28:05 ===> Epoch[30](8920/301): Loss 0.5200	LR: 9.328e-02	Score 83.919	Data time: 2.2380, Total iter time: 5.7836
thomas 04/06 00:32:04 ===> Epoch[30](8960/301): Loss 0.5424	LR: 9.325e-02	Score 83.589	Data time: 2.2956, Total iter time: 5.9160
thomas 04/06 00:36:07 ===> Epoch[30](9000/301): Loss 0.5214	LR: 9.322e-02	Score 84.029	Data time: 2.3540, Total iter time: 5.9859
thomas 04/06 00:36:08 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 00:36:08 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 00:38:22 101/312: Data time: 0.0027, Iter time: 0.6976	Loss 0.376 (AVG: 0.660)	Score 88.318 (AVG: 79.320)	mIOU 51.783 mAP 67.426 mAcc 62.141
IOU: 68.880 95.516 46.959 70.952 79.928 69.939 52.228 33.682 35.631 66.625 10.601 28.727 44.139 46.801 22.256 56.899 83.817 28.445 65.516 28.110
mAP: 73.640 96.621 59.691 67.770 86.514 83.160 61.723 56.998 45.886 73.439 36.129 50.953 68.165 67.804 45.976 77.630 92.379 78.839 84.667 40.539
mAcc: 80.152 98.626 60.914 77.987 83.778 93.146 58.412 82.659 40.471 81.357 13.524 30.855 83.566 49.414 27.146 59.173 87.382 28.998 66.188 39.077

thomas 04/06 00:40:32 201/312: Data time: 0.0034, Iter time: 0.6407	Loss 0.988 (AVG: 0.658)	Score 72.062 (AVG: 79.664)	mIOU 50.284 mAP 66.405 mAcc 60.361
IOU: 69.614 95.563 47.997 66.269 83.205 73.373 53.874 33.442 29.715 66.315 8.854 28.727 40.218 45.802 22.245 41.527 81.584 25.817 63.333 28.211
mAP: 75.593 96.332 56.047 66.560 86.547 82.627 64.584 57.462 46.796 63.874 30.910 55.203 63.429 68.912 44.196 78.468 92.935 78.658 77.680 41.294
mAcc: 80.857 98.598 64.764 73.002 88.084 92.540 58.891 83.669 32.338 81.776 11.219 30.272 81.077 47.911 25.244 42.994 85.100 26.146 63.814 38.918

thomas 04/06 00:42:33 301/312: Data time: 0.0028, Iter time: 0.6246	Loss 0.430 (AVG: 0.670)	Score 83.377 (AVG: 79.262)	mIOU 50.590 mAP 66.886 mAcc 60.739
IOU: 69.123 95.820 49.777 61.011 83.594 70.911 53.921 31.245 30.891 70.647 7.153 34.149 44.627 41.237 31.024 39.761 80.737 27.976 60.381 27.814
mAP: 76.140 96.646 56.214 64.784 87.488 82.673 63.354 55.447 46.055 68.109 27.910 59.257 65.913 66.196 49.218 79.659 92.064 77.309 80.809 42.480
mAcc: 80.561 98.655 68.236 71.827 88.581 92.542 59.358 82.019 33.444 85.812 9.111 35.808 80.948 43.162 34.246 41.963 83.564 28.363 60.835 35.736

thomas 04/06 00:42:43 312/312: Data time: 0.0029, Iter time: 0.3681	Loss 0.507 (AVG: 0.670)	Score 80.943 (AVG: 79.253)	mIOU 50.690 mAP 67.137 mAcc 60.894
IOU: 69.127 95.825 49.830 61.079 83.724 70.842 53.013 31.394 30.432 71.299 7.078 33.820 43.304 43.616 30.769 39.184 81.472 27.971 61.695 28.328
mAP: 75.845 96.715 55.697 65.307 87.652 82.673 63.627 56.660 46.232 68.377 27.535 59.264 66.101 68.051 49.427 79.119 92.311 77.309 81.925 42.904
mAcc: 80.505 98.657 68.345 72.020 88.649 92.542 58.196 82.496 32.861 86.175 9.001 35.412 80.781 45.550 33.942 41.649 84.241 28.363 62.129 36.366

thomas 04/06 00:42:43 Finished test. Elapsed time: 394.9586
thomas 04/06 00:42:45 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/06 00:42:45 Current best mIoU: 50.690 at iter 9000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 00:46:33 ===> Epoch[31](9040/301): Loss 0.5478	LR: 9.319e-02	Score 82.949	Data time: 2.2160, Total iter time: 5.6471
thomas 04/06 00:50:19 ===> Epoch[31](9080/301): Loss 0.5106	LR: 9.316e-02	Score 83.711	Data time: 2.1677, Total iter time: 5.5704
thomas 04/06 00:54:34 ===> Epoch[31](9120/301): Loss 0.5332	LR: 9.313e-02	Score 83.319	Data time: 2.4326, Total iter time: 6.2995
thomas 04/06 00:58:39 ===> Epoch[31](9160/301): Loss 0.5297	LR: 9.310e-02	Score 83.621	Data time: 2.3659, Total iter time: 6.0568
thomas 04/06 01:02:29 ===> Epoch[31](9200/301): Loss 0.4933	LR: 9.307e-02	Score 84.709	Data time: 2.2577, Total iter time: 5.6741
thomas 04/06 01:06:36 ===> Epoch[31](9240/301): Loss 0.5352	LR: 9.304e-02	Score 83.204	Data time: 2.4509, Total iter time: 6.0996
thomas 04/06 01:10:32 ===> Epoch[31](9280/301): Loss 0.5537	LR: 9.301e-02	Score 83.272	Data time: 2.2977, Total iter time: 5.8260
thomas 04/06 01:14:15 ===> Epoch[31](9320/301): Loss 0.5931	LR: 9.298e-02	Score 81.914	Data time: 2.1276, Total iter time: 5.5075
thomas 04/06 01:18:06 ===> Epoch[32](9360/301): Loss 0.5703	LR: 9.295e-02	Score 82.311	Data time: 2.2388, Total iter time: 5.7051
thomas 04/06 01:22:05 ===> Epoch[32](9400/301): Loss 0.5077	LR: 9.292e-02	Score 84.072	Data time: 2.3118, Total iter time: 5.8940
thomas 04/06 01:26:08 ===> Epoch[32](9440/301): Loss 0.4512	LR: 9.289e-02	Score 86.153	Data time: 2.4164, Total iter time: 5.9822
thomas 04/06 01:30:31 ===> Epoch[32](9480/301): Loss 0.5117	LR: 9.286e-02	Score 84.671	Data time: 2.6400, Total iter time: 6.5086
thomas 04/06 01:34:27 ===> Epoch[32](9520/301): Loss 0.5281	LR: 9.283e-02	Score 83.457	Data time: 2.2515, Total iter time: 5.8235
thomas 04/06 01:38:09 ===> Epoch[32](9560/301): Loss 0.4983	LR: 9.280e-02	Score 85.020	Data time: 2.1568, Total iter time: 5.4851
thomas 04/06 01:42:04 ===> Epoch[32](9600/301): Loss 0.5157	LR: 9.277e-02	Score 83.851	Data time: 2.2847, Total iter time: 5.8016
thomas 04/06 01:46:17 ===> Epoch[33](9640/301): Loss 0.5150	LR: 9.274e-02	Score 83.760	Data time: 2.4935, Total iter time: 6.2574
thomas 04/06 01:50:27 ===> Epoch[33](9680/301): Loss 0.4804	LR: 9.271e-02	Score 84.825	Data time: 2.4667, Total iter time: 6.1864
thomas 04/06 01:54:23 ===> Epoch[33](9720/301): Loss 0.5424	LR: 9.268e-02	Score 83.002	Data time: 2.3081, Total iter time: 5.8238
thomas 04/06 01:58:00 ===> Epoch[33](9760/301): Loss 0.4943	LR: 9.265e-02	Score 85.199	Data time: 2.0978, Total iter time: 5.3520
thomas 04/06 02:01:54 ===> Epoch[33](9800/301): Loss 0.5191	LR: 9.262e-02	Score 83.974	Data time: 2.2546, Total iter time: 5.7535
thomas 04/06 02:05:49 ===> Epoch[33](9840/301): Loss 0.5122	LR: 9.259e-02	Score 84.345	Data time: 2.2764, Total iter time: 5.7928
thomas 04/06 02:09:58 ===> Epoch[33](9880/301): Loss 0.5295	LR: 9.256e-02	Score 82.846	Data time: 2.4003, Total iter time: 6.1471
thomas 04/06 02:14:03 ===> Epoch[33](9920/301): Loss 0.5083	LR: 9.253e-02	Score 84.299	Data time: 2.4366, Total iter time: 6.0433
thomas 04/06 02:18:09 ===> Epoch[34](9960/301): Loss 0.5201	LR: 9.250e-02	Score 83.714	Data time: 2.4167, Total iter time: 6.0834
thomas 04/06 02:22:20 ===> Epoch[34](10000/301): Loss 0.4875	LR: 9.247e-02	Score 85.013	Data time: 2.3973, Total iter time: 6.1972
thomas 04/06 02:22:22 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 02:22:22 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 02:24:27 101/312: Data time: 0.0033, Iter time: 0.5370	Loss 0.535 (AVG: 0.745)	Score 89.568 (AVG: 77.660)	mIOU 41.896 mAP 64.398 mAcc 54.346
IOU: 66.375 95.491 53.630 45.263 82.496 77.622 58.899 32.631 35.704 76.316 5.680 46.971 40.052 10.826 28.076 6.660 9.933 17.228 18.400 29.662
mAP: 75.709 97.257 57.616 67.779 86.799 84.152 63.727 54.339 48.989 69.611 25.841 52.896 60.556 71.946 50.902 56.263 77.832 64.571 77.534 43.643
mAcc: 74.103 98.884 73.299 81.346 91.360 90.325 73.930 58.329 48.161 87.869 6.864 53.157 51.143 77.521 28.157 6.796 9.933 17.439 18.406 39.897

thomas 04/06 02:26:20 201/312: Data time: 0.0029, Iter time: 0.7695	Loss 0.641 (AVG: 0.748)	Score 78.967 (AVG: 77.386)	mIOU 42.708 mAP 65.337 mAcc 54.920
IOU: 65.383 95.357 51.121 52.569 82.344 77.647 59.157 30.901 39.515 68.123 6.097 46.962 40.106 20.711 30.721 10.373 9.917 20.550 19.704 26.902
mAP: 76.070 97.375 56.395 70.274 88.598 84.286 67.186 51.052 51.154 69.453 29.220 55.953 59.866 72.291 49.919 68.274 78.540 68.437 71.346 41.045
mAcc: 73.466 98.853 69.361 84.732 90.996 91.610 75.325 54.199 53.084 82.290 7.073 54.334 48.897 85.253 31.005 10.502 9.917 20.812 19.713 36.979

thomas 04/06 02:28:17 301/312: Data time: 0.0025, Iter time: 0.4187	Loss 0.384 (AVG: 0.739)	Score 88.621 (AVG: 77.570)	mIOU 42.635 mAP 65.741 mAcc 54.842
IOU: 65.974 95.515 50.829 53.069 83.307 76.173 62.284 31.528 39.264 67.316 5.534 50.789 40.528 20.687 27.689 8.380 7.072 22.339 16.796 27.637
mAP: 75.986 97.333 54.998 71.865 87.376 84.171 69.037 51.110 49.714 66.484 27.024 58.551 61.507 74.664 49.334 70.493 77.540 70.175 74.087 43.374
mAcc: 73.538 98.850 69.269 86.408 91.996 91.085 76.757 54.249 51.583 79.965 6.428 58.204 48.980 87.621 28.072 8.631 7.072 22.641 16.803 38.695

thomas 04/06 02:28:30 312/312: Data time: 0.0030, Iter time: 0.4758	Loss 0.254 (AVG: 0.733)	Score 94.144 (AVG: 77.705)	mIOU 43.009 mAP 65.926 mAcc 55.230
IOU: 66.069 95.534 51.485 52.910 83.159 76.630 62.423 31.823 40.021 67.240 5.400 50.602 41.458 21.760 29.634 9.764 6.793 22.622 17.001 27.853
mAP: 76.015 97.392 55.474 71.657 87.345 83.325 68.350 51.574 50.037 66.499 27.048 58.260 61.640 75.428 51.085 71.599 78.026 70.326 73.934 43.499
mAcc: 73.564 98.846 70.105 86.490 92.100 91.277 76.763 54.979 52.302 79.812 6.264 57.925 50.019 88.334 30.051 10.064 6.794 22.926 17.008 38.979

thomas 04/06 02:28:30 Finished test. Elapsed time: 368.3927
thomas 04/06 02:28:30 Current best mIoU: 50.690 at iter 9000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 02:32:26 ===> Epoch[34](10040/301): Loss 0.5226	LR: 9.244e-02	Score 83.580	Data time: 2.2649, Total iter time: 5.8154
thomas 04/06 02:36:31 ===> Epoch[34](10080/301): Loss 0.5469	LR: 9.241e-02	Score 84.078	Data time: 2.3994, Total iter time: 6.0639
thomas 04/06 02:40:32 ===> Epoch[34](10120/301): Loss 0.4745	LR: 9.238e-02	Score 85.324	Data time: 2.3843, Total iter time: 5.9467
thomas 04/06 02:44:25 ===> Epoch[34](10160/301): Loss 0.5178	LR: 9.235e-02	Score 83.820	Data time: 2.2464, Total iter time: 5.7374
thomas 04/06 02:48:13 ===> Epoch[34](10200/301): Loss 0.5212	LR: 9.232e-02	Score 83.591	Data time: 2.1746, Total iter time: 5.6278
thomas 04/06 02:51:59 ===> Epoch[35](10240/301): Loss 0.5001	LR: 9.229e-02	Score 84.580	Data time: 2.1706, Total iter time: 5.5815
thomas 04/06 02:55:47 ===> Epoch[35](10280/301): Loss 0.4807	LR: 9.226e-02	Score 85.043	Data time: 2.2124, Total iter time: 5.6325
thomas 04/06 02:59:45 ===> Epoch[35](10320/301): Loss 0.5204	LR: 9.223e-02	Score 83.741	Data time: 2.3331, Total iter time: 5.8806
thomas 04/06 03:03:47 ===> Epoch[35](10360/301): Loss 0.4739	LR: 9.220e-02	Score 85.147	Data time: 2.3984, Total iter time: 5.9779
thomas 04/06 03:07:42 ===> Epoch[35](10400/301): Loss 0.4894	LR: 9.217e-02	Score 84.648	Data time: 2.2768, Total iter time: 5.8004
thomas 04/06 03:11:37 ===> Epoch[35](10440/301): Loss 0.4947	LR: 9.213e-02	Score 84.543	Data time: 2.2594, Total iter time: 5.7826
thomas 04/06 03:15:36 ===> Epoch[35](10480/301): Loss 0.5315	LR: 9.210e-02	Score 83.475	Data time: 2.2895, Total iter time: 5.9042
thomas 04/06 03:19:54 ===> Epoch[35](10520/301): Loss 0.4971	LR: 9.207e-02	Score 84.510	Data time: 2.4831, Total iter time: 6.3647
thomas 04/06 03:24:13 ===> Epoch[36](10560/301): Loss 0.5082	LR: 9.204e-02	Score 84.580	Data time: 2.5412, Total iter time: 6.4243
thomas 04/06 03:28:17 ===> Epoch[36](10600/301): Loss 0.5213	LR: 9.201e-02	Score 84.169	Data time: 2.4242, Total iter time: 6.0313
thomas 04/06 03:32:12 ===> Epoch[36](10640/301): Loss 0.4912	LR: 9.198e-02	Score 84.624	Data time: 2.3025, Total iter time: 5.8011
thomas 04/06 03:36:16 ===> Epoch[36](10680/301): Loss 0.5015	LR: 9.195e-02	Score 84.146	Data time: 2.3473, Total iter time: 6.0298
thomas 04/06 03:40:31 ===> Epoch[36](10720/301): Loss 0.5118	LR: 9.192e-02	Score 83.795	Data time: 2.4575, Total iter time: 6.3073
thomas 04/06 03:44:59 ===> Epoch[36](10760/301): Loss 0.4894	LR: 9.189e-02	Score 83.976	Data time: 2.5569, Total iter time: 6.6047
thomas 04/06 03:49:08 ===> Epoch[36](10800/301): Loss 0.4861	LR: 9.186e-02	Score 85.052	Data time: 2.4502, Total iter time: 6.1550
thomas 04/06 03:53:37 ===> Epoch[37](10840/301): Loss 0.4827	LR: 9.183e-02	Score 85.290	Data time: 2.6260, Total iter time: 6.6362
thomas 04/06 03:57:42 ===> Epoch[37](10880/301): Loss 0.5317	LR: 9.180e-02	Score 83.579	Data time: 2.3788, Total iter time: 6.0423
thomas 04/06 04:02:05 ===> Epoch[37](10920/301): Loss 0.4681	LR: 9.177e-02	Score 85.488	Data time: 2.4868, Total iter time: 6.4717
thomas 04/06 04:06:07 ===> Epoch[37](10960/301): Loss 0.4944	LR: 9.174e-02	Score 84.755	Data time: 2.3589, Total iter time: 5.9766
thomas 04/06 04:10:11 ===> Epoch[37](11000/301): Loss 0.4800	LR: 9.171e-02	Score 85.007	Data time: 2.3934, Total iter time: 6.0263
thomas 04/06 04:10:12 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 04:10:12 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 04:12:28 101/312: Data time: 0.0027, Iter time: 1.2622	Loss 0.519 (AVG: 0.624)	Score 85.223 (AVG: 81.543)	mIOU 50.808 mAP 68.857 mAcc 61.337
IOU: 75.083 95.790 49.808 68.107 80.541 61.081 58.036 40.973 27.072 71.129 7.878 19.785 44.547 42.883 39.023 39.633 67.722 43.560 51.039 32.477
mAP: 77.197 97.526 56.900 71.351 86.797 75.144 66.597 59.616 47.951 63.252 40.036 59.610 62.483 66.548 47.691 91.633 92.290 81.734 83.771 49.014
mAcc: 87.447 98.766 65.984 87.534 82.877 84.965 61.968 59.505 28.270 93.721 8.154 20.306 63.001 66.979 43.142 45.021 67.997 44.541 51.127 65.436

thomas 04/06 04:14:31 201/312: Data time: 0.0030, Iter time: 1.3384	Loss 1.118 (AVG: 0.616)	Score 60.039 (AVG: 81.597)	mIOU 52.097 mAP 68.964 mAcc 62.431
IOU: 75.053 95.895 48.546 66.724 81.547 64.899 58.237 38.541 28.568 70.656 5.179 17.122 45.990 58.145 33.119 48.807 74.962 43.904 54.977 31.061
mAP: 77.937 97.651 57.147 70.113 88.234 76.734 67.949 56.620 49.749 65.477 33.558 57.752 61.966 74.948 44.279 88.112 94.441 84.001 84.748 47.859
mAcc: 86.932 98.856 67.647 85.719 83.943 84.416 62.554 62.223 30.241 86.731 5.313 17.572 62.906 80.886 39.477 55.896 77.482 45.117 55.162 59.543

thomas 04/06 04:16:30 301/312: Data time: 0.0032, Iter time: 0.8088	Loss 0.652 (AVG: 0.623)	Score 77.415 (AVG: 81.476)	mIOU 51.699 mAP 68.630 mAcc 62.274
IOU: 75.054 95.805 50.445 63.785 81.551 69.749 54.775 39.744 31.471 70.586 3.684 22.930 47.216 55.299 34.946 37.838 73.801 38.524 55.787 30.993
mAP: 77.772 97.580 59.283 67.252 87.605 78.878 66.072 57.125 50.655 69.343 33.704 57.416 61.507 77.696 45.947 83.170 94.180 79.397 80.353 47.671
mAcc: 86.685 98.729 69.963 83.311 84.293 87.527 59.079 63.938 33.995 86.349 3.739 23.622 64.411 81.689 41.924 42.829 78.296 39.512 56.064 59.537

thomas 04/06 04:16:43 312/312: Data time: 0.0045, Iter time: 0.5253	Loss 0.484 (AVG: 0.626)	Score 84.151 (AVG: 81.322)	mIOU 51.475 mAP 68.679 mAcc 62.167
IOU: 74.810 95.833 50.389 62.555 81.527 69.965 54.241 39.523 30.663 69.632 3.536 22.970 46.436 54.802 35.341 37.838 73.950 38.400 55.787 31.312
mAP: 77.552 97.620 59.564 67.657 87.422 79.130 66.035 57.389 49.840 69.964 34.024 57.863 61.507 76.330 46.810 83.170 94.217 79.597 80.353 47.525
mAcc: 86.519 98.743 70.386 83.706 84.237 87.722 58.545 64.143 33.043 86.461 3.587 23.659 64.411 81.629 42.316 42.829 78.360 39.376 56.064 57.612

thomas 04/06 04:16:43 Finished test. Elapsed time: 390.8479
thomas 04/06 04:16:45 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/06 04:16:45 Current best mIoU: 51.475 at iter 11000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 04:20:31 ===> Epoch[37](11040/301): Loss 0.4562	LR: 9.168e-02	Score 85.596	Data time: 2.1940, Total iter time: 5.5842
thomas 04/06 04:24:18 ===> Epoch[37](11080/301): Loss 0.5101	LR: 9.165e-02	Score 84.323	Data time: 2.1921, Total iter time: 5.5846
thomas 04/06 04:28:12 ===> Epoch[37](11120/301): Loss 0.4901	LR: 9.162e-02	Score 84.501	Data time: 2.2518, Total iter time: 5.7820
thomas 04/06 04:32:17 ===> Epoch[38](11160/301): Loss 0.5112	LR: 9.159e-02	Score 83.799	Data time: 2.3834, Total iter time: 6.0403
thomas 04/06 04:36:18 ===> Epoch[38](11200/301): Loss 0.5338	LR: 9.156e-02	Score 83.740	Data time: 2.3759, Total iter time: 5.9600
thomas 04/06 04:40:20 ===> Epoch[38](11240/301): Loss 0.4662	LR: 9.153e-02	Score 85.376	Data time: 2.3739, Total iter time: 5.9762
thomas 04/06 04:44:11 ===> Epoch[38](11280/301): Loss 0.4838	LR: 9.150e-02	Score 84.554	Data time: 2.2499, Total iter time: 5.6849
thomas 04/06 04:47:59 ===> Epoch[38](11320/301): Loss 0.5025	LR: 9.147e-02	Score 84.224	Data time: 2.1695, Total iter time: 5.6432
thomas 04/06 04:52:02 ===> Epoch[38](11360/301): Loss 0.4665	LR: 9.144e-02	Score 85.349	Data time: 2.3477, Total iter time: 5.9901
thomas 04/06 04:55:48 ===> Epoch[38](11400/301): Loss 0.4862	LR: 9.141e-02	Score 84.637	Data time: 2.1710, Total iter time: 5.5684
thomas 04/06 04:59:33 ===> Epoch[39](11440/301): Loss 0.4533	LR: 9.138e-02	Score 85.745	Data time: 2.2350, Total iter time: 5.5707
thomas 04/06 05:03:34 ===> Epoch[39](11480/301): Loss 0.5037	LR: 9.135e-02	Score 84.505	Data time: 2.3609, Total iter time: 5.9384
thomas 04/06 05:07:31 ===> Epoch[39](11520/301): Loss 0.4884	LR: 9.132e-02	Score 84.858	Data time: 2.3157, Total iter time: 5.8556
thomas 04/06 05:11:25 ===> Epoch[39](11560/301): Loss 0.4511	LR: 9.129e-02	Score 85.896	Data time: 2.2738, Total iter time: 5.7544
thomas 04/06 05:15:17 ===> Epoch[39](11600/301): Loss 0.4778	LR: 9.126e-02	Score 84.983	Data time: 2.2572, Total iter time: 5.7394
thomas 04/06 05:19:23 ===> Epoch[39](11640/301): Loss 0.4684	LR: 9.123e-02	Score 85.068	Data time: 2.3954, Total iter time: 6.0719
thomas 04/06 05:23:38 ===> Epoch[39](11680/301): Loss 0.5110	LR: 9.120e-02	Score 84.139	Data time: 2.4917, Total iter time: 6.2939
thomas 04/06 05:27:43 ===> Epoch[39](11720/301): Loss 0.4898	LR: 9.117e-02	Score 84.603	Data time: 2.3645, Total iter time: 6.0363
thomas 04/06 05:31:44 ===> Epoch[40](11760/301): Loss 0.4862	LR: 9.114e-02	Score 84.980	Data time: 2.3453, Total iter time: 5.9609
thomas 04/06 05:35:37 ===> Epoch[40](11800/301): Loss 0.4844	LR: 9.110e-02	Score 84.986	Data time: 2.2304, Total iter time: 5.7431
thomas 04/06 05:39:35 ===> Epoch[40](11840/301): Loss 0.5307	LR: 9.107e-02	Score 83.732	Data time: 2.2766, Total iter time: 5.8876
thomas 04/06 05:43:41 ===> Epoch[40](11880/301): Loss 0.4539	LR: 9.104e-02	Score 86.123	Data time: 2.3865, Total iter time: 6.0591
thomas 04/06 05:47:28 ===> Epoch[40](11920/301): Loss 0.4804	LR: 9.101e-02	Score 84.845	Data time: 2.2238, Total iter time: 5.6131
thomas 04/06 05:51:27 ===> Epoch[40](11960/301): Loss 0.4749	LR: 9.098e-02	Score 85.008	Data time: 2.3260, Total iter time: 5.8983
thomas 04/06 05:55:17 ===> Epoch[40](12000/301): Loss 0.4474	LR: 9.095e-02	Score 85.904	Data time: 2.2547, Total iter time: 5.6761
thomas 04/06 05:55:19 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 05:55:19 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 05:57:24 101/312: Data time: 0.0036, Iter time: 0.3353	Loss 0.091 (AVG: 0.693)	Score 98.581 (AVG: 79.226)	mIOU 51.713 mAP 66.971 mAcc 65.775
IOU: 68.699 96.106 45.073 64.617 84.818 76.250 62.233 36.934 31.924 64.623 11.742 38.699 48.210 32.273 24.312 50.280 78.011 28.445 63.214 27.789
mAP: 75.586 96.876 51.871 69.668 85.289 73.363 62.105 58.879 48.616 60.831 27.579 64.071 60.303 83.846 50.047 80.856 92.831 74.515 84.482 37.806
mAcc: 78.106 98.472 67.138 83.301 90.177 87.590 72.353 73.753 33.294 72.991 21.971 42.513 61.649 94.654 25.406 83.443 88.038 32.731 70.505 37.407

thomas 04/06 05:59:20 201/312: Data time: 0.0024, Iter time: 0.4265	Loss 1.305 (AVG: 0.745)	Score 53.937 (AVG: 77.782)	mIOU 50.188 mAP 66.180 mAcc 63.856
IOU: 65.910 95.797 41.394 64.224 83.148 73.554 62.364 33.192 32.050 61.355 11.124 35.387 45.306 31.450 21.117 40.828 78.116 36.054 61.180 30.210
mAP: 73.573 96.888 51.762 74.201 84.126 73.570 62.943 53.770 47.510 60.921 26.572 62.479 56.576 72.402 46.287 81.760 94.932 77.260 83.248 42.827
mAcc: 76.035 98.401 67.025 81.071 89.061 84.211 72.884 71.510 34.215 68.279 18.762 37.676 57.949 87.732 22.982 70.292 88.905 40.441 70.691 38.994

thomas 04/06 06:01:15 301/312: Data time: 0.0025, Iter time: 0.5948	Loss 0.614 (AVG: 0.716)	Score 81.513 (AVG: 78.682)	mIOU 50.020 mAP 66.948 mAcc 63.418
IOU: 67.427 95.906 43.331 61.937 84.255 76.557 65.043 33.390 30.182 61.815 10.392 34.493 42.961 29.078 21.544 43.853 76.505 31.763 58.989 30.987
mAP: 74.809 97.323 54.819 74.595 86.041 77.471 67.907 55.432 48.166 61.572 27.898 63.980 55.761 73.608 42.993 83.088 94.220 75.280 77.338 46.660
mAcc: 77.611 98.355 68.694 81.753 89.745 86.689 74.519 68.998 32.103 68.824 18.500 36.232 57.540 87.602 23.315 67.557 87.051 35.080 68.528 39.656

thomas 04/06 06:01:29 312/312: Data time: 0.0022, Iter time: 0.6789	Loss 0.163 (AVG: 0.715)	Score 96.914 (AVG: 78.692)	mIOU 50.163 mAP 66.921 mAcc 63.632
IOU: 67.569 95.945 43.859 61.236 84.060 76.973 64.968 33.770 31.081 62.130 10.364 36.035 42.877 29.982 21.686 43.459 75.983 31.482 58.849 30.946
mAP: 74.788 97.376 54.444 73.403 85.410 78.184 67.368 55.860 47.730 61.291 27.720 63.996 55.848 74.162 44.234 83.088 94.220 75.353 77.338 46.609
mAcc: 77.735 98.365 69.238 81.312 89.571 87.077 74.536 69.462 33.017 69.141 18.678 37.824 57.448 88.143 23.630 67.557 87.051 34.805 68.528 39.528

thomas 04/06 06:01:29 Finished test. Elapsed time: 369.8016
thomas 04/06 06:01:29 Current best mIoU: 51.475 at iter 11000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 06:05:14 ===> Epoch[40](12040/301): Loss 0.4704	LR: 9.092e-02	Score 84.975	Data time: 2.1841, Total iter time: 5.5579
thomas 04/06 06:09:19 ===> Epoch[41](12080/301): Loss 0.4338	LR: 9.089e-02	Score 86.541	Data time: 2.3694, Total iter time: 6.0289
thomas 04/06 06:13:26 ===> Epoch[41](12120/301): Loss 0.5017	LR: 9.086e-02	Score 84.606	Data time: 2.4098, Total iter time: 6.1091
thomas 04/06 06:17:28 ===> Epoch[41](12160/301): Loss 0.4854	LR: 9.083e-02	Score 84.610	Data time: 2.3571, Total iter time: 5.9722
thomas 04/06 06:21:46 ===> Epoch[41](12200/301): Loss 0.4570	LR: 9.080e-02	Score 85.622	Data time: 2.4745, Total iter time: 6.3568
thomas 04/06 06:25:32 ===> Epoch[41](12240/301): Loss 0.4609	LR: 9.077e-02	Score 85.501	Data time: 2.2167, Total iter time: 5.5792
thomas 04/06 06:29:27 ===> Epoch[41](12280/301): Loss 0.4858	LR: 9.074e-02	Score 84.842	Data time: 2.3384, Total iter time: 5.8140
thomas 04/06 06:33:27 ===> Epoch[41](12320/301): Loss 0.4883	LR: 9.071e-02	Score 84.854	Data time: 2.3430, Total iter time: 5.9231
thomas 04/06 06:37:34 ===> Epoch[42](12360/301): Loss 0.4753	LR: 9.068e-02	Score 85.687	Data time: 2.4092, Total iter time: 6.1082
thomas 04/06 06:41:32 ===> Epoch[42](12400/301): Loss 0.4428	LR: 9.065e-02	Score 86.107	Data time: 2.3434, Total iter time: 5.8713
thomas 04/06 06:45:41 ===> Epoch[42](12440/301): Loss 0.4575	LR: 9.062e-02	Score 86.204	Data time: 2.4070, Total iter time: 6.1428
thomas 04/06 06:49:37 ===> Epoch[42](12480/301): Loss 0.5381	LR: 9.059e-02	Score 83.375	Data time: 2.2939, Total iter time: 5.8353
thomas 04/06 06:53:29 ===> Epoch[42](12520/301): Loss 0.4457	LR: 9.056e-02	Score 85.995	Data time: 2.2463, Total iter time: 5.7298
thomas 04/06 06:57:35 ===> Epoch[42](12560/301): Loss 0.4675	LR: 9.053e-02	Score 85.441	Data time: 2.3867, Total iter time: 6.0504
thomas 04/06 07:01:28 ===> Epoch[42](12600/301): Loss 0.4797	LR: 9.050e-02	Score 85.164	Data time: 2.2813, Total iter time: 5.7518
thomas 04/06 07:05:27 ===> Epoch[42](12640/301): Loss 0.4712	LR: 9.047e-02	Score 85.002	Data time: 2.3133, Total iter time: 5.8979
thomas 04/06 07:09:30 ===> Epoch[43](12680/301): Loss 0.4760	LR: 9.044e-02	Score 84.824	Data time: 2.3830, Total iter time: 5.9829
thomas 04/06 07:13:33 ===> Epoch[43](12720/301): Loss 0.4707	LR: 9.041e-02	Score 85.275	Data time: 2.3533, Total iter time: 5.9874
thomas 04/06 07:17:23 ===> Epoch[43](12760/301): Loss 0.4751	LR: 9.038e-02	Score 85.603	Data time: 2.2451, Total iter time: 5.6767
thomas 04/06 07:21:24 ===> Epoch[43](12800/301): Loss 0.4887	LR: 9.035e-02	Score 85.061	Data time: 2.3327, Total iter time: 5.9481
thomas 04/06 07:25:17 ===> Epoch[43](12840/301): Loss 0.4556	LR: 9.032e-02	Score 85.972	Data time: 2.2882, Total iter time: 5.7510
thomas 04/06 07:29:17 ===> Epoch[43](12880/301): Loss 0.4620	LR: 9.029e-02	Score 85.860	Data time: 2.3297, Total iter time: 5.9228
thomas 04/06 07:33:10 ===> Epoch[43](12920/301): Loss 0.4462	LR: 9.026e-02	Score 86.039	Data time: 2.2646, Total iter time: 5.7496
thomas 04/06 07:36:57 ===> Epoch[44](12960/301): Loss 0.4718	LR: 9.023e-02	Score 85.379	Data time: 2.2222, Total iter time: 5.5880
thomas 04/06 07:41:01 ===> Epoch[44](13000/301): Loss 0.4628	LR: 9.020e-02	Score 85.490	Data time: 2.3893, Total iter time: 6.0366
thomas 04/06 07:41:03 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 07:41:03 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 07:43:03 101/312: Data time: 0.0026, Iter time: 0.4280	Loss 0.220 (AVG: 0.623)	Score 93.975 (AVG: 81.581)	mIOU 51.884 mAP 66.483 mAcc 62.050
IOU: 75.534 94.860 43.975 62.526 82.922 73.758 61.130 40.437 38.263 66.896 9.789 53.341 33.037 59.391 33.398 39.431 51.308 33.070 54.916 29.691
mAP: 78.957 94.423 45.993 58.390 88.560 82.205 74.564 62.351 48.907 65.347 23.143 55.095 65.782 75.176 36.870 87.578 81.366 79.941 82.474 42.529
mAcc: 85.939 98.886 52.474 69.429 93.616 88.481 79.445 78.433 40.550 86.555 15.174 65.492 36.553 73.089 40.061 44.688 52.318 34.724 55.026 50.075

thomas 04/06 07:44:57 201/312: Data time: 0.0030, Iter time: 0.5242	Loss 0.438 (AVG: 0.631)	Score 84.834 (AVG: 81.427)	mIOU 51.050 mAP 67.557 mAcc 61.003
IOU: 74.670 95.415 43.604 62.792 82.819 78.430 60.268 38.142 36.872 66.292 9.002 49.569 33.801 57.251 39.398 34.253 43.004 37.908 46.318 31.197
mAP: 78.931 95.464 48.437 62.386 89.128 84.151 67.792 59.210 51.796 68.935 29.008 57.304 64.038 76.959 48.096 87.804 81.451 73.132 79.886 47.226
mAcc: 85.301 99.014 53.563 73.890 94.071 91.735 76.375 73.571 39.414 81.010 12.004 60.065 38.531 79.155 45.710 36.381 43.531 39.545 46.385 50.804

thomas 04/06 07:46:57 301/312: Data time: 0.0030, Iter time: 0.9952	Loss 0.502 (AVG: 0.628)	Score 86.983 (AVG: 81.425)	mIOU 50.703 mAP 66.586 mAcc 60.941
IOU: 74.473 95.294 44.495 64.215 83.253 75.048 59.782 38.967 34.084 68.067 9.270 53.664 34.234 54.521 36.587 31.955 46.455 38.609 40.282 30.802
mAP: 78.049 95.805 47.985 65.793 89.631 80.516 67.321 57.777 50.605 66.224 28.753 58.288 61.755 76.245 44.101 86.171 83.925 70.471 76.686 45.614
mAcc: 85.194 99.022 54.078 75.542 93.976 91.321 76.964 72.685 36.823 83.837 12.449 65.148 38.547 79.529 44.010 33.555 46.956 40.060 40.336 48.778

thomas 04/06 07:47:13 312/312: Data time: 0.0025, Iter time: 0.9889	Loss 0.279 (AVG: 0.629)	Score 90.528 (AVG: 81.324)	mIOU 50.704 mAP 66.413 mAcc 61.001
IOU: 74.320 95.323 44.808 63.113 83.333 74.781 60.173 39.082 34.264 67.877 9.003 53.426 34.136 54.417 36.729 31.703 47.459 38.762 40.608 30.760
mAP: 77.870 95.717 47.589 63.911 89.161 80.716 67.013 57.813 50.619 66.224 28.601 55.853 61.391 76.707 44.437 85.916 84.372 70.827 77.712 45.815
mAcc: 84.863 99.032 54.246 74.283 93.953 91.219 77.296 72.736 37.003 83.837 12.011 65.426 38.464 79.979 44.252 33.275 47.976 40.305 40.661 49.203

thomas 04/06 07:47:13 Finished test. Elapsed time: 369.7141
thomas 04/06 07:47:13 Current best mIoU: 51.475 at iter 11000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 07:51:18 ===> Epoch[44](13040/301): Loss 0.4610	LR: 9.016e-02	Score 86.020	Data time: 2.4316, Total iter time: 6.0748
thomas 04/06 07:55:17 ===> Epoch[44](13080/301): Loss 0.4948	LR: 9.013e-02	Score 84.559	Data time: 2.3046, Total iter time: 5.8834
thomas 04/06 07:59:03 ===> Epoch[44](13120/301): Loss 0.4403	LR: 9.010e-02	Score 86.093	Data time: 2.1866, Total iter time: 5.5819
thomas 04/06 08:03:06 ===> Epoch[44](13160/301): Loss 0.4303	LR: 9.007e-02	Score 86.485	Data time: 2.3766, Total iter time: 5.9895
thomas 04/06 08:07:07 ===> Epoch[44](13200/301): Loss 0.4555	LR: 9.004e-02	Score 85.659	Data time: 2.3494, Total iter time: 5.9461
thomas 04/06 08:10:59 ===> Epoch[44](13240/301): Loss 0.4520	LR: 9.001e-02	Score 85.989	Data time: 2.2408, Total iter time: 5.7378
thomas 04/06 08:14:54 ===> Epoch[45](13280/301): Loss 0.4789	LR: 8.998e-02	Score 85.114	Data time: 2.3011, Total iter time: 5.7943
thomas 04/06 08:18:52 ===> Epoch[45](13320/301): Loss 0.4587	LR: 8.995e-02	Score 85.805	Data time: 2.3199, Total iter time: 5.8676
thomas 04/06 08:23:02 ===> Epoch[45](13360/301): Loss 0.4779	LR: 8.992e-02	Score 85.507	Data time: 2.4415, Total iter time: 6.1669
thomas 04/06 08:26:55 ===> Epoch[45](13400/301): Loss 0.4506	LR: 8.989e-02	Score 85.905	Data time: 2.2579, Total iter time: 5.7489
thomas 04/06 08:30:49 ===> Epoch[45](13440/301): Loss 0.4562	LR: 8.986e-02	Score 85.712	Data time: 2.2447, Total iter time: 5.7772
thomas 04/06 08:34:39 ===> Epoch[45](13480/301): Loss 0.4351	LR: 8.983e-02	Score 86.355	Data time: 2.1970, Total iter time: 5.6763
thomas 04/06 08:38:47 ===> Epoch[45](13520/301): Loss 0.4636	LR: 8.980e-02	Score 85.384	Data time: 2.3985, Total iter time: 6.1298
thomas 04/06 08:42:52 ===> Epoch[46](13560/301): Loss 0.4680	LR: 8.977e-02	Score 85.881	Data time: 2.4135, Total iter time: 6.0494
thomas 04/06 08:47:02 ===> Epoch[46](13600/301): Loss 0.4540	LR: 8.974e-02	Score 85.838	Data time: 2.4283, Total iter time: 6.1613
thomas 04/06 08:50:57 ===> Epoch[46](13640/301): Loss 0.4673	LR: 8.971e-02	Score 84.832	Data time: 2.2915, Total iter time: 5.8215
thomas 04/06 08:54:47 ===> Epoch[46](13680/301): Loss 0.5071	LR: 8.968e-02	Score 84.353	Data time: 2.2133, Total iter time: 5.6612
thomas 04/06 08:58:35 ===> Epoch[46](13720/301): Loss 0.4392	LR: 8.965e-02	Score 86.486	Data time: 2.2116, Total iter time: 5.6478
thomas 04/06 09:02:32 ===> Epoch[46](13760/301): Loss 0.4364	LR: 8.962e-02	Score 86.780	Data time: 2.2958, Total iter time: 5.8523
thomas 04/06 09:06:35 ===> Epoch[46](13800/301): Loss 0.4982	LR: 8.959e-02	Score 84.191	Data time: 2.3488, Total iter time: 5.9780
thomas 04/06 09:10:45 ===> Epoch[46](13840/301): Loss 0.4128	LR: 8.956e-02	Score 86.910	Data time: 2.4607, Total iter time: 6.1758
thomas 04/06 09:14:26 ===> Epoch[47](13880/301): Loss 0.3991	LR: 8.953e-02	Score 87.226	Data time: 2.1811, Total iter time: 5.4806
thomas 04/06 09:18:28 ===> Epoch[47](13920/301): Loss 0.5028	LR: 8.950e-02	Score 84.502	Data time: 2.3051, Total iter time: 5.9750
thomas 04/06 09:22:22 ===> Epoch[47](13960/301): Loss 0.5247	LR: 8.947e-02	Score 83.695	Data time: 2.2356, Total iter time: 5.7708
thomas 04/06 09:26:29 ===> Epoch[47](14000/301): Loss 0.4344	LR: 8.944e-02	Score 86.447	Data time: 2.4163, Total iter time: 6.0912
thomas 04/06 09:26:30 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 09:26:30 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 09:28:37 101/312: Data time: 0.0029, Iter time: 0.5868	Loss 0.425 (AVG: 0.589)	Score 89.176 (AVG: 83.242)	mIOU 53.187 mAP 68.850 mAcc 67.204
IOU: 75.746 96.091 57.296 62.559 83.796 65.011 60.627 32.835 18.881 69.141 8.038 58.094 38.170 41.554 33.331 23.342 73.218 64.664 67.560 33.791
mAP: 76.020 95.461 60.047 54.628 85.051 86.431 69.877 55.486 39.655 67.870 23.992 52.996 54.949 73.895 76.449 87.489 95.052 88.298 89.145 44.212
mAcc: 88.147 98.441 72.678 67.846 93.317 91.435 66.895 74.523 19.316 78.653 8.577 72.378 77.969 43.704 33.570 69.246 90.167 70.379 85.248 41.599

thomas 04/06 09:30:41 201/312: Data time: 0.0039, Iter time: 1.3219	Loss 0.522 (AVG: 0.603)	Score 82.424 (AVG: 82.649)	mIOU 53.777 mAP 68.327 mAcc 65.894
IOU: 74.880 96.179 52.046 64.564 83.230 66.932 59.216 38.331 24.341 74.654 6.545 48.780 47.466 43.507 16.793 44.614 75.566 50.581 73.633 33.672
mAP: 77.394 96.217 56.247 65.290 87.899 85.117 67.358 61.652 46.273 67.743 29.163 57.196 56.403 72.541 51.300 86.985 91.619 79.184 85.476 45.482
mAcc: 87.832 98.456 69.565 73.317 93.065 93.287 65.856 76.360 24.925 85.067 6.907 59.361 77.056 46.382 16.846 70.952 87.312 56.286 88.048 41.005

thomas 04/06 09:32:46 301/312: Data time: 0.0041, Iter time: 0.8621	Loss 0.860 (AVG: 0.628)	Score 73.312 (AVG: 82.176)	mIOU 54.498 mAP 68.316 mAcc 65.798
IOU: 73.730 95.882 52.840 66.284 83.484 71.323 61.543 37.931 25.639 72.059 6.266 47.733 50.379 42.752 20.757 48.261 75.198 50.965 71.996 34.944
mAP: 77.053 96.344 57.743 67.242 88.126 83.571 66.975 60.542 47.631 68.536 31.923 58.776 56.751 69.256 51.680 85.862 92.373 79.356 80.632 45.949
mAcc: 87.346 98.391 70.533 75.264 93.524 93.468 67.644 75.950 26.581 82.376 6.525 55.681 80.522 46.440 20.798 64.890 87.256 55.542 85.239 41.987

thomas 04/06 09:32:57 312/312: Data time: 0.0025, Iter time: 0.2789	Loss 0.877 (AVG: 0.626)	Score 74.502 (AVG: 82.111)	mIOU 54.462 mAP 68.341 mAcc 65.731
IOU: 73.764 95.886 52.899 65.977 83.467 71.112 60.777 37.836 25.478 71.971 6.256 47.307 49.674 42.750 21.336 48.428 75.995 50.525 72.601 35.211
mAP: 77.383 96.450 57.539 67.381 88.083 83.267 66.923 60.813 47.388 68.536 31.923 58.578 56.751 69.256 51.653 84.715 92.813 79.565 81.458 46.338
mAcc: 87.155 98.419 70.874 75.080 93.522 93.501 67.093 76.263 26.402 82.376 6.525 54.874 80.522 46.440 21.378 63.457 87.442 55.376 85.657 42.273

thomas 04/06 09:32:57 Finished test. Elapsed time: 387.0200
thomas 04/06 09:32:59 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/06 09:32:59 Current best mIoU: 54.462 at iter 14000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 09:37:08 ===> Epoch[47](14040/301): Loss 0.4680	LR: 8.941e-02	Score 85.336	Data time: 2.4344, Total iter time: 6.1409
thomas 04/06 09:40:51 ===> Epoch[47](14080/301): Loss 0.4590	LR: 8.938e-02	Score 85.805	Data time: 2.1577, Total iter time: 5.5012
thomas 04/06 09:44:49 ===> Epoch[47](14120/301): Loss 0.5219	LR: 8.934e-02	Score 84.071	Data time: 2.3153, Total iter time: 5.8783
thomas 04/06 09:48:39 ===> Epoch[48](14160/301): Loss 0.4667	LR: 8.931e-02	Score 85.436	Data time: 2.2305, Total iter time: 5.6799
thomas 04/06 09:52:41 ===> Epoch[48](14200/301): Loss 0.4862	LR: 8.928e-02	Score 85.270	Data time: 2.3569, Total iter time: 5.9733
thomas 04/06 09:57:02 ===> Epoch[48](14240/301): Loss 0.4321	LR: 8.925e-02	Score 86.681	Data time: 2.5758, Total iter time: 6.4446
thomas 04/06 10:00:57 ===> Epoch[48](14280/301): Loss 0.4214	LR: 8.922e-02	Score 86.920	Data time: 2.2833, Total iter time: 5.8023
thomas 04/06 10:04:49 ===> Epoch[48](14320/301): Loss 0.4469	LR: 8.919e-02	Score 85.844	Data time: 2.2089, Total iter time: 5.7119
thomas 04/06 10:08:35 ===> Epoch[48](14360/301): Loss 0.4862	LR: 8.916e-02	Score 84.954	Data time: 2.2043, Total iter time: 5.5866
thomas 04/06 10:12:46 ===> Epoch[48](14400/301): Loss 0.4457	LR: 8.913e-02	Score 86.178	Data time: 2.3821, Total iter time: 6.1945
thomas 04/06 10:16:38 ===> Epoch[48](14440/301): Loss 0.4380	LR: 8.910e-02	Score 86.612	Data time: 2.3194, Total iter time: 5.7347
thomas 04/06 10:20:53 ===> Epoch[49](14480/301): Loss 0.4526	LR: 8.907e-02	Score 85.551	Data time: 2.4950, Total iter time: 6.2948
thomas 04/06 10:24:40 ===> Epoch[49](14520/301): Loss 0.4178	LR: 8.904e-02	Score 87.157	Data time: 2.2628, Total iter time: 5.6106
thomas 04/06 10:28:28 ===> Epoch[49](14560/301): Loss 0.4364	LR: 8.901e-02	Score 86.558	Data time: 2.2043, Total iter time: 5.6053
thomas 04/06 10:32:42 ===> Epoch[49](14600/301): Loss 0.4492	LR: 8.898e-02	Score 85.800	Data time: 2.4395, Total iter time: 6.2907
thomas 04/06 10:36:45 ===> Epoch[49](14640/301): Loss 0.4475	LR: 8.895e-02	Score 86.096	Data time: 2.3598, Total iter time: 5.9934
thomas 04/06 10:40:51 ===> Epoch[49](14680/301): Loss 0.4648	LR: 8.892e-02	Score 85.823	Data time: 2.4336, Total iter time: 6.0654
thomas 04/06 10:44:58 ===> Epoch[49](14720/301): Loss 0.4625	LR: 8.889e-02	Score 85.701	Data time: 2.4275, Total iter time: 6.1076
thomas 04/06 10:49:02 ===> Epoch[50](14760/301): Loss 0.4294	LR: 8.886e-02	Score 86.348	Data time: 2.3785, Total iter time: 6.0156
thomas 04/06 10:52:59 ===> Epoch[50](14800/301): Loss 0.4424	LR: 8.883e-02	Score 86.344	Data time: 2.2938, Total iter time: 5.8741
thomas 04/06 10:56:51 ===> Epoch[50](14840/301): Loss 0.4301	LR: 8.880e-02	Score 86.819	Data time: 2.2139, Total iter time: 5.6990
thomas 04/06 11:00:50 ===> Epoch[50](14880/301): Loss 0.4914	LR: 8.877e-02	Score 85.144	Data time: 2.2848, Total iter time: 5.9000
thomas 04/06 11:04:49 ===> Epoch[50](14920/301): Loss 0.4280	LR: 8.874e-02	Score 86.336	Data time: 2.3511, Total iter time: 5.8916
thomas 04/06 11:09:12 ===> Epoch[50](14960/301): Loss 0.4258	LR: 8.871e-02	Score 86.802	Data time: 2.5962, Total iter time: 6.5024
thomas 04/06 11:12:54 ===> Epoch[50](15000/301): Loss 0.4816	LR: 8.868e-02	Score 84.738	Data time: 2.1578, Total iter time: 5.4633
thomas 04/06 11:12:55 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 11:12:55 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 11:14:57 101/312: Data time: 0.0024, Iter time: 1.0011	Loss 0.386 (AVG: 0.596)	Score 88.072 (AVG: 82.352)	mIOU 55.671 mAP 67.610 mAcc 66.304
IOU: 73.196 95.809 47.790 71.918 84.448 83.075 62.866 34.204 15.429 61.634 7.446 54.764 52.035 50.035 38.675 43.031 86.669 49.354 70.979 30.068
mAP: 74.802 97.899 53.495 64.327 88.598 82.529 67.410 49.294 45.643 67.614 34.625 66.984 63.780 56.937 63.910 88.991 94.441 77.723 70.409 42.790
mAcc: 85.771 98.385 64.244 79.284 93.874 93.458 70.732 72.997 15.756 72.268 8.547 63.289 62.709 60.662 55.000 60.237 94.698 53.813 79.696 40.663

thomas 04/06 11:16:55 201/312: Data time: 0.0023, Iter time: 0.8035	Loss 0.505 (AVG: 0.616)	Score 83.201 (AVG: 82.045)	mIOU 55.386 mAP 69.335 mAcc 67.002
IOU: 72.399 95.862 49.591 69.744 84.094 79.558 63.994 34.415 17.863 70.979 6.094 50.896 52.116 45.535 41.014 41.975 83.529 51.667 67.366 29.029
mAP: 75.337 97.388 59.319 67.970 89.425 82.638 69.493 53.812 47.658 70.092 37.046 64.715 66.292 64.272 55.705 88.397 95.252 78.378 77.981 45.536
mAcc: 86.482 98.383 68.447 78.292 94.143 91.459 71.344 68.921 18.520 79.054 8.093 56.720 65.061 60.757 53.600 65.624 94.217 57.337 85.930 37.654

thomas 04/06 11:18:54 301/312: Data time: 0.0024, Iter time: 0.4870	Loss 0.708 (AVG: 0.628)	Score 74.385 (AVG: 81.516)	mIOU 55.498 mAP 69.632 mAcc 67.590
IOU: 71.739 95.894 48.455 71.489 83.907 78.351 63.227 35.205 20.103 68.548 7.816 46.771 51.181 57.464 37.628 49.349 77.781 49.534 64.504 31.018
mAP: 76.461 97.249 60.477 71.273 88.695 81.763 66.583 54.977 49.925 68.569 34.791 61.561 66.662 72.557 55.026 87.666 92.350 77.294 82.096 46.665
mAcc: 85.970 98.434 69.390 81.988 93.270 91.922 70.179 70.544 20.790 78.315 9.366 53.258 64.529 72.846 49.242 70.209 90.407 54.672 88.565 37.904

thomas 04/06 11:19:02 312/312: Data time: 0.0023, Iter time: 0.2266	Loss 0.541 (AVG: 0.629)	Score 73.934 (AVG: 81.439)	mIOU 55.595 mAP 69.488 mAcc 67.617
IOU: 71.554 95.897 48.126 71.655 83.926 78.597 63.284 34.537 19.900 68.153 7.689 47.286 51.329 57.072 37.522 49.682 78.606 50.742 64.843 31.501
mAP: 76.540 97.210 60.569 71.467 88.444 80.582 66.613 54.311 49.394 67.468 34.057 62.161 66.621 72.214 55.026 87.977 92.869 78.262 82.036 45.939
mAcc: 85.685 98.428 68.911 82.186 93.287 91.997 70.266 70.230 20.572 77.635 9.300 53.724 64.670 72.595 49.242 70.733 90.601 55.911 87.872 38.486

thomas 04/06 11:19:02 Finished test. Elapsed time: 366.8634
thomas 04/06 11:19:03 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/06 11:19:03 Current best mIoU: 55.595 at iter 15000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 11:22:57 ===> Epoch[50](15040/301): Loss 0.4730	LR: 8.865e-02	Score 85.164	Data time: 2.2521, Total iter time: 5.7693
thomas 04/06 11:26:45 ===> Epoch[51](15080/301): Loss 0.4661	LR: 8.862e-02	Score 85.500	Data time: 2.2258, Total iter time: 5.6209
thomas 04/06 11:30:51 ===> Epoch[51](15120/301): Loss 0.4420	LR: 8.859e-02	Score 86.071	Data time: 2.4181, Total iter time: 6.0687
thomas 04/06 11:35:08 ===> Epoch[51](15160/301): Loss 0.4500	LR: 8.855e-02	Score 85.789	Data time: 2.5398, Total iter time: 6.3472
thomas 04/06 11:39:03 ===> Epoch[51](15200/301): Loss 0.4250	LR: 8.852e-02	Score 87.113	Data time: 2.2444, Total iter time: 5.8061
thomas 04/06 11:43:06 ===> Epoch[51](15240/301): Loss 0.4366	LR: 8.849e-02	Score 86.478	Data time: 2.3169, Total iter time: 5.9906
thomas 04/06 11:46:53 ===> Epoch[51](15280/301): Loss 0.4112	LR: 8.846e-02	Score 86.940	Data time: 2.1812, Total iter time: 5.6063
thomas 04/06 11:50:52 ===> Epoch[51](15320/301): Loss 0.4302	LR: 8.843e-02	Score 86.776	Data time: 2.2879, Total iter time: 5.8866
thomas 04/06 11:55:04 ===> Epoch[52](15360/301): Loss 0.4343	LR: 8.840e-02	Score 86.658	Data time: 2.5148, Total iter time: 6.2305
thomas 04/06 11:58:49 ===> Epoch[52](15400/301): Loss 0.4497	LR: 8.837e-02	Score 86.358	Data time: 2.2062, Total iter time: 5.5670
thomas 04/06 12:02:43 ===> Epoch[52](15440/301): Loss 0.4568	LR: 8.834e-02	Score 86.342	Data time: 2.2177, Total iter time: 5.7614
thomas 04/06 12:06:37 ===> Epoch[52](15480/301): Loss 0.4621	LR: 8.831e-02	Score 85.565	Data time: 2.2584, Total iter time: 5.7861
thomas 04/06 12:10:40 ===> Epoch[52](15520/301): Loss 0.4631	LR: 8.828e-02	Score 85.431	Data time: 2.3135, Total iter time: 5.9835
thomas 04/06 12:14:37 ===> Epoch[52](15560/301): Loss 0.4303	LR: 8.825e-02	Score 87.072	Data time: 2.3363, Total iter time: 5.8469
thomas 04/06 12:18:50 ===> Epoch[52](15600/301): Loss 0.4470	LR: 8.822e-02	Score 86.275	Data time: 2.5595, Total iter time: 6.2550
thomas 04/06 12:22:58 ===> Epoch[52](15640/301): Loss 0.4013	LR: 8.819e-02	Score 87.517	Data time: 2.4701, Total iter time: 6.1292
thomas 04/06 12:26:50 ===> Epoch[53](15680/301): Loss 0.4308	LR: 8.816e-02	Score 86.897	Data time: 2.2100, Total iter time: 5.7254
thomas 04/06 12:30:49 ===> Epoch[53](15720/301): Loss 0.4236	LR: 8.813e-02	Score 86.663	Data time: 2.2943, Total iter time: 5.8918
thomas 04/06 12:34:48 ===> Epoch[53](15760/301): Loss 0.4093	LR: 8.810e-02	Score 86.892	Data time: 2.2950, Total iter time: 5.8957
thomas 04/06 12:39:07 ===> Epoch[53](15800/301): Loss 0.4095	LR: 8.807e-02	Score 86.979	Data time: 2.5162, Total iter time: 6.3913
thomas 04/06 12:43:21 ===> Epoch[53](15840/301): Loss 0.4430	LR: 8.804e-02	Score 86.326	Data time: 2.5649, Total iter time: 6.2857
thomas 04/06 12:47:11 ===> Epoch[53](15880/301): Loss 0.4169	LR: 8.801e-02	Score 87.033	Data time: 2.2766, Total iter time: 5.6819
thomas 04/06 12:51:00 ===> Epoch[53](15920/301): Loss 0.4506	LR: 8.798e-02	Score 86.275	Data time: 2.2057, Total iter time: 5.6444
thomas 04/06 12:55:04 ===> Epoch[54](15960/301): Loss 0.4403	LR: 8.795e-02	Score 86.328	Data time: 2.3514, Total iter time: 6.0183
thomas 04/06 12:58:48 ===> Epoch[54](16000/301): Loss 0.4598	LR: 8.792e-02	Score 85.672	Data time: 2.1812, Total iter time: 5.5439
thomas 04/06 12:58:50 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 12:58:50 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 13:00:58 101/312: Data time: 0.0849, Iter time: 0.3824	Loss 0.413 (AVG: 0.598)	Score 86.584 (AVG: 82.177)	mIOU 58.604 mAP 68.828 mAcc 70.826
IOU: 73.914 95.732 52.883 64.171 82.626 69.876 63.558 38.110 38.017 71.427 7.748 55.078 52.747 60.790 48.755 58.902 75.089 49.963 79.965 32.737
mAP: 77.944 95.867 54.907 64.526 87.200 83.597 62.989 59.865 42.007 67.031 35.123 63.654 63.722 79.254 52.557 82.902 90.271 81.863 84.813 46.467
mAcc: 84.262 99.101 69.501 76.380 96.261 88.336 74.268 64.499 45.245 92.542 8.922 78.404 78.926 83.759 50.788 67.650 76.152 55.027 87.441 39.063

thomas 04/06 13:03:03 201/312: Data time: 0.0030, Iter time: 0.8220	Loss 0.150 (AVG: 0.593)	Score 96.949 (AVG: 82.489)	mIOU 58.428 mAP 68.940 mAcc 70.479
IOU: 74.278 95.764 50.951 64.611 81.954 73.649 63.831 40.389 37.002 70.288 7.574 56.116 51.033 55.568 50.140 56.323 76.648 49.179 80.615 32.645
mAP: 78.314 95.505 52.410 64.698 87.476 84.375 66.431 62.198 44.863 67.844 32.263 61.859 59.986 80.029 55.944 82.005 89.544 81.157 84.095 47.809
mAcc: 84.237 99.013 70.685 76.170 95.623 88.942 76.297 64.701 45.100 93.715 8.458 77.397 74.198 81.253 52.222 63.487 77.836 53.926 87.090 39.230

thomas 04/06 13:05:07 301/312: Data time: 0.0025, Iter time: 0.7004	Loss 0.719 (AVG: 0.587)	Score 77.979 (AVG: 82.720)	mIOU 57.839 mAP 69.568 mAcc 69.618
IOU: 74.304 95.656 48.509 63.301 82.622 74.574 65.421 39.367 38.882 71.203 7.132 57.204 49.831 57.511 41.862 55.825 75.140 46.968 78.659 32.802
mAP: 78.698 95.325 50.955 67.442 87.965 84.502 69.450 59.364 47.961 71.307 33.354 63.904 60.851 79.076 56.509 83.468 88.521 81.132 83.209 48.378
mAcc: 84.598 99.007 68.444 76.678 95.490 87.961 76.839 62.828 47.287 92.702 8.135 76.111 75.436 81.543 43.602 63.235 76.519 50.954 85.895 39.099

thomas 04/06 13:05:20 312/312: Data time: 0.0033, Iter time: 0.2328	Loss 0.537 (AVG: 0.586)	Score 73.839 (AVG: 82.722)	mIOU 57.967 mAP 69.741 mAcc 69.739
IOU: 74.200 95.583 48.481 63.366 82.489 74.531 65.266 39.145 39.777 70.255 7.269 56.511 51.114 57.719 42.080 56.286 75.792 48.241 78.110 33.117
mAP: 78.393 95.353 50.300 67.522 88.099 84.225 68.938 58.832 48.638 72.233 33.744 62.924 61.632 79.484 57.329 83.845 89.219 81.718 83.748 48.651
mAcc: 84.471 98.947 67.891 76.999 95.387 87.758 76.924 63.166 48.204 91.066 8.255 75.922 75.919 81.809 43.807 63.999 77.258 52.173 85.298 39.536

thomas 04/06 13:05:20 Finished test. Elapsed time: 390.5237
thomas 04/06 13:05:22 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/06 13:05:22 Current best mIoU: 57.967 at iter 16000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 13:09:41 ===> Epoch[54](16040/301): Loss 0.4226	LR: 8.789e-02	Score 86.491	Data time: 2.5841, Total iter time: 6.4003
thomas 04/06 13:13:30 ===> Epoch[54](16080/301): Loss 0.4098	LR: 8.786e-02	Score 87.438	Data time: 2.2063, Total iter time: 5.6490
thomas 04/06 13:17:29 ===> Epoch[54](16120/301): Loss 0.4661	LR: 8.782e-02	Score 85.550	Data time: 2.2990, Total iter time: 5.9027
thomas 04/06 13:21:14 ===> Epoch[54](16160/301): Loss 0.4642	LR: 8.779e-02	Score 85.646	Data time: 2.1434, Total iter time: 5.5572
thomas 04/06 13:25:14 ===> Epoch[54](16200/301): Loss 0.4087	LR: 8.776e-02	Score 87.529	Data time: 2.2942, Total iter time: 5.9226
thomas 04/06 13:29:21 ===> Epoch[54](16240/301): Loss 0.4255	LR: 8.773e-02	Score 86.963	Data time: 2.4303, Total iter time: 6.0844
thomas 04/06 13:33:41 ===> Epoch[55](16280/301): Loss 0.4304	LR: 8.770e-02	Score 87.009	Data time: 2.5644, Total iter time: 6.4339
thomas 04/06 13:37:28 ===> Epoch[55](16320/301): Loss 0.4214	LR: 8.767e-02	Score 87.166	Data time: 2.1737, Total iter time: 5.5977
thomas 04/06 13:41:27 ===> Epoch[55](16360/301): Loss 0.4386	LR: 8.764e-02	Score 86.412	Data time: 2.2728, Total iter time: 5.8894
thomas 04/06 13:45:01 ===> Epoch[55](16400/301): Loss 0.4361	LR: 8.761e-02	Score 86.265	Data time: 2.0522, Total iter time: 5.2767
thomas 04/06 13:48:50 ===> Epoch[55](16440/301): Loss 0.4215	LR: 8.758e-02	Score 86.894	Data time: 2.2207, Total iter time: 5.6468
thomas 04/06 13:52:57 ===> Epoch[55](16480/301): Loss 0.4351	LR: 8.755e-02	Score 86.734	Data time: 2.4799, Total iter time: 6.1156
thomas 04/06 13:57:23 ===> Epoch[55](16520/301): Loss 0.4291	LR: 8.752e-02	Score 86.735	Data time: 2.6339, Total iter time: 6.5565
thomas 04/06 14:01:27 ===> Epoch[56](16560/301): Loss 0.4129	LR: 8.749e-02	Score 86.912	Data time: 2.3275, Total iter time: 6.0217
thomas 04/06 14:05:16 ===> Epoch[56](16600/301): Loss 0.4370	LR: 8.746e-02	Score 86.132	Data time: 2.2080, Total iter time: 5.6670
thomas 04/06 14:09:16 ===> Epoch[56](16640/301): Loss 0.4295	LR: 8.743e-02	Score 86.305	Data time: 2.3166, Total iter time: 5.9141
thomas 04/06 14:13:23 ===> Epoch[56](16680/301): Loss 0.4534	LR: 8.740e-02	Score 86.367	Data time: 2.3464, Total iter time: 6.1070
thomas 04/06 14:17:17 ===> Epoch[56](16720/301): Loss 0.4315	LR: 8.737e-02	Score 86.873	Data time: 2.3209, Total iter time: 5.7739
thomas 04/06 14:21:36 ===> Epoch[56](16760/301): Loss 0.4152	LR: 8.734e-02	Score 87.145	Data time: 2.5574, Total iter time: 6.3993
thomas 04/06 14:25:23 ===> Epoch[56](16800/301): Loss 0.3957	LR: 8.731e-02	Score 87.855	Data time: 2.1949, Total iter time: 5.5996
thomas 04/06 14:28:59 ===> Epoch[56](16840/301): Loss 0.4446	LR: 8.728e-02	Score 86.178	Data time: 2.0849, Total iter time: 5.3321
thomas 04/06 14:32:56 ===> Epoch[57](16880/301): Loss 0.4096	LR: 8.725e-02	Score 87.153	Data time: 2.2612, Total iter time: 5.8349
thomas 04/06 14:37:03 ===> Epoch[57](16920/301): Loss 0.4886	LR: 8.722e-02	Score 85.191	Data time: 2.3537, Total iter time: 6.0883
thomas 04/06 14:41:05 ===> Epoch[57](16960/301): Loss 0.4604	LR: 8.719e-02	Score 85.735	Data time: 2.3627, Total iter time: 5.9647
thomas 04/06 14:45:31 ===> Epoch[57](17000/301): Loss 0.4219	LR: 8.715e-02	Score 86.739	Data time: 2.6289, Total iter time: 6.5719
thomas 04/06 14:45:33 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 14:45:33 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 14:47:41 101/312: Data time: 0.0024, Iter time: 0.3892	Loss 0.489 (AVG: 0.736)	Score 85.642 (AVG: 80.326)	mIOU 50.902 mAP 65.924 mAcc 60.861
IOU: 74.489 95.407 48.455 43.658 86.356 76.114 60.048 38.359 19.276 62.529 4.116 64.214 49.876 25.736 33.597 21.439 88.948 44.023 47.466 33.931
mAP: 78.601 95.802 61.948 54.256 88.585 77.695 65.715 50.975 49.349 58.642 30.901 60.711 63.597 55.629 43.585 88.136 97.752 75.243 79.875 41.481
mAcc: 90.091 98.192 80.245 45.711 92.986 91.351 63.241 57.068 19.630 92.168 4.316 77.301 74.695 26.476 47.369 21.447 90.473 47.927 47.914 48.625

thomas 04/06 14:49:36 201/312: Data time: 0.0023, Iter time: 0.6941	Loss 0.739 (AVG: 0.678)	Score 76.336 (AVG: 81.627)	mIOU 51.799 mAP 67.805 mAcc 61.972
IOU: 76.441 95.849 47.487 51.964 86.693 77.666 57.442 38.227 22.292 63.679 6.577 62.578 48.645 37.662 33.096 16.706 84.707 43.358 53.491 31.420
mAP: 79.690 95.526 59.639 61.488 88.553 82.823 68.096 54.833 49.510 65.973 30.608 58.348 64.784 67.336 50.482 80.264 95.301 78.932 83.184 40.737
mAcc: 90.012 98.285 80.001 54.118 93.875 93.563 60.978 55.687 22.979 88.436 6.847 76.108 74.899 38.466 52.605 17.335 85.714 46.315 53.709 49.514

thomas 04/06 14:51:31 301/312: Data time: 0.0024, Iter time: 0.3560	Loss 0.465 (AVG: 0.677)	Score 82.813 (AVG: 81.684)	mIOU 52.250 mAP 68.881 mAcc 62.668
IOU: 76.189 95.865 48.384 53.956 86.188 75.111 57.542 38.430 25.420 66.057 5.669 60.529 48.345 39.291 36.308 13.717 82.093 49.746 55.327 30.842
mAP: 78.167 95.968 60.641 61.949 88.577 79.585 70.786 55.000 51.385 69.876 34.940 60.732 64.652 69.206 55.611 79.414 96.002 79.928 82.675 42.516
mAcc: 89.315 98.214 79.604 56.491 93.440 93.000 60.326 56.912 26.237 88.417 5.829 75.040 76.618 39.916 56.608 14.068 83.084 53.472 55.517 51.247

thomas 04/06 14:51:44 312/312: Data time: 0.0022, Iter time: 0.4455	Loss 0.365 (AVG: 0.675)	Score 86.782 (AVG: 81.742)	mIOU 52.227 mAP 69.023 mAcc 62.754
IOU: 76.041 95.895 48.264 53.737 86.408 74.085 58.527 38.245 25.480 66.002 5.308 60.127 48.854 40.572 36.076 14.681 82.036 50.195 52.754 31.250
mAP: 78.250 96.016 61.261 62.040 88.863 79.870 71.334 54.891 51.354 69.876 34.169 60.732 64.757 69.760 55.611 79.377 95.881 80.405 83.033 42.981
mAcc: 89.184 98.221 79.501 56.311 93.573 93.125 61.273 56.960 26.378 88.417 5.447 75.040 77.058 41.243 56.608 15.044 82.986 54.051 52.919 51.744

thomas 04/06 14:51:44 Finished test. Elapsed time: 371.2522
thomas 04/06 14:51:44 Current best mIoU: 57.967 at iter 16000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 14:55:34 ===> Epoch[57](17040/301): Loss 0.3939	LR: 8.712e-02	Score 87.294	Data time: 2.2104, Total iter time: 5.6811
thomas 04/06 14:59:17 ===> Epoch[57](17080/301): Loss 0.4361	LR: 8.709e-02	Score 86.285	Data time: 2.1320, Total iter time: 5.4961
thomas 04/06 15:03:24 ===> Epoch[57](17120/301): Loss 0.3690	LR: 8.706e-02	Score 88.419	Data time: 2.4531, Total iter time: 6.1030
thomas 04/06 15:07:45 ===> Epoch[58](17160/301): Loss 0.4455	LR: 8.703e-02	Score 86.298	Data time: 2.5828, Total iter time: 6.4179
thomas 04/06 15:11:47 ===> Epoch[58](17200/301): Loss 0.4358	LR: 8.700e-02	Score 86.668	Data time: 2.3550, Total iter time: 5.9733
thomas 04/06 15:15:54 ===> Epoch[58](17240/301): Loss 0.4158	LR: 8.697e-02	Score 86.801	Data time: 2.3693, Total iter time: 6.1047
thomas 04/06 15:19:24 ===> Epoch[58](17280/301): Loss 0.4269	LR: 8.694e-02	Score 86.809	Data time: 2.0528, Total iter time: 5.1900
thomas 04/06 15:23:17 ===> Epoch[58](17320/301): Loss 0.4079	LR: 8.691e-02	Score 87.277	Data time: 2.2203, Total iter time: 5.7501
thomas 04/06 15:27:24 ===> Epoch[58](17360/301): Loss 0.4192	LR: 8.688e-02	Score 87.119	Data time: 2.3778, Total iter time: 6.0908
thomas 04/06 15:31:30 ===> Epoch[58](17400/301): Loss 0.4385	LR: 8.685e-02	Score 86.181	Data time: 2.4510, Total iter time: 6.0717
thomas 04/06 15:35:19 ===> Epoch[58](17440/301): Loss 0.4211	LR: 8.682e-02	Score 87.172	Data time: 2.2310, Total iter time: 5.6716
thomas 04/06 15:39:00 ===> Epoch[59](17480/301): Loss 0.4201	LR: 8.679e-02	Score 86.916	Data time: 2.1100, Total iter time: 5.4433
thomas 04/06 15:42:59 ===> Epoch[59](17520/301): Loss 0.4485	LR: 8.676e-02	Score 86.271	Data time: 2.2911, Total iter time: 5.8841
thomas 04/06 15:46:46 ===> Epoch[59](17560/301): Loss 0.4139	LR: 8.673e-02	Score 87.190	Data time: 2.2158, Total iter time: 5.6123
thomas 04/06 15:50:50 ===> Epoch[59](17600/301): Loss 0.4890	LR: 8.670e-02	Score 84.883	Data time: 2.3923, Total iter time: 6.0259
thomas 04/06 15:55:05 ===> Epoch[59](17640/301): Loss 0.4238	LR: 8.667e-02	Score 86.607	Data time: 2.5146, Total iter time: 6.2820
thomas 04/06 15:59:06 ===> Epoch[59](17680/301): Loss 0.4227	LR: 8.664e-02	Score 86.762	Data time: 2.3049, Total iter time: 5.9564
thomas 04/06 16:03:02 ===> Epoch[59](17720/301): Loss 0.4018	LR: 8.661e-02	Score 87.444	Data time: 2.2581, Total iter time: 5.8199
thomas 04/06 16:06:53 ===> Epoch[60](17760/301): Loss 0.3929	LR: 8.658e-02	Score 87.506	Data time: 2.2183, Total iter time: 5.7007
thomas 04/06 16:10:39 ===> Epoch[60](17800/301): Loss 0.4358	LR: 8.655e-02	Score 86.694	Data time: 2.1785, Total iter time: 5.5994
thomas 04/06 16:14:43 ===> Epoch[60](17840/301): Loss 0.4168	LR: 8.651e-02	Score 87.054	Data time: 2.4246, Total iter time: 6.0290
thomas 04/06 16:18:59 ===> Epoch[60](17880/301): Loss 0.4310	LR: 8.648e-02	Score 86.434	Data time: 2.5389, Total iter time: 6.3190
thomas 04/06 16:23:06 ===> Epoch[60](17920/301): Loss 0.3961	LR: 8.645e-02	Score 87.884	Data time: 2.3974, Total iter time: 6.0882
thomas 04/06 16:26:44 ===> Epoch[60](17960/301): Loss 0.4543	LR: 8.642e-02	Score 85.536	Data time: 2.0705, Total iter time: 5.3753
thomas 04/06 16:30:45 ===> Epoch[60](18000/301): Loss 0.4393	LR: 8.639e-02	Score 86.570	Data time: 2.2755, Total iter time: 5.9605
thomas 04/06 16:30:46 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 16:30:47 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 16:32:46 101/312: Data time: 0.0023, Iter time: 0.3996	Loss 0.448 (AVG: 0.642)	Score 85.585 (AVG: 80.338)	mIOU 53.725 mAP 68.043 mAcc 64.249
IOU: 73.956 95.957 51.611 56.394 85.720 61.853 60.252 33.527 32.399 50.460 9.248 44.646 53.968 56.915 40.141 32.894 71.715 57.742 79.785 25.323
mAP: 77.811 95.485 61.440 56.691 88.671 72.349 68.614 52.446 48.837 67.417 38.526 68.222 67.492 70.406 45.099 90.190 89.996 79.013 80.801 41.348
mAcc: 84.316 98.547 60.324 61.605 93.627 91.001 64.282 58.680 36.663 87.099 12.296 46.345 69.783 61.830 43.853 33.022 72.108 61.430 82.279 65.884

thomas 04/06 16:34:51 201/312: Data time: 0.0029, Iter time: 0.3718	Loss 0.528 (AVG: 0.614)	Score 85.355 (AVG: 81.291)	mIOU 55.375 mAP 69.201 mAcc 65.015
IOU: 74.370 96.016 46.573 55.424 86.636 71.498 57.966 36.423 37.510 63.188 10.358 50.687 51.638 58.220 39.078 27.739 78.182 56.877 78.867 30.257
mAP: 77.873 95.790 57.781 59.010 87.650 81.403 70.002 56.700 49.237 66.808 36.778 66.685 67.778 72.926 50.278 88.598 92.738 78.921 81.434 45.619
mAcc: 84.501 98.603 54.724 66.048 93.862 92.874 62.478 62.297 42.832 86.514 14.528 52.954 65.457 62.301 43.897 27.825 79.107 61.132 81.020 67.340

thomas 04/06 16:36:48 301/312: Data time: 0.0030, Iter time: 1.2082	Loss 0.339 (AVG: 0.616)	Score 90.123 (AVG: 81.404)	mIOU 55.118 mAP 69.738 mAcc 64.603
IOU: 74.671 95.918 46.141 55.393 86.365 71.785 58.460 39.268 38.736 65.616 12.783 46.389 49.119 60.326 39.633 23.554 78.699 50.271 79.827 29.410
mAP: 78.605 96.011 56.591 63.012 88.763 83.136 71.724 60.325 50.067 68.142 39.166 59.653 65.880 74.398 53.674 88.429 92.355 78.794 81.450 44.594
mAcc: 84.812 98.593 55.246 66.053 93.609 93.545 63.385 65.191 43.842 88.841 17.853 48.509 62.293 65.456 44.191 24.055 79.319 53.519 81.584 62.165

thomas 04/06 16:36:59 312/312: Data time: 0.0030, Iter time: 0.6734	Loss 0.304 (AVG: 0.613)	Score 91.460 (AVG: 81.506)	mIOU 55.225 mAP 69.778 mAcc 64.691
IOU: 74.714 95.941 46.496 55.809 86.337 72.260 59.042 39.260 39.923 65.319 12.605 46.194 49.737 60.133 38.966 23.554 79.027 50.075 79.827 29.284
mAP: 78.636 96.096 56.503 64.014 89.007 83.369 72.296 59.597 50.851 67.013 38.376 59.695 65.814 74.398 54.255 88.429 92.461 78.425 81.450 44.875
mAcc: 84.883 98.618 55.579 66.942 93.564 93.630 63.851 65.174 45.111 88.568 17.577 48.345 62.986 65.456 43.157 24.055 79.644 53.314 81.584 61.787

thomas 04/06 16:36:59 Finished test. Elapsed time: 372.8820
thomas 04/06 16:37:00 Current best mIoU: 57.967 at iter 16000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 16:41:11 ===> Epoch[60](18040/301): Loss 0.3978	LR: 8.636e-02	Score 87.713	Data time: 2.5207, Total iter time: 6.2112
thomas 04/06 16:45:16 ===> Epoch[61](18080/301): Loss 0.4106	LR: 8.633e-02	Score 87.365	Data time: 2.3927, Total iter time: 6.0440
thomas 04/06 16:49:10 ===> Epoch[61](18120/301): Loss 0.4204	LR: 8.630e-02	Score 86.993	Data time: 2.2457, Total iter time: 5.7845
thomas 04/06 16:52:58 ===> Epoch[61](18160/301): Loss 0.4441	LR: 8.627e-02	Score 86.483	Data time: 2.1734, Total iter time: 5.6128
thomas 04/06 16:56:45 ===> Epoch[61](18200/301): Loss 0.4167	LR: 8.624e-02	Score 87.106	Data time: 2.1812, Total iter time: 5.5989
thomas 04/06 17:00:57 ===> Epoch[61](18240/301): Loss 0.4534	LR: 8.621e-02	Score 85.589	Data time: 2.4431, Total iter time: 6.2112
thomas 04/06 17:05:03 ===> Epoch[61](18280/301): Loss 0.4172	LR: 8.618e-02	Score 86.970	Data time: 2.4372, Total iter time: 6.0919
thomas 04/06 17:08:57 ===> Epoch[61](18320/301): Loss 0.3823	LR: 8.615e-02	Score 87.945	Data time: 2.2973, Total iter time: 5.7662
thomas 04/06 17:12:53 ===> Epoch[61](18360/301): Loss 0.4112	LR: 8.612e-02	Score 86.832	Data time: 2.2750, Total iter time: 5.8243
thomas 04/06 17:16:36 ===> Epoch[62](18400/301): Loss 0.4403	LR: 8.609e-02	Score 86.287	Data time: 2.1337, Total iter time: 5.5024
thomas 04/06 17:20:28 ===> Epoch[62](18440/301): Loss 0.3765	LR: 8.606e-02	Score 88.205	Data time: 2.2343, Total iter time: 5.7313
thomas 04/06 17:24:34 ===> Epoch[62](18480/301): Loss 0.3825	LR: 8.603e-02	Score 88.045	Data time: 2.3616, Total iter time: 6.0714
thomas 04/06 17:28:32 ===> Epoch[62](18520/301): Loss 0.4287	LR: 8.600e-02	Score 86.532	Data time: 2.3522, Total iter time: 5.8622
thomas 04/06 17:32:42 ===> Epoch[62](18560/301): Loss 0.4807	LR: 8.597e-02	Score 85.269	Data time: 2.4339, Total iter time: 6.1765
thomas 04/06 17:36:42 ===> Epoch[62](18600/301): Loss 0.4005	LR: 8.594e-02	Score 87.624	Data time: 2.3056, Total iter time: 5.9000
thomas 04/06 17:40:51 ===> Epoch[62](18640/301): Loss 0.4482	LR: 8.590e-02	Score 86.195	Data time: 2.3890, Total iter time: 6.1582
thomas 04/06 17:44:33 ===> Epoch[63](18680/301): Loss 0.3924	LR: 8.587e-02	Score 88.205	Data time: 2.1252, Total iter time: 5.4577
thomas 04/06 17:48:46 ===> Epoch[63](18720/301): Loss 0.4691	LR: 8.584e-02	Score 85.578	Data time: 2.4483, Total iter time: 6.2451
thomas 04/06 17:52:53 ===> Epoch[63](18760/301): Loss 0.3929	LR: 8.581e-02	Score 87.659	Data time: 2.4941, Total iter time: 6.0981
thomas 04/06 17:56:44 ===> Epoch[63](18800/301): Loss 0.4193	LR: 8.578e-02	Score 86.950	Data time: 2.2546, Total iter time: 5.7079
thomas 04/06 18:00:30 ===> Epoch[63](18840/301): Loss 0.4017	LR: 8.575e-02	Score 87.406	Data time: 2.1934, Total iter time: 5.5952
thomas 04/06 18:04:30 ===> Epoch[63](18880/301): Loss 0.4453	LR: 8.572e-02	Score 86.504	Data time: 2.2998, Total iter time: 5.9074
thomas 04/06 18:08:24 ===> Epoch[63](18920/301): Loss 0.4111	LR: 8.569e-02	Score 87.093	Data time: 2.2444, Total iter time: 5.7902
thomas 04/06 18:12:17 ===> Epoch[63](18960/301): Loss 0.4059	LR: 8.566e-02	Score 87.559	Data time: 2.2692, Total iter time: 5.7443
thomas 04/06 18:16:24 ===> Epoch[64](19000/301): Loss 0.3929	LR: 8.563e-02	Score 87.537	Data time: 2.4025, Total iter time: 6.0983
thomas 04/06 18:16:26 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 18:16:26 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 18:18:25 101/312: Data time: 0.0031, Iter time: 0.4156	Loss 0.598 (AVG: 0.549)	Score 86.350 (AVG: 83.545)	mIOU 57.309 mAP 70.343 mAcc 69.191
IOU: 79.833 95.982 38.974 72.448 82.196 70.463 55.023 43.860 50.686 62.872 19.254 40.396 52.489 47.177 59.365 29.351 85.840 50.045 74.845 35.072
mAP: 78.148 97.747 49.956 70.518 91.158 79.860 65.806 62.242 59.401 75.182 40.274 46.651 60.671 66.926 62.855 81.828 92.569 81.723 89.674 53.676
mAcc: 89.142 98.393 44.515 76.138 91.909 96.364 59.793 66.870 59.956 90.242 25.519 58.815 85.505 54.283 65.045 30.486 89.783 52.182 90.722 58.152

thomas 04/06 18:20:32 201/312: Data time: 0.0023, Iter time: 0.5837	Loss 0.693 (AVG: 0.604)	Score 83.151 (AVG: 82.554)	mIOU 56.243 mAP 69.524 mAcc 68.456
IOU: 76.758 95.673 49.155 69.543 83.475 71.226 58.339 41.549 41.995 57.628 11.869 52.468 44.173 49.729 53.515 26.516 88.328 44.793 69.626 38.495
mAP: 76.647 97.407 54.491 68.293 88.533 82.560 63.576 59.731 55.278 74.527 36.379 52.960 61.091 71.778 59.372 80.461 94.140 78.793 83.537 50.930
mAcc: 87.734 98.393 55.926 75.461 92.289 95.377 62.245 66.373 51.369 89.459 13.699 67.144 85.818 56.532 60.794 27.698 91.496 46.728 89.351 55.225

thomas 04/06 18:22:26 301/312: Data time: 0.0028, Iter time: 0.7586	Loss 0.171 (AVG: 0.584)	Score 94.321 (AVG: 83.020)	mIOU 56.507 mAP 70.058 mAcc 68.064
IOU: 77.243 96.040 49.602 69.498 84.038 71.140 59.952 41.979 41.728 60.627 12.231 56.973 44.665 49.653 43.152 23.793 87.239 47.789 75.453 37.349
mAP: 78.149 97.605 52.672 68.938 88.820 83.815 65.537 60.322 55.430 72.937 35.894 59.460 63.943 71.696 56.067 78.285 92.789 79.936 86.688 52.173
mAcc: 87.704 98.482 56.134 75.946 92.695 95.674 63.537 68.953 50.266 91.156 14.010 69.576 82.749 55.375 48.372 24.964 89.797 49.736 90.981 55.180

thomas 04/06 18:22:38 312/312: Data time: 0.0026, Iter time: 0.3140	Loss 0.162 (AVG: 0.588)	Score 95.458 (AVG: 82.908)	mIOU 56.388 mAP 69.891 mAcc 67.919
IOU: 77.030 96.083 49.730 69.585 83.475 70.942 59.585 42.644 41.574 60.480 12.166 56.796 44.574 48.712 41.623 23.793 86.312 49.615 75.442 37.594
mAP: 78.301 97.630 52.932 69.118 88.367 83.632 65.228 60.935 54.749 72.715 35.124 59.896 63.675 70.355 54.862 78.285 92.837 80.434 86.688 52.068
mAcc: 87.532 98.500 56.481 76.206 92.189 95.243 63.148 68.885 50.145 91.297 13.925 69.098 82.546 54.216 46.871 24.964 88.740 51.569 90.981 55.841

thomas 04/06 18:22:38 Finished test. Elapsed time: 372.1067
thomas 04/06 18:22:38 Current best mIoU: 57.967 at iter 16000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 18:26:30 ===> Epoch[64](19040/301): Loss 0.4370	LR: 8.560e-02	Score 86.910	Data time: 2.2305, Total iter time: 5.7156
thomas 04/06 18:30:17 ===> Epoch[64](19080/301): Loss 0.4027	LR: 8.557e-02	Score 87.336	Data time: 2.1686, Total iter time: 5.6066
thomas 04/06 18:33:59 ===> Epoch[64](19120/301): Loss 0.3901	LR: 8.554e-02	Score 87.894	Data time: 2.1489, Total iter time: 5.4737
thomas 04/06 18:38:11 ===> Epoch[64](19160/301): Loss 0.4073	LR: 8.551e-02	Score 87.232	Data time: 2.4493, Total iter time: 6.2158
thomas 04/06 18:42:12 ===> Epoch[64](19200/301): Loss 0.4308	LR: 8.548e-02	Score 86.621	Data time: 2.3548, Total iter time: 5.9556
thomas 04/06 18:45:52 ===> Epoch[64](19240/301): Loss 0.4057	LR: 8.545e-02	Score 87.551	Data time: 2.1562, Total iter time: 5.4393
thomas 04/06 18:49:42 ===> Epoch[65](19280/301): Loss 0.3899	LR: 8.542e-02	Score 87.890	Data time: 2.2050, Total iter time: 5.6572
thomas 04/06 18:53:44 ===> Epoch[65](19320/301): Loss 0.3933	LR: 8.539e-02	Score 87.559	Data time: 2.3186, Total iter time: 5.9748
thomas 04/06 18:57:45 ===> Epoch[65](19360/301): Loss 0.4164	LR: 8.536e-02	Score 86.854	Data time: 2.3284, Total iter time: 5.9519
thomas 04/06 19:01:28 ===> Epoch[65](19400/301): Loss 0.4035	LR: 8.532e-02	Score 87.174	Data time: 2.1402, Total iter time: 5.4981
thomas 04/06 19:05:34 ===> Epoch[65](19440/301): Loss 0.3880	LR: 8.529e-02	Score 87.754	Data time: 2.3868, Total iter time: 6.0688
thomas 04/06 19:09:23 ===> Epoch[65](19480/301): Loss 0.4170	LR: 8.526e-02	Score 87.576	Data time: 2.2525, Total iter time: 5.6711
thomas 04/06 19:13:11 ===> Epoch[65](19520/301): Loss 0.3664	LR: 8.523e-02	Score 88.533	Data time: 2.1841, Total iter time: 5.6147
thomas 04/06 19:17:06 ===> Epoch[65](19560/301): Loss 0.4237	LR: 8.520e-02	Score 86.668	Data time: 2.2375, Total iter time: 5.8147
thomas 04/06 19:20:57 ===> Epoch[66](19600/301): Loss 0.4176	LR: 8.517e-02	Score 87.031	Data time: 2.1754, Total iter time: 5.6832
thomas 04/06 19:24:56 ===> Epoch[66](19640/301): Loss 0.4317	LR: 8.514e-02	Score 86.369	Data time: 2.3333, Total iter time: 5.8882
thomas 04/06 19:28:59 ===> Epoch[66](19680/301): Loss 0.4243	LR: 8.511e-02	Score 86.832	Data time: 2.3864, Total iter time: 5.9963
thomas 04/06 19:33:05 ===> Epoch[66](19720/301): Loss 0.4300	LR: 8.508e-02	Score 87.194	Data time: 2.4061, Total iter time: 6.0625
thomas 04/06 19:36:53 ===> Epoch[66](19760/301): Loss 0.4129	LR: 8.505e-02	Score 87.160	Data time: 2.1887, Total iter time: 5.6147
thomas 04/06 19:40:30 ===> Epoch[66](19800/301): Loss 0.4138	LR: 8.502e-02	Score 87.333	Data time: 2.0917, Total iter time: 5.3760
thomas 04/06 19:44:35 ===> Epoch[66](19840/301): Loss 0.4031	LR: 8.499e-02	Score 87.623	Data time: 2.3883, Total iter time: 6.0439
thomas 04/06 19:48:27 ===> Epoch[67](19880/301): Loss 0.4331	LR: 8.496e-02	Score 86.630	Data time: 2.2625, Total iter time: 5.7356
thomas 04/06 19:52:17 ===> Epoch[67](19920/301): Loss 0.4358	LR: 8.493e-02	Score 86.427	Data time: 2.2246, Total iter time: 5.6624
thomas 04/06 19:55:57 ===> Epoch[67](19960/301): Loss 0.4269	LR: 8.490e-02	Score 86.548	Data time: 2.1573, Total iter time: 5.4368
thomas 04/06 20:00:06 ===> Epoch[67](20000/301): Loss 0.4068	LR: 8.487e-02	Score 87.219	Data time: 2.4071, Total iter time: 6.1521
thomas 04/06 20:00:07 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 20:00:07 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 20:02:01 101/312: Data time: 0.0024, Iter time: 0.7069	Loss 0.987 (AVG: 0.708)	Score 73.461 (AVG: 78.467)	mIOU 54.526 mAP 70.920 mAcc 69.247
IOU: 63.333 95.565 46.372 43.497 85.843 65.718 64.695 31.396 25.398 73.811 11.989 58.102 40.916 53.745 41.315 26.703 91.838 68.059 72.812 29.410
mAP: 75.410 96.741 52.884 69.745 90.344 79.913 75.597 59.505 40.364 73.290 40.012 56.485 63.492 74.938 74.355 79.696 97.886 92.331 78.195 47.222
mAcc: 70.401 97.447 60.619 81.406 92.933 94.293 70.843 81.228 28.172 94.340 16.288 70.540 88.279 74.342 60.804 27.930 93.564 73.176 72.966 35.373

thomas 04/06 20:03:52 201/312: Data time: 0.0020, Iter time: 0.6778	Loss 0.881 (AVG: 0.696)	Score 69.332 (AVG: 78.652)	mIOU 55.028 mAP 69.409 mAcc 69.358
IOU: 64.940 95.376 50.515 45.350 85.972 67.887 63.519 30.412 27.476 67.339 14.241 59.793 47.386 57.798 39.719 28.327 88.013 60.697 71.145 34.651
mAP: 75.921 96.731 56.385 68.280 89.002 79.087 68.564 57.781 41.515 71.420 39.004 63.710 64.336 75.001 57.959 74.567 95.598 88.105 76.333 48.875
mAcc: 71.079 97.214 62.619 84.022 93.728 95.082 69.845 81.738 30.301 91.102 21.470 74.062 85.123 72.628 57.316 29.208 89.513 67.066 71.345 42.689

thomas 04/06 20:05:57 301/312: Data time: 0.0024, Iter time: 0.6647	Loss 0.780 (AVG: 0.689)	Score 77.257 (AVG: 78.738)	mIOU 54.787 mAP 69.502 mAcc 69.311
IOU: 64.724 95.427 55.430 43.553 86.198 68.401 61.422 31.604 27.104 68.443 14.141 58.604 46.479 54.731 43.681 26.221 84.891 55.461 74.066 35.160
mAP: 76.274 96.907 58.082 71.791 89.635 81.170 68.253 59.545 42.553 69.931 35.382 58.339 63.738 70.373 63.168 76.853 93.328 83.946 80.297 50.474
mAcc: 71.286 97.024 68.558 86.840 94.668 94.733 67.444 82.843 29.719 92.101 22.059 71.078 85.545 68.987 62.294 27.990 86.359 59.865 74.470 42.351

thomas 04/06 20:06:11 312/312: Data time: 0.0024, Iter time: 0.4526	Loss 0.155 (AVG: 0.690)	Score 96.958 (AVG: 78.730)	mIOU 54.739 mAP 69.205 mAcc 69.162
IOU: 64.678 95.431 55.161 43.786 86.220 68.408 61.855 32.010 27.548 68.384 13.639 58.412 47.050 54.014 42.139 26.221 84.891 55.442 74.066 35.433
mAP: 75.863 96.897 57.869 72.155 89.358 81.131 67.864 59.580 42.566 69.503 34.724 57.757 63.612 68.916 61.688 76.853 93.328 83.891 80.297 50.249
mAcc: 71.206 97.013 68.306 87.300 94.632 94.845 67.868 83.126 30.148 92.103 21.167 70.877 85.346 68.239 59.262 27.990 86.359 59.943 74.470 43.043

thomas 04/06 20:06:11 Finished test. Elapsed time: 364.0085
thomas 04/06 20:06:12 Current best mIoU: 57.967 at iter 16000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 20:10:12 ===> Epoch[67](20040/301): Loss 0.4048	LR: 8.484e-02	Score 87.504	Data time: 2.3222, Total iter time: 5.9393
thomas 04/06 20:14:10 ===> Epoch[67](20080/301): Loss 0.4387	LR: 8.481e-02	Score 86.265	Data time: 2.2880, Total iter time: 5.8609
thomas 04/06 20:18:00 ===> Epoch[67](20120/301): Loss 0.3868	LR: 8.478e-02	Score 87.934	Data time: 2.2525, Total iter time: 5.6804
thomas 04/06 20:21:54 ===> Epoch[67](20160/301): Loss 0.3730	LR: 8.474e-02	Score 88.314	Data time: 2.2820, Total iter time: 5.7655
thomas 04/06 20:25:52 ===> Epoch[68](20200/301): Loss 0.4085	LR: 8.471e-02	Score 87.335	Data time: 2.2743, Total iter time: 5.8755
thomas 04/06 20:29:45 ===> Epoch[68](20240/301): Loss 0.3783	LR: 8.468e-02	Score 88.186	Data time: 2.2440, Total iter time: 5.7304
thomas 04/06 20:33:34 ===> Epoch[68](20280/301): Loss 0.3975	LR: 8.465e-02	Score 87.491	Data time: 2.2271, Total iter time: 5.6662
thomas 04/06 20:37:35 ===> Epoch[68](20320/301): Loss 0.3891	LR: 8.462e-02	Score 88.298	Data time: 2.3079, Total iter time: 5.9277
thomas 04/06 20:41:30 ===> Epoch[68](20360/301): Loss 0.3820	LR: 8.459e-02	Score 88.050	Data time: 2.2812, Total iter time: 5.8146
thomas 04/06 20:45:26 ===> Epoch[68](20400/301): Loss 0.4150	LR: 8.456e-02	Score 87.271	Data time: 2.3321, Total iter time: 5.8234
thomas 04/06 20:49:31 ===> Epoch[68](20440/301): Loss 0.4353	LR: 8.453e-02	Score 86.408	Data time: 2.2981, Total iter time: 6.0564
thomas 04/06 20:53:18 ===> Epoch[69](20480/301): Loss 0.4138	LR: 8.450e-02	Score 87.116	Data time: 2.2078, Total iter time: 5.6070
thomas 04/06 20:57:29 ===> Epoch[69](20520/301): Loss 0.3955	LR: 8.447e-02	Score 87.472	Data time: 2.4380, Total iter time: 6.1713
thomas 04/06 21:01:11 ===> Epoch[69](20560/301): Loss 0.3708	LR: 8.444e-02	Score 88.403	Data time: 2.1472, Total iter time: 5.4918
thomas 04/06 21:05:10 ===> Epoch[69](20600/301): Loss 0.4069	LR: 8.441e-02	Score 87.525	Data time: 2.3299, Total iter time: 5.8898
thomas 04/06 21:09:06 ===> Epoch[69](20640/301): Loss 0.4024	LR: 8.438e-02	Score 87.377	Data time: 2.2984, Total iter time: 5.8196
thomas 04/06 21:12:55 ===> Epoch[69](20680/301): Loss 0.4224	LR: 8.435e-02	Score 86.497	Data time: 2.2186, Total iter time: 5.6493
thomas 04/06 21:16:52 ===> Epoch[69](20720/301): Loss 0.4149	LR: 8.432e-02	Score 86.954	Data time: 2.2825, Total iter time: 5.8740
thomas 04/06 21:20:54 ===> Epoch[69](20760/301): Loss 0.4032	LR: 8.429e-02	Score 87.310	Data time: 2.3429, Total iter time: 5.9808
thomas 04/06 21:24:46 ===> Epoch[70](20800/301): Loss 0.3863	LR: 8.426e-02	Score 87.728	Data time: 2.2263, Total iter time: 5.7118
thomas 04/06 21:28:34 ===> Epoch[70](20840/301): Loss 0.4204	LR: 8.422e-02	Score 87.415	Data time: 2.2508, Total iter time: 5.6472
thomas 04/06 21:32:36 ===> Epoch[70](20880/301): Loss 0.4041	LR: 8.419e-02	Score 87.346	Data time: 2.3515, Total iter time: 5.9778
thomas 04/06 21:36:11 ===> Epoch[70](20920/301): Loss 0.3989	LR: 8.416e-02	Score 87.846	Data time: 2.0700, Total iter time: 5.3015
thomas 04/06 21:40:21 ===> Epoch[70](20960/301): Loss 0.4429	LR: 8.413e-02	Score 86.136	Data time: 2.4284, Total iter time: 6.1592
thomas 04/06 21:44:25 ===> Epoch[70](21000/301): Loss 0.3931	LR: 8.410e-02	Score 87.731	Data time: 2.3922, Total iter time: 6.0299
thomas 04/06 21:44:27 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 21:44:27 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 21:46:30 101/312: Data time: 0.0032, Iter time: 0.7731	Loss 0.797 (AVG: 0.751)	Score 76.482 (AVG: 78.888)	mIOU 47.211 mAP 66.530 mAcc 58.483
IOU: 73.794 95.683 32.119 57.913 85.589 68.115 55.847 41.312 31.309 18.245 2.250 7.260 40.171 59.502 0.568 30.089 85.119 35.593 87.400 36.336
mAP: 79.587 97.710 48.380 67.479 89.548 79.799 67.392 60.800 47.972 65.814 31.327 44.228 52.192 83.901 21.077 87.575 92.287 74.298 86.340 52.891
mAcc: 84.458 98.004 43.434 84.602 90.651 95.424 63.512 66.789 34.592 89.258 2.295 7.375 54.111 64.290 0.568 31.274 85.601 36.438 88.532 48.460

thomas 04/06 21:48:26 201/312: Data time: 0.0024, Iter time: 0.5735	Loss 0.161 (AVG: 0.714)	Score 97.379 (AVG: 79.717)	mIOU 48.917 mAP 66.202 mAcc 59.929
IOU: 73.371 95.907 36.418 61.299 86.118 72.419 62.188 40.638 26.941 26.854 3.769 11.884 42.032 58.263 16.100 30.219 82.239 37.396 80.999 33.280
mAP: 77.002 97.217 47.629 68.653 90.787 81.373 69.580 59.670 44.519 70.140 31.546 44.549 55.068 75.718 32.987 83.272 89.290 72.258 85.324 47.464
mAcc: 84.376 98.136 46.056 87.066 90.063 96.712 70.189 68.809 29.806 91.845 3.909 12.031 59.873 61.267 16.135 30.799 83.041 38.229 82.163 48.071

thomas 04/06 21:50:29 301/312: Data time: 0.0032, Iter time: 1.3474	Loss 0.728 (AVG: 0.727)	Score 81.224 (AVG: 79.519)	mIOU 49.111 mAP 65.939 mAcc 59.685
IOU: 72.981 95.903 38.227 60.078 84.895 70.813 60.270 39.214 26.900 37.553 3.474 12.742 41.204 55.888 17.483 29.487 81.383 38.576 81.431 33.726
mAP: 77.094 97.262 50.425 67.830 88.869 83.601 68.223 59.344 44.977 66.610 29.316 46.340 56.185 72.543 37.407 83.071 88.983 72.343 82.098 46.250
mAcc: 84.185 98.250 49.235 81.939 88.571 96.617 68.721 67.226 29.438 94.081 3.604 12.923 59.753 58.949 17.530 30.609 82.075 39.642 82.717 47.643

thomas 04/06 21:50:40 312/312: Data time: 0.0036, Iter time: 0.5362	Loss 0.479 (AVG: 0.729)	Score 85.474 (AVG: 79.456)	mIOU 49.163 mAP 66.003 mAcc 59.827
IOU: 72.921 95.942 38.949 59.733 84.354 70.342 60.214 39.321 26.616 36.901 4.120 13.053 41.407 56.414 16.708 29.487 81.789 40.012 81.431 33.543
mAP: 76.992 97.325 50.692 68.334 88.751 83.689 68.074 59.442 45.074 67.127 29.809 45.359 56.667 73.094 36.953 83.071 89.278 72.182 82.098 46.055
mAcc: 84.093 98.251 50.252 82.093 87.940 96.605 68.626 67.212 29.068 94.129 4.273 13.247 60.153 59.537 16.750 30.609 82.456 41.100 82.717 47.426

thomas 04/06 21:50:40 Finished test. Elapsed time: 372.8104
thomas 04/06 21:50:40 Current best mIoU: 57.967 at iter 16000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 21:54:25 ===> Epoch[70](21040/301): Loss 0.4212	LR: 8.407e-02	Score 86.989	Data time: 2.1863, Total iter time: 5.5511
thomas 04/06 21:58:33 ===> Epoch[71](21080/301): Loss 0.4378	LR: 8.404e-02	Score 86.454	Data time: 2.3939, Total iter time: 6.1237
thomas 04/06 22:02:20 ===> Epoch[71](21120/301): Loss 0.4106	LR: 8.401e-02	Score 86.996	Data time: 2.2101, Total iter time: 5.6015
thomas 04/06 22:06:23 ===> Epoch[71](21160/301): Loss 0.4351	LR: 8.398e-02	Score 86.896	Data time: 2.3537, Total iter time: 5.9904
thomas 04/06 22:10:15 ===> Epoch[71](21200/301): Loss 0.3699	LR: 8.395e-02	Score 88.766	Data time: 2.2215, Total iter time: 5.7117
thomas 04/06 22:14:08 ===> Epoch[71](21240/301): Loss 0.3958	LR: 8.392e-02	Score 87.820	Data time: 2.2410, Total iter time: 5.7396
thomas 04/06 22:18:12 ===> Epoch[71](21280/301): Loss 0.3917	LR: 8.389e-02	Score 87.796	Data time: 2.3840, Total iter time: 6.0201
thomas 04/06 22:22:07 ===> Epoch[71](21320/301): Loss 0.3967	LR: 8.386e-02	Score 87.528	Data time: 2.3239, Total iter time: 5.8143
thomas 04/06 22:26:06 ===> Epoch[71](21360/301): Loss 0.3731	LR: 8.383e-02	Score 88.160	Data time: 2.3173, Total iter time: 5.8880
thomas 04/06 22:30:10 ===> Epoch[72](21400/301): Loss 0.4165	LR: 8.380e-02	Score 87.111	Data time: 2.3870, Total iter time: 6.0290
thomas 04/06 22:34:19 ===> Epoch[72](21440/301): Loss 0.3999	LR: 8.377e-02	Score 87.533	Data time: 2.4231, Total iter time: 6.1518
thomas 04/06 22:38:08 ===> Epoch[72](21480/301): Loss 0.3818	LR: 8.374e-02	Score 88.611	Data time: 2.2242, Total iter time: 5.6482
thomas 04/06 22:42:01 ===> Epoch[72](21520/301): Loss 0.4023	LR: 8.370e-02	Score 87.491	Data time: 2.2837, Total iter time: 5.7475
thomas 04/06 22:46:03 ===> Epoch[72](21560/301): Loss 0.4367	LR: 8.367e-02	Score 86.332	Data time: 2.3863, Total iter time: 5.9699
thomas 04/06 22:50:08 ===> Epoch[72](21600/301): Loss 0.4046	LR: 8.364e-02	Score 87.437	Data time: 2.3822, Total iter time: 6.0438
thomas 04/06 22:53:49 ===> Epoch[72](21640/301): Loss 0.3922	LR: 8.361e-02	Score 87.979	Data time: 2.1636, Total iter time: 5.4697
thomas 04/06 22:57:43 ===> Epoch[73](21680/301): Loss 0.3933	LR: 8.358e-02	Score 87.460	Data time: 2.2472, Total iter time: 5.7672
thomas 04/06 23:01:35 ===> Epoch[73](21720/301): Loss 0.3992	LR: 8.355e-02	Score 87.297	Data time: 2.2188, Total iter time: 5.7220
thomas 04/06 23:05:26 ===> Epoch[73](21760/301): Loss 0.3983	LR: 8.352e-02	Score 87.850	Data time: 2.2416, Total iter time: 5.7012
thomas 04/06 23:09:17 ===> Epoch[73](21800/301): Loss 0.3784	LR: 8.349e-02	Score 87.975	Data time: 2.2919, Total iter time: 5.6942
thomas 04/06 23:13:30 ===> Epoch[73](21840/301): Loss 0.3992	LR: 8.346e-02	Score 87.484	Data time: 2.4536, Total iter time: 6.2564
thomas 04/06 23:17:31 ===> Epoch[73](21880/301): Loss 0.3937	LR: 8.343e-02	Score 88.094	Data time: 2.3207, Total iter time: 5.9323
thomas 04/06 23:21:30 ===> Epoch[73](21920/301): Loss 0.3833	LR: 8.340e-02	Score 88.068	Data time: 2.3177, Total iter time: 5.9241
thomas 04/06 23:25:30 ===> Epoch[73](21960/301): Loss 0.3822	LR: 8.337e-02	Score 88.003	Data time: 2.3241, Total iter time: 5.9135
thomas 04/06 23:29:23 ===> Epoch[74](22000/301): Loss 0.3852	LR: 8.334e-02	Score 87.929	Data time: 2.2778, Total iter time: 5.7518
thomas 04/06 23:29:25 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/06 23:29:25 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/06 23:31:26 101/312: Data time: 0.0031, Iter time: 0.9267	Loss 1.451 (AVG: 0.605)	Score 64.522 (AVG: 82.463)	mIOU 53.329 mAP 69.236 mAcc 61.839
IOU: 76.554 96.203 41.069 68.667 85.790 74.595 60.441 37.600 36.531 55.085 11.039 43.945 49.993 46.827 42.180 20.840 69.656 35.242 68.905 45.412
mAP: 78.079 97.685 57.297 70.351 86.937 77.304 64.867 58.026 48.524 63.209 37.505 67.140 64.716 71.163 56.116 83.097 89.545 77.440 83.888 51.824
mAcc: 90.102 98.564 78.399 74.180 92.806 91.396 76.255 58.413 43.245 59.687 12.461 47.150 71.859 48.655 45.280 20.855 70.114 35.771 69.337 52.242

thomas 04/06 23:33:29 201/312: Data time: 0.0027, Iter time: 0.4330	Loss 0.339 (AVG: 0.598)	Score 91.117 (AVG: 82.830)	mIOU 53.329 mAP 69.492 mAcc 61.903
IOU: 77.091 95.916 45.898 70.214 84.879 74.878 64.926 40.307 39.377 52.891 12.695 45.374 48.455 50.078 39.980 23.399 58.981 31.889 70.534 38.818
mAP: 78.147 97.401 58.612 69.591 88.510 82.118 66.216 59.180 48.821 62.876 36.192 65.521 66.437 72.998 61.901 76.304 82.738 78.374 89.770 48.140
mAcc: 90.144 98.664 77.320 74.098 91.978 93.019 78.595 63.987 47.039 60.163 13.829 48.591 71.590 52.381 43.682 24.333 59.350 32.242 70.802 46.247

thomas 04/06 23:35:32 301/312: Data time: 0.0033, Iter time: 1.2964	Loss 0.801 (AVG: 0.609)	Score 67.890 (AVG: 82.494)	mIOU 52.756 mAP 68.936 mAcc 61.362
IOU: 76.503 95.969 42.844 68.815 83.962 77.567 64.046 38.680 39.912 51.133 13.387 45.348 49.236 49.279 40.617 18.149 62.192 30.659 67.871 38.947
mAP: 78.500 97.269 58.775 70.484 87.622 81.436 65.651 56.002 49.797 64.834 37.098 62.218 67.693 71.655 58.804 79.126 85.450 75.599 83.340 47.367
mAcc: 89.901 98.629 75.477 73.637 90.732 92.695 77.999 62.147 47.456 57.373 14.722 48.541 73.853 51.426 45.351 18.755 62.637 30.967 68.149 46.800

thomas 04/06 23:35:46 312/312: Data time: 0.0024, Iter time: 0.7174	Loss 0.302 (AVG: 0.605)	Score 91.106 (AVG: 82.620)	mIOU 52.864 mAP 69.023 mAcc 61.489
IOU: 76.337 96.025 43.472 68.188 84.183 77.047 64.901 38.753 39.884 51.095 13.290 45.472 49.468 49.249 41.281 19.259 61.424 29.372 68.177 40.407
mAP: 78.522 97.336 58.880 70.509 87.901 81.613 66.386 56.216 49.974 64.834 37.026 61.734 67.729 71.655 59.561 79.627 84.200 75.112 83.716 47.937
mAcc: 89.904 98.622 76.102 73.589 90.823 92.763 78.661 62.061 47.349 57.373 14.611 48.466 74.152 51.426 46.042 19.886 61.850 29.648 68.456 47.995

thomas 04/06 23:35:46 Finished test. Elapsed time: 380.8988
thomas 04/06 23:35:46 Current best mIoU: 57.967 at iter 16000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/06 23:39:34 ===> Epoch[74](22040/301): Loss 0.4000	LR: 8.331e-02	Score 87.367	Data time: 2.2283, Total iter time: 5.6283
thomas 04/06 23:43:19 ===> Epoch[74](22080/301): Loss 0.4016	LR: 8.328e-02	Score 87.148	Data time: 2.1752, Total iter time: 5.5585
thomas 04/06 23:47:17 ===> Epoch[74](22120/301): Loss 0.4216	LR: 8.325e-02	Score 86.721	Data time: 2.2920, Total iter time: 5.8739
thomas 04/06 23:51:11 ===> Epoch[74](22160/301): Loss 0.3737	LR: 8.322e-02	Score 88.812	Data time: 2.2905, Total iter time: 5.7732
thomas 04/06 23:55:26 ===> Epoch[74](22200/301): Loss 0.4072	LR: 8.318e-02	Score 87.723	Data time: 2.5049, Total iter time: 6.2881
thomas 04/06 23:59:17 ===> Epoch[74](22240/301): Loss 0.3596	LR: 8.315e-02	Score 88.492	Data time: 2.3072, Total iter time: 5.7041
thomas 04/07 00:03:19 ===> Epoch[75](22280/301): Loss 0.3952	LR: 8.312e-02	Score 87.511	Data time: 2.3427, Total iter time: 5.9669
thomas 04/07 00:07:10 ===> Epoch[75](22320/301): Loss 0.3928	LR: 8.309e-02	Score 87.726	Data time: 2.2132, Total iter time: 5.7012
thomas 04/07 00:11:18 ===> Epoch[75](22360/301): Loss 0.3658	LR: 8.306e-02	Score 88.417	Data time: 2.3521, Total iter time: 6.1040
thomas 04/07 00:15:08 ===> Epoch[75](22400/301): Loss 0.3762	LR: 8.303e-02	Score 88.258	Data time: 2.2696, Total iter time: 5.6795
thomas 04/07 00:19:09 ===> Epoch[75](22440/301): Loss 0.3914	LR: 8.300e-02	Score 87.685	Data time: 2.3432, Total iter time: 5.9624
thomas 04/07 00:23:13 ===> Epoch[75](22480/301): Loss 0.3874	LR: 8.297e-02	Score 88.032	Data time: 2.4222, Total iter time: 6.0155
thomas 04/07 00:27:15 ===> Epoch[75](22520/301): Loss 0.4569	LR: 8.294e-02	Score 86.214	Data time: 2.3606, Total iter time: 5.9689
thomas 04/07 00:31:07 ===> Epoch[75](22560/301): Loss 0.3704	LR: 8.291e-02	Score 88.255	Data time: 2.2384, Total iter time: 5.7224
thomas 04/07 00:35:02 ===> Epoch[76](22600/301): Loss 0.3524	LR: 8.288e-02	Score 88.760	Data time: 2.2457, Total iter time: 5.7879
thomas 04/07 00:39:10 ===> Epoch[76](22640/301): Loss 0.3823	LR: 8.285e-02	Score 88.366	Data time: 2.4009, Total iter time: 6.1268
thomas 04/07 00:43:06 ===> Epoch[76](22680/301): Loss 0.3970	LR: 8.282e-02	Score 87.163	Data time: 2.3304, Total iter time: 5.8249
thomas 04/07 00:47:00 ===> Epoch[76](22720/301): Loss 0.4005	LR: 8.279e-02	Score 87.500	Data time: 2.3057, Total iter time: 5.7763
thomas 04/07 00:50:54 ===> Epoch[76](22760/301): Loss 0.3925	LR: 8.276e-02	Score 88.159	Data time: 2.2862, Total iter time: 5.7544
thomas 04/07 00:54:54 ===> Epoch[76](22800/301): Loss 0.3831	LR: 8.273e-02	Score 88.175	Data time: 2.3055, Total iter time: 5.9205
thomas 04/07 00:58:57 ===> Epoch[76](22840/301): Loss 0.3770	LR: 8.269e-02	Score 88.411	Data time: 2.3024, Total iter time: 5.9851
thomas 04/07 01:03:02 ===> Epoch[77](22880/301): Loss 0.3579	LR: 8.266e-02	Score 88.677	Data time: 2.4080, Total iter time: 6.0484
thomas 04/07 01:07:12 ===> Epoch[77](22920/301): Loss 0.4133	LR: 8.263e-02	Score 86.999	Data time: 2.4731, Total iter time: 6.1806
thomas 04/07 01:10:58 ===> Epoch[77](22960/301): Loss 0.3661	LR: 8.260e-02	Score 88.739	Data time: 2.2209, Total iter time: 5.5602
thomas 04/07 01:15:06 ===> Epoch[77](23000/301): Loss 0.3548	LR: 8.257e-02	Score 89.230	Data time: 2.3998, Total iter time: 6.1191
thomas 04/07 01:15:08 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 01:15:08 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 01:17:13 101/312: Data time: 0.0027, Iter time: 0.5238	Loss 0.735 (AVG: 0.571)	Score 80.654 (AVG: 83.851)	mIOU 58.974 mAP 71.823 mAcc 70.030
IOU: 75.248 95.564 57.972 68.782 86.757 76.181 63.580 41.190 34.383 70.666 22.811 46.540 53.930 62.446 29.145 34.878 91.848 45.012 80.037 42.517
mAP: 77.321 97.477 64.097 81.411 89.349 81.938 71.464 61.770 49.389 71.960 54.160 54.335 69.212 76.729 55.495 88.651 95.424 70.140 70.480 55.668
mAcc: 84.483 97.585 79.149 87.828 92.925 94.346 67.594 67.822 36.500 96.287 27.273 55.036 68.585 84.391 32.436 36.631 93.331 47.184 80.849 70.356

thomas 04/07 01:19:11 201/312: Data time: 0.0028, Iter time: 0.6243	Loss 0.663 (AVG: 0.558)	Score 82.117 (AVG: 84.169)	mIOU 59.756 mAP 71.617 mAcc 70.428
IOU: 75.186 95.954 59.599 68.953 87.805 77.307 66.075 43.869 36.860 70.593 17.317 47.750 53.156 67.371 36.257 38.722 83.251 48.147 79.069 41.881
mAP: 78.500 97.828 66.974 76.691 90.320 84.234 70.905 62.636 48.672 73.905 45.596 57.938 63.940 76.792 51.637 86.156 92.834 76.386 77.826 52.564
mAcc: 84.629 97.758 79.709 87.323 94.815 93.744 70.508 71.600 38.977 93.337 21.903 55.226 65.902 85.303 41.318 40.349 84.853 50.346 80.166 70.790

thomas 04/07 01:21:03 301/312: Data time: 0.0027, Iter time: 0.7028	Loss 1.225 (AVG: 0.570)	Score 74.911 (AVG: 83.882)	mIOU 59.431 mAP 71.409 mAcc 69.950
IOU: 75.307 95.858 57.080 68.710 86.994 76.871 64.598 45.065 35.449 70.181 15.594 49.053 52.844 63.634 37.402 41.856 79.628 49.622 81.977 40.887
mAP: 78.499 97.395 62.773 74.482 89.896 81.889 71.568 63.310 51.538 71.928 41.378 60.109 64.175 77.347 52.333 88.238 90.196 78.960 82.017 50.157
mAcc: 85.352 97.734 76.933 85.174 95.161 93.902 68.929 69.995 37.416 92.300 20.477 55.545 65.668 80.490 44.381 45.208 80.976 52.716 83.414 67.219

thomas 04/07 01:21:14 312/312: Data time: 0.0025, Iter time: 0.6708	Loss 0.462 (AVG: 0.570)	Score 84.346 (AVG: 83.880)	mIOU 59.584 mAP 71.451 mAcc 70.158
IOU: 75.557 95.880 57.658 68.563 87.015 75.976 64.064 44.667 35.168 69.269 16.581 49.502 52.486 64.363 42.666 40.985 79.563 49.076 81.977 40.656
mAP: 78.680 97.445 63.139 74.738 90.121 82.523 71.257 63.254 51.249 71.928 41.780 59.568 63.899 77.872 54.305 86.439 90.330 78.099 82.017 50.382
mAcc: 85.541 97.737 77.572 84.940 95.235 94.072 68.838 68.942 37.133 92.300 21.894 55.694 65.507 81.128 50.058 44.194 80.892 52.161 83.414 65.899

thomas 04/07 01:21:14 Finished test. Elapsed time: 366.5519
thomas 04/07 01:21:16 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/07 01:21:16 Current best mIoU: 59.584 at iter 23000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 01:25:04 ===> Epoch[77](23040/301): Loss 0.3548	LR: 8.254e-02	Score 88.953	Data time: 2.2031, Total iter time: 5.6385
thomas 04/07 01:29:10 ===> Epoch[77](23080/301): Loss 0.3880	LR: 8.251e-02	Score 87.743	Data time: 2.4008, Total iter time: 6.0689
thomas 04/07 01:33:06 ===> Epoch[77](23120/301): Loss 0.4220	LR: 8.248e-02	Score 87.273	Data time: 2.3590, Total iter time: 5.8343
thomas 04/07 01:37:02 ===> Epoch[77](23160/301): Loss 0.3971	LR: 8.245e-02	Score 87.659	Data time: 2.3069, Total iter time: 5.8124
thomas 04/07 01:40:54 ===> Epoch[78](23200/301): Loss 0.4344	LR: 8.242e-02	Score 86.887	Data time: 2.2560, Total iter time: 5.7180
thomas 04/07 01:45:06 ===> Epoch[78](23240/301): Loss 0.4296	LR: 8.239e-02	Score 86.411	Data time: 2.3920, Total iter time: 6.2224
thomas 04/07 01:48:51 ===> Epoch[78](23280/301): Loss 0.4187	LR: 8.236e-02	Score 87.303	Data time: 2.1561, Total iter time: 5.5485
thomas 04/07 01:52:23 ===> Epoch[78](23320/301): Loss 0.3667	LR: 8.233e-02	Score 88.842	Data time: 2.0826, Total iter time: 5.2305
thomas 04/07 01:56:27 ===> Epoch[78](23360/301): Loss 0.3981	LR: 8.230e-02	Score 87.523	Data time: 2.4339, Total iter time: 6.0086
thomas 04/07 02:00:36 ===> Epoch[78](23400/301): Loss 0.4223	LR: 8.227e-02	Score 86.909	Data time: 2.4509, Total iter time: 6.1461
thomas 04/07 02:04:28 ===> Epoch[78](23440/301): Loss 0.3635	LR: 8.223e-02	Score 88.533	Data time: 2.2186, Total iter time: 5.7265
thomas 04/07 02:08:03 ===> Epoch[79](23480/301): Loss 0.3788	LR: 8.220e-02	Score 88.174	Data time: 2.0572, Total iter time: 5.3258
thomas 04/07 02:12:02 ===> Epoch[79](23520/301): Loss 0.3733	LR: 8.217e-02	Score 88.439	Data time: 2.2403, Total iter time: 5.8898
thomas 04/07 02:15:52 ===> Epoch[79](23560/301): Loss 0.3846	LR: 8.214e-02	Score 87.864	Data time: 2.2429, Total iter time: 5.6961
thomas 04/07 02:20:08 ===> Epoch[79](23600/301): Loss 0.3925	LR: 8.211e-02	Score 87.859	Data time: 2.5364, Total iter time: 6.3181
thomas 04/07 02:24:05 ===> Epoch[79](23640/301): Loss 0.4042	LR: 8.208e-02	Score 87.582	Data time: 2.3887, Total iter time: 5.8599
thomas 04/07 02:28:01 ===> Epoch[79](23680/301): Loss 0.3807	LR: 8.205e-02	Score 87.706	Data time: 2.2910, Total iter time: 5.8256
thomas 04/07 02:32:10 ===> Epoch[79](23720/301): Loss 0.3516	LR: 8.202e-02	Score 89.393	Data time: 2.4068, Total iter time: 6.1764
thomas 04/07 02:36:06 ===> Epoch[79](23760/301): Loss 0.3479	LR: 8.199e-02	Score 88.769	Data time: 2.2530, Total iter time: 5.8016
thomas 04/07 02:39:56 ===> Epoch[80](23800/301): Loss 0.3541	LR: 8.196e-02	Score 88.933	Data time: 2.2757, Total iter time: 5.7039
thomas 04/07 02:43:52 ===> Epoch[80](23840/301): Loss 0.3707	LR: 8.193e-02	Score 88.752	Data time: 2.3306, Total iter time: 5.8292
thomas 04/07 02:48:11 ===> Epoch[80](23880/301): Loss 0.3684	LR: 8.190e-02	Score 88.789	Data time: 2.5240, Total iter time: 6.3832
thomas 04/07 02:52:14 ===> Epoch[80](23920/301): Loss 0.3813	LR: 8.187e-02	Score 87.916	Data time: 2.3300, Total iter time: 5.9750
thomas 04/07 02:56:01 ===> Epoch[80](23960/301): Loss 0.4328	LR: 8.184e-02	Score 86.695	Data time: 2.1793, Total iter time: 5.6062
thomas 04/07 02:59:53 ===> Epoch[80](24000/301): Loss 0.4313	LR: 8.181e-02	Score 86.287	Data time: 2.2389, Total iter time: 5.7236
thomas 04/07 02:59:54 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 02:59:54 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 03:02:05 101/312: Data time: 0.0031, Iter time: 0.3371	Loss 0.377 (AVG: 0.595)	Score 81.091 (AVG: 83.304)	mIOU 59.000 mAP 70.341 mAcc 70.243
IOU: 76.561 95.411 54.078 64.605 83.704 79.605 63.079 41.510 42.034 61.610 9.733 62.024 57.458 64.185 34.422 61.705 87.536 30.761 71.154 38.836
mAP: 79.746 95.473 58.273 66.959 87.217 81.839 70.575 59.918 49.903 73.094 40.764 58.333 71.216 75.019 52.260 89.993 96.266 80.073 70.337 49.556
mAcc: 89.363 98.367 79.612 71.572 93.685 93.356 77.860 56.317 51.741 74.311 10.607 79.620 73.309 83.909 55.173 71.098 93.584 30.832 75.521 45.024

thomas 04/07 03:04:15 201/312: Data time: 0.0024, Iter time: 0.6240	Loss 0.547 (AVG: 0.599)	Score 82.049 (AVG: 83.342)	mIOU 57.706 mAP 69.732 mAcc 69.215
IOU: 75.950 95.976 50.287 65.597 83.824 76.572 65.840 43.925 37.630 66.279 8.740 55.580 52.539 59.874 40.054 53.004 83.709 30.966 68.878 38.889
mAP: 78.009 96.158 57.876 70.947 87.557 80.382 71.122 59.574 48.893 70.203 33.809 60.389 68.379 69.143 55.154 90.042 96.481 77.620 75.148 47.752
mAcc: 89.424 98.610 79.826 73.214 94.303 91.129 75.988 58.651 44.803 77.811 9.566 68.979 71.460 73.240 60.190 74.687 89.545 31.128 77.102 44.634

thomas 04/07 03:06:09 301/312: Data time: 0.0024, Iter time: 0.4296	Loss 0.556 (AVG: 0.574)	Score 74.675 (AVG: 83.970)	mIOU 58.482 mAP 70.429 mAcc 70.282
IOU: 76.594 95.926 49.637 66.261 85.367 75.449 67.948 42.902 37.430 68.433 9.626 56.286 53.064 58.002 39.442 53.472 85.293 31.691 78.178 38.630
mAP: 77.484 96.305 57.611 69.282 88.186 81.657 71.358 59.266 50.529 70.774 33.865 58.712 70.176 71.182 56.684 89.113 96.108 78.678 82.472 49.127
mAcc: 89.104 98.583 78.617 74.015 94.753 92.932 76.967 59.134 43.349 78.693 10.462 67.310 72.945 76.690 62.960 76.353 91.355 31.808 85.050 44.550

thomas 04/07 03:06:19 312/312: Data time: 0.0024, Iter time: 0.2547	Loss 0.344 (AVG: 0.573)	Score 89.201 (AVG: 84.031)	mIOU 58.658 mAP 70.650 mAcc 70.487
IOU: 76.849 95.891 49.470 66.106 85.518 74.478 68.246 42.789 38.057 68.731 9.776 56.226 53.863 59.606 39.386 53.336 85.356 31.715 79.004 38.756
mAP: 77.795 96.404 57.915 69.282 88.217 81.657 71.453 59.137 50.423 70.419 34.801 58.645 70.359 72.143 56.684 89.204 96.220 79.085 83.033 50.122
mAcc: 89.263 98.584 78.737 74.015 94.812 92.932 77.354 58.889 43.710 78.990 10.614 67.136 73.129 78.214 62.960 76.667 91.609 31.829 85.692 44.602

thomas 04/07 03:06:19 Finished test. Elapsed time: 384.2776
thomas 04/07 03:06:19 Current best mIoU: 59.584 at iter 23000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 03:10:21 ===> Epoch[80](24040/301): Loss 0.3964	LR: 8.177e-02	Score 87.665	Data time: 2.4030, Total iter time: 5.9853
thomas 04/07 03:14:25 ===> Epoch[80](24080/301): Loss 0.3840	LR: 8.174e-02	Score 87.871	Data time: 2.3665, Total iter time: 6.0016
thomas 04/07 03:18:08 ===> Epoch[81](24120/301): Loss 0.3702	LR: 8.171e-02	Score 88.634	Data time: 2.1464, Total iter time: 5.5081
thomas 04/07 03:22:01 ===> Epoch[81](24160/301): Loss 0.3809	LR: 8.168e-02	Score 88.300	Data time: 2.2464, Total iter time: 5.7615
thomas 04/07 03:25:45 ===> Epoch[81](24200/301): Loss 0.4226	LR: 8.165e-02	Score 87.307	Data time: 2.1647, Total iter time: 5.5086
thomas 04/07 03:29:44 ===> Epoch[81](24240/301): Loss 0.3995	LR: 8.162e-02	Score 87.793	Data time: 2.3431, Total iter time: 5.9059
thomas 04/07 03:33:57 ===> Epoch[81](24280/301): Loss 0.3941	LR: 8.159e-02	Score 87.902	Data time: 2.5577, Total iter time: 6.2639
thomas 04/07 03:37:55 ===> Epoch[81](24320/301): Loss 0.3787	LR: 8.156e-02	Score 87.897	Data time: 2.2628, Total iter time: 5.8492
thomas 04/07 03:41:39 ===> Epoch[81](24360/301): Loss 0.3867	LR: 8.153e-02	Score 88.198	Data time: 2.1620, Total iter time: 5.5355
thomas 04/07 03:45:32 ===> Epoch[82](24400/301): Loss 0.3957	LR: 8.150e-02	Score 87.835	Data time: 2.2258, Total iter time: 5.7519
thomas 04/07 03:49:33 ===> Epoch[82](24440/301): Loss 0.4083	LR: 8.147e-02	Score 87.419	Data time: 2.2974, Total iter time: 5.9494
thomas 04/07 03:53:29 ===> Epoch[82](24480/301): Loss 0.3836	LR: 8.144e-02	Score 87.941	Data time: 2.3137, Total iter time: 5.8333
thomas 04/07 03:57:45 ===> Epoch[82](24520/301): Loss 0.3842	LR: 8.141e-02	Score 88.152	Data time: 2.5242, Total iter time: 6.3233
thomas 04/07 04:01:37 ===> Epoch[82](24560/301): Loss 0.3650	LR: 8.138e-02	Score 88.345	Data time: 2.2272, Total iter time: 5.7379
thomas 04/07 04:05:37 ===> Epoch[82](24600/301): Loss 0.3824	LR: 8.135e-02	Score 88.051	Data time: 2.2971, Total iter time: 5.9025
thomas 04/07 04:09:20 ===> Epoch[82](24640/301): Loss 0.4314	LR: 8.131e-02	Score 86.986	Data time: 2.1463, Total iter time: 5.5028
thomas 04/07 04:13:07 ===> Epoch[82](24680/301): Loss 0.3658	LR: 8.128e-02	Score 88.394	Data time: 2.2236, Total iter time: 5.6174
thomas 04/07 04:17:20 ===> Epoch[83](24720/301): Loss 0.3818	LR: 8.125e-02	Score 88.290	Data time: 2.4905, Total iter time: 6.2268
thomas 04/07 04:21:25 ===> Epoch[83](24760/301): Loss 0.4216	LR: 8.122e-02	Score 87.045	Data time: 2.4149, Total iter time: 6.0393
thomas 04/07 04:25:20 ===> Epoch[83](24800/301): Loss 0.3665	LR: 8.119e-02	Score 88.900	Data time: 2.2874, Total iter time: 5.8196
thomas 04/07 04:29:13 ===> Epoch[83](24840/301): Loss 0.3475	LR: 8.116e-02	Score 89.247	Data time: 2.2428, Total iter time: 5.7509
thomas 04/07 04:33:06 ===> Epoch[83](24880/301): Loss 0.3842	LR: 8.113e-02	Score 87.974	Data time: 2.2371, Total iter time: 5.7446
thomas 04/07 04:37:03 ===> Epoch[83](24920/301): Loss 0.3671	LR: 8.110e-02	Score 88.177	Data time: 2.2946, Total iter time: 5.8587
thomas 04/07 04:41:06 ===> Epoch[83](24960/301): Loss 0.3670	LR: 8.107e-02	Score 88.323	Data time: 2.4259, Total iter time: 6.0031
thomas 04/07 04:45:03 ===> Epoch[84](25000/301): Loss 0.3533	LR: 8.104e-02	Score 88.729	Data time: 2.3604, Total iter time: 5.8354
thomas 04/07 04:45:04 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 04:45:05 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 04:47:10 101/312: Data time: 0.0029, Iter time: 0.4896	Loss 0.340 (AVG: 0.770)	Score 91.180 (AVG: 75.644)	mIOU 48.988 mAP 69.262 mAcc 64.457
IOU: 63.943 95.852 43.202 37.764 77.103 49.128 56.454 34.627 36.758 66.275 11.026 47.694 45.525 30.128 36.076 40.988 59.616 33.959 85.410 28.226
mAP: 76.456 97.725 55.398 75.605 88.973 81.700 64.491 64.836 49.182 68.804 34.156 56.619 64.840 75.694 47.724 84.859 96.229 74.619 81.571 45.764
mAcc: 70.382 98.173 46.470 92.363 81.119 97.921 69.634 71.880 38.786 93.192 11.729 49.801 62.886 81.385 39.932 46.862 59.806 34.161 88.076 54.590

thomas 04/07 04:49:08 201/312: Data time: 0.0027, Iter time: 0.6250	Loss 0.731 (AVG: 0.746)	Score 77.573 (AVG: 76.888)	mIOU 49.114 mAP 67.538 mAcc 63.741
IOU: 63.615 96.101 40.970 42.169 81.484 50.194 62.346 33.959 34.464 67.773 10.701 44.021 50.171 41.769 22.363 38.840 61.835 34.796 76.718 27.990
mAP: 75.988 97.615 52.430 75.032 89.195 78.738 66.593 61.539 45.118 72.581 37.766 55.487 66.520 71.573 38.702 85.272 93.672 68.171 73.722 45.053
mAcc: 69.400 98.331 44.214 90.910 85.166 93.987 73.163 75.946 36.429 94.595 11.341 45.866 70.854 83.542 24.214 43.484 62.165 35.024 79.063 57.131

thomas 04/07 04:50:59 301/312: Data time: 0.0025, Iter time: 0.3899	Loss 0.328 (AVG: 0.739)	Score 90.543 (AVG: 77.038)	mIOU 50.289 mAP 68.058 mAcc 64.282
IOU: 63.694 96.061 40.616 45.107 82.232 53.077 64.122 34.630 35.038 71.144 10.361 43.982 52.020 47.557 22.665 43.158 63.374 35.581 74.149 27.209
mAP: 76.712 97.390 53.175 71.533 88.694 79.684 68.361 60.666 46.667 71.723 34.638 54.195 66.409 75.900 39.740 85.919 93.311 72.324 79.697 44.423
mAcc: 69.278 98.370 43.457 88.171 85.803 94.951 75.447 76.179 37.310 94.437 11.130 45.901 71.127 84.094 24.487 49.537 63.662 35.849 79.145 57.308

thomas 04/07 04:51:12 312/312: Data time: 0.0033, Iter time: 0.3169	Loss 0.680 (AVG: 0.739)	Score 77.117 (AVG: 77.057)	mIOU 50.155 mAP 68.113 mAcc 64.253
IOU: 63.528 96.091 40.638 44.433 82.397 52.356 64.762 34.245 34.937 71.080 9.756 42.863 51.417 47.202 22.492 43.156 63.879 35.659 74.149 28.070
mAP: 76.647 97.445 53.577 71.087 88.348 79.927 69.085 60.461 46.841 71.489 33.976 54.828 65.948 75.560 39.929 85.919 93.400 72.547 79.697 45.555
mAcc: 69.077 98.382 43.549 86.939 85.917 95.045 75.933 75.878 37.224 94.525 10.461 45.546 70.903 83.761 24.285 49.537 64.166 35.926 79.145 58.851

thomas 04/07 04:51:12 Finished test. Elapsed time: 367.6927
thomas 04/07 04:51:12 Current best mIoU: 59.584 at iter 23000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 04:55:14 ===> Epoch[84](25040/301): Loss 0.3255	LR: 8.101e-02	Score 89.849	Data time: 2.3389, Total iter time: 5.9640
thomas 04/07 04:58:59 ===> Epoch[84](25080/301): Loss 0.3473	LR: 8.098e-02	Score 89.119	Data time: 2.1562, Total iter time: 5.5631
thomas 04/07 05:02:52 ===> Epoch[84](25120/301): Loss 0.3870	LR: 8.095e-02	Score 87.861	Data time: 2.2710, Total iter time: 5.7402
thomas 04/07 05:07:06 ===> Epoch[84](25160/301): Loss 0.3769	LR: 8.092e-02	Score 88.385	Data time: 2.5283, Total iter time: 6.2566
thomas 04/07 05:11:16 ===> Epoch[84](25200/301): Loss 0.3749	LR: 8.088e-02	Score 88.241	Data time: 2.4526, Total iter time: 6.1759
thomas 04/07 05:15:00 ===> Epoch[84](25240/301): Loss 0.3711	LR: 8.085e-02	Score 88.318	Data time: 2.1688, Total iter time: 5.5341
thomas 04/07 05:19:00 ===> Epoch[84](25280/301): Loss 0.3817	LR: 8.082e-02	Score 88.101	Data time: 2.3118, Total iter time: 5.9302
thomas 04/07 05:22:45 ===> Epoch[85](25320/301): Loss 0.4271	LR: 8.079e-02	Score 86.900	Data time: 2.1950, Total iter time: 5.5567
thomas 04/07 05:26:51 ===> Epoch[85](25360/301): Loss 0.3914	LR: 8.076e-02	Score 87.528	Data time: 2.3601, Total iter time: 6.0598
thomas 04/07 05:31:17 ===> Epoch[85](25400/301): Loss 0.3476	LR: 8.073e-02	Score 89.296	Data time: 2.6296, Total iter time: 6.5431
thomas 04/07 05:35:10 ===> Epoch[85](25440/301): Loss 0.3877	LR: 8.070e-02	Score 88.157	Data time: 2.3189, Total iter time: 5.7561
thomas 04/07 05:39:02 ===> Epoch[85](25480/301): Loss 0.4004	LR: 8.067e-02	Score 87.326	Data time: 2.2188, Total iter time: 5.7217
thomas 04/07 05:42:44 ===> Epoch[85](25520/301): Loss 0.3755	LR: 8.064e-02	Score 88.305	Data time: 2.1590, Total iter time: 5.4796
thomas 04/07 05:46:31 ===> Epoch[85](25560/301): Loss 0.3682	LR: 8.061e-02	Score 88.604	Data time: 2.1962, Total iter time: 5.5955
thomas 04/07 05:50:39 ===> Epoch[86](25600/301): Loss 0.3866	LR: 8.058e-02	Score 87.906	Data time: 2.3891, Total iter time: 6.1154
thomas 04/07 05:55:00 ===> Epoch[86](25640/301): Loss 0.3683	LR: 8.055e-02	Score 88.657	Data time: 2.6298, Total iter time: 6.4544
thomas 04/07 05:58:51 ===> Epoch[86](25680/301): Loss 0.4031	LR: 8.052e-02	Score 87.523	Data time: 2.2929, Total iter time: 5.6862
thomas 04/07 06:02:42 ===> Epoch[86](25720/301): Loss 0.3680	LR: 8.049e-02	Score 88.605	Data time: 2.2402, Total iter time: 5.7034
thomas 04/07 06:06:41 ===> Epoch[86](25760/301): Loss 0.3730	LR: 8.045e-02	Score 88.138	Data time: 2.2778, Total iter time: 5.9135
thomas 04/07 06:10:25 ===> Epoch[86](25800/301): Loss 0.4245	LR: 8.042e-02	Score 86.924	Data time: 2.1761, Total iter time: 5.5295
thomas 04/07 06:14:01 ===> Epoch[86](25840/301): Loss 0.3852	LR: 8.039e-02	Score 87.977	Data time: 2.0923, Total iter time: 5.3243
thomas 04/07 06:18:07 ===> Epoch[86](25880/301): Loss 0.3920	LR: 8.036e-02	Score 87.639	Data time: 2.4492, Total iter time: 6.0804
thomas 04/07 06:22:13 ===> Epoch[87](25920/301): Loss 0.3705	LR: 8.033e-02	Score 88.634	Data time: 2.4322, Total iter time: 6.0645
thomas 04/07 06:26:01 ===> Epoch[87](25960/301): Loss 0.3835	LR: 8.030e-02	Score 88.105	Data time: 2.1862, Total iter time: 5.6368
thomas 04/07 06:29:57 ===> Epoch[87](26000/301): Loss 0.3726	LR: 8.027e-02	Score 88.261	Data time: 2.2629, Total iter time: 5.8304
thomas 04/07 06:29:59 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 06:29:59 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 06:31:59 101/312: Data time: 0.0040, Iter time: 1.0384	Loss 0.434 (AVG: 0.614)	Score 85.492 (AVG: 82.028)	mIOU 59.288 mAP 72.468 mAcc 70.775
IOU: 71.831 95.889 49.180 76.234 81.801 70.602 71.613 39.847 21.763 71.755 19.954 47.059 61.395 66.031 57.472 40.537 81.613 56.663 77.212 27.313
mAP: 76.029 96.562 61.631 79.959 87.709 90.237 73.251 60.259 44.770 58.437 41.071 62.351 68.714 81.852 68.713 86.287 94.036 84.242 82.286 50.963
mAcc: 82.489 98.292 85.846 87.768 94.181 88.643 82.454 66.391 22.879 93.110 23.250 50.302 84.071 84.581 66.145 41.712 82.705 58.760 90.227 31.705

thomas 04/07 06:34:05 201/312: Data time: 0.0033, Iter time: 0.4275	Loss 0.482 (AVG: 0.603)	Score 85.575 (AVG: 82.542)	mIOU 58.880 mAP 70.739 mAcc 70.379
IOU: 73.192 95.935 49.061 72.660 83.348 75.832 64.735 43.211 32.327 67.714 13.669 48.269 53.812 64.597 50.137 40.039 83.012 56.259 80.604 29.181
mAP: 76.351 96.584 59.985 72.716 89.193 83.095 70.779 61.334 52.411 65.936 37.907 58.271 67.559 77.773 60.959 80.010 93.309 81.366 80.707 48.536
mAcc: 83.390 98.207 84.198 80.627 94.553 88.783 73.890 70.105 33.503 91.101 16.672 52.535 84.311 81.118 61.123 43.415 83.905 60.158 90.324 35.659

thomas 04/07 06:35:54 301/312: Data time: 0.0025, Iter time: 0.6510	Loss 1.028 (AVG: 0.613)	Score 67.047 (AVG: 82.384)	mIOU 58.082 mAP 71.176 mAcc 69.493
IOU: 73.041 96.081 45.213 72.688 83.756 79.296 65.668 43.009 30.287 66.492 13.191 46.912 53.035 62.861 47.839 34.908 85.416 50.967 81.536 29.450
mAP: 76.285 96.713 57.931 73.654 89.226 83.658 72.681 60.509 51.356 69.822 38.810 59.314 66.926 77.252 62.263 82.510 94.604 80.817 79.999 49.190
mAcc: 83.635 98.231 81.994 82.053 94.964 90.153 74.081 68.462 31.189 89.721 16.780 50.771 85.342 80.484 58.786 37.100 86.482 53.691 89.883 36.060

thomas 04/07 06:36:05 312/312: Data time: 0.0030, Iter time: 0.4784	Loss 0.367 (AVG: 0.613)	Score 90.242 (AVG: 82.327)	mIOU 58.034 mAP 71.293 mAcc 69.470
IOU: 72.973 96.095 45.028 73.660 83.900 79.219 65.285 42.139 30.262 66.282 13.520 47.500 52.616 62.873 47.698 34.908 85.416 50.867 81.536 28.913
mAP: 76.441 96.732 58.170 74.180 89.460 83.804 72.839 60.743 51.501 70.054 38.629 59.655 67.022 76.808 62.917 82.510 94.604 80.817 79.999 48.984
mAcc: 83.542 98.242 82.120 82.882 95.056 90.260 73.647 66.537 31.281 90.388 17.288 51.279 85.370 80.556 58.391 37.100 86.482 53.691 89.883 35.407

thomas 04/07 06:36:05 Finished test. Elapsed time: 365.9681
thomas 04/07 06:36:05 Current best mIoU: 59.584 at iter 23000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 06:40:04 ===> Epoch[87](26040/301): Loss 0.4095	LR: 8.024e-02	Score 87.745	Data time: 2.3666, Total iter time: 5.9121
thomas 04/07 06:44:23 ===> Epoch[87](26080/301): Loss 0.3952	LR: 8.021e-02	Score 87.762	Data time: 2.5637, Total iter time: 6.3961
thomas 04/07 06:48:28 ===> Epoch[87](26120/301): Loss 0.3679	LR: 8.018e-02	Score 88.377	Data time: 2.3847, Total iter time: 6.0308
thomas 04/07 06:52:17 ===> Epoch[87](26160/301): Loss 0.3728	LR: 8.015e-02	Score 88.520	Data time: 2.1939, Total iter time: 5.6677
thomas 04/07 06:56:13 ===> Epoch[88](26200/301): Loss 0.3689	LR: 8.012e-02	Score 88.372	Data time: 2.2699, Total iter time: 5.8089
thomas 04/07 07:00:01 ===> Epoch[88](26240/301): Loss 0.3635	LR: 8.009e-02	Score 88.523	Data time: 2.1816, Total iter time: 5.6352
thomas 04/07 07:04:02 ===> Epoch[88](26280/301): Loss 0.3922	LR: 8.005e-02	Score 87.773	Data time: 2.4066, Total iter time: 5.9528
thomas 04/07 07:08:04 ===> Epoch[88](26320/301): Loss 0.3504	LR: 8.002e-02	Score 88.833	Data time: 2.4340, Total iter time: 5.9612
thomas 04/07 07:12:19 ===> Epoch[88](26360/301): Loss 0.3588	LR: 7.999e-02	Score 88.615	Data time: 2.4854, Total iter time: 6.3128
thomas 04/07 07:16:15 ===> Epoch[88](26400/301): Loss 0.3943	LR: 7.996e-02	Score 87.974	Data time: 2.2801, Total iter time: 5.8193
thomas 04/07 07:20:10 ===> Epoch[88](26440/301): Loss 0.3643	LR: 7.993e-02	Score 88.539	Data time: 2.2682, Total iter time: 5.7952
thomas 04/07 07:24:05 ===> Epoch[88](26480/301): Loss 0.3626	LR: 7.990e-02	Score 88.697	Data time: 2.2843, Total iter time: 5.8148
thomas 04/07 07:28:20 ===> Epoch[89](26520/301): Loss 0.3609	LR: 7.987e-02	Score 88.529	Data time: 2.5619, Total iter time: 6.3066
thomas 04/07 07:32:24 ===> Epoch[89](26560/301): Loss 0.3803	LR: 7.984e-02	Score 88.103	Data time: 2.4439, Total iter time: 6.0000
thomas 04/07 07:36:24 ===> Epoch[89](26600/301): Loss 0.4052	LR: 7.981e-02	Score 87.958	Data time: 2.3512, Total iter time: 5.9216
thomas 04/07 07:40:07 ===> Epoch[89](26640/301): Loss 0.3888	LR: 7.978e-02	Score 87.540	Data time: 2.1641, Total iter time: 5.4978
thomas 04/07 07:44:06 ===> Epoch[89](26680/301): Loss 0.3756	LR: 7.975e-02	Score 88.397	Data time: 2.2921, Total iter time: 5.8974
thomas 04/07 07:47:58 ===> Epoch[89](26720/301): Loss 0.3849	LR: 7.972e-02	Score 88.191	Data time: 2.2699, Total iter time: 5.7314
thomas 04/07 07:51:47 ===> Epoch[89](26760/301): Loss 0.3429	LR: 7.969e-02	Score 89.262	Data time: 2.2941, Total iter time: 5.6604
thomas 04/07 07:56:03 ===> Epoch[90](26800/301): Loss 0.3935	LR: 7.965e-02	Score 87.662	Data time: 2.5328, Total iter time: 6.3171
thomas 04/07 08:00:05 ===> Epoch[90](26840/301): Loss 0.3394	LR: 7.962e-02	Score 89.464	Data time: 2.3605, Total iter time: 5.9922
thomas 04/07 08:03:53 ===> Epoch[90](26880/301): Loss 0.3721	LR: 7.959e-02	Score 88.115	Data time: 2.1949, Total iter time: 5.6277
thomas 04/07 08:07:42 ===> Epoch[90](26920/301): Loss 0.3696	LR: 7.956e-02	Score 88.510	Data time: 2.2002, Total iter time: 5.6568
thomas 04/07 08:11:31 ===> Epoch[90](26960/301): Loss 0.3911	LR: 7.953e-02	Score 88.074	Data time: 2.2056, Total iter time: 5.6506
thomas 04/07 08:15:45 ===> Epoch[90](27000/301): Loss 0.3980	LR: 7.950e-02	Score 87.371	Data time: 2.5149, Total iter time: 6.2727
thomas 04/07 08:15:47 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 08:15:47 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 08:17:54 101/312: Data time: 0.0025, Iter time: 0.6575	Loss 0.854 (AVG: 0.709)	Score 72.109 (AVG: 79.067)	mIOU 55.371 mAP 68.794 mAcc 69.049
IOU: 65.934 95.609 58.938 51.701 88.700 65.386 66.486 33.081 38.962 49.172 17.565 60.917 57.149 34.899 53.691 40.677 80.252 52.039 62.911 33.347
mAP: 72.314 97.564 54.540 52.038 91.512 84.710 75.079 57.754 41.034 74.017 36.554 61.220 62.003 74.794 72.392 72.138 93.910 81.895 71.079 49.333
mAcc: 74.575 98.307 64.181 77.388 93.440 94.920 74.304 75.309 45.692 76.413 20.276 77.008 72.073 84.635 60.430 49.380 80.963 53.298 63.259 45.127

thomas 04/07 08:20:00 201/312: Data time: 0.0031, Iter time: 0.7743	Loss 0.564 (AVG: 0.672)	Score 78.746 (AVG: 79.382)	mIOU 55.818 mAP 68.799 mAcc 68.974
IOU: 64.870 95.803 56.837 58.559 87.535 69.781 67.870 33.262 36.982 61.875 12.138 61.563 55.421 25.929 35.582 43.706 82.152 56.517 73.253 36.717
mAP: 73.605 97.814 53.979 65.226 91.088 85.212 74.988 56.551 42.967 73.227 30.497 60.446 61.750 69.287 52.610 76.339 94.941 84.447 78.117 52.894
mAcc: 72.439 98.222 61.598 82.884 92.193 95.871 76.571 72.269 42.773 88.289 14.298 74.849 68.747 79.607 38.908 51.911 82.783 57.754 74.098 53.411

thomas 04/07 08:21:58 301/312: Data time: 0.0041, Iter time: 0.9790	Loss 0.984 (AVG: 0.669)	Score 75.220 (AVG: 79.508)	mIOU 55.522 mAP 68.981 mAcc 68.541
IOU: 65.521 95.945 55.552 59.231 86.711 70.191 64.676 33.112 39.203 65.806 14.249 57.541 56.681 27.444 31.929 44.443 84.645 52.437 69.720 35.396
mAP: 75.086 97.724 55.123 67.288 89.739 82.372 73.109 58.129 44.068 71.845 33.376 59.120 62.875 69.807 54.100 75.356 94.878 83.294 80.396 51.937
mAcc: 72.646 98.313 61.950 82.617 91.126 95.227 73.606 72.559 45.348 91.044 17.063 69.235 72.703 79.799 34.530 50.040 85.582 53.560 70.470 53.402

thomas 04/07 08:22:16 312/312: Data time: 0.0034, Iter time: 0.3878	Loss 0.154 (AVG: 0.676)	Score 94.404 (AVG: 79.123)	mIOU 55.376 mAP 69.011 mAcc 68.526
IOU: 64.849 95.971 54.715 58.382 86.492 70.361 64.140 32.897 39.389 65.219 13.912 56.993 56.577 26.321 32.559 44.528 84.796 52.638 71.400 35.386
mAP: 74.522 97.758 55.284 67.715 89.761 83.007 72.690 57.892 43.614 72.456 33.774 58.401 62.852 70.414 53.982 73.859 95.089 83.332 81.428 52.392
mAcc: 72.005 98.291 60.988 82.758 91.014 95.490 73.012 72.243 45.525 91.092 16.645 68.857 73.013 80.481 35.194 49.957 85.714 53.750 72.158 52.331

thomas 04/07 08:22:16 Finished test. Elapsed time: 389.2360
thomas 04/07 08:22:16 Current best mIoU: 59.584 at iter 23000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 08:26:12 ===> Epoch[90](27040/301): Loss 0.3476	LR: 7.947e-02	Score 89.082	Data time: 2.2855, Total iter time: 5.8327
thomas 04/07 08:30:19 ===> Epoch[90](27080/301): Loss 0.3993	LR: 7.944e-02	Score 87.543	Data time: 2.3904, Total iter time: 6.1060
thomas 04/07 08:34:25 ===> Epoch[91](27120/301): Loss 0.3721	LR: 7.941e-02	Score 88.454	Data time: 2.3517, Total iter time: 6.0564
thomas 04/07 08:38:42 ===> Epoch[91](27160/301): Loss 0.3707	LR: 7.938e-02	Score 88.252	Data time: 2.5287, Total iter time: 6.3521
thomas 04/07 08:42:42 ===> Epoch[91](27200/301): Loss 0.3535	LR: 7.935e-02	Score 89.062	Data time: 2.4095, Total iter time: 5.9455
thomas 04/07 08:46:26 ===> Epoch[91](27240/301): Loss 0.3796	LR: 7.932e-02	Score 87.980	Data time: 2.1871, Total iter time: 5.5273
thomas 04/07 08:50:17 ===> Epoch[91](27280/301): Loss 0.3707	LR: 7.929e-02	Score 88.651	Data time: 2.2115, Total iter time: 5.6855
thomas 04/07 08:54:02 ===> Epoch[91](27320/301): Loss 0.3697	LR: 7.925e-02	Score 88.640	Data time: 2.1921, Total iter time: 5.5826
thomas 04/07 08:58:03 ===> Epoch[91](27360/301): Loss 0.3796	LR: 7.922e-02	Score 88.300	Data time: 2.3226, Total iter time: 5.9400
thomas 04/07 09:01:41 ===> Epoch[92](27400/301): Loss 0.3719	LR: 7.919e-02	Score 88.646	Data time: 2.1585, Total iter time: 5.3903
thomas 04/07 09:06:06 ===> Epoch[92](27440/301): Loss 0.3385	LR: 7.916e-02	Score 89.514	Data time: 2.5988, Total iter time: 6.5498
thomas 04/07 09:10:06 ===> Epoch[92](27480/301): Loss 0.3694	LR: 7.913e-02	Score 88.778	Data time: 2.3431, Total iter time: 5.9247
thomas 04/07 09:14:31 ===> Epoch[92](27520/301): Loss 0.3640	LR: 7.910e-02	Score 88.667	Data time: 2.5349, Total iter time: 6.5480
thomas 04/07 09:18:26 ===> Epoch[92](27560/301): Loss 0.3398	LR: 7.907e-02	Score 89.262	Data time: 2.2688, Total iter time: 5.8097
thomas 04/07 09:22:41 ===> Epoch[92](27600/301): Loss 0.3531	LR: 7.904e-02	Score 88.927	Data time: 2.4849, Total iter time: 6.3042
thomas 04/07 09:27:07 ===> Epoch[92](27640/301): Loss 0.3199	LR: 7.901e-02	Score 89.590	Data time: 2.6541, Total iter time: 6.5763
thomas 04/07 09:31:14 ===> Epoch[92](27680/301): Loss 0.3259	LR: 7.898e-02	Score 89.600	Data time: 2.4456, Total iter time: 6.0909
thomas 04/07 09:35:32 ===> Epoch[93](27720/301): Loss 0.3506	LR: 7.895e-02	Score 89.030	Data time: 2.4790, Total iter time: 6.3451
thomas 04/07 09:39:51 ===> Epoch[93](27760/301): Loss 0.3924	LR: 7.892e-02	Score 87.915	Data time: 2.4797, Total iter time: 6.4112
thomas 04/07 09:44:01 ===> Epoch[93](27800/301): Loss 0.3510	LR: 7.889e-02	Score 88.898	Data time: 2.4240, Total iter time: 6.1654
thomas 04/07 09:48:06 ===> Epoch[93](27840/301): Loss 0.3773	LR: 7.885e-02	Score 88.315	Data time: 2.3650, Total iter time: 6.0726
thomas 04/07 09:52:28 ===> Epoch[93](27880/301): Loss 0.3634	LR: 7.882e-02	Score 88.673	Data time: 2.6222, Total iter time: 6.4655
thomas 04/07 09:56:40 ===> Epoch[93](27920/301): Loss 0.4084	LR: 7.879e-02	Score 87.222	Data time: 2.4757, Total iter time: 6.2314
thomas 04/07 10:01:00 ===> Epoch[93](27960/301): Loss 0.3490	LR: 7.876e-02	Score 88.765	Data time: 2.5277, Total iter time: 6.4234
thomas 04/07 10:05:27 ===> Epoch[94](28000/301): Loss 0.3556	LR: 7.873e-02	Score 89.206	Data time: 2.5356, Total iter time: 6.6011
thomas 04/07 10:05:28 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 10:05:28 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 10:07:27 101/312: Data time: 0.0029, Iter time: 0.3105	Loss 0.240 (AVG: 0.548)	Score 92.048 (AVG: 83.180)	mIOU 60.769 mAP 72.802 mAcc 73.107
IOU: 73.755 96.686 51.608 77.277 86.851 85.940 67.308 42.774 43.961 58.081 8.563 56.372 53.249 60.866 57.176 39.278 93.000 53.222 73.092 36.326
mAP: 75.204 97.647 67.940 84.162 88.697 84.873 71.990 62.362 49.850 65.951 45.367 60.626 65.817 76.712 74.097 81.793 94.667 80.881 76.625 50.786
mAcc: 84.203 98.498 79.185 94.518 92.011 94.920 76.348 60.310 51.611 91.788 8.941 74.548 90.001 85.589 63.831 47.051 94.073 56.329 73.810 44.577

thomas 04/07 10:09:24 201/312: Data time: 0.0027, Iter time: 0.6599	Loss 0.390 (AVG: 0.552)	Score 86.137 (AVG: 83.505)	mIOU 59.411 mAP 72.191 mAcc 71.549
IOU: 74.990 96.064 51.499 69.945 87.485 75.715 65.394 43.682 45.237 60.775 8.213 58.847 51.564 63.992 47.741 44.294 84.587 49.502 74.448 34.243
mAP: 77.362 97.315 63.990 75.409 90.428 81.359 71.184 61.974 52.979 69.160 43.136 55.551 64.958 78.814 67.300 83.509 93.183 78.806 86.152 51.248
mAcc: 84.946 98.332 79.082 85.117 93.921 93.998 73.228 62.282 53.682 95.162 8.588 71.777 84.606 82.808 53.775 55.099 85.667 51.483 75.213 42.209

thomas 04/07 10:11:24 301/312: Data time: 0.0026, Iter time: 0.7414	Loss 0.915 (AVG: 0.555)	Score 75.676 (AVG: 83.527)	mIOU 59.100 mAP 71.376 mAcc 70.565
IOU: 75.630 96.004 51.985 67.198 87.303 75.310 64.775 43.739 46.584 62.198 9.793 58.879 51.151 63.722 42.697 40.977 83.182 49.981 76.568 34.323
mAP: 77.149 97.300 61.714 72.020 89.403 81.482 70.610 61.809 53.220 70.758 41.397 56.614 65.125 77.381 64.012 84.087 92.216 79.116 82.789 49.323
mAcc: 85.624 98.315 77.392 80.835 94.117 91.644 73.284 62.495 54.932 93.519 10.201 70.926 83.919 80.675 48.062 48.127 84.284 51.747 77.468 43.734

thomas 04/07 10:11:36 312/312: Data time: 0.0031, Iter time: 0.5222	Loss 0.509 (AVG: 0.553)	Score 82.630 (AVG: 83.608)	mIOU 59.080 mAP 71.327 mAcc 70.488
IOU: 75.638 95.996 51.849 67.141 87.264 75.184 64.811 43.775 45.416 63.295 9.133 59.311 51.346 63.664 42.697 40.977 83.182 49.981 76.568 34.382
mAP: 76.730 97.368 61.748 72.020 89.516 80.426 70.520 61.636 52.836 71.581 40.927 57.141 65.599 77.381 64.012 84.087 92.216 79.116 82.789 48.886
mAcc: 85.757 98.291 77.217 80.835 94.072 91.409 73.386 62.755 53.622 93.325 9.518 71.170 84.299 80.675 48.062 48.127 84.284 51.747 77.468 43.748

thomas 04/07 10:11:36 Finished test. Elapsed time: 367.7899
thomas 04/07 10:11:36 Current best mIoU: 59.584 at iter 23000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 10:15:36 ===> Epoch[94](28040/301): Loss 0.3302	LR: 7.870e-02	Score 89.289	Data time: 2.3584, Total iter time: 5.9362
thomas 04/07 10:19:31 ===> Epoch[94](28080/301): Loss 0.3475	LR: 7.867e-02	Score 89.078	Data time: 2.3165, Total iter time: 5.8059
thomas 04/07 10:23:33 ===> Epoch[94](28120/301): Loss 0.3535	LR: 7.864e-02	Score 88.740	Data time: 2.3458, Total iter time: 5.9824
thomas 04/07 10:27:16 ===> Epoch[94](28160/301): Loss 0.3604	LR: 7.861e-02	Score 88.987	Data time: 2.1316, Total iter time: 5.5081
thomas 04/07 10:30:54 ===> Epoch[94](28200/301): Loss 0.3791	LR: 7.858e-02	Score 88.609	Data time: 2.0862, Total iter time: 5.3721
thomas 04/07 10:34:52 ===> Epoch[94](28240/301): Loss 0.3619	LR: 7.855e-02	Score 89.144	Data time: 2.3203, Total iter time: 5.8751
thomas 04/07 10:38:48 ===> Epoch[94](28280/301): Loss 0.3772	LR: 7.852e-02	Score 88.000	Data time: 2.3116, Total iter time: 5.8294
thomas 04/07 10:42:57 ===> Epoch[95](28320/301): Loss 0.3751	LR: 7.848e-02	Score 88.263	Data time: 2.4781, Total iter time: 6.1532
thomas 04/07 10:47:18 ===> Epoch[95](28360/301): Loss 0.3600	LR: 7.845e-02	Score 88.752	Data time: 2.5375, Total iter time: 6.4329
thomas 04/07 10:51:11 ===> Epoch[95](28400/301): Loss 0.3450	LR: 7.842e-02	Score 89.190	Data time: 2.2520, Total iter time: 5.7571
thomas 04/07 10:55:12 ===> Epoch[95](28440/301): Loss 0.3371	LR: 7.839e-02	Score 89.573	Data time: 2.3255, Total iter time: 5.9637
thomas 04/07 10:59:28 ===> Epoch[95](28480/301): Loss 0.3893	LR: 7.836e-02	Score 88.381	Data time: 2.4999, Total iter time: 6.3110
thomas 04/07 11:03:17 ===> Epoch[95](28520/301): Loss 0.3448	LR: 7.833e-02	Score 89.231	Data time: 2.2712, Total iter time: 5.6647
thomas 04/07 11:07:38 ===> Epoch[95](28560/301): Loss 0.3463	LR: 7.830e-02	Score 89.290	Data time: 2.5621, Total iter time: 6.4370
thomas 04/07 11:12:01 ===> Epoch[96](28600/301): Loss 0.3705	LR: 7.827e-02	Score 88.276	Data time: 2.5575, Total iter time: 6.5109
thomas 04/07 11:16:09 ===> Epoch[96](28640/301): Loss 0.3252	LR: 7.824e-02	Score 89.618	Data time: 2.3915, Total iter time: 6.1223
thomas 04/07 11:20:13 ===> Epoch[96](28680/301): Loss 0.3709	LR: 7.821e-02	Score 88.762	Data time: 2.3186, Total iter time: 6.0307
thomas 04/07 11:24:00 ===> Epoch[96](28720/301): Loss 0.3744	LR: 7.818e-02	Score 88.213	Data time: 2.2130, Total iter time: 5.5957
thomas 04/07 11:27:56 ===> Epoch[96](28760/301): Loss 0.4019	LR: 7.815e-02	Score 87.789	Data time: 2.2967, Total iter time: 5.8119
thomas 04/07 11:31:44 ===> Epoch[96](28800/301): Loss 0.3624	LR: 7.811e-02	Score 88.930	Data time: 2.2000, Total iter time: 5.6182
thomas 04/07 11:35:54 ===> Epoch[96](28840/301): Loss 0.3398	LR: 7.808e-02	Score 89.113	Data time: 2.4081, Total iter time: 6.1729
thomas 04/07 11:39:51 ===> Epoch[96](28880/301): Loss 0.3111	LR: 7.805e-02	Score 90.118	Data time: 2.2785, Total iter time: 5.8445
thomas 04/07 11:43:49 ===> Epoch[97](28920/301): Loss 0.3434	LR: 7.802e-02	Score 89.135	Data time: 2.3168, Total iter time: 5.8580
thomas 04/07 11:47:35 ===> Epoch[97](28960/301): Loss 0.3813	LR: 7.799e-02	Score 88.145	Data time: 2.2339, Total iter time: 5.5915
thomas 04/07 11:51:30 ===> Epoch[97](29000/301): Loss 0.3692	LR: 7.796e-02	Score 88.204	Data time: 2.2709, Total iter time: 5.7862
thomas 04/07 11:51:31 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 11:51:31 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 11:53:37 101/312: Data time: 0.0032, Iter time: 0.7855	Loss 0.688 (AVG: 0.569)	Score 80.998 (AVG: 84.024)	mIOU 58.749 mAP 71.186 mAcc 69.867
IOU: 76.825 96.003 41.494 68.355 83.076 80.741 62.335 39.918 35.423 73.984 11.856 58.047 49.501 61.439 46.259 62.468 84.290 43.218 66.875 32.869
mAP: 78.560 98.349 48.034 75.266 86.091 89.931 64.229 58.420 50.824 67.638 31.159 58.380 58.533 74.776 78.527 94.281 94.881 70.176 93.777 51.883
mAcc: 90.491 99.015 71.883 84.056 87.097 88.529 78.922 55.006 39.281 79.286 12.771 75.831 80.825 82.880 71.162 68.042 84.743 43.494 67.011 37.010

thomas 04/07 11:55:30 201/312: Data time: 0.0026, Iter time: 0.6692	Loss 0.468 (AVG: 0.591)	Score 87.037 (AVG: 83.560)	mIOU 58.647 mAP 70.156 mAcc 68.986
IOU: 76.646 95.618 43.011 69.292 84.477 79.888 64.052 40.053 35.976 73.517 12.201 54.648 48.596 66.859 42.559 63.182 82.914 47.039 60.266 32.138
mAP: 78.765 98.083 50.061 71.174 87.481 83.299 66.311 56.093 48.586 72.129 32.617 59.132 60.300 78.841 70.092 92.760 91.517 77.290 82.579 46.019
mAcc: 91.147 98.922 71.585 79.931 89.162 87.440 79.318 56.150 38.491 78.787 13.767 72.923 79.184 78.890 68.559 67.048 83.389 47.629 60.675 36.730

thomas 04/07 11:57:36 301/312: Data time: 0.0026, Iter time: 0.6426	Loss 1.121 (AVG: 0.621)	Score 77.866 (AVG: 82.955)	mIOU 57.389 mAP 69.397 mAcc 67.676
IOU: 76.106 95.539 44.771 69.471 85.049 79.719 63.536 40.085 33.047 72.019 12.752 56.811 48.953 60.616 41.555 51.169 78.903 41.487 64.556 31.644
mAP: 78.709 97.752 51.858 72.616 87.990 83.177 67.198 55.507 46.787 70.841 36.273 57.955 60.878 75.194 62.340 89.021 90.184 77.914 80.591 45.159
mAcc: 90.168 98.947 75.243 78.665 89.769 86.707 79.881 55.302 36.278 79.155 14.797 71.690 79.502 74.032 63.825 55.615 80.349 41.968 65.007 36.615

thomas 04/07 11:57:48 312/312: Data time: 0.0023, Iter time: 0.3766	Loss 0.136 (AVG: 0.622)	Score 96.081 (AVG: 83.009)	mIOU 57.405 mAP 69.336 mAcc 67.646
IOU: 76.116 95.625 44.566 69.475 85.226 79.151 64.015 39.587 32.449 72.131 12.657 56.864 49.144 59.560 41.672 51.610 79.301 41.692 65.507 31.745
mAP: 78.638 97.779 51.134 72.828 87.779 83.086 67.768 54.967 46.520 71.277 35.895 57.404 60.984 73.729 63.017 89.426 90.330 77.872 81.131 45.149
mAcc: 90.228 98.959 74.844 78.860 90.010 85.956 80.336 54.594 35.567 78.968 14.766 71.828 79.268 72.483 64.465 56.051 80.734 42.197 65.954 36.846

thomas 04/07 11:57:48 Finished test. Elapsed time: 377.0770
thomas 04/07 11:57:48 Current best mIoU: 59.584 at iter 23000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 12:01:51 ===> Epoch[97](29040/301): Loss 0.3722	LR: 7.793e-02	Score 88.493	Data time: 2.3334, Total iter time: 5.9809
thomas 04/07 12:05:35 ===> Epoch[97](29080/301): Loss 0.3716	LR: 7.790e-02	Score 88.587	Data time: 2.1587, Total iter time: 5.5456
thomas 04/07 12:09:52 ===> Epoch[97](29120/301): Loss 0.3681	LR: 7.787e-02	Score 88.776	Data time: 2.5036, Total iter time: 6.3245
thomas 04/07 12:13:51 ===> Epoch[97](29160/301): Loss 0.3132	LR: 7.784e-02	Score 90.208	Data time: 2.3333, Total iter time: 5.9087
thomas 04/07 12:18:02 ===> Epoch[98](29200/301): Loss 0.3613	LR: 7.781e-02	Score 88.620	Data time: 2.4433, Total iter time: 6.1936
thomas 04/07 12:22:12 ===> Epoch[98](29240/301): Loss 0.4034	LR: 7.778e-02	Score 87.649	Data time: 2.4186, Total iter time: 6.1601
thomas 04/07 12:26:19 ===> Epoch[98](29280/301): Loss 0.3242	LR: 7.774e-02	Score 90.027	Data time: 2.4314, Total iter time: 6.1109
thomas 04/07 12:30:17 ===> Epoch[98](29320/301): Loss 0.3703	LR: 7.771e-02	Score 88.545	Data time: 2.2755, Total iter time: 5.8763
thomas 04/07 12:34:43 ===> Epoch[98](29360/301): Loss 0.3800	LR: 7.768e-02	Score 88.555	Data time: 2.5494, Total iter time: 6.5648
thomas 04/07 12:38:45 ===> Epoch[98](29400/301): Loss 0.3702	LR: 7.765e-02	Score 88.745	Data time: 2.3912, Total iter time: 5.9686
thomas 04/07 12:42:43 ===> Epoch[98](29440/301): Loss 0.3525	LR: 7.762e-02	Score 89.061	Data time: 2.3191, Total iter time: 5.8683
thomas 04/07 12:46:55 ===> Epoch[98](29480/301): Loss 0.3522	LR: 7.759e-02	Score 88.848	Data time: 2.4515, Total iter time: 6.2229
thomas 04/07 12:50:49 ===> Epoch[99](29520/301): Loss 0.3798	LR: 7.756e-02	Score 88.227	Data time: 2.2778, Total iter time: 5.7703
thomas 04/07 12:54:51 ===> Epoch[99](29560/301): Loss 0.3787	LR: 7.753e-02	Score 88.187	Data time: 2.3470, Total iter time: 5.9720
thomas 04/07 12:58:58 ===> Epoch[99](29600/301): Loss 0.3729	LR: 7.750e-02	Score 88.534	Data time: 2.3674, Total iter time: 6.1049
thomas 04/07 13:02:55 ===> Epoch[99](29640/301): Loss 0.3509	LR: 7.747e-02	Score 89.315	Data time: 2.2774, Total iter time: 5.8479
thomas 04/07 13:07:08 ===> Epoch[99](29680/301): Loss 0.3489	LR: 7.744e-02	Score 89.033	Data time: 2.4624, Total iter time: 6.2518
thomas 04/07 13:11:02 ===> Epoch[99](29720/301): Loss 0.3733	LR: 7.741e-02	Score 88.408	Data time: 2.2777, Total iter time: 5.7851
thomas 04/07 13:15:01 ===> Epoch[99](29760/301): Loss 0.3471	LR: 7.737e-02	Score 88.890	Data time: 2.3062, Total iter time: 5.8907
thomas 04/07 13:19:20 ===> Epoch[100](29800/301): Loss 0.3379	LR: 7.734e-02	Score 89.578	Data time: 2.4810, Total iter time: 6.3829
thomas 04/07 13:23:27 ===> Epoch[100](29840/301): Loss 0.3524	LR: 7.731e-02	Score 89.056	Data time: 2.3932, Total iter time: 6.0997
thomas 04/07 13:27:16 ===> Epoch[100](29880/301): Loss 0.3659	LR: 7.728e-02	Score 88.319	Data time: 2.2102, Total iter time: 5.6676
thomas 04/07 13:31:13 ===> Epoch[100](29920/301): Loss 0.3784	LR: 7.725e-02	Score 88.784	Data time: 2.3010, Total iter time: 5.8505
thomas 04/07 13:35:19 ===> Epoch[100](29960/301): Loss 0.3467	LR: 7.722e-02	Score 89.352	Data time: 2.4096, Total iter time: 6.0731
thomas 04/07 13:39:10 ===> Epoch[100](30000/301): Loss 0.4000	LR: 7.719e-02	Score 88.080	Data time: 2.2292, Total iter time: 5.6907
thomas 04/07 13:39:11 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 13:39:11 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 13:41:23 101/312: Data time: 0.0027, Iter time: 0.6742	Loss 0.621 (AVG: 0.570)	Score 78.667 (AVG: 84.405)	mIOU 58.030 mAP 69.773 mAcc 68.986
IOU: 77.758 96.668 54.174 62.205 86.375 69.474 64.820 45.091 28.035 65.025 9.809 65.736 48.608 43.674 43.777 39.408 80.477 56.264 82.488 40.741
mAP: 79.668 98.529 63.313 72.087 89.153 91.787 70.632 60.362 43.912 65.064 16.505 64.442 57.376 61.671 62.400 89.345 91.553 79.259 82.542 55.862
mAcc: 90.587 98.318 64.772 85.581 92.901 98.686 67.626 54.585 29.927 92.062 12.054 76.735 78.014 45.240 50.430 45.613 83.338 59.846 86.968 66.444

thomas 04/07 13:43:25 201/312: Data time: 0.0027, Iter time: 0.9139	Loss 0.482 (AVG: 0.589)	Score 85.330 (AVG: 83.575)	mIOU 57.743 mAP 70.098 mAcc 69.176
IOU: 76.823 96.443 54.714 63.977 85.145 62.154 63.428 41.358 34.517 59.864 8.840 64.677 53.889 49.903 43.670 36.757 84.769 52.454 79.391 42.094
mAP: 78.560 98.001 64.881 71.052 88.997 87.716 69.969 59.140 49.816 66.601 31.668 60.387 60.319 72.474 57.111 81.458 92.483 76.019 80.791 54.514
mAcc: 89.394 98.203 66.582 84.710 91.031 97.231 67.952 53.562 37.208 92.966 10.269 74.663 75.626 52.097 49.941 45.894 86.625 57.514 84.492 67.560

thomas 04/07 13:45:28 301/312: Data time: 0.0026, Iter time: 0.2896	Loss 0.256 (AVG: 0.611)	Score 92.268 (AVG: 83.006)	mIOU 57.765 mAP 69.765 mAcc 68.904
IOU: 76.491 96.079 51.227 63.179 85.600 63.628 63.444 40.123 34.911 59.244 10.720 59.911 56.046 52.694 40.757 40.506 85.710 52.700 82.364 39.972
mAP: 79.075 97.779 60.911 67.645 88.689 84.055 70.152 58.606 49.409 69.775 35.140 60.591 60.195 70.658 50.537 84.858 93.024 77.571 83.297 53.330
mAcc: 89.176 98.053 63.157 79.953 91.068 97.124 69.684 50.223 37.489 92.963 12.446 71.500 76.653 55.319 47.463 49.131 87.264 57.242 87.116 65.054

thomas 04/07 13:45:40 312/312: Data time: 0.0038, Iter time: 1.1417	Loss 0.320 (AVG: 0.605)	Score 91.594 (AVG: 83.192)	mIOU 57.936 mAP 69.936 mAcc 69.119
IOU: 76.702 96.144 50.916 64.119 85.844 63.175 64.153 39.860 34.696 58.927 11.099 59.911 55.667 55.344 40.053 40.506 86.099 53.360 82.364 39.785
mAP: 79.326 97.839 60.572 68.418 88.847 84.055 70.960 58.504 49.287 69.775 35.413 60.591 60.647 72.492 49.546 84.858 93.070 77.849 83.297 53.381
mAcc: 89.170 98.080 62.981 80.726 91.315 97.124 70.209 49.994 37.241 92.963 12.887 71.500 76.424 57.797 46.772 49.131 87.607 57.914 87.116 65.426

thomas 04/07 13:45:40 Finished test. Elapsed time: 389.1093
thomas 04/07 13:45:41 Current best mIoU: 59.584 at iter 23000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 13:49:50 ===> Epoch[100](30040/301): Loss 0.3280	LR: 7.716e-02	Score 89.493	Data time: 2.4624, Total iter time: 6.1588
thomas 04/07 13:53:46 ===> Epoch[100](30080/301): Loss 0.3421	LR: 7.713e-02	Score 88.986	Data time: 2.2917, Total iter time: 5.8183
thomas 04/07 13:57:57 ===> Epoch[101](30120/301): Loss 0.3633	LR: 7.710e-02	Score 88.891	Data time: 2.4947, Total iter time: 6.2216
thomas 04/07 14:01:49 ===> Epoch[101](30160/301): Loss 0.3381	LR: 7.707e-02	Score 89.754	Data time: 2.2493, Total iter time: 5.7160
thomas 04/07 14:05:58 ===> Epoch[101](30200/301): Loss 0.3390	LR: 7.703e-02	Score 89.307	Data time: 2.4279, Total iter time: 6.1555
thomas 04/07 14:10:07 ===> Epoch[101](30240/301): Loss 0.3101	LR: 7.700e-02	Score 90.346	Data time: 2.4311, Total iter time: 6.1451
thomas 04/07 14:13:59 ===> Epoch[101](30280/301): Loss 0.3750	LR: 7.697e-02	Score 88.460	Data time: 2.2444, Total iter time: 5.7424
thomas 04/07 14:18:03 ===> Epoch[101](30320/301): Loss 0.3710	LR: 7.694e-02	Score 88.246	Data time: 2.3452, Total iter time: 6.0058
thomas 04/07 14:22:12 ===> Epoch[101](30360/301): Loss 0.3293	LR: 7.691e-02	Score 89.630	Data time: 2.4227, Total iter time: 6.1228
thomas 04/07 14:26:16 ===> Epoch[101](30400/301): Loss 0.3239	LR: 7.688e-02	Score 89.680	Data time: 2.3740, Total iter time: 6.0337
thomas 04/07 14:30:26 ===> Epoch[102](30440/301): Loss 0.3625	LR: 7.685e-02	Score 88.627	Data time: 2.4425, Total iter time: 6.1825
thomas 04/07 14:34:30 ===> Epoch[102](30480/301): Loss 0.3522	LR: 7.682e-02	Score 88.881	Data time: 2.4182, Total iter time: 6.0494
thomas 04/07 14:38:22 ===> Epoch[102](30520/301): Loss 0.3224	LR: 7.679e-02	Score 89.976	Data time: 2.2507, Total iter time: 5.7234
thomas 04/07 14:42:32 ===> Epoch[102](30560/301): Loss 0.3550	LR: 7.676e-02	Score 89.127	Data time: 2.4565, Total iter time: 6.1786
thomas 04/07 14:46:19 ===> Epoch[102](30600/301): Loss 0.3266	LR: 7.673e-02	Score 89.670	Data time: 2.2184, Total iter time: 5.5846
thomas 04/07 14:50:27 ===> Epoch[102](30640/301): Loss 0.3616	LR: 7.669e-02	Score 88.482	Data time: 2.3994, Total iter time: 6.1159
thomas 04/07 14:54:44 ===> Epoch[102](30680/301): Loss 0.3367	LR: 7.666e-02	Score 89.528	Data time: 2.5028, Total iter time: 6.3606
thomas 04/07 14:58:56 ===> Epoch[103](30720/301): Loss 0.3399	LR: 7.663e-02	Score 89.485	Data time: 2.4415, Total iter time: 6.2057
thomas 04/07 15:03:08 ===> Epoch[103](30760/301): Loss 0.3581	LR: 7.660e-02	Score 88.671	Data time: 2.4009, Total iter time: 6.2160
thomas 04/07 15:07:10 ===> Epoch[103](30800/301): Loss 0.3296	LR: 7.657e-02	Score 89.523	Data time: 2.3873, Total iter time: 5.9909
thomas 04/07 15:10:58 ===> Epoch[103](30840/301): Loss 0.4059	LR: 7.654e-02	Score 87.324	Data time: 2.2566, Total iter time: 5.6177
thomas 04/07 15:14:48 ===> Epoch[103](30880/301): Loss 0.3677	LR: 7.651e-02	Score 88.739	Data time: 2.2529, Total iter time: 5.6705
thomas 04/07 15:18:46 ===> Epoch[103](30920/301): Loss 0.3733	LR: 7.648e-02	Score 88.446	Data time: 2.3113, Total iter time: 5.8787
thomas 04/07 15:23:03 ===> Epoch[103](30960/301): Loss 0.3475	LR: 7.645e-02	Score 89.072	Data time: 2.4863, Total iter time: 6.3516
thomas 04/07 15:26:55 ===> Epoch[103](31000/301): Loss 0.3403	LR: 7.642e-02	Score 89.202	Data time: 2.1909, Total iter time: 5.7200
thomas 04/07 15:26:57 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 15:26:57 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 15:29:02 101/312: Data time: 0.0028, Iter time: 0.3632	Loss 0.083 (AVG: 0.540)	Score 98.121 (AVG: 85.135)	mIOU 60.848 mAP 70.312 mAcc 69.993
IOU: 76.998 96.138 53.882 57.405 86.278 86.209 70.846 45.117 42.780 71.308 6.025 55.533 50.789 67.451 42.076 65.308 76.310 32.606 81.823 52.070
mAP: 77.641 97.282 64.118 58.899 88.035 82.150 68.943 62.725 50.246 59.887 45.786 65.148 69.231 75.119 58.497 82.384 89.062 74.571 81.565 54.948
mAcc: 88.895 98.651 64.070 72.754 90.042 94.957 77.880 71.885 50.256 93.116 6.196 61.068 69.855 76.393 54.931 67.390 76.856 33.207 82.666 68.788

thomas 04/07 15:31:08 201/312: Data time: 0.0028, Iter time: 0.6599	Loss 0.539 (AVG: 0.548)	Score 84.550 (AVG: 84.736)	mIOU 59.939 mAP 71.151 mAcc 69.316
IOU: 77.315 96.005 53.303 67.988 88.222 80.184 64.446 45.031 44.332 72.865 6.875 51.451 50.803 59.052 41.644 55.259 82.558 40.264 77.325 43.853
mAP: 77.312 97.658 63.786 71.021 89.298 82.629 69.387 62.747 47.938 66.948 43.407 59.712 67.622 73.179 66.118 82.920 93.545 75.096 77.062 55.637
mAcc: 89.478 98.538 63.119 83.197 92.792 94.330 70.690 70.829 50.935 91.171 7.086 56.272 72.426 68.194 50.506 62.175 83.170 41.051 78.373 61.993

thomas 04/07 15:33:11 301/312: Data time: 0.0039, Iter time: 0.3224	Loss 0.374 (AVG: 0.548)	Score 85.680 (AVG: 84.537)	mIOU 59.783 mAP 71.272 mAcc 69.440
IOU: 77.248 96.038 50.459 68.292 88.678 79.398 64.419 43.755 42.430 69.887 7.860 51.439 50.372 65.371 41.005 55.559 81.549 39.339 77.886 44.677
mAP: 78.252 97.604 59.325 73.358 89.624 82.613 68.770 62.591 48.918 70.216 41.349 58.561 67.366 76.816 61.049 85.440 91.910 75.913 81.891 53.885
mAcc: 88.943 98.477 61.736 84.643 93.089 93.632 72.186 68.599 49.664 91.323 8.077 55.818 70.307 75.524 51.465 62.666 82.141 40.014 78.724 61.780

thomas 04/07 15:33:23 312/312: Data time: 0.0022, Iter time: 0.5038	Loss 0.177 (AVG: 0.545)	Score 94.871 (AVG: 84.582)	mIOU 59.826 mAP 71.374 mAcc 69.673
IOU: 77.323 96.048 51.004 68.493 88.745 79.390 64.798 43.822 43.725 69.668 7.774 52.334 50.647 65.098 41.938 53.011 81.549 39.542 76.966 44.645
mAP: 78.288 97.552 59.221 74.033 89.621 82.613 69.220 62.766 50.099 70.230 40.909 58.868 67.423 76.915 60.612 85.440 91.910 75.978 81.891 53.901
mAcc: 88.793 98.488 62.381 85.387 93.165 93.632 72.434 68.882 51.131 91.344 7.987 56.737 69.857 75.105 52.549 62.666 82.141 40.261 78.724 61.787

thomas 04/07 15:33:23 Finished test. Elapsed time: 386.4798
thomas 04/07 15:33:25 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/07 15:33:25 Current best mIoU: 59.826 at iter 31000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 15:37:40 ===> Epoch[104](31040/301): Loss 0.3149	LR: 7.639e-02	Score 90.192	Data time: 2.5203, Total iter time: 6.3034
thomas 04/07 15:41:46 ===> Epoch[104](31080/301): Loss 0.3314	LR: 7.636e-02	Score 89.366	Data time: 2.3960, Total iter time: 6.0635
thomas 04/07 15:45:40 ===> Epoch[104](31120/301): Loss 0.3339	LR: 7.632e-02	Score 89.466	Data time: 2.2769, Total iter time: 5.7695
thomas 04/07 15:49:32 ===> Epoch[104](31160/301): Loss 0.3111	LR: 7.629e-02	Score 90.249	Data time: 2.2298, Total iter time: 5.7290
thomas 04/07 15:53:20 ===> Epoch[104](31200/301): Loss 0.3376	LR: 7.626e-02	Score 89.541	Data time: 2.2155, Total iter time: 5.6161
thomas 04/07 15:57:30 ===> Epoch[104](31240/301): Loss 0.4025	LR: 7.623e-02	Score 88.016	Data time: 2.4236, Total iter time: 6.1647
thomas 04/07 16:01:35 ===> Epoch[104](31280/301): Loss 0.3325	LR: 7.620e-02	Score 89.667	Data time: 2.3880, Total iter time: 6.0615
thomas 04/07 16:05:31 ===> Epoch[105](31320/301): Loss 0.3459	LR: 7.617e-02	Score 89.013	Data time: 2.3208, Total iter time: 5.8330
thomas 04/07 16:09:32 ===> Epoch[105](31360/301): Loss 0.3238	LR: 7.614e-02	Score 89.706	Data time: 2.3101, Total iter time: 5.9553
thomas 04/07 16:13:14 ===> Epoch[105](31400/301): Loss 0.3262	LR: 7.611e-02	Score 89.768	Data time: 2.1377, Total iter time: 5.4567
thomas 04/07 16:17:01 ===> Epoch[105](31440/301): Loss 0.3060	LR: 7.608e-02	Score 90.545	Data time: 2.2218, Total iter time: 5.6208
thomas 04/07 16:20:52 ===> Epoch[105](31480/301): Loss 0.3869	LR: 7.605e-02	Score 88.136	Data time: 2.2408, Total iter time: 5.6753
thomas 04/07 16:25:09 ===> Epoch[105](31520/301): Loss 0.3725	LR: 7.601e-02	Score 88.703	Data time: 2.5186, Total iter time: 6.3530
thomas 04/07 16:29:11 ===> Epoch[105](31560/301): Loss 0.3716	LR: 7.598e-02	Score 88.255	Data time: 2.3761, Total iter time: 5.9676
thomas 04/07 16:33:13 ===> Epoch[105](31600/301): Loss 0.3674	LR: 7.595e-02	Score 88.210	Data time: 2.3733, Total iter time: 5.9715
thomas 04/07 16:37:09 ===> Epoch[106](31640/301): Loss 0.3127	LR: 7.592e-02	Score 90.319	Data time: 2.2524, Total iter time: 5.8067
thomas 04/07 16:41:03 ===> Epoch[106](31680/301): Loss 0.3785	LR: 7.589e-02	Score 88.625	Data time: 2.2718, Total iter time: 5.7704
thomas 04/07 16:44:47 ===> Epoch[106](31720/301): Loss 0.3845	LR: 7.586e-02	Score 88.236	Data time: 2.1968, Total iter time: 5.5377
thomas 04/07 16:48:56 ===> Epoch[106](31760/301): Loss 0.3725	LR: 7.583e-02	Score 88.239	Data time: 2.4274, Total iter time: 6.1457
thomas 04/07 16:52:46 ===> Epoch[106](31800/301): Loss 0.3216	LR: 7.580e-02	Score 89.896	Data time: 2.2091, Total iter time: 5.6750
thomas 04/07 16:56:32 ===> Epoch[106](31840/301): Loss 0.3169	LR: 7.577e-02	Score 90.298	Data time: 2.2122, Total iter time: 5.5918
thomas 04/07 17:00:33 ===> Epoch[106](31880/301): Loss 0.3461	LR: 7.574e-02	Score 88.676	Data time: 2.2835, Total iter time: 5.9558
thomas 04/07 17:04:27 ===> Epoch[107](31920/301): Loss 0.3085	LR: 7.571e-02	Score 90.732	Data time: 2.2800, Total iter time: 5.7782
thomas 04/07 17:08:13 ===> Epoch[107](31960/301): Loss 0.3611	LR: 7.567e-02	Score 88.493	Data time: 2.2157, Total iter time: 5.5764
thomas 04/07 17:12:21 ===> Epoch[107](32000/301): Loss 0.3694	LR: 7.564e-02	Score 88.835	Data time: 2.4379, Total iter time: 6.1070
thomas 04/07 17:12:22 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 17:12:22 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 17:14:15 101/312: Data time: 0.0023, Iter time: 1.3420	Loss 0.961 (AVG: 0.627)	Score 68.336 (AVG: 83.095)	mIOU 58.986 mAP 70.083 mAcc 69.859
IOU: 76.047 95.438 54.863 66.672 84.820 83.853 66.132 39.463 27.165 63.262 14.826 57.614 47.998 65.076 42.252 52.695 82.239 58.299 68.211 32.786
mAP: 79.086 94.930 58.256 68.463 87.316 83.319 72.279 55.818 46.982 75.369 41.427 60.135 70.760 66.578 45.820 88.200 95.330 82.002 79.888 49.695
mAcc: 86.581 97.561 71.676 75.832 93.479 91.522 71.536 54.433 28.642 92.764 16.163 83.747 79.272 70.364 50.746 53.483 83.811 63.431 68.543 63.592

thomas 04/07 17:16:20 201/312: Data time: 0.0027, Iter time: 0.4372	Loss 0.281 (AVG: 0.595)	Score 92.005 (AVG: 83.506)	mIOU 60.793 mAP 71.343 mAcc 71.160
IOU: 75.592 95.899 57.137 69.159 85.519 84.420 65.505 43.247 31.598 67.353 12.853 61.072 51.691 63.184 48.397 48.100 84.711 56.241 76.298 37.882
mAP: 79.277 94.476 60.922 73.062 87.733 83.362 71.166 59.980 48.349 71.205 34.429 60.242 68.822 73.546 57.083 90.602 94.866 82.708 84.902 50.126
mAcc: 86.206 97.584 73.490 80.185 94.596 90.692 70.469 60.611 33.466 88.691 14.966 84.587 78.151 66.270 57.202 53.143 85.827 59.665 76.707 70.690

thomas 04/07 17:18:25 301/312: Data time: 0.0025, Iter time: 0.7498	Loss 0.772 (AVG: 0.604)	Score 79.697 (AVG: 83.397)	mIOU 60.303 mAP 71.120 mAcc 70.888
IOU: 75.645 95.854 56.631 70.006 85.476 80.088 67.284 42.960 28.568 68.621 11.723 56.965 55.471 59.094 46.034 51.567 85.533 54.045 79.015 35.475
mAP: 79.527 94.786 61.662 73.646 88.419 83.784 72.915 60.623 45.342 69.201 37.273 58.472 68.434 72.001 58.441 88.700 94.476 81.728 82.929 50.047
mAcc: 86.815 97.638 72.200 81.092 94.639 90.129 72.445 60.348 30.074 90.037 13.528 81.192 79.072 61.691 56.511 58.277 86.589 59.510 79.429 66.552

thomas 04/07 17:18:38 312/312: Data time: 0.0026, Iter time: 0.3479	Loss 0.839 (AVG: 0.604)	Score 75.897 (AVG: 83.373)	mIOU 60.227 mAP 71.037 mAcc 70.855
IOU: 75.577 95.848 56.465 69.216 85.656 79.616 67.602 43.056 28.816 68.333 11.115 56.494 55.924 59.715 45.986 51.549 85.533 54.038 79.014 34.979
mAP: 79.237 94.654 60.762 72.570 88.444 83.862 73.112 60.827 45.964 70.004 36.539 58.472 67.890 72.631 58.441 88.700 94.476 81.728 82.929 49.503
mAcc: 86.719 97.640 71.899 80.175 94.681 90.011 72.952 60.769 30.312 89.842 12.751 81.192 79.489 62.173 56.511 58.277 86.589 59.510 79.429 66.190

thomas 04/07 17:18:38 Finished test. Elapsed time: 376.1601
thomas 04/07 17:18:40 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/07 17:18:40 Current best mIoU: 60.227 at iter 32000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 17:22:29 ===> Epoch[107](32040/301): Loss 0.3115	LR: 7.561e-02	Score 90.009	Data time: 2.2221, Total iter time: 5.6606
thomas 04/07 17:26:22 ===> Epoch[107](32080/301): Loss 0.3475	LR: 7.558e-02	Score 89.345	Data time: 2.2180, Total iter time: 5.7644
thomas 04/07 17:30:25 ===> Epoch[107](32120/301): Loss 0.3172	LR: 7.555e-02	Score 89.998	Data time: 2.4070, Total iter time: 5.9980
thomas 04/07 17:34:35 ===> Epoch[107](32160/301): Loss 0.3330	LR: 7.552e-02	Score 89.212	Data time: 2.4408, Total iter time: 6.1678
thomas 04/07 17:38:27 ===> Epoch[107](32200/301): Loss 0.3861	LR: 7.549e-02	Score 87.762	Data time: 2.2660, Total iter time: 5.7400
thomas 04/07 17:42:25 ===> Epoch[108](32240/301): Loss 0.3162	LR: 7.546e-02	Score 89.928	Data time: 2.2932, Total iter time: 5.8667
thomas 04/07 17:46:25 ===> Epoch[108](32280/301): Loss 0.3373	LR: 7.543e-02	Score 89.489	Data time: 2.2970, Total iter time: 5.9216
thomas 04/07 17:50:36 ===> Epoch[108](32320/301): Loss 0.3725	LR: 7.540e-02	Score 88.119	Data time: 2.4109, Total iter time: 6.2059
thomas 04/07 17:54:38 ===> Epoch[108](32360/301): Loss 0.3592	LR: 7.537e-02	Score 88.871	Data time: 2.3530, Total iter time: 5.9729
thomas 04/07 17:58:48 ===> Epoch[108](32400/301): Loss 0.3691	LR: 7.533e-02	Score 88.611	Data time: 2.4308, Total iter time: 6.1650
thomas 04/07 18:02:58 ===> Epoch[108](32440/301): Loss 0.3310	LR: 7.530e-02	Score 89.831	Data time: 2.4404, Total iter time: 6.1686
thomas 04/07 18:07:15 ===> Epoch[108](32480/301): Loss 0.3296	LR: 7.527e-02	Score 89.390	Data time: 2.5197, Total iter time: 6.3253
thomas 04/07 18:11:00 ===> Epoch[109](32520/301): Loss 0.3637	LR: 7.524e-02	Score 88.434	Data time: 2.1618, Total iter time: 5.5656
thomas 04/07 18:15:07 ===> Epoch[109](32560/301): Loss 0.3315	LR: 7.521e-02	Score 89.295	Data time: 2.3845, Total iter time: 6.0918
thomas 04/07 18:19:33 ===> Epoch[109](32600/301): Loss 0.3348	LR: 7.518e-02	Score 89.591	Data time: 2.5642, Total iter time: 6.5545
thomas 04/07 18:23:45 ===> Epoch[109](32640/301): Loss 0.3885	LR: 7.515e-02	Score 88.484	Data time: 2.5024, Total iter time: 6.2298
thomas 04/07 18:27:46 ===> Epoch[109](32680/301): Loss 0.3292	LR: 7.512e-02	Score 89.918	Data time: 2.3545, Total iter time: 5.9658
thomas 04/07 18:31:54 ===> Epoch[109](32720/301): Loss 0.3275	LR: 7.509e-02	Score 89.676	Data time: 2.4045, Total iter time: 6.1184
thomas 04/07 18:35:50 ===> Epoch[109](32760/301): Loss 0.3238	LR: 7.506e-02	Score 89.471	Data time: 2.2452, Total iter time: 5.8394
thomas 04/07 18:39:44 ===> Epoch[109](32800/301): Loss 0.3748	LR: 7.502e-02	Score 88.571	Data time: 2.2355, Total iter time: 5.7727
thomas 04/07 18:43:56 ===> Epoch[110](32840/301): Loss 0.3291	LR: 7.499e-02	Score 89.745	Data time: 2.4522, Total iter time: 6.2162
thomas 04/07 18:48:29 ===> Epoch[110](32880/301): Loss 0.3404	LR: 7.496e-02	Score 89.372	Data time: 2.7086, Total iter time: 6.7422
thomas 04/07 18:52:38 ===> Epoch[110](32920/301): Loss 0.3205	LR: 7.493e-02	Score 90.040	Data time: 2.4205, Total iter time: 6.1461
thomas 04/07 18:56:43 ===> Epoch[110](32960/301): Loss 0.3225	LR: 7.490e-02	Score 89.487	Data time: 2.3518, Total iter time: 6.0505
thomas 04/07 19:00:47 ===> Epoch[110](33000/301): Loss 0.3177	LR: 7.487e-02	Score 90.127	Data time: 2.3571, Total iter time: 6.0231
thomas 04/07 19:00:48 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 19:00:48 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 19:02:55 101/312: Data time: 0.0023, Iter time: 0.6285	Loss 0.560 (AVG: 0.554)	Score 82.423 (AVG: 83.766)	mIOU 59.926 mAP 71.767 mAcc 71.662
IOU: 76.202 95.760 55.406 79.129 84.267 70.662 56.448 44.131 37.283 60.229 11.398 58.023 59.629 71.275 45.488 49.029 74.521 38.714 86.150 44.780
mAP: 76.966 97.108 57.203 79.151 87.206 84.495 64.539 56.655 53.638 80.949 36.449 63.126 70.823 82.372 56.685 81.904 83.028 70.122 94.991 57.938
mAcc: 86.768 98.753 79.890 89.687 94.524 93.932 59.322 59.597 41.469 85.714 14.805 73.377 77.584 87.201 56.242 67.098 76.318 40.162 86.683 64.112

thomas 04/07 19:04:57 201/312: Data time: 0.0026, Iter time: 0.6802	Loss 0.261 (AVG: 0.551)	Score 94.495 (AVG: 83.996)	mIOU 60.204 mAP 72.740 mAcc 71.498
IOU: 77.013 95.582 52.014 73.510 83.331 70.870 62.036 45.238 39.351 63.487 17.360 53.034 59.268 63.080 42.066 50.756 81.471 43.585 85.845 45.188
mAP: 78.287 97.278 58.014 76.115 87.605 82.094 70.461 61.825 52.533 72.563 46.503 64.538 68.210 76.857 60.933 87.503 88.980 76.541 90.378 57.579
mAcc: 87.398 98.798 80.732 84.025 92.679 95.496 65.562 61.092 45.151 72.129 21.592 67.046 76.794 82.423 58.361 61.244 83.168 45.863 87.748 62.654

thomas 04/07 19:07:07 301/312: Data time: 0.0032, Iter time: 1.0977	Loss 0.673 (AVG: 0.534)	Score 79.772 (AVG: 84.337)	mIOU 60.888 mAP 72.588 mAcc 72.178
IOU: 77.010 95.800 52.495 73.245 83.571 71.539 60.790 45.182 44.318 69.628 17.566 52.472 56.977 61.684 45.332 52.852 84.189 47.647 82.468 43.000
mAP: 77.660 97.268 58.679 76.262 88.228 82.515 71.910 62.549 52.348 72.559 42.232 64.671 67.970 76.709 62.492 88.656 91.023 79.622 82.324 56.084
mAcc: 87.100 98.855 78.868 84.755 93.246 95.888 64.427 60.363 50.745 77.262 24.072 65.468 76.842 80.737 60.633 61.509 86.277 49.914 84.053 62.543

thomas 04/07 19:07:23 312/312: Data time: 0.0027, Iter time: 0.3885	Loss 0.282 (AVG: 0.533)	Score 91.441 (AVG: 84.333)	mIOU 60.891 mAP 72.528 mAcc 72.264
IOU: 76.955 95.795 53.063 73.738 83.398 70.745 61.454 44.151 44.177 69.742 18.281 53.093 57.524 59.780 46.217 53.584 84.401 47.732 81.161 42.833
mAP: 77.593 97.244 58.677 76.312 88.425 82.656 71.398 62.631 52.076 73.155 42.504 63.247 67.499 75.828 62.963 88.980 91.337 79.819 82.828 55.379
mAcc: 86.986 98.856 78.568 85.156 93.052 95.957 65.093 58.757 50.962 77.373 25.121 66.098 76.969 80.498 61.638 62.383 86.423 50.014 82.647 62.721

thomas 04/07 19:07:23 Finished test. Elapsed time: 395.3904
thomas 04/07 19:07:25 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/07 19:07:25 Current best mIoU: 60.891 at iter 33000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 19:11:58 ===> Epoch[110](33040/301): Loss 0.3039	LR: 7.484e-02	Score 90.481	Data time: 2.6775, Total iter time: 6.7429
thomas 04/07 19:16:16 ===> Epoch[110](33080/301): Loss 0.2942	LR: 7.481e-02	Score 90.489	Data time: 2.5033, Total iter time: 6.3595
thomas 04/07 19:20:20 ===> Epoch[111](33120/301): Loss 0.3365	LR: 7.478e-02	Score 89.445	Data time: 2.3701, Total iter time: 6.0460
thomas 04/07 19:24:19 ===> Epoch[111](33160/301): Loss 0.3314	LR: 7.475e-02	Score 89.526	Data time: 2.2760, Total iter time: 5.8796
thomas 04/07 19:28:35 ===> Epoch[111](33200/301): Loss 0.3472	LR: 7.471e-02	Score 89.098	Data time: 2.4434, Total iter time: 6.3422
thomas 04/07 19:32:40 ===> Epoch[111](33240/301): Loss 0.3500	LR: 7.468e-02	Score 89.188	Data time: 2.4098, Total iter time: 6.0322
thomas 04/07 19:37:10 ===> Epoch[111](33280/301): Loss 0.3870	LR: 7.465e-02	Score 87.834	Data time: 2.6774, Total iter time: 6.6804
thomas 04/07 19:41:06 ===> Epoch[111](33320/301): Loss 0.3680	LR: 7.462e-02	Score 88.778	Data time: 2.2704, Total iter time: 5.8423
thomas 04/07 19:45:00 ===> Epoch[111](33360/301): Loss 0.3686	LR: 7.459e-02	Score 88.326	Data time: 2.2443, Total iter time: 5.7617
thomas 04/07 19:49:06 ===> Epoch[111](33400/301): Loss 0.3231	LR: 7.456e-02	Score 89.619	Data time: 2.3381, Total iter time: 6.0705
thomas 04/07 19:53:16 ===> Epoch[112](33440/301): Loss 0.3869	LR: 7.453e-02	Score 87.538	Data time: 2.4121, Total iter time: 6.1851
thomas 04/07 19:57:41 ===> Epoch[112](33480/301): Loss 0.3351	LR: 7.450e-02	Score 89.961	Data time: 2.6105, Total iter time: 6.5292
thomas 04/07 20:01:53 ===> Epoch[112](33520/301): Loss 0.3743	LR: 7.447e-02	Score 88.519	Data time: 2.5237, Total iter time: 6.2209
thomas 04/07 20:05:55 ===> Epoch[112](33560/301): Loss 0.3381	LR: 7.444e-02	Score 89.622	Data time: 2.3501, Total iter time: 5.9833
thomas 04/07 20:09:56 ===> Epoch[112](33600/301): Loss 0.3202	LR: 7.440e-02	Score 89.770	Data time: 2.3035, Total iter time: 5.9385
thomas 04/07 20:14:10 ===> Epoch[112](33640/301): Loss 0.3163	LR: 7.437e-02	Score 90.040	Data time: 2.4399, Total iter time: 6.2597
thomas 04/07 20:18:20 ===> Epoch[112](33680/301): Loss 0.3243	LR: 7.434e-02	Score 90.094	Data time: 2.4207, Total iter time: 6.1869
thomas 04/07 20:22:37 ===> Epoch[113](33720/301): Loss 0.3039	LR: 7.431e-02	Score 90.415	Data time: 2.5793, Total iter time: 6.3324
thomas 04/07 20:26:42 ===> Epoch[113](33760/301): Loss 0.3330	LR: 7.428e-02	Score 89.355	Data time: 2.4102, Total iter time: 6.0556
thomas 04/07 20:30:55 ===> Epoch[113](33800/301): Loss 0.3206	LR: 7.425e-02	Score 89.908	Data time: 2.4329, Total iter time: 6.2343
thomas 04/07 20:34:51 ===> Epoch[113](33840/301): Loss 0.3454	LR: 7.422e-02	Score 89.391	Data time: 2.2563, Total iter time: 5.8246
thomas 04/07 20:38:45 ===> Epoch[113](33880/301): Loss 0.3526	LR: 7.419e-02	Score 88.952	Data time: 2.2762, Total iter time: 5.7938
thomas 04/07 20:42:16 ===> Epoch[113](33920/301): Loss 0.3264	LR: 7.416e-02	Score 89.780	Data time: 2.0586, Total iter time: 5.1980
thomas 04/07 20:46:36 ===> Epoch[113](33960/301): Loss 0.3255	LR: 7.413e-02	Score 89.443	Data time: 2.5870, Total iter time: 6.4239
thomas 04/07 20:50:35 ===> Epoch[113](34000/301): Loss 0.3272	LR: 7.409e-02	Score 89.401	Data time: 2.3741, Total iter time: 5.8975
thomas 04/07 20:50:37 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 20:50:37 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 20:52:38 101/312: Data time: 0.0024, Iter time: 0.4983	Loss 0.610 (AVG: 0.595)	Score 79.701 (AVG: 83.682)	mIOU 58.491 mAP 70.189 mAcc 69.382
IOU: 77.546 95.873 56.001 72.438 84.336 71.570 62.154 44.840 40.994 62.844 18.778 46.955 52.456 46.367 52.979 26.997 90.924 51.022 77.431 37.307
mAP: 77.997 97.177 61.084 65.747 92.215 78.461 70.128 57.269 52.263 64.490 46.202 53.058 63.872 68.278 66.722 84.933 97.518 84.069 71.669 50.623
mAcc: 90.891 98.339 86.062 86.955 87.029 93.860 76.777 57.077 45.641 90.524 20.943 62.835 75.863 47.151 67.709 28.245 91.750 51.794 78.826 49.369

thomas 04/07 20:54:32 201/312: Data time: 0.0033, Iter time: 0.3065	Loss 0.478 (AVG: 0.569)	Score 85.360 (AVG: 84.193)	mIOU 58.722 mAP 71.195 mAcc 68.944
IOU: 77.310 95.913 50.462 73.157 86.370 74.631 66.319 42.274 44.720 64.296 13.809 50.125 54.771 44.490 51.006 28.591 86.582 49.056 80.376 40.191
mAP: 77.593 97.303 59.611 71.669 91.068 81.986 72.060 58.737 55.390 67.283 42.270 57.275 64.417 72.445 64.737 78.168 94.400 83.627 81.421 52.440
mAcc: 91.187 98.294 79.439 84.823 89.026 94.463 80.451 54.144 52.254 84.011 15.440 66.459 76.307 44.989 65.795 30.051 88.353 49.882 81.544 51.977

thomas 04/07 20:56:31 301/312: Data time: 0.0025, Iter time: 0.7376	Loss 0.466 (AVG: 0.552)	Score 85.181 (AVG: 84.753)	mIOU 59.419 mAP 71.235 mAcc 69.177
IOU: 77.339 96.190 54.102 72.069 86.877 75.763 67.541 44.567 45.307 68.764 12.692 57.884 55.192 44.442 52.183 25.270 86.714 45.689 79.289 40.497
mAP: 77.688 97.459 60.225 72.431 90.517 83.749 70.677 60.732 53.607 69.325 41.260 59.429 62.376 71.803 67.206 79.025 94.428 81.353 78.362 53.044
mAcc: 91.092 98.340 79.574 83.961 89.526 94.134 81.376 57.285 51.945 86.447 13.949 73.576 74.889 45.026 68.554 26.154 88.313 46.267 80.371 52.754

thomas 04/07 20:56:45 312/312: Data time: 0.0024, Iter time: 0.5337	Loss 0.409 (AVG: 0.554)	Score 84.421 (AVG: 84.628)	mIOU 59.453 mAP 71.107 mAcc 69.167
IOU: 77.019 96.172 53.493 72.451 86.731 76.569 67.446 44.631 44.867 70.332 13.035 57.796 55.403 44.442 50.225 26.726 87.325 45.876 78.185 40.332
mAP: 77.794 97.380 59.586 72.612 90.158 83.629 70.404 60.912 53.646 69.827 40.800 58.686 62.196 71.803 64.407 80.392 94.588 81.572 79.446 52.295
mAcc: 90.848 98.320 79.208 84.309 89.366 94.443 81.570 56.867 51.302 87.681 14.424 73.795 74.411 45.026 66.597 27.637 88.895 46.476 79.312 52.858

thomas 04/07 20:56:45 Finished test. Elapsed time: 368.0777
thomas 04/07 20:56:45 Current best mIoU: 60.891 at iter 33000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 21:00:40 ===> Epoch[114](34040/301): Loss 0.3370	LR: 7.406e-02	Score 89.277	Data time: 2.2461, Total iter time: 5.7990
thomas 04/07 21:04:23 ===> Epoch[114](34080/301): Loss 0.3201	LR: 7.403e-02	Score 90.134	Data time: 2.1546, Total iter time: 5.4960
thomas 04/07 21:08:31 ===> Epoch[114](34120/301): Loss 0.3585	LR: 7.400e-02	Score 88.887	Data time: 2.4024, Total iter time: 6.1182
thomas 04/07 21:12:30 ===> Epoch[114](34160/301): Loss 0.3454	LR: 7.397e-02	Score 89.457	Data time: 2.4093, Total iter time: 5.9130
thomas 04/07 21:16:42 ===> Epoch[114](34200/301): Loss 0.3232	LR: 7.394e-02	Score 89.893	Data time: 2.4368, Total iter time: 6.1997
thomas 04/07 21:20:34 ===> Epoch[114](34240/301): Loss 0.3173	LR: 7.391e-02	Score 90.309	Data time: 2.2531, Total iter time: 5.7494
thomas 04/07 21:24:53 ===> Epoch[114](34280/301): Loss 0.3158	LR: 7.388e-02	Score 89.910	Data time: 2.4983, Total iter time: 6.3946
thomas 04/07 21:28:43 ===> Epoch[115](34320/301): Loss 0.3121	LR: 7.385e-02	Score 90.043	Data time: 2.2303, Total iter time: 5.6783
thomas 04/07 21:32:50 ===> Epoch[115](34360/301): Loss 0.3243	LR: 7.382e-02	Score 89.669	Data time: 2.4215, Total iter time: 6.0857
thomas 04/07 21:36:46 ===> Epoch[115](34400/301): Loss 0.3608	LR: 7.378e-02	Score 88.721	Data time: 2.3806, Total iter time: 5.8365
thomas 04/07 21:40:30 ===> Epoch[115](34440/301): Loss 0.3020	LR: 7.375e-02	Score 90.447	Data time: 2.1687, Total iter time: 5.5336
thomas 04/07 21:44:19 ===> Epoch[115](34480/301): Loss 0.3370	LR: 7.372e-02	Score 89.527	Data time: 2.1812, Total iter time: 5.6569
thomas 04/07 21:48:20 ===> Epoch[115](34520/301): Loss 0.3289	LR: 7.369e-02	Score 89.739	Data time: 2.3104, Total iter time: 5.9481
thomas 04/07 21:52:06 ===> Epoch[115](34560/301): Loss 0.3558	LR: 7.366e-02	Score 88.861	Data time: 2.2071, Total iter time: 5.5741
thomas 04/07 21:56:05 ===> Epoch[115](34600/301): Loss 0.3172	LR: 7.363e-02	Score 90.037	Data time: 2.3505, Total iter time: 5.9063
thomas 04/07 22:00:18 ===> Epoch[116](34640/301): Loss 0.3263	LR: 7.360e-02	Score 89.573	Data time: 2.5492, Total iter time: 6.2455
thomas 04/07 22:04:08 ===> Epoch[116](34680/301): Loss 0.3285	LR: 7.357e-02	Score 90.113	Data time: 2.2435, Total iter time: 5.6524
thomas 04/07 22:08:07 ===> Epoch[116](34720/301): Loss 0.3494	LR: 7.354e-02	Score 88.968	Data time: 2.2860, Total iter time: 5.8929
thomas 04/07 22:12:02 ===> Epoch[116](34760/301): Loss 0.3261	LR: 7.351e-02	Score 89.803	Data time: 2.2908, Total iter time: 5.8030
thomas 04/07 22:16:02 ===> Epoch[116](34800/301): Loss 0.3346	LR: 7.347e-02	Score 89.590	Data time: 2.2871, Total iter time: 5.9070
thomas 04/07 22:20:04 ===> Epoch[116](34840/301): Loss 0.3366	LR: 7.344e-02	Score 89.655	Data time: 2.3943, Total iter time: 5.9563
thomas 04/07 22:24:16 ===> Epoch[116](34880/301): Loss 0.3286	LR: 7.341e-02	Score 89.612	Data time: 2.5194, Total iter time: 6.2299
thomas 04/07 22:28:22 ===> Epoch[117](34920/301): Loss 0.3261	LR: 7.338e-02	Score 89.547	Data time: 2.3674, Total iter time: 6.0585
thomas 04/07 22:32:14 ===> Epoch[117](34960/301): Loss 0.3195	LR: 7.335e-02	Score 89.855	Data time: 2.2196, Total iter time: 5.7338
thomas 04/07 22:36:10 ===> Epoch[117](35000/301): Loss 0.3923	LR: 7.332e-02	Score 88.479	Data time: 2.2662, Total iter time: 5.8406
thomas 04/07 22:36:12 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/07 22:36:12 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/07 22:38:04 101/312: Data time: 0.0027, Iter time: 0.2534	Loss 0.234 (AVG: 0.541)	Score 90.804 (AVG: 84.653)	mIOU 60.479 mAP 71.159 mAcc 71.222
IOU: 78.533 95.864 56.289 71.104 87.305 80.528 68.307 38.878 39.177 67.303 9.749 32.000 46.846 49.726 58.430 68.807 87.845 54.629 87.802 30.462
mAP: 78.696 96.947 56.035 67.193 88.260 78.575 75.318 57.296 55.838 79.622 34.661 51.636 59.872 69.556 70.205 92.993 93.883 79.976 89.636 46.978
mAcc: 90.611 97.730 80.899 81.909 92.349 90.592 78.631 54.333 51.891 88.360 11.272 33.892 91.859 54.649 65.851 85.751 90.413 56.171 92.030 35.243

thomas 04/07 22:40:05 201/312: Data time: 0.0028, Iter time: 0.9097	Loss 0.412 (AVG: 0.566)	Score 87.526 (AVG: 83.875)	mIOU 57.774 mAP 70.196 mAcc 68.088
IOU: 77.441 96.269 50.508 67.116 87.812 82.411 63.896 39.573 42.998 57.967 12.436 34.725 49.512 49.941 48.887 53.096 86.896 42.986 77.869 33.139
mAP: 76.965 97.510 53.780 72.228 88.530 82.609 72.927 58.023 57.759 72.710 33.223 53.144 63.287 69.541 63.199 87.814 95.235 76.659 79.975 48.797
mAcc: 90.246 98.070 76.935 84.577 93.857 89.349 76.180 54.251 54.196 85.657 15.009 37.327 87.728 54.536 53.650 58.175 89.769 43.861 81.059 37.334

thomas 04/07 22:42:00 301/312: Data time: 0.0031, Iter time: 0.3272	Loss 0.178 (AVG: 0.572)	Score 94.610 (AVG: 83.664)	mIOU 58.275 mAP 70.731 mAcc 68.545
IOU: 77.820 96.049 47.703 67.162 87.095 82.918 62.889 41.107 43.637 60.343 14.846 35.910 48.151 60.200 47.939 54.258 84.646 39.268 81.749 31.798
mAP: 76.712 97.125 55.607 74.136 88.772 83.287 69.038 59.905 55.529 70.809 40.671 54.825 63.571 74.771 62.811 89.790 91.302 76.469 80.749 48.739
mAcc: 90.230 97.978 77.340 82.192 93.003 90.516 74.306 56.125 54.318 83.274 18.067 38.849 88.555 64.621 54.631 59.346 87.877 40.025 84.280 35.376

thomas 04/07 22:42:15 312/312: Data time: 0.0030, Iter time: 0.8162	Loss 0.771 (AVG: 0.578)	Score 82.222 (AVG: 83.601)	mIOU 58.216 mAP 70.704 mAcc 68.363
IOU: 77.749 96.039 47.128 64.955 87.219 82.378 63.325 41.604 43.123 60.162 15.155 35.905 49.489 60.217 47.902 53.638 84.938 39.268 82.473 31.658
mAP: 76.766 97.111 55.697 72.299 88.499 83.014 69.189 60.509 56.438 71.507 40.808 54.825 62.336 74.375 62.811 89.790 91.470 76.469 81.366 48.802
mAcc: 90.354 97.965 77.218 80.900 93.045 90.282 74.745 56.586 52.946 80.774 18.372 38.849 88.283 64.463 54.631 59.346 88.153 40.025 84.974 35.351

thomas 04/07 22:42:15 Finished test. Elapsed time: 363.5837
thomas 04/07 22:42:16 Current best mIoU: 60.891 at iter 33000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/07 22:46:16 ===> Epoch[117](35040/301): Loss 0.3284	LR: 7.329e-02	Score 89.942	Data time: 2.3747, Total iter time: 5.9373
thomas 04/07 22:50:03 ===> Epoch[117](35080/301): Loss 0.3232	LR: 7.326e-02	Score 89.689	Data time: 2.2222, Total iter time: 5.5934
thomas 04/07 22:53:47 ===> Epoch[117](35120/301): Loss 0.3314	LR: 7.323e-02	Score 89.599	Data time: 2.1435, Total iter time: 5.5390
thomas 04/07 22:57:28 ===> Epoch[117](35160/301): Loss 0.3475	LR: 7.319e-02	Score 89.113	Data time: 2.1169, Total iter time: 5.4591
thomas 04/07 23:01:20 ===> Epoch[117](35200/301): Loss 0.3172	LR: 7.316e-02	Score 90.246	Data time: 2.1910, Total iter time: 5.7220
thomas 04/07 23:05:24 ===> Epoch[118](35240/301): Loss 0.3281	LR: 7.313e-02	Score 89.486	Data time: 2.3283, Total iter time: 6.0258
thomas 04/07 23:09:41 ===> Epoch[118](35280/301): Loss 0.3255	LR: 7.310e-02	Score 89.795	Data time: 2.5203, Total iter time: 6.3709
thomas 04/07 23:13:30 ===> Epoch[118](35320/301): Loss 0.3468	LR: 7.307e-02	Score 89.132	Data time: 2.2777, Total iter time: 5.6346
thomas 04/07 23:17:18 ===> Epoch[118](35360/301): Loss 0.3179	LR: 7.304e-02	Score 90.038	Data time: 2.1546, Total iter time: 5.6257
thomas 04/07 23:21:06 ===> Epoch[118](35400/301): Loss 0.3006	LR: 7.301e-02	Score 90.636	Data time: 2.1986, Total iter time: 5.6267
thomas 04/07 23:24:50 ===> Epoch[118](35440/301): Loss 0.3417	LR: 7.298e-02	Score 89.489	Data time: 2.1208, Total iter time: 5.5318
thomas 04/07 23:28:39 ===> Epoch[118](35480/301): Loss 0.3299	LR: 7.295e-02	Score 89.581	Data time: 2.1931, Total iter time: 5.6529
thomas 04/07 23:32:41 ===> Epoch[119](35520/301): Loss 0.3326	LR: 7.291e-02	Score 89.486	Data time: 2.4281, Total iter time: 5.9921
thomas 04/07 23:36:55 ===> Epoch[119](35560/301): Loss 0.3373	LR: 7.288e-02	Score 89.708	Data time: 2.4888, Total iter time: 6.2510
thomas 04/07 23:40:51 ===> Epoch[119](35600/301): Loss 0.3039	LR: 7.285e-02	Score 90.274	Data time: 2.2129, Total iter time: 5.8149
thomas 04/07 23:44:39 ===> Epoch[119](35640/301): Loss 0.3062	LR: 7.282e-02	Score 90.554	Data time: 2.1797, Total iter time: 5.6272
thomas 04/07 23:48:34 ===> Epoch[119](35680/301): Loss 0.3374	LR: 7.279e-02	Score 89.716	Data time: 2.2210, Total iter time: 5.7964
thomas 04/07 23:52:15 ===> Epoch[119](35720/301): Loss 0.3111	LR: 7.276e-02	Score 90.339	Data time: 2.1006, Total iter time: 5.4494
thomas 04/07 23:56:20 ===> Epoch[119](35760/301): Loss 0.3235	LR: 7.273e-02	Score 89.967	Data time: 2.4058, Total iter time: 6.0652
thomas 04/08 00:00:28 ===> Epoch[119](35800/301): Loss 0.3253	LR: 7.270e-02	Score 89.970	Data time: 2.4316, Total iter time: 6.1001
thomas 04/08 00:04:10 ===> Epoch[120](35840/301): Loss 0.3625	LR: 7.267e-02	Score 88.750	Data time: 2.1304, Total iter time: 5.4958
thomas 04/08 00:07:59 ===> Epoch[120](35880/301): Loss 0.3784	LR: 7.264e-02	Score 88.326	Data time: 2.1999, Total iter time: 5.6592
thomas 04/08 00:11:52 ===> Epoch[120](35920/301): Loss 0.3187	LR: 7.260e-02	Score 90.162	Data time: 2.2157, Total iter time: 5.7429
thomas 04/08 00:15:43 ===> Epoch[120](35960/301): Loss 0.3162	LR: 7.257e-02	Score 90.015	Data time: 2.2174, Total iter time: 5.7223
thomas 04/08 00:19:56 ===> Epoch[120](36000/301): Loss 0.3446	LR: 7.254e-02	Score 88.971	Data time: 2.4825, Total iter time: 6.2363
thomas 04/08 00:19:57 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 00:19:57 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 00:22:14 101/312: Data time: 0.0031, Iter time: 0.5536	Loss 1.097 (AVG: 0.613)	Score 71.817 (AVG: 82.687)	mIOU 53.495 mAP 69.355 mAcc 64.450
IOU: 75.583 96.179 38.330 54.300 87.520 70.280 64.394 37.507 39.134 60.416 6.412 46.377 54.382 60.751 40.025 6.590 80.192 19.961 85.072 46.504
mAP: 77.825 97.748 43.562 68.515 88.706 90.075 69.999 60.881 53.443 61.371 28.898 52.768 64.869 72.959 67.971 84.698 92.466 69.753 83.949 56.644
mAcc: 88.877 98.434 56.594 81.010 93.961 93.214 73.133 48.997 41.265 91.678 6.825 53.530 68.964 64.279 62.300 6.625 84.717 20.237 91.762 62.602

thomas 04/08 00:24:25 201/312: Data time: 0.0024, Iter time: 0.7454	Loss 0.348 (AVG: 0.621)	Score 89.118 (AVG: 83.095)	mIOU 54.997 mAP 69.068 mAcc 65.809
IOU: 76.986 95.652 45.004 56.647 86.391 75.455 65.638 39.999 31.770 57.339 3.742 53.182 56.196 57.115 44.509 14.603 81.491 30.751 81.767 45.694
mAP: 77.746 96.756 50.078 64.901 88.305 83.849 72.597 60.913 45.061 64.081 25.387 57.255 63.440 73.496 68.791 83.683 93.842 74.386 81.832 54.960
mAcc: 89.155 98.300 64.830 78.327 92.954 93.160 74.896 52.458 33.185 92.467 4.244 59.026 69.590 60.622 65.974 14.851 87.768 31.211 89.361 63.810

thomas 04/08 00:26:14 301/312: Data time: 0.0026, Iter time: 0.5192	Loss 0.994 (AVG: 0.625)	Score 81.712 (AVG: 83.115)	mIOU 55.656 mAP 69.313 mAcc 66.484
IOU: 77.189 95.726 46.974 61.366 86.134 74.884 65.532 40.133 28.977 54.713 5.760 54.972 52.993 60.154 45.365 13.324 85.238 37.545 82.967 43.162
mAP: 77.465 96.750 51.911 67.821 87.692 82.683 69.666 57.613 45.110 66.306 27.065 57.574 62.632 74.170 69.382 79.871 95.322 77.259 85.936 54.029
mAcc: 89.346 98.406 64.275 80.606 92.678 92.464 74.570 53.244 30.201 92.653 6.563 61.949 67.727 64.182 66.902 13.690 89.729 37.916 89.397 63.176

thomas 04/08 00:26:29 312/312: Data time: 0.0026, Iter time: 0.4747	Loss 0.672 (AVG: 0.621)	Score 82.817 (AVG: 83.175)	mIOU 55.750 mAP 69.283 mAcc 66.567
IOU: 77.170 95.762 46.002 62.989 86.164 75.082 65.813 40.129 28.959 54.470 6.615 54.657 53.052 62.264 44.880 12.367 84.490 36.645 82.366 45.118
mAP: 77.733 96.820 51.623 69.315 87.890 82.880 69.817 57.740 44.892 66.145 29.256 57.276 62.903 75.154 68.256 78.382 94.919 77.529 83.600 53.523
mAcc: 89.222 98.418 63.799 82.401 92.679 92.622 74.880 53.647 30.212 92.706 7.485 61.602 67.746 66.316 66.009 12.645 88.820 36.989 88.519 64.624

thomas 04/08 00:26:29 Finished test. Elapsed time: 391.8883
thomas 04/08 00:26:29 Current best mIoU: 60.891 at iter 33000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 00:30:28 ===> Epoch[120](36040/301): Loss 0.3481	LR: 7.251e-02	Score 89.219	Data time: 2.3078, Total iter time: 5.8968
thomas 04/08 00:34:29 ===> Epoch[120](36080/301): Loss 0.3164	LR: 7.248e-02	Score 89.965	Data time: 2.3083, Total iter time: 5.9319
thomas 04/08 00:38:21 ===> Epoch[120](36120/301): Loss 0.3473	LR: 7.245e-02	Score 89.360	Data time: 2.2269, Total iter time: 5.7277
thomas 04/08 00:42:06 ===> Epoch[121](36160/301): Loss 0.3341	LR: 7.242e-02	Score 89.463	Data time: 2.1579, Total iter time: 5.5566
thomas 04/08 00:46:04 ===> Epoch[121](36200/301): Loss 0.3314	LR: 7.239e-02	Score 89.957	Data time: 2.3621, Total iter time: 5.8655
thomas 04/08 00:50:08 ===> Epoch[121](36240/301): Loss 0.3141	LR: 7.236e-02	Score 89.955	Data time: 2.4107, Total iter time: 6.0359
thomas 04/08 00:53:57 ===> Epoch[121](36280/301): Loss 0.3117	LR: 7.232e-02	Score 90.208	Data time: 2.1790, Total iter time: 5.6360
thomas 04/08 00:57:47 ===> Epoch[121](36320/301): Loss 0.2978	LR: 7.229e-02	Score 90.608	Data time: 2.2096, Total iter time: 5.6824
thomas 04/08 01:01:34 ===> Epoch[121](36360/301): Loss 0.3157	LR: 7.226e-02	Score 89.699	Data time: 2.1641, Total iter time: 5.6015
thomas 04/08 01:05:34 ===> Epoch[121](36400/301): Loss 0.3379	LR: 7.223e-02	Score 89.527	Data time: 2.3189, Total iter time: 5.9242
thomas 04/08 01:09:51 ===> Epoch[122](36440/301): Loss 0.3398	LR: 7.220e-02	Score 89.189	Data time: 2.5463, Total iter time: 6.3360
thomas 04/08 01:13:52 ===> Epoch[122](36480/301): Loss 0.3009	LR: 7.217e-02	Score 90.596	Data time: 2.3527, Total iter time: 5.9464
thomas 04/08 01:17:44 ===> Epoch[122](36520/301): Loss 0.3353	LR: 7.214e-02	Score 89.483	Data time: 2.2436, Total iter time: 5.7312
thomas 04/08 01:21:22 ===> Epoch[122](36560/301): Loss 0.3212	LR: 7.211e-02	Score 90.020	Data time: 2.1105, Total iter time: 5.3766
thomas 04/08 01:25:28 ===> Epoch[122](36600/301): Loss 0.3273	LR: 7.208e-02	Score 89.856	Data time: 2.3342, Total iter time: 6.0526
thomas 04/08 01:29:44 ===> Epoch[122](36640/301): Loss 0.3245	LR: 7.204e-02	Score 90.065	Data time: 2.4880, Total iter time: 6.3430
thomas 04/08 01:33:51 ===> Epoch[122](36680/301): Loss 0.3285	LR: 7.201e-02	Score 89.821	Data time: 2.4279, Total iter time: 6.1039
thomas 04/08 01:37:58 ===> Epoch[122](36720/301): Loss 0.2999	LR: 7.198e-02	Score 90.450	Data time: 2.4303, Total iter time: 6.0833
thomas 04/08 01:42:09 ===> Epoch[123](36760/301): Loss 0.3204	LR: 7.195e-02	Score 90.077	Data time: 2.4218, Total iter time: 6.1906
thomas 04/08 01:45:47 ===> Epoch[123](36800/301): Loss 0.3317	LR: 7.192e-02	Score 89.609	Data time: 2.1056, Total iter time: 5.3827
thomas 04/08 01:49:38 ===> Epoch[123](36840/301): Loss 0.3614	LR: 7.189e-02	Score 88.680	Data time: 2.2346, Total iter time: 5.7042
thomas 04/08 01:53:27 ===> Epoch[123](36880/301): Loss 0.3074	LR: 7.186e-02	Score 90.530	Data time: 2.2435, Total iter time: 5.6623
thomas 04/08 01:57:41 ===> Epoch[123](36920/301): Loss 0.3031	LR: 7.183e-02	Score 90.529	Data time: 2.4926, Total iter time: 6.2696
thomas 04/08 02:01:43 ===> Epoch[123](36960/301): Loss 0.3386	LR: 7.180e-02	Score 89.239	Data time: 2.3641, Total iter time: 5.9700
thomas 04/08 02:05:34 ===> Epoch[123](37000/301): Loss 0.3717	LR: 7.176e-02	Score 88.734	Data time: 2.2115, Total iter time: 5.6993
thomas 04/08 02:05:35 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 02:05:36 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 02:07:26 101/312: Data time: 0.0026, Iter time: 0.8462	Loss 1.044 (AVG: 0.658)	Score 70.422 (AVG: 81.928)	mIOU 55.643 mAP 69.655 mAcc 68.696
IOU: 77.016 95.471 48.466 74.474 82.284 72.707 47.509 34.521 34.862 77.121 7.512 46.780 42.012 40.019 36.011 44.327 80.270 49.816 82.671 39.019
mAP: 75.356 97.623 50.305 83.364 89.177 75.444 65.149 61.255 52.504 66.553 23.679 51.169 69.812 72.763 64.812 79.940 94.107 80.911 87.661 51.507
mAcc: 86.724 98.433 61.249 93.093 91.438 78.455 49.348 63.906 37.671 93.078 7.903 57.447 86.995 40.762 81.192 56.598 84.838 52.100 87.746 64.946

thomas 04/08 02:09:24 201/312: Data time: 0.0024, Iter time: 0.7781	Loss 0.567 (AVG: 0.641)	Score 82.556 (AVG: 82.629)	mIOU 56.499 mAP 69.954 mAcc 68.033
IOU: 77.113 95.906 49.717 66.637 83.804 74.025 49.523 39.503 39.199 74.848 4.941 51.423 44.164 42.410 41.808 41.037 82.176 55.868 75.156 40.718
mAP: 74.791 97.697 50.821 78.371 88.814 74.507 67.452 61.488 51.769 68.225 25.644 57.634 67.640 73.007 64.729 79.529 93.975 82.697 88.679 51.611
mAcc: 87.685 98.535 63.231 86.619 91.662 79.542 51.917 69.079 41.542 91.756 5.110 62.081 86.792 43.628 63.767 52.112 86.991 58.235 78.552 61.822

thomas 04/08 02:11:30 301/312: Data time: 0.0025, Iter time: 0.3534	Loss 0.153 (AVG: 0.658)	Score 97.448 (AVG: 82.565)	mIOU 55.861 mAP 69.084 mAcc 67.346
IOU: 76.754 96.057 50.523 63.545 83.799 73.082 53.159 40.562 35.853 71.899 6.644 57.388 42.373 45.033 35.385 38.211 81.195 54.844 70.725 40.193
mAP: 74.837 97.260 52.364 71.080 87.819 77.486 68.750 60.321 48.650 65.898 30.942 58.596 66.989 74.334 55.399 81.387 94.876 82.978 80.635 51.070
mAcc: 87.939 98.649 63.254 81.198 91.370 78.089 55.571 69.153 37.942 88.145 6.917 68.963 87.194 46.363 58.537 45.192 87.828 57.344 74.166 63.110

thomas 04/08 02:11:41 312/312: Data time: 0.0024, Iter time: 0.4161	Loss 0.796 (AVG: 0.655)	Score 75.710 (AVG: 82.637)	mIOU 56.131 mAP 68.986 mAcc 67.496
IOU: 76.755 96.075 50.964 64.028 84.121 73.407 53.694 40.750 35.527 71.143 6.266 57.390 43.603 45.796 36.955 38.823 80.683 55.192 71.471 39.983
mAP: 74.784 97.264 52.566 71.721 88.119 76.551 68.888 60.707 48.661 63.652 29.602 58.521 67.413 74.140 56.770 80.812 94.285 83.072 81.187 51.007
mAcc: 87.852 98.641 63.893 81.598 91.510 78.335 56.094 69.586 37.597 87.262 6.508 68.293 87.860 47.363 59.079 45.692 87.001 57.654 74.834 63.264

thomas 04/08 02:11:41 Finished test. Elapsed time: 365.8801
thomas 04/08 02:11:41 Current best mIoU: 60.891 at iter 33000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 02:15:40 ===> Epoch[124](37040/301): Loss 0.3369	LR: 7.173e-02	Score 89.651	Data time: 2.2795, Total iter time: 5.8782
thomas 04/08 02:19:49 ===> Epoch[124](37080/301): Loss 0.2963	LR: 7.170e-02	Score 90.811	Data time: 2.4698, Total iter time: 6.1439
thomas 04/08 02:23:55 ===> Epoch[124](37120/301): Loss 0.3205	LR: 7.167e-02	Score 89.791	Data time: 2.4088, Total iter time: 6.0704
thomas 04/08 02:27:57 ===> Epoch[124](37160/301): Loss 0.3056	LR: 7.164e-02	Score 90.141	Data time: 2.3472, Total iter time: 5.9761
thomas 04/08 02:31:45 ===> Epoch[124](37200/301): Loss 0.3402	LR: 7.161e-02	Score 89.324	Data time: 2.2222, Total iter time: 5.6416
thomas 04/08 02:35:32 ===> Epoch[124](37240/301): Loss 0.3212	LR: 7.158e-02	Score 89.581	Data time: 2.1678, Total iter time: 5.5940
thomas 04/08 02:39:25 ===> Epoch[124](37280/301): Loss 0.3080	LR: 7.155e-02	Score 90.523	Data time: 2.2975, Total iter time: 5.7483
thomas 04/08 02:43:29 ===> Epoch[124](37320/301): Loss 0.3131	LR: 7.152e-02	Score 89.959	Data time: 2.3597, Total iter time: 6.0192
thomas 04/08 02:47:28 ===> Epoch[125](37360/301): Loss 0.3361	LR: 7.148e-02	Score 89.430	Data time: 2.3373, Total iter time: 5.8960
thomas 04/08 02:51:31 ===> Epoch[125](37400/301): Loss 0.3630	LR: 7.145e-02	Score 88.938	Data time: 2.3798, Total iter time: 6.0008
thomas 04/08 02:55:24 ===> Epoch[125](37440/301): Loss 0.3508	LR: 7.142e-02	Score 89.184	Data time: 2.2208, Total iter time: 5.7461
thomas 04/08 02:59:21 ===> Epoch[125](37480/301): Loss 0.3045	LR: 7.139e-02	Score 90.267	Data time: 2.2846, Total iter time: 5.8362
thomas 04/08 03:03:28 ===> Epoch[125](37520/301): Loss 0.3238	LR: 7.136e-02	Score 89.745	Data time: 2.4306, Total iter time: 6.1147
thomas 04/08 03:07:29 ===> Epoch[125](37560/301): Loss 0.3051	LR: 7.133e-02	Score 90.411	Data time: 2.3878, Total iter time: 5.9405
thomas 04/08 03:11:35 ===> Epoch[125](37600/301): Loss 0.2873	LR: 7.130e-02	Score 91.049	Data time: 2.4120, Total iter time: 6.0703
thomas 04/08 03:15:41 ===> Epoch[126](37640/301): Loss 0.3114	LR: 7.127e-02	Score 90.214	Data time: 2.3956, Total iter time: 6.0731
thomas 04/08 03:19:34 ===> Epoch[126](37680/301): Loss 0.3090	LR: 7.123e-02	Score 90.473	Data time: 2.2588, Total iter time: 5.7586
thomas 04/08 03:23:28 ===> Epoch[126](37720/301): Loss 0.3501	LR: 7.120e-02	Score 88.753	Data time: 2.2644, Total iter time: 5.7720
thomas 04/08 03:27:19 ===> Epoch[126](37760/301): Loss 0.2982	LR: 7.117e-02	Score 90.689	Data time: 2.2511, Total iter time: 5.6814
thomas 04/08 03:31:15 ===> Epoch[126](37800/301): Loss 0.3179	LR: 7.114e-02	Score 89.947	Data time: 2.3376, Total iter time: 5.8393
thomas 04/08 03:35:15 ===> Epoch[126](37840/301): Loss 0.3201	LR: 7.111e-02	Score 89.968	Data time: 2.3184, Total iter time: 5.9044
thomas 04/08 03:39:03 ===> Epoch[126](37880/301): Loss 0.3170	LR: 7.108e-02	Score 90.184	Data time: 2.2572, Total iter time: 5.6294
thomas 04/08 03:43:17 ===> Epoch[126](37920/301): Loss 0.2854	LR: 7.105e-02	Score 90.895	Data time: 2.4500, Total iter time: 6.2744
thomas 04/08 03:47:11 ===> Epoch[127](37960/301): Loss 0.3067	LR: 7.102e-02	Score 90.319	Data time: 2.2821, Total iter time: 5.7765
thomas 04/08 03:51:15 ===> Epoch[127](38000/301): Loss 0.2911	LR: 7.099e-02	Score 90.927	Data time: 2.4109, Total iter time: 6.0293
thomas 04/08 03:51:16 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 03:51:17 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 03:53:17 101/312: Data time: 0.1612, Iter time: 0.4697	Loss 0.535 (AVG: 0.545)	Score 86.317 (AVG: 84.997)	mIOU 61.276 mAP 71.851 mAcc 70.574
IOU: 76.953 95.405 53.254 67.598 86.214 83.775 57.223 41.780 42.042 69.971 6.987 58.135 45.718 74.605 54.115 54.607 75.887 40.251 85.720 55.271
mAP: 79.945 96.812 51.235 76.658 90.205 88.377 71.823 55.887 55.318 62.548 30.591 60.982 68.358 84.642 75.927 77.428 87.698 81.008 87.941 53.642
mAcc: 94.433 98.273 72.834 81.632 89.819 95.442 59.359 50.723 43.900 78.067 7.314 66.875 84.037 81.418 71.328 60.951 76.196 40.710 93.551 64.616

thomas 04/08 03:55:28 201/312: Data time: 0.1975, Iter time: 0.7190	Loss 0.260 (AVG: 0.557)	Score 91.149 (AVG: 84.855)	mIOU 61.329 mAP 71.154 mAcc 70.821
IOU: 77.609 95.752 53.938 69.054 87.255 81.639 61.241 41.982 38.561 71.360 9.811 58.774 50.094 71.065 41.147 54.933 84.034 47.916 82.516 47.901
mAP: 79.764 96.421 54.535 72.032 90.387 87.548 71.103 57.590 52.344 65.300 32.857 63.800 65.408 81.591 61.796 82.686 92.903 82.093 80.138 52.789
mAcc: 94.110 98.423 72.497 78.742 91.679 96.376 64.507 51.204 42.519 82.758 10.403 71.922 86.115 78.710 52.653 64.153 84.527 48.730 89.454 56.943

thomas 04/08 03:57:38 301/312: Data time: 0.0029, Iter time: 0.5761	Loss 0.530 (AVG: 0.549)	Score 87.097 (AVG: 85.132)	mIOU 61.611 mAP 70.922 mAcc 70.937
IOU: 77.489 96.025 56.598 69.724 86.919 80.543 63.404 41.053 40.491 72.440 10.149 58.431 51.757 70.155 40.999 57.437 84.727 46.608 81.144 46.129
mAP: 79.293 96.585 57.675 72.509 90.285 85.628 72.307 58.661 52.013 65.117 30.542 61.392 64.310 79.875 56.223 84.908 93.658 80.508 84.127 52.833
mAcc: 93.945 98.513 75.708 79.780 91.619 94.382 66.799 49.903 44.971 81.625 10.816 73.721 86.714 76.913 49.072 68.114 86.374 47.335 86.325 56.120

thomas 04/08 03:57:50 312/312: Data time: 0.0031, Iter time: 0.3095	Loss 0.014 (AVG: 0.544)	Score 99.946 (AVG: 85.276)	mIOU 61.872 mAP 70.985 mAcc 71.064
IOU: 77.465 96.057 56.954 70.005 87.176 80.541 64.253 41.277 39.712 73.633 10.329 58.607 53.385 70.424 41.761 58.121 84.903 46.776 80.282 45.777
mAP: 79.287 96.652 57.779 72.944 90.227 85.505 73.010 58.861 52.142 66.596 31.241 60.664 64.247 80.095 57.105 85.020 93.747 80.604 81.659 52.308
mAcc: 94.027 98.514 75.588 80.150 91.827 94.448 67.609 50.097 43.975 82.445 10.998 74.070 87.261 77.216 50.071 67.568 86.551 47.501 85.584 55.777

thomas 04/08 03:57:50 Finished test. Elapsed time: 393.6701
thomas 04/08 03:57:52 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/08 03:57:52 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 04:01:49 ===> Epoch[127](38040/301): Loss 0.3138	LR: 7.095e-02	Score 90.011	Data time: 2.3626, Total iter time: 5.8582
thomas 04/08 04:05:36 ===> Epoch[127](38080/301): Loss 0.3574	LR: 7.092e-02	Score 88.949	Data time: 2.2264, Total iter time: 5.5959
thomas 04/08 04:09:37 ===> Epoch[127](38120/301): Loss 0.3554	LR: 7.089e-02	Score 89.205	Data time: 2.3120, Total iter time: 5.9293
thomas 04/08 04:13:36 ===> Epoch[127](38160/301): Loss 0.3118	LR: 7.086e-02	Score 90.359	Data time: 2.3347, Total iter time: 5.8958
thomas 04/08 04:17:32 ===> Epoch[127](38200/301): Loss 0.2879	LR: 7.083e-02	Score 90.945	Data time: 2.2960, Total iter time: 5.8258
thomas 04/08 04:21:31 ===> Epoch[128](38240/301): Loss 0.3393	LR: 7.080e-02	Score 89.761	Data time: 2.3351, Total iter time: 5.8970
thomas 04/08 04:25:37 ===> Epoch[128](38280/301): Loss 0.3252	LR: 7.077e-02	Score 89.599	Data time: 2.4206, Total iter time: 6.0852
thomas 04/08 04:29:36 ===> Epoch[128](38320/301): Loss 0.3249	LR: 7.074e-02	Score 89.701	Data time: 2.3323, Total iter time: 5.9037
thomas 04/08 04:33:36 ===> Epoch[128](38360/301): Loss 0.3406	LR: 7.071e-02	Score 89.395	Data time: 2.2961, Total iter time: 5.9173
thomas 04/08 04:37:25 ===> Epoch[128](38400/301): Loss 0.3085	LR: 7.067e-02	Score 90.231	Data time: 2.2042, Total iter time: 5.6693
thomas 04/08 04:41:38 ===> Epoch[128](38440/301): Loss 0.3235	LR: 7.064e-02	Score 90.294	Data time: 2.4756, Total iter time: 6.2378
thomas 04/08 04:45:57 ===> Epoch[128](38480/301): Loss 0.3487	LR: 7.061e-02	Score 89.403	Data time: 2.4903, Total iter time: 6.3908
thomas 04/08 04:50:00 ===> Epoch[128](38520/301): Loss 0.2987	LR: 7.058e-02	Score 90.527	Data time: 2.3836, Total iter time: 6.0205
thomas 04/08 04:53:56 ===> Epoch[129](38560/301): Loss 0.3237	LR: 7.055e-02	Score 89.877	Data time: 2.2787, Total iter time: 5.8251
thomas 04/08 04:57:52 ===> Epoch[129](38600/301): Loss 0.3127	LR: 7.052e-02	Score 90.104	Data time: 2.2688, Total iter time: 5.8067
thomas 04/08 05:01:53 ===> Epoch[129](38640/301): Loss 0.3491	LR: 7.049e-02	Score 88.766	Data time: 2.3466, Total iter time: 5.9647
thomas 04/08 05:05:36 ===> Epoch[129](38680/301): Loss 0.3128	LR: 7.046e-02	Score 90.121	Data time: 2.1581, Total iter time: 5.4858
thomas 04/08 05:09:22 ===> Epoch[129](38720/301): Loss 0.3194	LR: 7.042e-02	Score 90.130	Data time: 2.1927, Total iter time: 5.5893
thomas 04/08 05:13:23 ===> Epoch[129](38760/301): Loss 0.3011	LR: 7.039e-02	Score 90.512	Data time: 2.3712, Total iter time: 5.9521
thomas 04/08 05:17:27 ===> Epoch[129](38800/301): Loss 0.2994	LR: 7.036e-02	Score 90.521	Data time: 2.3458, Total iter time: 6.0035
thomas 04/08 05:21:19 ===> Epoch[130](38840/301): Loss 0.3431	LR: 7.033e-02	Score 89.283	Data time: 2.2654, Total iter time: 5.7401
thomas 04/08 05:25:18 ===> Epoch[130](38880/301): Loss 0.3096	LR: 7.030e-02	Score 90.372	Data time: 2.3103, Total iter time: 5.8881
thomas 04/08 05:29:30 ===> Epoch[130](38920/301): Loss 0.3221	LR: 7.027e-02	Score 89.854	Data time: 2.4370, Total iter time: 6.2206
thomas 04/08 05:33:33 ===> Epoch[130](38960/301): Loss 0.3408	LR: 7.024e-02	Score 89.779	Data time: 2.3584, Total iter time: 6.0018
thomas 04/08 05:37:45 ===> Epoch[130](39000/301): Loss 0.2794	LR: 7.021e-02	Score 91.369	Data time: 2.4400, Total iter time: 6.2300
thomas 04/08 05:37:47 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 05:37:47 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 05:39:53 101/312: Data time: 0.0031, Iter time: 0.3286	Loss 0.012 (AVG: 0.550)	Score 99.837 (AVG: 84.594)	mIOU 57.419 mAP 69.737 mAcc 68.589
IOU: 76.082 95.941 59.648 65.748 86.488 63.404 70.519 39.529 40.988 59.511 24.180 51.635 63.759 55.781 47.726 27.574 58.019 46.373 72.448 43.035
mAP: 76.388 97.899 61.145 69.545 88.981 80.645 72.175 55.054 49.168 62.124 49.420 63.726 64.642 69.956 56.479 78.987 92.895 81.377 73.402 50.726
mAcc: 88.550 99.094 74.999 77.628 93.121 92.405 82.898 60.637 43.673 86.465 29.750 89.319 80.457 66.204 50.869 27.699 58.154 48.005 72.621 49.238

thomas 04/08 05:41:56 201/312: Data time: 0.0027, Iter time: 0.8615	Loss 0.141 (AVG: 0.558)	Score 96.079 (AVG: 84.378)	mIOU 57.028 mAP 70.485 mAcc 68.425
IOU: 76.637 95.805 56.394 68.578 85.113 68.751 68.779 41.966 38.641 60.553 22.707 49.912 58.032 63.875 45.281 16.981 68.007 49.282 62.455 42.800
mAP: 76.712 97.492 60.616 72.815 88.765 82.910 72.258 58.655 48.407 64.599 45.033 60.474 66.352 74.516 62.556 77.969 93.802 81.205 72.820 51.753
mAcc: 88.470 98.958 73.001 80.674 91.783 95.360 79.556 65.365 40.797 89.212 29.628 81.725 82.528 74.314 49.404 17.617 68.230 50.934 62.599 48.338

thomas 04/08 05:44:01 301/312: Data time: 0.0031, Iter time: 0.8324	Loss 0.307 (AVG: 0.575)	Score 92.698 (AVG: 84.028)	mIOU 56.779 mAP 70.292 mAcc 67.879
IOU: 76.774 95.819 54.357 63.647 85.346 67.781 69.418 41.757 36.939 63.038 18.497 50.879 55.604 66.534 47.506 20.058 66.731 48.165 66.820 39.919
mAP: 77.319 97.476 56.325 65.478 88.620 84.822 73.827 57.985 48.063 66.481 44.663 61.530 65.223 76.480 60.159 78.025 93.446 80.032 78.595 51.287
mAcc: 89.044 98.976 71.385 73.397 92.406 95.129 80.095 63.804 39.123 87.542 22.924 83.553 82.612 76.897 51.631 20.677 66.930 49.611 67.004 44.841

thomas 04/08 05:44:12 312/312: Data time: 0.0033, Iter time: 0.6473	Loss 0.528 (AVG: 0.572)	Score 84.170 (AVG: 84.057)	mIOU 57.022 mAP 70.400 mAcc 68.142
IOU: 76.848 95.822 54.565 63.943 85.488 68.007 69.291 41.795 36.779 63.272 18.450 50.841 55.315 66.358 46.778 21.967 68.206 48.004 68.645 40.067
mAP: 77.541 97.365 56.716 66.417 88.805 83.119 73.237 58.342 47.685 67.036 44.930 60.028 65.307 76.966 58.915 79.307 93.798 80.144 80.763 51.577
mAcc: 88.968 98.977 71.604 73.917 92.485 95.150 79.730 63.931 39.111 87.645 22.832 83.428 82.988 76.665 50.777 22.896 68.404 49.513 68.870 44.940

thomas 04/08 05:44:12 Finished test. Elapsed time: 384.8406
thomas 04/08 05:44:12 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 05:47:54 ===> Epoch[130](39040/301): Loss 0.3396	LR: 7.017e-02	Score 89.161	Data time: 2.1959, Total iter time: 5.4897
thomas 04/08 05:51:59 ===> Epoch[130](39080/301): Loss 0.3090	LR: 7.014e-02	Score 90.364	Data time: 2.3883, Total iter time: 6.0355
thomas 04/08 05:55:44 ===> Epoch[130](39120/301): Loss 0.3143	LR: 7.011e-02	Score 89.820	Data time: 2.1421, Total iter time: 5.5529
thomas 04/08 05:59:43 ===> Epoch[131](39160/301): Loss 0.3186	LR: 7.008e-02	Score 89.862	Data time: 2.3251, Total iter time: 5.8901
thomas 04/08 06:03:57 ===> Epoch[131](39200/301): Loss 0.3454	LR: 7.005e-02	Score 89.297	Data time: 2.5069, Total iter time: 6.2749
thomas 04/08 06:07:47 ===> Epoch[131](39240/301): Loss 0.3351	LR: 7.002e-02	Score 89.180	Data time: 2.2707, Total iter time: 5.6816
thomas 04/08 06:11:59 ===> Epoch[131](39280/301): Loss 0.3189	LR: 6.999e-02	Score 90.156	Data time: 2.4746, Total iter time: 6.2098
thomas 04/08 06:16:14 ===> Epoch[131](39320/301): Loss 0.2757	LR: 6.996e-02	Score 91.399	Data time: 2.4578, Total iter time: 6.2897
thomas 04/08 06:19:47 ===> Epoch[131](39360/301): Loss 0.3325	LR: 6.993e-02	Score 89.377	Data time: 2.0747, Total iter time: 5.2663
thomas 04/08 06:23:59 ===> Epoch[131](39400/301): Loss 0.2974	LR: 6.989e-02	Score 90.647	Data time: 2.4923, Total iter time: 6.1988
thomas 04/08 06:28:19 ===> Epoch[132](39440/301): Loss 0.2989	LR: 6.986e-02	Score 90.795	Data time: 2.5350, Total iter time: 6.4279
thomas 04/08 06:32:38 ===> Epoch[132](39480/301): Loss 0.3097	LR: 6.983e-02	Score 89.918	Data time: 2.5623, Total iter time: 6.3980
thomas 04/08 06:36:48 ===> Epoch[132](39520/301): Loss 0.3086	LR: 6.980e-02	Score 90.237	Data time: 2.4193, Total iter time: 6.1638
thomas 04/08 06:40:36 ===> Epoch[132](39560/301): Loss 0.3068	LR: 6.977e-02	Score 90.299	Data time: 2.2193, Total iter time: 5.6415
thomas 04/08 06:44:28 ===> Epoch[132](39600/301): Loss 0.3083	LR: 6.974e-02	Score 90.385	Data time: 2.2504, Total iter time: 5.7236
thomas 04/08 06:48:08 ===> Epoch[132](39640/301): Loss 0.3169	LR: 6.971e-02	Score 89.668	Data time: 2.1742, Total iter time: 5.4249
thomas 04/08 06:52:01 ===> Epoch[132](39680/301): Loss 0.3056	LR: 6.968e-02	Score 90.215	Data time: 2.3024, Total iter time: 5.7599
thomas 04/08 06:56:02 ===> Epoch[132](39720/301): Loss 0.3218	LR: 6.964e-02	Score 89.846	Data time: 2.3664, Total iter time: 5.9416
thomas 04/08 07:00:02 ===> Epoch[133](39760/301): Loss 0.2840	LR: 6.961e-02	Score 91.011	Data time: 2.3557, Total iter time: 5.9318
thomas 04/08 07:04:02 ===> Epoch[133](39800/301): Loss 0.3116	LR: 6.958e-02	Score 90.114	Data time: 2.3053, Total iter time: 5.9112
thomas 04/08 07:08:11 ===> Epoch[133](39840/301): Loss 0.3390	LR: 6.955e-02	Score 89.693	Data time: 2.4315, Total iter time: 6.1562
thomas 04/08 07:12:14 ===> Epoch[133](39880/301): Loss 0.3177	LR: 6.952e-02	Score 90.089	Data time: 2.4000, Total iter time: 5.9860
thomas 04/08 07:16:26 ===> Epoch[133](39920/301): Loss 0.3206	LR: 6.949e-02	Score 89.775	Data time: 2.4836, Total iter time: 6.2262
thomas 04/08 07:20:19 ===> Epoch[133](39960/301): Loss 0.3241	LR: 6.946e-02	Score 89.680	Data time: 2.2562, Total iter time: 5.7312
thomas 04/08 07:24:21 ===> Epoch[133](40000/301): Loss 0.3041	LR: 6.943e-02	Score 90.756	Data time: 2.3683, Total iter time: 5.9728
thomas 04/08 07:24:22 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 07:24:22 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 07:26:28 101/312: Data time: 0.0025, Iter time: 1.1377	Loss 1.126 (AVG: 0.613)	Score 69.673 (AVG: 83.064)	mIOU 57.283 mAP 69.434 mAcc 68.524
IOU: 74.666 95.722 56.302 69.690 88.900 74.974 69.656 40.559 21.365 72.837 16.547 56.365 56.809 42.888 27.807 45.532 73.953 51.783 77.255 32.056
mAP: 76.854 96.036 61.988 73.812 89.173 78.861 67.867 55.981 52.447 65.219 43.310 57.673 61.097 66.648 48.793 87.516 93.214 84.140 77.809 50.232
mAcc: 86.216 98.058 73.229 83.742 95.405 87.639 81.703 68.534 21.691 93.399 23.542 66.478 79.927 45.632 57.574 50.607 74.618 52.882 78.644 50.960

thomas 04/08 07:28:27 201/312: Data time: 0.0040, Iter time: 0.5267	Loss 0.298 (AVG: 0.618)	Score 92.243 (AVG: 82.886)	mIOU 56.926 mAP 70.153 mAcc 68.378
IOU: 74.057 95.882 54.097 59.330 87.727 79.453 68.718 41.812 21.298 68.847 18.425 52.827 52.919 54.761 39.359 36.950 77.794 45.526 69.794 38.935
mAP: 77.396 96.528 61.602 67.597 88.189 81.564 69.742 61.793 49.300 67.245 44.187 53.275 62.039 76.307 58.408 81.498 94.794 77.753 79.504 54.333
mAcc: 85.546 98.199 74.206 79.863 93.571 90.664 76.967 71.407 21.626 90.347 24.028 59.807 83.683 56.943 65.272 43.005 78.564 46.506 72.052 55.314

thomas 04/08 07:30:24 301/312: Data time: 0.0027, Iter time: 0.5208	Loss 0.257 (AVG: 0.614)	Score 93.616 (AVG: 83.071)	mIOU 57.208 mAP 70.603 mAcc 68.935
IOU: 74.706 96.030 55.764 60.594 86.922 77.039 67.738 43.087 21.720 71.020 17.597 53.349 52.639 51.238 38.924 36.964 80.968 47.004 71.051 39.803
mAP: 78.385 96.636 61.152 71.588 89.118 81.625 70.192 61.743 48.681 65.926 41.852 52.946 61.375 75.050 63.506 82.663 95.406 79.694 79.712 54.809
mAcc: 85.506 98.384 73.552 82.670 92.697 91.176 76.917 73.577 22.234 91.906 23.042 58.479 80.436 53.107 67.120 47.222 81.769 48.254 74.593 56.058

thomas 04/08 07:30:35 312/312: Data time: 0.0030, Iter time: 0.3571	Loss 0.793 (AVG: 0.615)	Score 73.160 (AVG: 83.051)	mIOU 57.339 mAP 70.798 mAcc 69.146
IOU: 74.782 95.996 56.143 60.754 86.916 76.329 67.647 43.072 21.245 71.107 17.391 53.888 52.931 53.277 39.952 36.996 79.984 46.868 71.568 39.923
mAP: 78.472 96.689 60.403 72.213 89.271 80.881 69.982 62.360 48.835 67.038 41.496 53.394 61.246 76.097 64.257 83.279 95.502 79.589 80.220 54.741
mAcc: 85.574 98.375 73.403 83.431 92.725 90.358 76.682 73.735 21.727 91.884 22.968 59.124 80.704 55.193 68.792 47.658 80.754 48.114 75.313 56.401

thomas 04/08 07:30:35 Finished test. Elapsed time: 372.5435
thomas 04/08 07:30:35 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 07:34:32 ===> Epoch[134](40040/301): Loss 0.3510	LR: 6.939e-02	Score 89.543	Data time: 2.3584, Total iter time: 5.8459
thomas 04/08 07:38:44 ===> Epoch[134](40080/301): Loss 0.3448	LR: 6.936e-02	Score 89.060	Data time: 2.4513, Total iter time: 6.2179
thomas 04/08 07:42:43 ===> Epoch[134](40120/301): Loss 0.3203	LR: 6.933e-02	Score 90.165	Data time: 2.3554, Total iter time: 5.9027
thomas 04/08 07:46:38 ===> Epoch[134](40160/301): Loss 0.3090	LR: 6.930e-02	Score 90.377	Data time: 2.3175, Total iter time: 5.8081
thomas 04/08 07:50:28 ===> Epoch[134](40200/301): Loss 0.3185	LR: 6.927e-02	Score 90.085	Data time: 2.2429, Total iter time: 5.6851
thomas 04/08 07:54:20 ===> Epoch[134](40240/301): Loss 0.3106	LR: 6.924e-02	Score 89.833	Data time: 2.2315, Total iter time: 5.7153
thomas 04/08 07:58:30 ===> Epoch[134](40280/301): Loss 0.2959	LR: 6.921e-02	Score 90.708	Data time: 2.4274, Total iter time: 6.1738
thomas 04/08 08:02:17 ===> Epoch[134](40320/301): Loss 0.2969	LR: 6.918e-02	Score 90.812	Data time: 2.2353, Total iter time: 5.6111
thomas 04/08 08:06:13 ===> Epoch[135](40360/301): Loss 0.2897	LR: 6.914e-02	Score 90.954	Data time: 2.3137, Total iter time: 5.8067
thomas 04/08 08:10:18 ===> Epoch[135](40400/301): Loss 0.2999	LR: 6.911e-02	Score 90.672	Data time: 2.3979, Total iter time: 6.0503
thomas 04/08 08:14:01 ===> Epoch[135](40440/301): Loss 0.3031	LR: 6.908e-02	Score 90.412	Data time: 2.1541, Total iter time: 5.4861
thomas 04/08 08:18:11 ===> Epoch[135](40480/301): Loss 0.3299	LR: 6.905e-02	Score 89.346	Data time: 2.4067, Total iter time: 6.1691
thomas 04/08 08:22:01 ===> Epoch[135](40520/301): Loss 0.2925	LR: 6.902e-02	Score 90.827	Data time: 2.2389, Total iter time: 5.6663
thomas 04/08 08:25:56 ===> Epoch[135](40560/301): Loss 0.2990	LR: 6.899e-02	Score 90.576	Data time: 2.3175, Total iter time: 5.8126
thomas 04/08 08:30:10 ===> Epoch[135](40600/301): Loss 0.2942	LR: 6.896e-02	Score 90.695	Data time: 2.5145, Total iter time: 6.2677
thomas 04/08 08:33:59 ===> Epoch[136](40640/301): Loss 0.2882	LR: 6.893e-02	Score 90.821	Data time: 2.2189, Total iter time: 5.6430
thomas 04/08 08:37:41 ===> Epoch[136](40680/301): Loss 0.2938	LR: 6.889e-02	Score 90.783	Data time: 2.1668, Total iter time: 5.4919
thomas 04/08 08:41:38 ===> Epoch[136](40720/301): Loss 0.2781	LR: 6.886e-02	Score 91.300	Data time: 2.2847, Total iter time: 5.8494
thomas 04/08 08:45:17 ===> Epoch[136](40760/301): Loss 0.3311	LR: 6.883e-02	Score 89.644	Data time: 2.1465, Total iter time: 5.4049
thomas 04/08 08:49:26 ===> Epoch[136](40800/301): Loss 0.2830	LR: 6.880e-02	Score 91.401	Data time: 2.4376, Total iter time: 6.1439
thomas 04/08 08:53:49 ===> Epoch[136](40840/301): Loss 0.3118	LR: 6.877e-02	Score 90.116	Data time: 2.5774, Total iter time: 6.5034
thomas 04/08 08:58:01 ===> Epoch[136](40880/301): Loss 0.2991	LR: 6.874e-02	Score 90.308	Data time: 2.4616, Total iter time: 6.2146
thomas 04/08 09:01:44 ===> Epoch[136](40920/301): Loss 0.3148	LR: 6.871e-02	Score 90.084	Data time: 2.1609, Total iter time: 5.5165
thomas 04/08 09:05:52 ===> Epoch[137](40960/301): Loss 0.3248	LR: 6.868e-02	Score 89.874	Data time: 2.4152, Total iter time: 6.1182
thomas 04/08 09:09:55 ===> Epoch[137](41000/301): Loss 0.3199	LR: 6.864e-02	Score 90.089	Data time: 2.3605, Total iter time: 5.9979
thomas 04/08 09:09:56 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 09:09:56 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 09:12:19 101/312: Data time: 0.2274, Iter time: 0.8869	Loss 0.212 (AVG: 0.599)	Score 91.469 (AVG: 83.114)	mIOU 58.466 mAP 69.081 mAcc 70.235
IOU: 76.675 95.833 42.971 53.303 88.186 75.255 66.197 50.429 42.552 41.458 17.084 49.102 60.012 59.202 47.046 44.100 81.020 60.334 83.653 34.918
mAP: 78.838 96.472 49.210 70.787 89.923 83.264 64.128 65.771 42.294 73.110 31.378 57.565 63.584 73.558 60.179 75.424 85.117 81.711 94.320 44.996
mAcc: 86.765 98.603 52.152 85.348 93.204 87.826 77.983 80.607 49.494 45.091 24.923 86.716 76.080 60.255 56.822 51.002 82.575 65.900 90.865 52.497

thomas 04/08 09:14:22 201/312: Data time: 0.0027, Iter time: 0.3639	Loss 0.420 (AVG: 0.631)	Score 84.186 (AVG: 82.482)	mIOU 57.132 mAP 69.219 mAcc 69.215
IOU: 75.306 95.687 40.362 49.823 87.829 75.051 64.290 47.387 35.375 53.166 14.335 45.416 57.986 59.275 46.104 32.822 82.532 61.893 79.156 38.855
mAP: 78.088 96.724 47.660 69.558 88.766 80.526 65.676 67.628 42.926 69.031 39.650 64.072 62.915 70.593 63.997 75.709 88.122 84.824 79.896 48.006
mAcc: 86.371 98.618 50.934 84.958 92.285 87.222 74.142 80.414 40.400 55.900 19.115 89.970 78.039 60.579 59.274 34.428 84.409 66.443 83.142 57.662

thomas 04/08 09:16:35 301/312: Data time: 0.0024, Iter time: 0.5826	Loss 1.594 (AVG: 0.634)	Score 63.969 (AVG: 82.520)	mIOU 57.760 mAP 70.600 mAcc 69.708
IOU: 75.203 95.762 43.929 51.345 87.777 77.089 64.059 46.275 38.895 50.094 15.949 49.628 59.859 56.564 46.887 33.377 86.013 59.591 77.997 38.904
mAP: 78.188 96.936 50.736 75.178 89.175 81.732 68.379 66.384 45.826 65.662 39.906 65.762 65.708 71.494 67.496 75.495 91.417 82.344 84.052 50.141
mAcc: 85.928 98.480 53.602 88.994 91.790 88.680 74.190 79.418 44.143 52.175 21.327 84.595 80.079 58.722 58.103 35.662 88.151 64.121 85.154 60.841

thomas 04/08 09:16:48 312/312: Data time: 0.0024, Iter time: 0.8868	Loss 0.419 (AVG: 0.633)	Score 86.310 (AVG: 82.509)	mIOU 57.614 mAP 70.408 mAcc 69.582
IOU: 75.269 95.792 43.743 51.516 87.864 77.029 64.015 46.269 39.249 50.244 15.814 48.921 59.391 56.812 46.581 32.675 86.149 58.563 77.997 38.380
mAP: 78.161 96.959 51.012 74.558 88.807 81.285 68.250 66.168 46.202 66.251 39.496 65.056 64.983 71.459 67.496 74.233 91.562 81.925 84.052 50.247
mAcc: 86.022 98.488 53.218 88.886 91.874 88.731 73.960 79.312 44.476 52.327 21.087 83.945 80.170 59.426 58.103 34.862 88.278 63.052 85.154 60.277

thomas 04/08 09:16:48 Finished test. Elapsed time: 411.4510
thomas 04/08 09:16:48 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 09:20:28 ===> Epoch[137](41040/301): Loss 0.3066	LR: 6.861e-02	Score 90.092	Data time: 2.1716, Total iter time: 5.4512
thomas 04/08 09:24:20 ===> Epoch[137](41080/301): Loss 0.3342	LR: 6.858e-02	Score 89.583	Data time: 2.2349, Total iter time: 5.7263
thomas 04/08 09:28:26 ===> Epoch[137](41120/301): Loss 0.3401	LR: 6.855e-02	Score 89.394	Data time: 2.3670, Total iter time: 6.0647
thomas 04/08 09:32:09 ===> Epoch[137](41160/301): Loss 0.2998	LR: 6.852e-02	Score 90.595	Data time: 2.1740, Total iter time: 5.5287
thomas 04/08 09:36:06 ===> Epoch[137](41200/301): Loss 0.2873	LR: 6.849e-02	Score 90.679	Data time: 2.3398, Total iter time: 5.8601
thomas 04/08 09:40:10 ===> Epoch[138](41240/301): Loss 0.3179	LR: 6.846e-02	Score 90.209	Data time: 2.3989, Total iter time: 6.0096
thomas 04/08 09:44:07 ===> Epoch[138](41280/301): Loss 0.3724	LR: 6.843e-02	Score 88.990	Data time: 2.2972, Total iter time: 5.8554
thomas 04/08 09:48:08 ===> Epoch[138](41320/301): Loss 0.3430	LR: 6.839e-02	Score 88.985	Data time: 2.3622, Total iter time: 5.9473
thomas 04/08 09:51:58 ===> Epoch[138](41360/301): Loss 0.2928	LR: 6.836e-02	Score 90.651	Data time: 2.2234, Total iter time: 5.6978
thomas 04/08 09:55:54 ===> Epoch[138](41400/301): Loss 0.3054	LR: 6.833e-02	Score 90.499	Data time: 2.2543, Total iter time: 5.8156
thomas 04/08 10:00:03 ===> Epoch[138](41440/301): Loss 0.2738	LR: 6.830e-02	Score 91.457	Data time: 2.4379, Total iter time: 6.1552
thomas 04/08 10:04:33 ===> Epoch[138](41480/301): Loss 0.2886	LR: 6.827e-02	Score 90.640	Data time: 2.7314, Total iter time: 6.6667
thomas 04/08 10:08:23 ===> Epoch[138](41520/301): Loss 0.2787	LR: 6.824e-02	Score 91.226	Data time: 2.2506, Total iter time: 5.6955
thomas 04/08 10:12:15 ===> Epoch[139](41560/301): Loss 0.3375	LR: 6.821e-02	Score 89.281	Data time: 2.2510, Total iter time: 5.7247
thomas 04/08 10:16:00 ===> Epoch[139](41600/301): Loss 0.3301	LR: 6.817e-02	Score 89.439	Data time: 2.1719, Total iter time: 5.5432
thomas 04/08 10:19:44 ===> Epoch[139](41640/301): Loss 0.2915	LR: 6.814e-02	Score 90.637	Data time: 2.1781, Total iter time: 5.5375
thomas 04/08 10:23:49 ===> Epoch[139](41680/301): Loss 0.3057	LR: 6.811e-02	Score 90.430	Data time: 2.3804, Total iter time: 6.0608
thomas 04/08 10:27:59 ===> Epoch[139](41720/301): Loss 0.2962	LR: 6.808e-02	Score 90.753	Data time: 2.4726, Total iter time: 6.1659
thomas 04/08 10:32:21 ===> Epoch[139](41760/301): Loss 0.3138	LR: 6.805e-02	Score 90.252	Data time: 2.5591, Total iter time: 6.4374
thomas 04/08 10:36:18 ===> Epoch[139](41800/301): Loss 0.2746	LR: 6.802e-02	Score 91.190	Data time: 2.3245, Total iter time: 5.8592
thomas 04/08 10:40:22 ===> Epoch[140](41840/301): Loss 0.2962	LR: 6.799e-02	Score 90.782	Data time: 2.3239, Total iter time: 6.0052
thomas 04/08 10:43:58 ===> Epoch[140](41880/301): Loss 0.2899	LR: 6.796e-02	Score 90.699	Data time: 2.0936, Total iter time: 5.3536
thomas 04/08 10:47:57 ===> Epoch[140](41920/301): Loss 0.3135	LR: 6.792e-02	Score 90.171	Data time: 2.3191, Total iter time: 5.8872
thomas 04/08 10:52:06 ===> Epoch[140](41960/301): Loss 0.3382	LR: 6.789e-02	Score 89.693	Data time: 2.4839, Total iter time: 6.1540
thomas 04/08 10:56:02 ===> Epoch[140](42000/301): Loss 0.3376	LR: 6.786e-02	Score 89.278	Data time: 2.3109, Total iter time: 5.8260
thomas 04/08 10:56:04 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 10:56:04 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 10:58:11 101/312: Data time: 0.0035, Iter time: 0.6132	Loss 0.688 (AVG: 0.636)	Score 80.712 (AVG: 81.702)	mIOU 55.640 mAP 68.816 mAcc 68.492
IOU: 70.973 95.872 51.838 38.790 88.449 64.733 63.061 47.753 47.938 71.376 14.275 57.073 58.068 40.445 10.337 39.760 84.523 44.907 81.493 41.146
mAP: 77.352 98.050 57.507 46.516 86.204 72.041 64.447 61.952 54.239 68.829 39.264 60.374 71.763 87.942 27.997 90.433 96.203 78.931 78.572 57.706
mAcc: 79.445 98.150 72.079 55.812 96.128 94.782 70.126 68.971 54.746 88.992 18.011 68.954 76.547 95.232 14.382 41.070 84.806 45.841 82.498 63.263

thomas 04/08 11:00:04 201/312: Data time: 0.0030, Iter time: 0.3417	Loss 0.439 (AVG: 0.608)	Score 85.678 (AVG: 82.339)	mIOU 57.880 mAP 69.455 mAcc 70.507
IOU: 72.107 96.035 54.688 53.377 87.275 69.803 63.451 46.651 41.868 74.474 16.329 59.134 55.039 50.260 30.098 39.048 84.785 47.826 78.901 36.450
mAP: 77.102 97.125 59.590 55.156 88.806 80.052 66.086 62.706 49.139 67.554 37.486 57.241 69.348 81.056 46.505 89.332 93.785 80.165 77.874 52.993
mAcc: 79.839 98.096 72.305 66.986 95.871 92.255 71.602 70.515 48.302 90.188 21.168 72.624 75.280 86.206 40.772 46.977 85.057 48.898 84.427 62.770

thomas 04/08 11:02:02 301/312: Data time: 0.0026, Iter time: 0.8160	Loss 0.202 (AVG: 0.606)	Score 94.377 (AVG: 82.634)	mIOU 58.206 mAP 70.305 mAcc 70.695
IOU: 72.320 96.153 56.583 56.494 87.352 71.065 66.520 45.515 43.077 72.942 15.838 61.323 54.833 49.386 33.432 38.186 83.165 46.297 78.370 35.278
mAP: 76.967 97.328 60.922 57.628 89.359 81.185 69.113 62.980 50.228 67.728 42.421 58.273 70.570 77.797 51.156 87.457 90.832 80.212 80.583 53.362
mAcc: 79.946 98.232 74.509 69.938 94.764 93.257 75.746 68.557 49.356 91.329 19.400 74.875 76.600 84.777 43.493 42.887 83.772 47.079 82.371 63.008

thomas 04/08 11:02:12 312/312: Data time: 0.0024, Iter time: 0.1928	Loss 0.229 (AVG: 0.609)	Score 93.846 (AVG: 82.592)	mIOU 58.268 mAP 70.340 mAcc 70.792
IOU: 72.361 96.146 56.609 57.096 87.303 70.645 66.761 45.510 42.678 72.696 16.330 60.906 54.788 49.045 34.792 37.757 83.754 46.454 78.826 34.908
mAP: 77.156 97.358 60.552 58.266 89.274 81.153 69.588 63.469 49.482 68.080 42.197 57.885 70.416 77.360 51.564 87.457 91.189 80.381 80.972 53.009
mAcc: 79.934 98.211 74.378 70.571 94.685 93.372 75.923 68.900 48.801 90.958 19.853 74.426 76.595 84.786 44.538 42.887 84.369 47.232 82.583 62.845

thomas 04/08 11:02:12 Finished test. Elapsed time: 368.5821
thomas 04/08 11:02:12 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 11:06:18 ===> Epoch[140](42040/301): Loss 0.2763	LR: 6.783e-02	Score 91.056	Data time: 2.3670, Total iter time: 6.0775
thomas 04/08 11:10:16 ===> Epoch[140](42080/301): Loss 0.2641	LR: 6.780e-02	Score 91.645	Data time: 2.3210, Total iter time: 5.8728
thomas 04/08 11:14:21 ===> Epoch[140](42120/301): Loss 0.3146	LR: 6.777e-02	Score 90.399	Data time: 2.4135, Total iter time: 6.0223
thomas 04/08 11:18:23 ===> Epoch[141](42160/301): Loss 0.3248	LR: 6.774e-02	Score 89.900	Data time: 2.4086, Total iter time: 5.9707
thomas 04/08 11:22:17 ===> Epoch[141](42200/301): Loss 0.3168	LR: 6.770e-02	Score 90.084	Data time: 2.2438, Total iter time: 5.7935
thomas 04/08 11:26:01 ===> Epoch[141](42240/301): Loss 0.3254	LR: 6.767e-02	Score 89.967	Data time: 2.1408, Total iter time: 5.5311
thomas 04/08 11:29:50 ===> Epoch[141](42280/301): Loss 0.2983	LR: 6.764e-02	Score 90.491	Data time: 2.2117, Total iter time: 5.6302
thomas 04/08 11:33:48 ===> Epoch[141](42320/301): Loss 0.2864	LR: 6.761e-02	Score 90.958	Data time: 2.2881, Total iter time: 5.8726
thomas 04/08 11:38:00 ===> Epoch[141](42360/301): Loss 0.2741	LR: 6.758e-02	Score 91.299	Data time: 2.5030, Total iter time: 6.2417
thomas 04/08 11:42:23 ===> Epoch[141](42400/301): Loss 0.2648	LR: 6.755e-02	Score 91.365	Data time: 2.6422, Total iter time: 6.4998
thomas 04/08 11:46:15 ===> Epoch[141](42440/301): Loss 0.2957	LR: 6.752e-02	Score 90.687	Data time: 2.2116, Total iter time: 5.7162
thomas 04/08 11:50:28 ===> Epoch[142](42480/301): Loss 0.3495	LR: 6.749e-02	Score 89.327	Data time: 2.4256, Total iter time: 6.2532
thomas 04/08 11:54:25 ===> Epoch[142](42520/301): Loss 0.2969	LR: 6.745e-02	Score 90.983	Data time: 2.2921, Total iter time: 5.8505
thomas 04/08 11:58:14 ===> Epoch[142](42560/301): Loss 0.3209	LR: 6.742e-02	Score 89.772	Data time: 2.2147, Total iter time: 5.6465
thomas 04/08 12:02:07 ===> Epoch[142](42600/301): Loss 0.3136	LR: 6.739e-02	Score 90.318	Data time: 2.3474, Total iter time: 5.7598
thomas 04/08 12:06:02 ===> Epoch[142](42640/301): Loss 0.3049	LR: 6.736e-02	Score 90.343	Data time: 2.2993, Total iter time: 5.7807
thomas 04/08 12:09:56 ===> Epoch[142](42680/301): Loss 0.2746	LR: 6.733e-02	Score 91.291	Data time: 2.2565, Total iter time: 5.7664
thomas 04/08 12:13:51 ===> Epoch[142](42720/301): Loss 0.2934	LR: 6.730e-02	Score 90.723	Data time: 2.2563, Total iter time: 5.7967
thomas 04/08 12:17:44 ===> Epoch[143](42760/301): Loss 0.3094	LR: 6.727e-02	Score 90.413	Data time: 2.2593, Total iter time: 5.7605
thomas 04/08 12:21:35 ===> Epoch[143](42800/301): Loss 0.3016	LR: 6.723e-02	Score 90.288	Data time: 2.2222, Total iter time: 5.6934
thomas 04/08 12:25:50 ===> Epoch[143](42840/301): Loss 0.3128	LR: 6.720e-02	Score 90.331	Data time: 2.5037, Total iter time: 6.3132
thomas 04/08 12:29:47 ===> Epoch[143](42880/301): Loss 0.2853	LR: 6.717e-02	Score 90.933	Data time: 2.3241, Total iter time: 5.8308
thomas 04/08 12:33:50 ===> Epoch[143](42920/301): Loss 0.3130	LR: 6.714e-02	Score 89.907	Data time: 2.3199, Total iter time: 5.9941
thomas 04/08 12:37:36 ===> Epoch[143](42960/301): Loss 0.2874	LR: 6.711e-02	Score 91.042	Data time: 2.1611, Total iter time: 5.5923
thomas 04/08 12:41:31 ===> Epoch[143](43000/301): Loss 0.3044	LR: 6.708e-02	Score 90.646	Data time: 2.2378, Total iter time: 5.7946
thomas 04/08 12:41:33 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 12:41:33 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 12:43:33 101/312: Data time: 0.0024, Iter time: 0.9089	Loss 0.296 (AVG: 0.631)	Score 92.896 (AVG: 82.405)	mIOU 53.372 mAP 68.478 mAcc 65.248
IOU: 75.000 95.858 46.290 50.238 87.100 74.125 70.749 40.648 42.581 54.211 5.650 60.242 41.613 59.732 31.975 24.491 65.221 41.897 57.469 42.347
mAP: 78.523 97.802 53.716 59.544 86.921 76.408 73.379 58.377 50.889 64.369 38.536 61.247 59.041 79.965 62.672 65.145 82.049 76.301 86.581 58.097
mAcc: 87.416 98.730 64.042 56.572 90.864 88.617 77.534 59.096 47.533 59.892 5.898 69.633 73.465 72.969 75.327 30.615 72.307 42.808 58.084 73.554

thomas 04/08 12:45:26 201/312: Data time: 0.0029, Iter time: 0.3645	Loss 0.173 (AVG: 0.605)	Score 96.366 (AVG: 83.035)	mIOU 55.168 mAP 68.130 mAcc 66.387
IOU: 75.936 95.640 45.770 61.026 87.756 74.559 68.638 41.209 37.176 65.160 9.813 58.428 50.977 62.487 30.478 25.938 69.707 41.508 59.764 41.379
mAP: 77.820 97.732 50.900 65.412 88.793 80.645 69.707 58.333 49.759 66.409 36.671 56.985 62.632 76.783 60.153 72.523 84.750 72.941 79.496 54.157
mAcc: 88.036 98.810 64.933 70.118 92.430 88.397 76.746 60.027 40.785 74.346 10.707 65.387 79.505 76.362 73.408 29.245 73.662 42.175 60.610 62.050

thomas 04/08 12:47:28 301/312: Data time: 0.0026, Iter time: 1.4618	Loss 0.749 (AVG: 0.598)	Score 81.080 (AVG: 83.339)	mIOU 55.231 mAP 68.191 mAcc 66.287
IOU: 76.695 95.807 46.632 60.876 88.962 76.052 66.664 42.864 35.639 65.700 12.549 56.803 48.454 63.661 31.161 22.907 73.536 39.725 56.667 43.262
mAP: 78.156 97.473 51.415 64.667 89.786 80.678 70.983 60.257 47.685 65.819 39.213 54.823 62.850 77.240 60.454 72.567 87.759 72.380 77.402 52.209
mAcc: 88.640 98.786 65.979 70.654 93.541 89.448 75.785 62.096 39.031 74.967 14.044 62.825 77.382 76.267 74.692 24.514 77.050 40.448 57.224 62.365

thomas 04/08 12:47:45 312/312: Data time: 0.0026, Iter time: 0.5585	Loss 0.254 (AVG: 0.592)	Score 93.662 (AVG: 83.538)	mIOU 55.459 mAP 68.122 mAcc 66.481
IOU: 77.023 95.879 46.500 61.057 88.909 76.096 66.679 42.653 36.072 65.394 12.655 56.803 50.555 62.880 30.621 23.691 73.896 40.750 57.866 43.198
mAP: 78.318 97.520 51.694 64.079 89.637 79.611 71.193 60.255 47.415 66.317 38.735 54.823 62.492 77.043 60.220 72.697 88.096 72.988 77.417 51.885
mAcc: 88.815 98.782 65.954 70.961 93.559 89.541 75.883 61.658 39.557 74.733 14.323 62.825 78.382 75.257 74.322 25.318 77.304 41.480 58.421 62.547

thomas 04/08 12:47:45 Finished test. Elapsed time: 371.7448
thomas 04/08 12:47:45 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 12:51:49 ===> Epoch[143](43040/301): Loss 0.2820	LR: 6.705e-02	Score 90.977	Data time: 2.4428, Total iter time: 6.0178
thomas 04/08 12:56:00 ===> Epoch[144](43080/301): Loss 0.2882	LR: 6.702e-02	Score 90.968	Data time: 2.4771, Total iter time: 6.2071
thomas 04/08 12:59:54 ===> Epoch[144](43120/301): Loss 0.3033	LR: 6.698e-02	Score 90.312	Data time: 2.2389, Total iter time: 5.7843
thomas 04/08 13:03:45 ===> Epoch[144](43160/301): Loss 0.3206	LR: 6.695e-02	Score 90.084	Data time: 2.2081, Total iter time: 5.7063
thomas 04/08 13:07:40 ===> Epoch[144](43200/301): Loss 0.3128	LR: 6.692e-02	Score 89.873	Data time: 2.2721, Total iter time: 5.8003
thomas 04/08 13:11:34 ===> Epoch[144](43240/301): Loss 0.3435	LR: 6.689e-02	Score 89.213	Data time: 2.2559, Total iter time: 5.7795
thomas 04/08 13:15:58 ===> Epoch[144](43280/301): Loss 0.3383	LR: 6.686e-02	Score 89.405	Data time: 2.6173, Total iter time: 6.5016
thomas 04/08 13:20:12 ===> Epoch[144](43320/301): Loss 0.2980	LR: 6.683e-02	Score 90.255	Data time: 2.5015, Total iter time: 6.2676
thomas 04/08 13:23:57 ===> Epoch[145](43360/301): Loss 0.3092	LR: 6.680e-02	Score 89.944	Data time: 2.1582, Total iter time: 5.5555
thomas 04/08 13:27:55 ===> Epoch[145](43400/301): Loss 0.3219	LR: 6.676e-02	Score 89.964	Data time: 2.2897, Total iter time: 5.8951
thomas 04/08 13:31:44 ===> Epoch[145](43440/301): Loss 0.3083	LR: 6.673e-02	Score 90.469	Data time: 2.1767, Total iter time: 5.6490
thomas 04/08 13:35:28 ===> Epoch[145](43480/301): Loss 0.3095	LR: 6.670e-02	Score 90.462	Data time: 2.1631, Total iter time: 5.5166
thomas 04/08 13:39:41 ===> Epoch[145](43520/301): Loss 0.3322	LR: 6.667e-02	Score 89.736	Data time: 2.5103, Total iter time: 6.2650
thomas 04/08 13:43:48 ===> Epoch[145](43560/301): Loss 0.3173	LR: 6.664e-02	Score 89.958	Data time: 2.4413, Total iter time: 6.1135
thomas 04/08 13:47:36 ===> Epoch[145](43600/301): Loss 0.3180	LR: 6.661e-02	Score 90.042	Data time: 2.1704, Total iter time: 5.6171
thomas 04/08 13:51:39 ===> Epoch[145](43640/301): Loss 0.2826	LR: 6.658e-02	Score 91.006	Data time: 2.3529, Total iter time: 5.9990
thomas 04/08 13:55:29 ===> Epoch[146](43680/301): Loss 0.2847	LR: 6.654e-02	Score 91.077	Data time: 2.1954, Total iter time: 5.6890
thomas 04/08 13:59:41 ===> Epoch[146](43720/301): Loss 0.3075	LR: 6.651e-02	Score 90.330	Data time: 2.4490, Total iter time: 6.2228
thomas 04/08 14:04:06 ===> Epoch[146](43760/301): Loss 0.3486	LR: 6.648e-02	Score 89.253	Data time: 2.6290, Total iter time: 6.5345
thomas 04/08 14:08:22 ===> Epoch[146](43800/301): Loss 0.3070	LR: 6.645e-02	Score 90.129	Data time: 2.5085, Total iter time: 6.3279
thomas 04/08 14:12:33 ===> Epoch[146](43840/301): Loss 0.3069	LR: 6.642e-02	Score 90.251	Data time: 2.3967, Total iter time: 6.1916
thomas 04/08 14:16:43 ===> Epoch[146](43880/301): Loss 0.3026	LR: 6.639e-02	Score 90.622	Data time: 2.3914, Total iter time: 6.1817
thomas 04/08 14:20:41 ===> Epoch[146](43920/301): Loss 0.2748	LR: 6.636e-02	Score 91.129	Data time: 2.2689, Total iter time: 5.8627
thomas 04/08 14:24:52 ===> Epoch[147](43960/301): Loss 0.2785	LR: 6.632e-02	Score 91.345	Data time: 2.4611, Total iter time: 6.2084
thomas 04/08 14:29:12 ===> Epoch[147](44000/301): Loss 0.2887	LR: 6.629e-02	Score 90.959	Data time: 2.5986, Total iter time: 6.4106
thomas 04/08 14:29:13 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 14:29:13 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 14:31:34 101/312: Data time: 0.0028, Iter time: 0.3896	Loss 0.294 (AVG: 0.639)	Score 91.600 (AVG: 82.139)	mIOU 56.237 mAP 71.578 mAcc 68.021
IOU: 72.891 95.355 48.095 73.884 85.054 69.734 63.248 41.410 29.333 69.329 19.936 48.732 54.376 57.275 52.942 13.409 79.738 37.874 68.166 43.954
mAP: 76.586 97.493 59.270 76.006 88.242 80.913 66.628 63.779 43.805 74.514 39.966 56.200 69.083 72.109 78.835 82.126 92.244 81.813 82.774 49.166
mAcc: 81.831 96.994 65.742 83.924 87.902 92.463 77.262 87.696 30.953 97.317 22.044 71.213 62.164 61.089 73.427 13.454 80.584 38.233 68.825 67.303

thomas 04/08 14:33:34 201/312: Data time: 0.0025, Iter time: 0.3250	Loss 0.555 (AVG: 0.629)	Score 84.546 (AVG: 82.616)	mIOU 56.302 mAP 70.927 mAcc 68.292
IOU: 74.059 95.140 51.407 74.322 84.900 70.882 63.991 40.393 27.866 64.056 21.447 51.861 54.664 58.431 49.946 12.355 77.923 41.639 70.647 40.104
mAP: 78.234 97.752 58.884 74.372 88.750 79.383 69.923 63.001 45.333 73.447 45.831 56.860 71.597 72.847 67.984 80.390 91.593 77.757 76.935 47.674
mAcc: 82.582 96.818 69.723 81.701 88.123 93.288 74.661 82.880 29.932 97.016 24.035 76.534 65.617 62.844 70.176 12.382 78.504 42.246 71.259 65.521

thomas 04/08 14:35:33 301/312: Data time: 0.0030, Iter time: 0.8630	Loss 0.215 (AVG: 0.655)	Score 93.346 (AVG: 81.983)	mIOU 56.073 mAP 70.852 mAcc 67.890
IOU: 73.116 95.051 52.980 73.937 86.384 69.197 64.404 38.056 30.435 61.388 16.714 53.940 53.630 54.934 48.950 11.501 80.130 45.136 71.536 40.042
mAP: 78.114 97.656 57.726 75.954 89.424 79.434 68.899 58.483 49.070 71.120 41.629 57.640 69.265 71.036 66.732 81.058 92.454 81.396 80.683 49.267
mAcc: 82.406 96.940 70.338 81.640 89.558 93.206 75.053 77.305 32.498 95.105 18.038 75.270 65.746 61.321 70.460 11.646 80.674 45.850 72.106 62.640

thomas 04/08 14:35:47 312/312: Data time: 0.0024, Iter time: 0.9331	Loss 0.720 (AVG: 0.651)	Score 82.058 (AVG: 82.079)	mIOU 56.242 mAP 70.801 mAcc 67.929
IOU: 73.144 95.019 52.545 73.504 86.442 70.186 64.844 38.009 31.491 62.063 16.515 53.599 54.058 54.566 49.414 11.501 80.036 45.884 71.536 40.492
mAP: 78.123 97.698 57.531 74.767 89.429 79.751 68.728 58.368 49.528 70.672 41.395 57.094 70.001 70.654 67.116 81.058 92.466 81.541 80.683 49.427
mAcc: 82.414 96.899 70.252 81.122 89.627 93.384 75.203 77.224 33.557 95.254 17.976 73.836 66.477 60.873 70.373 11.646 80.575 46.595 72.106 63.188

thomas 04/08 14:35:47 Finished test. Elapsed time: 393.0947
thomas 04/08 14:35:47 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 14:40:06 ===> Epoch[147](44040/301): Loss 0.2979	LR: 6.626e-02	Score 91.091	Data time: 2.4627, Total iter time: 6.4032
thomas 04/08 14:44:15 ===> Epoch[147](44080/301): Loss 0.2898	LR: 6.623e-02	Score 91.016	Data time: 2.3722, Total iter time: 6.1422
thomas 04/08 14:48:03 ===> Epoch[147](44120/301): Loss 0.2967	LR: 6.620e-02	Score 90.220	Data time: 2.2208, Total iter time: 5.6156
thomas 04/08 14:52:03 ===> Epoch[147](44160/301): Loss 0.2928	LR: 6.617e-02	Score 90.543	Data time: 2.3966, Total iter time: 5.9429
thomas 04/08 14:56:04 ===> Epoch[147](44200/301): Loss 0.2624	LR: 6.614e-02	Score 91.632	Data time: 2.3898, Total iter time: 5.9525
thomas 04/08 15:00:06 ===> Epoch[147](44240/301): Loss 0.2984	LR: 6.611e-02	Score 90.321	Data time: 2.3084, Total iter time: 5.9509
thomas 04/08 15:04:02 ===> Epoch[148](44280/301): Loss 0.3225	LR: 6.607e-02	Score 89.657	Data time: 2.2597, Total iter time: 5.8239
thomas 04/08 15:08:05 ===> Epoch[148](44320/301): Loss 0.2766	LR: 6.604e-02	Score 91.083	Data time: 2.3440, Total iter time: 5.9982
thomas 04/08 15:12:13 ===> Epoch[148](44360/301): Loss 0.2883	LR: 6.601e-02	Score 90.855	Data time: 2.4414, Total iter time: 6.1388
thomas 04/08 15:16:11 ===> Epoch[148](44400/301): Loss 0.3090	LR: 6.598e-02	Score 90.432	Data time: 2.3771, Total iter time: 5.8730
thomas 04/08 15:19:59 ===> Epoch[148](44440/301): Loss 0.3040	LR: 6.595e-02	Score 90.307	Data time: 2.2133, Total iter time: 5.6127
thomas 04/08 15:23:47 ===> Epoch[148](44480/301): Loss 0.3069	LR: 6.592e-02	Score 90.479	Data time: 2.2017, Total iter time: 5.6281
thomas 04/08 15:27:39 ===> Epoch[148](44520/301): Loss 0.3062	LR: 6.589e-02	Score 90.302	Data time: 2.1972, Total iter time: 5.7058
thomas 04/08 15:31:54 ===> Epoch[149](44560/301): Loss 0.3286	LR: 6.585e-02	Score 89.763	Data time: 2.4644, Total iter time: 6.3032
thomas 04/08 15:36:08 ===> Epoch[149](44600/301): Loss 0.3359	LR: 6.582e-02	Score 89.305	Data time: 2.5125, Total iter time: 6.2900
thomas 04/08 15:40:01 ===> Epoch[149](44640/301): Loss 0.3018	LR: 6.579e-02	Score 90.276	Data time: 2.2822, Total iter time: 5.7393
thomas 04/08 15:43:52 ===> Epoch[149](44680/301): Loss 0.3184	LR: 6.576e-02	Score 89.914	Data time: 2.2409, Total iter time: 5.7070
thomas 04/08 15:47:43 ===> Epoch[149](44720/301): Loss 0.3127	LR: 6.573e-02	Score 90.003	Data time: 2.2211, Total iter time: 5.7058
thomas 04/08 15:51:47 ===> Epoch[149](44760/301): Loss 0.2906	LR: 6.570e-02	Score 90.700	Data time: 2.3234, Total iter time: 6.0167
thomas 04/08 15:55:41 ===> Epoch[149](44800/301): Loss 0.3200	LR: 6.567e-02	Score 90.193	Data time: 2.2710, Total iter time: 5.7739
thomas 04/08 15:59:47 ===> Epoch[149](44840/301): Loss 0.2794	LR: 6.563e-02	Score 91.083	Data time: 2.4023, Total iter time: 6.0777
thomas 04/08 16:04:06 ===> Epoch[150](44880/301): Loss 0.2774	LR: 6.560e-02	Score 91.207	Data time: 2.5536, Total iter time: 6.3966
thomas 04/08 16:07:59 ===> Epoch[150](44920/301): Loss 0.3009	LR: 6.557e-02	Score 90.151	Data time: 2.2744, Total iter time: 5.7560
thomas 04/08 16:11:44 ===> Epoch[150](44960/301): Loss 0.2900	LR: 6.554e-02	Score 91.035	Data time: 2.1685, Total iter time: 5.5579
thomas 04/08 16:15:37 ===> Epoch[150](45000/301): Loss 0.2915	LR: 6.551e-02	Score 90.500	Data time: 2.2342, Total iter time: 5.7481
thomas 04/08 16:15:38 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 16:15:38 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 16:17:37 101/312: Data time: 0.0024, Iter time: 0.5619	Loss 1.591 (AVG: 0.616)	Score 60.336 (AVG: 83.574)	mIOU 56.495 mAP 68.097 mAcc 66.342
IOU: 77.898 95.429 49.267 68.929 86.601 69.262 66.171 23.586 38.975 68.109 4.540 60.394 66.305 53.714 36.143 33.599 76.252 50.863 69.667 34.203
mAP: 79.474 97.144 56.422 69.820 88.415 70.875 70.886 56.386 51.679 61.778 24.993 64.586 64.081 79.407 48.220 89.073 86.857 78.804 76.630 46.410
mAcc: 93.881 98.421 69.615 81.217 91.814 77.606 77.417 25.152 44.951 78.651 4.783 70.753 80.421 83.090 57.062 34.952 77.085 54.354 69.825 55.794

thomas 04/08 16:19:44 201/312: Data time: 0.0024, Iter time: 0.4345	Loss 0.141 (AVG: 0.589)	Score 95.495 (AVG: 83.755)	mIOU 56.875 mAP 68.527 mAcc 66.784
IOU: 77.558 95.991 47.796 66.853 87.976 70.755 65.314 28.218 38.237 64.383 8.342 54.516 59.139 60.702 36.147 36.180 80.930 56.164 67.566 34.729
mAP: 78.470 97.481 52.317 71.170 89.633 75.334 69.628 56.620 50.516 61.840 28.967 63.689 64.597 82.070 50.447 86.865 91.565 78.183 76.459 44.693
mAcc: 93.329 98.633 64.849 77.412 93.040 80.702 75.070 30.328 44.027 78.617 9.058 66.715 78.491 85.881 54.520 38.325 81.390 61.694 67.782 55.818

thomas 04/08 16:21:48 301/312: Data time: 0.0023, Iter time: 0.4364	Loss 0.459 (AVG: 0.603)	Score 85.918 (AVG: 83.330)	mIOU 57.076 mAP 68.168 mAcc 66.837
IOU: 76.835 96.206 45.675 66.654 87.666 71.062 65.677 27.435 39.593 69.429 8.992 54.050 54.791 59.740 38.105 37.477 82.509 55.898 70.405 33.317
mAP: 77.532 97.698 49.446 69.950 89.226 76.332 70.205 54.506 50.533 61.433 28.772 61.943 63.803 76.842 51.903 87.746 92.804 78.607 79.359 44.713
mAcc: 93.002 98.589 62.241 77.697 93.195 81.124 75.371 29.531 45.569 82.122 9.695 66.456 76.390 83.091 54.990 39.425 83.237 61.234 70.619 53.169

thomas 04/08 16:21:59 312/312: Data time: 0.0026, Iter time: 0.3467	Loss 0.474 (AVG: 0.604)	Score 83.599 (AVG: 83.232)	mIOU 57.103 mAP 68.150 mAcc 66.924
IOU: 76.712 96.171 46.312 65.736 87.638 71.193 66.126 27.036 39.783 69.244 8.805 55.093 54.420 59.508 38.532 37.477 82.509 56.137 70.405 33.222
mAP: 77.629 97.591 49.735 68.960 89.123 76.447 70.663 54.150 51.138 61.716 28.132 61.014 63.967 76.638 52.599 87.746 92.804 78.698 79.359 44.893
mAcc: 92.850 98.561 63.514 76.645 93.207 81.576 75.844 29.184 45.741 82.202 9.488 67.149 76.501 82.714 55.818 39.425 83.237 61.757 70.619 52.457

thomas 04/08 16:21:59 Finished test. Elapsed time: 380.9215
thomas 04/08 16:21:59 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 16:25:55 ===> Epoch[150](45040/301): Loss 0.3135	LR: 6.548e-02	Score 90.194	Data time: 2.3227, Total iter time: 5.8310
thomas 04/08 16:30:01 ===> Epoch[150](45080/301): Loss 0.2892	LR: 6.545e-02	Score 90.843	Data time: 2.4019, Total iter time: 6.0784
thomas 04/08 16:33:57 ===> Epoch[150](45120/301): Loss 0.2766	LR: 6.541e-02	Score 91.263	Data time: 2.2909, Total iter time: 5.8088
thomas 04/08 16:37:50 ===> Epoch[151](45160/301): Loss 0.3124	LR: 6.538e-02	Score 90.009	Data time: 2.2471, Total iter time: 5.7629
thomas 04/08 16:41:49 ===> Epoch[151](45200/301): Loss 0.3065	LR: 6.535e-02	Score 90.463	Data time: 2.2986, Total iter time: 5.8833
thomas 04/08 16:45:48 ===> Epoch[151](45240/301): Loss 0.3021	LR: 6.532e-02	Score 90.436	Data time: 2.3636, Total iter time: 5.9147
thomas 04/08 16:50:13 ===> Epoch[151](45280/301): Loss 0.2877	LR: 6.529e-02	Score 90.884	Data time: 2.6168, Total iter time: 6.5261
thomas 04/08 16:54:20 ===> Epoch[151](45320/301): Loss 0.3012	LR: 6.526e-02	Score 90.603	Data time: 2.4039, Total iter time: 6.1072
thomas 04/08 16:58:04 ===> Epoch[151](45360/301): Loss 0.3230	LR: 6.522e-02	Score 89.917	Data time: 2.1908, Total iter time: 5.5203
thomas 04/08 17:02:00 ===> Epoch[151](45400/301): Loss 0.2968	LR: 6.519e-02	Score 90.657	Data time: 2.2560, Total iter time: 5.8207
thomas 04/08 17:06:00 ===> Epoch[151](45440/301): Loss 0.3090	LR: 6.516e-02	Score 89.983	Data time: 2.3314, Total iter time: 5.9103
thomas 04/08 17:09:58 ===> Epoch[152](45480/301): Loss 0.2999	LR: 6.513e-02	Score 90.530	Data time: 2.3199, Total iter time: 5.8718
thomas 04/08 17:14:00 ===> Epoch[152](45520/301): Loss 0.2874	LR: 6.510e-02	Score 90.961	Data time: 2.3595, Total iter time: 5.9686
thomas 04/08 17:18:09 ===> Epoch[152](45560/301): Loss 0.2902	LR: 6.507e-02	Score 91.045	Data time: 2.4580, Total iter time: 6.1424
thomas 04/08 17:22:05 ===> Epoch[152](45600/301): Loss 0.2726	LR: 6.504e-02	Score 91.435	Data time: 2.2872, Total iter time: 5.8152
thomas 04/08 17:25:55 ===> Epoch[152](45640/301): Loss 0.2991	LR: 6.500e-02	Score 90.684	Data time: 2.2081, Total iter time: 5.6928
thomas 04/08 17:30:02 ===> Epoch[152](45680/301): Loss 0.3116	LR: 6.497e-02	Score 90.064	Data time: 2.3771, Total iter time: 6.1004
thomas 04/08 17:34:01 ===> Epoch[152](45720/301): Loss 0.3016	LR: 6.494e-02	Score 90.563	Data time: 2.3549, Total iter time: 5.8920
thomas 04/08 17:38:06 ===> Epoch[153](45760/301): Loss 0.3028	LR: 6.491e-02	Score 90.651	Data time: 2.3968, Total iter time: 6.0581
thomas 04/08 17:42:18 ===> Epoch[153](45800/301): Loss 0.3028	LR: 6.488e-02	Score 90.467	Data time: 2.4541, Total iter time: 6.2171
thomas 04/08 17:46:07 ===> Epoch[153](45840/301): Loss 0.2942	LR: 6.485e-02	Score 90.571	Data time: 2.2339, Total iter time: 5.6316
thomas 04/08 17:50:00 ===> Epoch[153](45880/301): Loss 0.2821	LR: 6.482e-02	Score 91.192	Data time: 2.2535, Total iter time: 5.7465
thomas 04/08 17:54:08 ===> Epoch[153](45920/301): Loss 0.2673	LR: 6.478e-02	Score 91.585	Data time: 2.4186, Total iter time: 6.1196
thomas 04/08 17:58:01 ===> Epoch[153](45960/301): Loss 0.2670	LR: 6.475e-02	Score 92.012	Data time: 2.2810, Total iter time: 5.7816
thomas 04/08 18:02:06 ===> Epoch[153](46000/301): Loss 0.2522	LR: 6.472e-02	Score 92.219	Data time: 2.3943, Total iter time: 6.0455
thomas 04/08 18:02:08 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 18:02:08 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 18:04:17 101/312: Data time: 0.0029, Iter time: 0.6647	Loss 0.077 (AVG: 0.591)	Score 98.285 (AVG: 84.244)	mIOU 58.441 mAP 71.617 mAcc 69.926
IOU: 78.069 96.177 49.317 70.031 81.434 66.909 63.721 45.811 34.780 73.093 15.112 40.306 41.103 70.505 41.245 51.797 72.719 51.407 81.875 43.407
mAP: 79.257 96.566 53.091 76.585 87.458 82.093 73.196 61.961 48.819 63.191 36.180 50.351 71.885 84.174 66.911 92.794 88.855 85.648 88.437 44.879
mAcc: 91.157 98.667 71.412 78.376 83.889 96.070 67.933 70.735 38.852 81.783 16.292 74.621 76.531 75.760 55.684 56.118 72.911 52.840 85.169 53.725

thomas 04/08 18:06:09 201/312: Data time: 0.0023, Iter time: 0.6261	Loss 0.377 (AVG: 0.574)	Score 89.589 (AVG: 84.698)	mIOU 60.257 mAP 72.868 mAcc 71.021
IOU: 77.037 96.337 53.170 73.871 84.724 70.014 66.177 44.470 40.930 69.663 13.236 49.573 52.174 68.254 53.210 40.372 80.525 55.235 72.430 43.742
mAP: 79.814 97.261 56.835 79.041 88.976 85.391 74.760 62.467 55.181 65.119 35.582 58.777 72.056 80.612 67.541 90.002 93.529 84.654 78.019 51.748
mAcc: 89.906 98.734 73.033 83.995 87.713 96.259 70.736 71.007 45.711 77.144 15.242 78.855 77.746 74.361 66.384 43.762 80.861 56.888 76.761 55.327

thomas 04/08 18:08:15 301/312: Data time: 0.1733, Iter time: 0.6572	Loss 0.272 (AVG: 0.576)	Score 90.432 (AVG: 84.792)	mIOU 60.638 mAP 71.835 mAcc 70.963
IOU: 77.277 96.248 53.665 72.259 84.650 68.133 66.739 46.527 38.905 70.689 9.438 55.643 58.159 66.637 51.472 43.412 78.365 54.241 76.914 43.394
mAP: 79.147 97.536 56.599 77.075 87.816 81.920 72.090 63.541 53.644 64.583 31.356 62.274 69.782 77.295 65.885 87.428 92.390 82.199 80.488 53.647
mAcc: 90.510 98.679 73.250 82.588 87.549 95.173 70.914 71.669 42.870 78.936 10.394 79.871 79.518 72.962 65.478 46.420 78.974 56.755 80.639 56.103

thomas 04/08 18:08:30 312/312: Data time: 0.0024, Iter time: 0.6471	Loss 0.601 (AVG: 0.583)	Score 90.040 (AVG: 84.678)	mIOU 60.503 mAP 71.745 mAcc 70.643
IOU: 77.042 96.210 54.373 71.076 84.770 67.761 66.931 46.793 39.120 70.615 9.249 54.269 58.722 66.785 50.444 43.412 78.365 53.798 76.914 43.420
mAP: 78.725 97.597 56.676 76.157 87.734 82.003 72.335 64.051 53.396 64.583 30.679 61.169 69.872 77.438 66.363 87.428 92.390 82.272 80.488 53.551
mAcc: 90.494 98.664 73.950 82.154 87.664 95.207 71.193 71.863 43.073 78.936 10.166 74.975 79.981 72.857 63.540 46.420 78.974 56.229 80.639 55.881

thomas 04/08 18:08:30 Finished test. Elapsed time: 381.7685
thomas 04/08 18:08:30 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 18:12:22 ===> Epoch[153](46040/301): Loss 0.3015	LR: 6.469e-02	Score 90.618	Data time: 2.2487, Total iter time: 5.7249
thomas 04/08 18:16:29 ===> Epoch[154](46080/301): Loss 0.2751	LR: 6.466e-02	Score 91.038	Data time: 2.3713, Total iter time: 6.1096
thomas 04/08 18:20:32 ===> Epoch[154](46120/301): Loss 0.2824	LR: 6.463e-02	Score 90.982	Data time: 2.3692, Total iter time: 5.9793
thomas 04/08 18:24:22 ===> Epoch[154](46160/301): Loss 0.2874	LR: 6.460e-02	Score 90.530	Data time: 2.2583, Total iter time: 5.6685
thomas 04/08 18:28:24 ===> Epoch[154](46200/301): Loss 0.2999	LR: 6.456e-02	Score 90.722	Data time: 2.3861, Total iter time: 5.9902
thomas 04/08 18:32:24 ===> Epoch[154](46240/301): Loss 0.2903	LR: 6.453e-02	Score 91.170	Data time: 2.2993, Total iter time: 5.9048
thomas 04/08 18:36:27 ===> Epoch[154](46280/301): Loss 0.2706	LR: 6.450e-02	Score 91.453	Data time: 2.3413, Total iter time: 6.0126
thomas 04/08 18:40:21 ===> Epoch[154](46320/301): Loss 0.2698	LR: 6.447e-02	Score 91.362	Data time: 2.2656, Total iter time: 5.7756
thomas 04/08 18:44:14 ===> Epoch[155](46360/301): Loss 0.2612	LR: 6.444e-02	Score 91.517	Data time: 2.2761, Total iter time: 5.7448
thomas 04/08 18:48:02 ===> Epoch[155](46400/301): Loss 0.3127	LR: 6.441e-02	Score 90.232	Data time: 2.2333, Total iter time: 5.6356
thomas 04/08 18:52:04 ===> Epoch[155](46440/301): Loss 0.2950	LR: 6.437e-02	Score 90.587	Data time: 2.3861, Total iter time: 5.9581
thomas 04/08 18:56:04 ===> Epoch[155](46480/301): Loss 0.2841	LR: 6.434e-02	Score 91.193	Data time: 2.3504, Total iter time: 5.9263
thomas 04/08 19:00:03 ===> Epoch[155](46520/301): Loss 0.2765	LR: 6.431e-02	Score 91.313	Data time: 2.3276, Total iter time: 5.9065
thomas 04/08 19:04:06 ===> Epoch[155](46560/301): Loss 0.2685	LR: 6.428e-02	Score 91.754	Data time: 2.3879, Total iter time: 6.0090
thomas 04/08 19:07:59 ===> Epoch[155](46600/301): Loss 0.2554	LR: 6.425e-02	Score 91.839	Data time: 2.2794, Total iter time: 5.7414
thomas 04/08 19:11:53 ===> Epoch[155](46640/301): Loss 0.2784	LR: 6.422e-02	Score 91.040	Data time: 2.2926, Total iter time: 5.7861
thomas 04/08 19:16:07 ===> Epoch[156](46680/301): Loss 0.2810	LR: 6.419e-02	Score 91.027	Data time: 2.4374, Total iter time: 6.2603
thomas 04/08 19:20:19 ===> Epoch[156](46720/301): Loss 0.2894	LR: 6.415e-02	Score 90.802	Data time: 2.4893, Total iter time: 6.2122
thomas 04/08 19:24:09 ===> Epoch[156](46760/301): Loss 0.2664	LR: 6.412e-02	Score 91.609	Data time: 2.2506, Total iter time: 5.6704
thomas 04/08 19:28:21 ===> Epoch[156](46800/301): Loss 0.2675	LR: 6.409e-02	Score 91.486	Data time: 2.4499, Total iter time: 6.2205
thomas 04/08 19:32:25 ===> Epoch[156](46840/301): Loss 0.3324	LR: 6.406e-02	Score 89.552	Data time: 2.3753, Total iter time: 6.0342
thomas 04/08 19:36:22 ===> Epoch[156](46880/301): Loss 0.2864	LR: 6.403e-02	Score 90.887	Data time: 2.3394, Total iter time: 5.8546
thomas 04/08 19:40:36 ===> Epoch[156](46920/301): Loss 0.2907	LR: 6.400e-02	Score 90.913	Data time: 2.4649, Total iter time: 6.2615
thomas 04/08 19:44:31 ===> Epoch[157](46960/301): Loss 0.2840	LR: 6.397e-02	Score 90.987	Data time: 2.3189, Total iter time: 5.7935
thomas 04/08 19:48:14 ===> Epoch[157](47000/301): Loss 0.2689	LR: 6.393e-02	Score 91.568	Data time: 2.1489, Total iter time: 5.4862
thomas 04/08 19:48:15 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 19:48:15 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 19:50:19 101/312: Data time: 0.0030, Iter time: 1.2169	Loss 0.263 (AVG: 0.587)	Score 91.555 (AVG: 84.282)	mIOU 62.324 mAP 72.170 mAcc 73.078
IOU: 78.079 95.548 59.905 59.425 82.948 65.890 67.719 40.731 41.102 66.259 12.688 66.413 58.083 72.299 68.080 62.472 66.963 50.258 87.897 43.727
mAP: 78.828 97.110 62.296 55.865 86.271 88.919 71.165 57.046 51.029 79.332 40.316 59.875 61.617 78.129 78.622 88.011 85.648 75.726 91.554 56.039
mAcc: 92.131 97.943 77.924 67.060 88.222 99.578 75.018 47.521 42.993 87.351 16.119 85.978 71.771 80.437 77.584 78.282 67.053 54.148 92.408 62.046

thomas 04/08 19:52:19 201/312: Data time: 0.0026, Iter time: 0.5745	Loss 0.904 (AVG: 0.601)	Score 65.384 (AVG: 84.148)	mIOU 60.053 mAP 69.990 mAcc 70.441
IOU: 77.260 96.015 58.724 64.448 82.992 59.813 71.505 40.067 34.801 72.085 16.173 59.994 56.134 67.758 56.643 49.565 69.293 49.208 78.669 39.906
mAP: 78.272 97.130 62.069 64.459 86.793 81.921 73.100 55.950 47.552 70.203 39.096 57.372 64.703 76.730 64.386 86.416 86.583 78.847 76.623 51.597
mAcc: 91.105 98.195 77.942 72.666 87.824 98.617 79.365 46.396 36.780 91.712 21.682 78.040 68.423 74.847 64.428 54.271 69.503 52.626 84.035 60.360

thomas 04/08 19:54:23 301/312: Data time: 0.0031, Iter time: 0.5349	Loss 0.444 (AVG: 0.606)	Score 89.507 (AVG: 83.825)	mIOU 58.969 mAP 69.674 mAcc 69.624
IOU: 77.560 95.736 55.266 63.492 84.327 58.408 69.481 38.049 34.611 69.295 14.887 60.712 57.909 66.328 46.619 48.583 69.424 51.109 79.536 38.043
mAP: 79.303 96.819 58.043 65.358 88.389 80.675 71.856 55.873 46.626 69.070 39.185 59.919 66.706 76.482 58.152 85.176 85.160 79.462 80.606 50.625
mAcc: 91.693 98.061 74.217 71.463 89.235 97.035 79.600 43.575 37.159 89.377 21.021 79.394 69.000 71.815 53.519 56.532 69.827 54.823 86.598 58.545

thomas 04/08 19:54:38 312/312: Data time: 0.0029, Iter time: 0.2700	Loss 0.030 (AVG: 0.603)	Score 99.787 (AVG: 83.875)	mIOU 59.162 mAP 69.809 mAcc 69.744
IOU: 77.470 95.773 54.589 64.226 83.631 58.738 69.192 37.944 36.812 71.533 14.567 60.682 57.065 66.217 46.471 49.286 69.749 51.201 80.082 38.014
mAP: 79.024 96.891 58.536 65.876 88.270 80.421 72.172 55.957 47.296 69.376 38.395 59.919 66.145 77.143 58.152 85.205 85.429 79.695 81.170 51.107
mAcc: 91.508 98.076 73.315 72.165 88.322 97.079 79.656 43.409 39.686 89.888 20.219 79.394 67.712 72.351 53.519 57.272 70.153 54.962 86.971 59.225

thomas 04/08 19:54:38 Finished test. Elapsed time: 382.1726
thomas 04/08 19:54:38 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 19:58:40 ===> Epoch[157](47040/301): Loss 0.3047	LR: 6.390e-02	Score 90.640	Data time: 2.3296, Total iter time: 6.0017
thomas 04/08 20:02:36 ===> Epoch[157](47080/301): Loss 0.3154	LR: 6.387e-02	Score 90.160	Data time: 2.3081, Total iter time: 5.8212
thomas 04/08 20:06:42 ===> Epoch[157](47120/301): Loss 0.3155	LR: 6.384e-02	Score 90.406	Data time: 2.4006, Total iter time: 6.0678
thomas 04/08 20:10:30 ===> Epoch[157](47160/301): Loss 0.2978	LR: 6.381e-02	Score 90.482	Data time: 2.2473, Total iter time: 5.6294
thomas 04/08 20:14:28 ===> Epoch[157](47200/301): Loss 0.2692	LR: 6.378e-02	Score 91.509	Data time: 2.3384, Total iter time: 5.8759
thomas 04/08 20:18:38 ===> Epoch[157](47240/301): Loss 0.2710	LR: 6.374e-02	Score 91.314	Data time: 2.4273, Total iter time: 6.1747
thomas 04/08 20:22:34 ===> Epoch[158](47280/301): Loss 0.3169	LR: 6.371e-02	Score 90.169	Data time: 2.2745, Total iter time: 5.8510
thomas 04/08 20:26:34 ===> Epoch[158](47320/301): Loss 0.3008	LR: 6.368e-02	Score 90.631	Data time: 2.3425, Total iter time: 5.9123
thomas 04/08 20:30:34 ===> Epoch[158](47360/301): Loss 0.3308	LR: 6.365e-02	Score 89.624	Data time: 2.3704, Total iter time: 5.9432
thomas 04/08 20:34:24 ===> Epoch[158](47400/301): Loss 0.2711	LR: 6.362e-02	Score 91.692	Data time: 2.2307, Total iter time: 5.6708
thomas 04/08 20:38:30 ===> Epoch[158](47440/301): Loss 0.3002	LR: 6.359e-02	Score 90.589	Data time: 2.4082, Total iter time: 6.0685
thomas 04/08 20:42:19 ===> Epoch[158](47480/301): Loss 0.2820	LR: 6.356e-02	Score 91.089	Data time: 2.2447, Total iter time: 5.6467
thomas 04/08 20:45:56 ===> Epoch[158](47520/301): Loss 0.2917	LR: 6.352e-02	Score 90.609	Data time: 2.0862, Total iter time: 5.3631
thomas 04/08 20:49:50 ===> Epoch[159](47560/301): Loss 0.2735	LR: 6.349e-02	Score 91.421	Data time: 2.2523, Total iter time: 5.7565
thomas 04/08 20:54:01 ===> Epoch[159](47600/301): Loss 0.2924	LR: 6.346e-02	Score 90.780	Data time: 2.4325, Total iter time: 6.2171
thomas 04/08 20:58:03 ===> Epoch[159](47640/301): Loss 0.3038	LR: 6.343e-02	Score 90.542	Data time: 2.3478, Total iter time: 5.9567
thomas 04/08 21:02:03 ===> Epoch[159](47680/301): Loss 0.3271	LR: 6.340e-02	Score 90.295	Data time: 2.3225, Total iter time: 5.9178
thomas 04/08 21:06:09 ===> Epoch[159](47720/301): Loss 0.3145	LR: 6.337e-02	Score 90.074	Data time: 2.4094, Total iter time: 6.0685
thomas 04/08 21:09:47 ===> Epoch[159](47760/301): Loss 0.2934	LR: 6.333e-02	Score 90.697	Data time: 2.0869, Total iter time: 5.3903
thomas 04/08 21:13:54 ===> Epoch[159](47800/301): Loss 0.3000	LR: 6.330e-02	Score 90.374	Data time: 2.3908, Total iter time: 6.0926
thomas 04/08 21:17:51 ===> Epoch[159](47840/301): Loss 0.2501	LR: 6.327e-02	Score 91.997	Data time: 2.3158, Total iter time: 5.8312
thomas 04/08 21:22:01 ===> Epoch[160](47880/301): Loss 0.3012	LR: 6.324e-02	Score 90.744	Data time: 2.4259, Total iter time: 6.1713
thomas 04/08 21:26:00 ===> Epoch[160](47920/301): Loss 0.2957	LR: 6.321e-02	Score 90.574	Data time: 2.3112, Total iter time: 5.9219
thomas 04/08 21:29:58 ===> Epoch[160](47960/301): Loss 0.3274	LR: 6.318e-02	Score 89.628	Data time: 2.3005, Total iter time: 5.8685
thomas 04/08 21:34:09 ===> Epoch[160](48000/301): Loss 0.2878	LR: 6.314e-02	Score 90.900	Data time: 2.4071, Total iter time: 6.2046
thomas 04/08 21:34:11 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 21:34:11 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 21:36:11 101/312: Data time: 0.0029, Iter time: 0.4231	Loss 1.344 (AVG: 0.654)	Score 66.742 (AVG: 83.424)	mIOU 56.024 mAP 69.659 mAcc 68.118
IOU: 75.174 96.504 45.400 47.020 86.011 59.928 72.312 37.545 29.478 75.439 7.815 48.772 59.325 68.669 38.955 38.604 71.614 35.976 80.856 45.090
mAP: 80.085 98.065 46.046 64.634 90.862 79.480 71.824 55.882 41.666 73.195 26.314 53.342 66.421 70.679 71.982 89.122 88.338 79.647 94.421 51.176
mAcc: 89.806 99.013 57.703 79.221 87.899 98.071 82.275 47.969 30.650 96.261 12.241 74.781 81.781 72.218 62.366 44.605 72.901 37.203 81.481 53.913

thomas 04/08 21:38:03 201/312: Data time: 0.0024, Iter time: 0.8707	Loss 0.802 (AVG: 0.646)	Score 78.595 (AVG: 83.574)	mIOU 57.279 mAP 70.216 mAcc 68.611
IOU: 75.564 96.177 52.677 50.951 86.455 63.858 71.659 39.007 27.630 67.701 4.832 54.738 60.086 59.021 44.104 43.875 77.250 44.758 80.761 44.479
mAP: 79.195 97.851 53.016 65.330 89.466 81.333 73.157 54.747 45.430 69.056 24.272 59.292 67.310 68.017 64.454 92.141 92.609 82.858 89.198 55.579
mAcc: 89.684 99.061 63.465 80.691 88.812 95.790 82.710 50.276 28.751 91.986 6.671 81.243 80.393 62.739 59.862 48.248 78.183 46.596 81.361 55.707

thomas 04/08 21:40:07 301/312: Data time: 0.0025, Iter time: 0.6848	Loss 0.753 (AVG: 0.649)	Score 79.841 (AVG: 83.554)	mIOU 56.882 mAP 69.798 mAcc 68.369
IOU: 75.670 95.967 54.415 53.891 86.058 63.415 70.679 39.164 26.737 72.520 9.494 54.067 59.075 56.969 47.473 27.436 75.511 47.830 79.045 42.230
mAP: 77.135 97.713 55.835 67.595 90.114 82.060 73.516 53.161 42.695 70.166 30.507 59.128 66.369 68.625 66.187 83.832 93.164 81.240 82.621 54.295
mAcc: 90.011 98.922 65.316 82.957 88.479 96.719 82.662 49.983 27.677 92.251 14.045 84.233 78.756 61.455 63.626 28.627 77.692 49.577 79.856 54.524

thomas 04/08 21:40:24 312/312: Data time: 0.0030, Iter time: 0.9545	Loss 0.917 (AVG: 0.657)	Score 79.076 (AVG: 83.358)	mIOU 56.626 mAP 69.475 mAcc 68.142
IOU: 75.458 95.983 54.822 53.665 86.113 63.454 70.094 39.143 26.081 71.549 9.695 54.559 59.640 58.552 46.317 26.173 74.691 46.198 78.372 41.953
mAP: 76.993 97.699 55.863 67.170 89.871 82.516 72.134 53.526 42.272 69.213 32.071 58.885 66.673 70.374 64.339 83.862 91.896 80.194 80.455 53.496
mAcc: 90.023 98.929 65.487 82.591 88.549 96.593 82.432 49.714 27.162 91.967 13.966 84.475 79.377 62.938 63.200 27.133 77.004 47.758 79.168 54.382

thomas 04/08 21:40:24 Finished test. Elapsed time: 372.9255
thomas 04/08 21:40:24 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 21:44:11 ===> Epoch[160](48040/301): Loss 0.2712	LR: 6.311e-02	Score 91.592	Data time: 2.2151, Total iter time: 5.6122
thomas 04/08 21:48:08 ===> Epoch[160](48080/301): Loss 0.2744	LR: 6.308e-02	Score 91.349	Data time: 2.2608, Total iter time: 5.8408
thomas 04/08 21:52:10 ===> Epoch[160](48120/301): Loss 0.3036	LR: 6.305e-02	Score 90.556	Data time: 2.3208, Total iter time: 5.9836
thomas 04/08 21:56:09 ===> Epoch[160](48160/301): Loss 0.2797	LR: 6.302e-02	Score 91.015	Data time: 2.2727, Total iter time: 5.8970
thomas 04/08 21:59:55 ===> Epoch[161](48200/301): Loss 0.3389	LR: 6.299e-02	Score 89.604	Data time: 2.1751, Total iter time: 5.5812
thomas 04/08 22:03:47 ===> Epoch[161](48240/301): Loss 0.2477	LR: 6.296e-02	Score 92.018	Data time: 2.2504, Total iter time: 5.7282
thomas 04/08 22:07:50 ===> Epoch[161](48280/301): Loss 0.3073	LR: 6.292e-02	Score 90.447	Data time: 2.3764, Total iter time: 6.0052
thomas 04/08 22:11:51 ===> Epoch[161](48320/301): Loss 0.2887	LR: 6.289e-02	Score 90.914	Data time: 2.3502, Total iter time: 5.9450
thomas 04/08 22:15:39 ===> Epoch[161](48360/301): Loss 0.3021	LR: 6.286e-02	Score 90.569	Data time: 2.2018, Total iter time: 5.6291
thomas 04/08 22:19:39 ===> Epoch[161](48400/301): Loss 0.2742	LR: 6.283e-02	Score 91.494	Data time: 2.3010, Total iter time: 5.9219
thomas 04/08 22:23:27 ===> Epoch[161](48440/301): Loss 0.2978	LR: 6.280e-02	Score 90.760	Data time: 2.1882, Total iter time: 5.6302
thomas 04/08 22:27:35 ===> Epoch[162](48480/301): Loss 0.3541	LR: 6.277e-02	Score 88.752	Data time: 2.4120, Total iter time: 6.1076
thomas 04/08 22:31:29 ===> Epoch[162](48520/301): Loss 0.3392	LR: 6.273e-02	Score 89.545	Data time: 2.2738, Total iter time: 5.7952
thomas 04/08 22:35:20 ===> Epoch[162](48560/301): Loss 0.2966	LR: 6.270e-02	Score 90.658	Data time: 2.2595, Total iter time: 5.7113
thomas 04/08 22:39:18 ===> Epoch[162](48600/301): Loss 0.2744	LR: 6.267e-02	Score 91.436	Data time: 2.3015, Total iter time: 5.8528
thomas 04/08 22:43:06 ===> Epoch[162](48640/301): Loss 0.2334	LR: 6.264e-02	Score 92.601	Data time: 2.1891, Total iter time: 5.6395
thomas 04/08 22:46:55 ===> Epoch[162](48680/301): Loss 0.2525	LR: 6.261e-02	Score 91.823	Data time: 2.1906, Total iter time: 5.6456
thomas 04/08 22:50:35 ===> Epoch[162](48720/301): Loss 0.2597	LR: 6.258e-02	Score 91.731	Data time: 2.1585, Total iter time: 5.4368
thomas 04/08 22:54:31 ===> Epoch[162](48760/301): Loss 0.2919	LR: 6.254e-02	Score 90.817	Data time: 2.2761, Total iter time: 5.8000
thomas 04/08 22:58:35 ===> Epoch[163](48800/301): Loss 0.2969	LR: 6.251e-02	Score 90.947	Data time: 2.3593, Total iter time: 6.0191
thomas 04/08 23:02:27 ===> Epoch[163](48840/301): Loss 0.2938	LR: 6.248e-02	Score 90.824	Data time: 2.2724, Total iter time: 5.7194
thomas 04/08 23:06:26 ===> Epoch[163](48880/301): Loss 0.3248	LR: 6.245e-02	Score 89.937	Data time: 2.3057, Total iter time: 5.9058
thomas 04/08 23:10:14 ===> Epoch[163](48920/301): Loss 0.2858	LR: 6.242e-02	Score 90.993	Data time: 2.1943, Total iter time: 5.6346
thomas 04/08 23:14:29 ===> Epoch[163](48960/301): Loss 0.2784	LR: 6.239e-02	Score 91.188	Data time: 2.4950, Total iter time: 6.2867
thomas 04/08 23:18:35 ===> Epoch[163](49000/301): Loss 0.2909	LR: 6.236e-02	Score 91.038	Data time: 2.3900, Total iter time: 6.0638
thomas 04/08 23:18:36 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/08 23:18:37 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/08 23:20:48 101/312: Data time: 0.0027, Iter time: 0.7376	Loss 0.486 (AVG: 0.656)	Score 86.537 (AVG: 82.742)	mIOU 57.398 mAP 69.883 mAcc 67.393
IOU: 74.188 95.834 43.601 67.571 87.401 76.082 65.335 40.817 31.150 62.578 15.081 50.243 62.661 59.559 31.654 37.714 87.053 38.219 76.423 44.799
mAP: 77.608 97.276 61.127 75.957 88.711 82.273 73.138 58.667 47.403 62.794 45.851 59.174 66.269 69.911 51.950 84.265 90.976 79.087 76.110 49.103
mAcc: 88.650 98.685 65.254 80.808 91.855 95.521 68.551 55.369 33.216 90.695 22.686 69.707 82.150 66.363 37.646 37.921 88.004 39.166 77.260 58.351

thomas 04/08 23:22:43 201/312: Data time: 0.0026, Iter time: 0.6285	Loss 0.373 (AVG: 0.629)	Score 92.807 (AVG: 83.541)	mIOU 59.564 mAP 71.732 mAcc 70.313
IOU: 76.433 95.726 47.421 70.514 88.264 72.911 65.423 39.620 32.948 59.400 17.986 52.418 59.819 70.517 48.322 35.926 88.331 43.211 80.445 45.640
mAP: 77.750 97.100 59.841 73.064 89.667 80.869 74.204 54.197 50.971 67.127 50.329 59.646 67.380 79.157 62.001 86.096 91.082 79.505 81.594 53.061
mAcc: 89.319 98.730 69.540 80.506 92.438 94.077 69.053 55.420 34.609 90.589 27.690 73.657 81.490 76.509 58.896 38.186 89.124 43.840 82.435 60.143

thomas 04/08 23:24:46 301/312: Data time: 0.0026, Iter time: 0.7056	Loss 0.534 (AVG: 0.594)	Score 82.378 (AVG: 84.296)	mIOU 60.466 mAP 70.966 mAcc 71.028
IOU: 77.190 96.019 50.461 74.098 89.013 73.211 66.960 44.206 31.154 59.459 17.475 59.209 59.568 68.124 46.902 35.995 89.571 45.790 81.056 43.866
mAP: 78.617 97.534 59.798 75.562 89.962 79.561 73.806 58.149 47.001 65.174 44.600 60.858 67.499 77.045 58.242 79.291 92.944 78.876 82.854 51.953
mAcc: 89.175 98.836 72.569 84.017 92.672 94.563 70.772 59.566 32.751 90.881 27.964 78.057 80.025 73.918 56.897 37.752 90.705 46.517 82.600 60.316

thomas 04/08 23:24:59 312/312: Data time: 0.0027, Iter time: 0.2889	Loss 0.096 (AVG: 0.588)	Score 97.467 (AVG: 84.457)	mIOU 60.739 mAP 71.266 mAcc 71.266
IOU: 77.360 96.107 50.338 74.079 89.117 75.332 66.968 44.140 30.573 58.878 17.105 59.242 59.322 67.929 48.273 37.095 90.084 46.649 82.094 44.086
mAP: 79.001 97.572 59.951 75.562 90.107 80.770 74.033 58.616 46.540 65.094 43.434 60.879 67.353 77.045 59.536 80.568 93.267 79.362 83.713 52.922
mAcc: 89.140 98.859 72.681 84.017 92.800 95.201 70.886 59.155 32.276 90.947 27.567 77.961 80.101 73.918 58.210 38.810 91.166 47.442 83.602 60.591

thomas 04/08 23:24:59 Finished test. Elapsed time: 382.0639
thomas 04/08 23:24:59 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/08 23:28:41 ===> Epoch[163](49040/301): Loss 0.2771	LR: 6.232e-02	Score 91.072	Data time: 2.1499, Total iter time: 5.4904
thomas 04/08 23:32:39 ===> Epoch[164](49080/301): Loss 0.3054	LR: 6.229e-02	Score 90.233	Data time: 2.2832, Total iter time: 5.8781
thomas 04/08 23:36:27 ===> Epoch[164](49120/301): Loss 0.2804	LR: 6.226e-02	Score 91.130	Data time: 2.2030, Total iter time: 5.6189
thomas 04/08 23:40:16 ===> Epoch[164](49160/301): Loss 0.3109	LR: 6.223e-02	Score 89.990	Data time: 2.2415, Total iter time: 5.6491
thomas 04/08 23:44:22 ===> Epoch[164](49200/301): Loss 0.2814	LR: 6.220e-02	Score 90.908	Data time: 2.4067, Total iter time: 6.0666
thomas 04/08 23:48:21 ===> Epoch[164](49240/301): Loss 0.2796	LR: 6.217e-02	Score 91.088	Data time: 2.3312, Total iter time: 5.9235
thomas 04/08 23:52:24 ===> Epoch[164](49280/301): Loss 0.3000	LR: 6.213e-02	Score 90.672	Data time: 2.3229, Total iter time: 5.9954
thomas 04/08 23:56:16 ===> Epoch[164](49320/301): Loss 0.2954	LR: 6.210e-02	Score 90.455	Data time: 2.2141, Total iter time: 5.7300
thomas 04/09 00:00:16 ===> Epoch[164](49360/301): Loss 0.2962	LR: 6.207e-02	Score 90.513	Data time: 2.3044, Total iter time: 5.9193
thomas 04/09 00:04:14 ===> Epoch[165](49400/301): Loss 0.2884	LR: 6.204e-02	Score 90.514	Data time: 2.3032, Total iter time: 5.8765
thomas 04/09 00:08:15 ===> Epoch[165](49440/301): Loss 0.2496	LR: 6.201e-02	Score 92.253	Data time: 2.3729, Total iter time: 5.9461
thomas 04/09 00:12:26 ===> Epoch[165](49480/301): Loss 0.2787	LR: 6.198e-02	Score 90.987	Data time: 2.4437, Total iter time: 6.1978
thomas 04/09 00:16:25 ===> Epoch[165](49520/301): Loss 0.3042	LR: 6.194e-02	Score 90.749	Data time: 2.2975, Total iter time: 5.8986
thomas 04/09 00:20:11 ===> Epoch[165](49560/301): Loss 0.2903	LR: 6.191e-02	Score 90.765	Data time: 2.1555, Total iter time: 5.5853
thomas 04/09 00:24:03 ===> Epoch[165](49600/301): Loss 0.2565	LR: 6.188e-02	Score 91.715	Data time: 2.2002, Total iter time: 5.7270
thomas 04/09 00:27:48 ===> Epoch[165](49640/301): Loss 0.2439	LR: 6.185e-02	Score 92.380	Data time: 2.1623, Total iter time: 5.5336
thomas 04/09 00:31:44 ===> Epoch[166](49680/301): Loss 0.2786	LR: 6.182e-02	Score 91.245	Data time: 2.3039, Total iter time: 5.8102
thomas 04/09 00:35:32 ===> Epoch[166](49720/301): Loss 0.2787	LR: 6.179e-02	Score 91.459	Data time: 2.1892, Total iter time: 5.6206
thomas 04/09 00:39:28 ===> Epoch[166](49760/301): Loss 0.2659	LR: 6.175e-02	Score 91.659	Data time: 2.2666, Total iter time: 5.8328
thomas 04/09 00:43:18 ===> Epoch[166](49800/301): Loss 0.2897	LR: 6.172e-02	Score 90.848	Data time: 2.2002, Total iter time: 5.6848
thomas 04/09 00:47:07 ===> Epoch[166](49840/301): Loss 0.2832	LR: 6.169e-02	Score 91.063	Data time: 2.1835, Total iter time: 5.6425
thomas 04/09 00:51:18 ===> Epoch[166](49880/301): Loss 0.2957	LR: 6.166e-02	Score 90.502	Data time: 2.3846, Total iter time: 6.1786
thomas 04/09 00:55:22 ===> Epoch[166](49920/301): Loss 0.2889	LR: 6.163e-02	Score 90.653	Data time: 2.4002, Total iter time: 6.0174
thomas 04/09 00:59:10 ===> Epoch[166](49960/301): Loss 0.2720	LR: 6.160e-02	Score 91.573	Data time: 2.1771, Total iter time: 5.6217
thomas 04/09 01:03:00 ===> Epoch[167](50000/301): Loss 0.2936	LR: 6.156e-02	Score 91.175	Data time: 2.2053, Total iter time: 5.6864
thomas 04/09 01:03:02 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/09 01:03:02 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/09 01:05:07 101/312: Data time: 0.0031, Iter time: 0.4071	Loss 0.076 (AVG: 0.669)	Score 98.135 (AVG: 82.528)	mIOU 56.541 mAP 69.154 mAcc 67.954
IOU: 78.222 89.537 51.632 46.366 86.562 73.657 62.371 38.705 27.815 65.040 7.816 55.502 53.531 63.303 19.670 49.807 83.841 60.054 71.257 46.126
mAP: 78.190 95.071 59.707 71.313 85.435 86.557 62.651 58.241 44.229 71.342 30.761 56.078 64.025 81.976 43.855 73.901 95.037 84.603 86.386 53.715
mAcc: 93.345 92.477 63.389 75.761 88.343 90.428 74.699 46.076 28.417 91.398 8.349 61.244 81.857 83.149 31.254 58.896 85.301 63.987 75.083 65.623

thomas 04/09 01:06:56 201/312: Data time: 0.0879, Iter time: 0.8112	Loss 0.731 (AVG: 0.635)	Score 77.537 (AVG: 83.590)	mIOU 58.926 mAP 70.894 mAcc 70.272
IOU: 78.461 90.456 56.903 49.568 87.444 73.718 66.463 43.286 28.659 71.085 9.975 60.948 55.047 61.952 44.794 50.607 85.501 54.265 70.174 39.212
mAP: 78.669 95.607 60.667 74.365 87.624 80.826 68.280 60.366 47.457 69.741 33.107 57.762 67.579 83.289 61.734 78.235 95.810 83.693 81.658 51.404
mAcc: 92.349 93.764 69.427 78.154 89.282 89.653 77.190 52.526 29.467 90.542 10.461 67.590 81.621 83.512 61.686 56.337 86.819 60.312 75.331 59.414

thomas 04/09 01:08:51 301/312: Data time: 0.0024, Iter time: 1.1476	Loss 0.955 (AVG: 0.644)	Score 75.015 (AVG: 83.364)	mIOU 58.980 mAP 70.996 mAcc 70.559
IOU: 78.328 90.809 56.970 45.771 86.764 71.515 63.730 43.618 29.378 70.930 9.405 59.914 54.835 58.834 49.932 48.534 85.958 57.142 72.381 44.853
mAP: 78.351 95.497 60.144 69.976 87.906 81.720 67.406 60.702 47.489 70.335 31.803 57.815 68.191 83.927 65.523 83.165 94.659 83.902 78.570 52.844
mAcc: 92.560 94.115 67.941 73.637 89.055 88.954 73.923 53.429 30.184 91.937 9.803 67.814 83.576 82.752 67.677 52.542 86.897 63.585 76.317 64.490

thomas 04/09 01:09:02 312/312: Data time: 0.0024, Iter time: 0.3600	Loss 0.988 (AVG: 0.640)	Score 79.340 (AVG: 83.500)	mIOU 58.974 mAP 70.838 mAcc 70.464
IOU: 78.635 90.821 56.676 44.793 86.858 72.249 63.677 43.514 29.328 70.739 9.405 59.910 55.491 58.332 49.295 48.534 86.059 57.822 72.381 44.954
mAP: 78.763 95.571 59.763 67.979 88.141 81.169 68.154 60.171 48.200 70.335 31.803 57.815 68.095 83.342 63.389 83.165 94.758 84.087 78.570 53.488
mAcc: 92.607 94.079 67.932 73.141 89.169 88.484 74.474 53.368 30.124 91.937 9.803 67.814 82.491 82.702 66.377 52.542 86.985 64.211 76.317 64.721

thomas 04/09 01:09:02 Finished test. Elapsed time: 360.4787
thomas 04/09 01:09:02 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/09 01:12:59 ===> Epoch[167](50040/301): Loss 0.2759	LR: 6.153e-02	Score 91.374	Data time: 2.2691, Total iter time: 5.8407
thomas 04/09 01:16:49 ===> Epoch[167](50080/301): Loss 0.3054	LR: 6.150e-02	Score 90.425	Data time: 2.2348, Total iter time: 5.6884
thomas 04/09 01:20:45 ===> Epoch[167](50120/301): Loss 0.2969	LR: 6.147e-02	Score 90.609	Data time: 2.3310, Total iter time: 5.8250
thomas 04/09 01:24:43 ===> Epoch[167](50160/301): Loss 0.2982	LR: 6.144e-02	Score 90.771	Data time: 2.2700, Total iter time: 5.8648
thomas 04/09 01:28:30 ===> Epoch[167](50200/301): Loss 0.3006	LR: 6.141e-02	Score 90.665	Data time: 2.1611, Total iter time: 5.6033
thomas 04/09 01:32:17 ===> Epoch[167](50240/301): Loss 0.2511	LR: 6.137e-02	Score 92.299	Data time: 2.1912, Total iter time: 5.6063
thomas 04/09 01:36:29 ===> Epoch[168](50280/301): Loss 0.2584	LR: 6.134e-02	Score 91.706	Data time: 2.4132, Total iter time: 6.2067
thomas 04/09 01:40:20 ===> Epoch[168](50320/301): Loss 0.2795	LR: 6.131e-02	Score 90.803	Data time: 2.2370, Total iter time: 5.7086
thomas 04/09 01:44:16 ===> Epoch[168](50360/301): Loss 0.2705	LR: 6.128e-02	Score 91.454	Data time: 2.3786, Total iter time: 5.8310
thomas 04/09 01:48:13 ===> Epoch[168](50400/301): Loss 0.2937	LR: 6.125e-02	Score 90.736	Data time: 2.2991, Total iter time: 5.8580
thomas 04/09 01:52:09 ===> Epoch[168](50440/301): Loss 0.2596	LR: 6.122e-02	Score 91.805	Data time: 2.2681, Total iter time: 5.8256
thomas 04/09 01:56:01 ===> Epoch[168](50480/301): Loss 0.2852	LR: 6.118e-02	Score 90.959	Data time: 2.2098, Total iter time: 5.7271
thomas 04/09 01:59:55 ===> Epoch[168](50520/301): Loss 0.2505	LR: 6.115e-02	Score 91.994	Data time: 2.2369, Total iter time: 5.7696
thomas 04/09 02:04:07 ===> Epoch[168](50560/301): Loss 0.2673	LR: 6.112e-02	Score 91.283	Data time: 2.5055, Total iter time: 6.2258
thomas 04/09 02:08:29 ===> Epoch[169](50600/301): Loss 0.2971	LR: 6.109e-02	Score 90.650	Data time: 2.5821, Total iter time: 6.4697
thomas 04/09 02:12:34 ===> Epoch[169](50640/301): Loss 0.2909	LR: 6.106e-02	Score 91.183	Data time: 2.3827, Total iter time: 6.0343
thomas 04/09 02:16:34 ===> Epoch[169](50680/301): Loss 0.2695	LR: 6.103e-02	Score 91.217	Data time: 2.3208, Total iter time: 5.9420
thomas 04/09 02:20:25 ===> Epoch[169](50720/301): Loss 0.3004	LR: 6.099e-02	Score 90.366	Data time: 2.2289, Total iter time: 5.6929
thomas 04/09 02:24:15 ===> Epoch[169](50760/301): Loss 0.2953	LR: 6.096e-02	Score 90.778	Data time: 2.2274, Total iter time: 5.6787
thomas 04/09 02:28:34 ===> Epoch[169](50800/301): Loss 0.2685	LR: 6.093e-02	Score 91.898	Data time: 2.5866, Total iter time: 6.3898
thomas 04/09 02:32:45 ===> Epoch[169](50840/301): Loss 0.2580	LR: 6.090e-02	Score 91.679	Data time: 2.4986, Total iter time: 6.1908
thomas 04/09 02:36:41 ===> Epoch[170](50880/301): Loss 0.2927	LR: 6.087e-02	Score 90.921	Data time: 2.2834, Total iter time: 5.8069
thomas 04/09 02:40:32 ===> Epoch[170](50920/301): Loss 0.3033	LR: 6.084e-02	Score 90.495	Data time: 2.2367, Total iter time: 5.7068
thomas 04/09 02:44:16 ===> Epoch[170](50960/301): Loss 0.2904	LR: 6.080e-02	Score 90.885	Data time: 2.1776, Total iter time: 5.5418
thomas 04/09 02:48:22 ===> Epoch[170](51000/301): Loss 0.2697	LR: 6.077e-02	Score 91.267	Data time: 2.3863, Total iter time: 6.0717
thomas 04/09 02:48:24 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/09 02:48:24 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/09 02:50:27 101/312: Data time: 0.0033, Iter time: 0.3961	Loss 0.779 (AVG: 0.597)	Score 79.050 (AVG: 84.569)	mIOU 58.856 mAP 72.037 mAcc 68.921
IOU: 75.981 96.697 52.488 77.981 81.033 76.172 63.974 50.496 13.303 79.835 14.190 62.675 58.406 56.615 50.843 21.992 86.239 48.073 78.805 31.324
mAP: 78.204 98.185 63.365 76.011 87.259 77.957 77.619 65.716 40.732 61.914 47.570 62.165 70.413 72.952 71.652 82.347 96.940 76.485 83.543 49.704
mAcc: 91.227 98.884 59.527 89.975 83.433 95.566 69.462 70.267 14.273 88.391 15.569 84.701 75.047 58.502 69.993 21.995 86.700 51.395 79.600 73.907

thomas 04/09 02:52:40 201/312: Data time: 0.0040, Iter time: 0.5534	Loss 2.597 (AVG: 0.627)	Score 57.430 (AVG: 83.454)	mIOU 57.858 mAP 70.759 mAcc 67.737
IOU: 75.351 96.268 55.158 67.832 83.193 72.767 63.889 46.897 19.179 75.145 15.485 60.854 59.265 59.700 48.596 19.152 80.008 45.121 77.517 35.772
mAP: 77.920 98.118 64.167 69.495 87.640 80.871 70.994 61.886 44.327 63.973 41.610 62.032 70.262 76.690 64.485 72.848 91.569 76.937 88.562 50.800
mAcc: 90.688 98.814 61.667 80.529 85.678 94.742 69.512 67.100 19.960 88.977 16.480 84.517 74.880 61.758 67.415 19.630 80.965 48.335 78.142 64.947

thomas 04/09 02:54:55 301/312: Data time: 0.0027, Iter time: 1.3923	Loss 0.783 (AVG: 0.651)	Score 78.645 (AVG: 83.099)	mIOU 57.568 mAP 70.543 mAcc 67.420
IOU: 74.730 96.101 54.780 68.456 84.198 72.502 64.701 43.128 21.433 71.042 10.270 60.726 57.247 57.767 46.303 24.466 75.122 51.980 79.221 37.196
mAP: 77.469 97.906 62.621 72.063 88.127 80.946 71.743 60.387 43.159 62.926 37.508 63.865 69.375 75.964 62.367 75.922 90.176 80.849 87.335 50.145
mAcc: 90.116 98.753 62.572 80.497 86.790 95.298 71.295 61.826 22.233 87.728 10.828 84.075 71.833 60.484 63.714 25.490 75.700 55.010 79.998 64.156

thomas 04/09 02:55:06 312/312: Data time: 0.0025, Iter time: 0.2584	Loss 0.027 (AVG: 0.656)	Score 99.922 (AVG: 82.999)	mIOU 57.007 mAP 70.285 mAcc 66.940
IOU: 74.735 96.020 54.168 68.744 83.890 71.239 64.224 42.868 21.733 70.611 11.061 59.746 56.532 57.660 45.800 20.943 75.188 51.116 77.307 36.559
mAP: 77.386 97.938 62.672 71.774 88.294 80.946 71.619 59.817 43.413 62.811 39.594 63.865 68.545 76.648 61.054 75.959 90.612 80.880 82.020 49.858
mAcc: 90.134 98.720 62.240 80.668 86.419 95.298 70.692 61.639 22.610 86.375 11.692 84.075 71.067 60.377 63.245 21.673 75.754 53.924 78.040 64.153

thomas 04/09 02:55:06 Finished test. Elapsed time: 402.3124
thomas 04/09 02:55:06 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/09 02:59:15 ===> Epoch[170](51040/301): Loss 0.2957	LR: 6.074e-02	Score 90.461	Data time: 2.4795, Total iter time: 6.1580
thomas 04/09 03:03:01 ===> Epoch[170](51080/301): Loss 0.2980	LR: 6.071e-02	Score 90.580	Data time: 2.1921, Total iter time: 5.5628
thomas 04/09 03:06:55 ===> Epoch[170](51120/301): Loss 0.2766	LR: 6.068e-02	Score 91.131	Data time: 2.2841, Total iter time: 5.7849
thomas 04/09 03:10:46 ===> Epoch[170](51160/301): Loss 0.2543	LR: 6.065e-02	Score 91.985	Data time: 2.2179, Total iter time: 5.7077
thomas 04/09 03:14:58 ===> Epoch[171](51200/301): Loss 0.2739	LR: 6.061e-02	Score 91.356	Data time: 2.4346, Total iter time: 6.2000
thomas 04/09 03:19:05 ===> Epoch[171](51240/301): Loss 0.2842	LR: 6.058e-02	Score 90.895	Data time: 2.4414, Total iter time: 6.1037
thomas 04/09 03:23:15 ===> Epoch[171](51280/301): Loss 0.2886	LR: 6.055e-02	Score 90.607	Data time: 2.4745, Total iter time: 6.1937
thomas 04/09 03:27:09 ===> Epoch[171](51320/301): Loss 0.2864	LR: 6.052e-02	Score 91.380	Data time: 2.2777, Total iter time: 5.7616
thomas 04/09 03:31:13 ===> Epoch[171](51360/301): Loss 0.2607	LR: 6.049e-02	Score 91.639	Data time: 2.3509, Total iter time: 6.0348
thomas 04/09 03:35:04 ===> Epoch[171](51400/301): Loss 0.2521	LR: 6.045e-02	Score 91.915	Data time: 2.2009, Total iter time: 5.6845
thomas 04/09 03:39:11 ===> Epoch[171](51440/301): Loss 0.2928	LR: 6.042e-02	Score 90.902	Data time: 2.4049, Total iter time: 6.0908
thomas 04/09 03:43:16 ===> Epoch[172](51480/301): Loss 0.3152	LR: 6.039e-02	Score 90.199	Data time: 2.4511, Total iter time: 6.0613
thomas 04/09 03:47:30 ===> Epoch[172](51520/301): Loss 0.2635	LR: 6.036e-02	Score 91.577	Data time: 2.4751, Total iter time: 6.2686
thomas 04/09 03:51:16 ===> Epoch[172](51560/301): Loss 0.2808	LR: 6.033e-02	Score 91.096	Data time: 2.1677, Total iter time: 5.5904
thomas 04/09 03:55:06 ===> Epoch[172](51600/301): Loss 0.2847	LR: 6.030e-02	Score 90.889	Data time: 2.1953, Total iter time: 5.6680
thomas 04/09 03:58:41 ===> Epoch[172](51640/301): Loss 0.2568	LR: 6.026e-02	Score 91.868	Data time: 2.0976, Total iter time: 5.3199
thomas 04/09 04:02:44 ===> Epoch[172](51680/301): Loss 0.2537	LR: 6.023e-02	Score 91.959	Data time: 2.3194, Total iter time: 5.9832
thomas 04/09 04:06:50 ===> Epoch[172](51720/301): Loss 0.2693	LR: 6.020e-02	Score 91.495	Data time: 2.4395, Total iter time: 6.0822
thomas 04/09 04:10:53 ===> Epoch[172](51760/301): Loss 0.2787	LR: 6.017e-02	Score 91.106	Data time: 2.3497, Total iter time: 5.9864
thomas 04/09 04:14:42 ===> Epoch[173](51800/301): Loss 0.2544	LR: 6.014e-02	Score 91.718	Data time: 2.1912, Total iter time: 5.6339
thomas 04/09 04:18:28 ===> Epoch[173](51840/301): Loss 0.2534	LR: 6.011e-02	Score 92.117	Data time: 2.2010, Total iter time: 5.5848
thomas 04/09 04:22:21 ===> Epoch[173](51880/301): Loss 0.2943	LR: 6.007e-02	Score 90.820	Data time: 2.2434, Total iter time: 5.7552
thomas 04/09 04:26:36 ===> Epoch[173](51920/301): Loss 0.3013	LR: 6.004e-02	Score 90.988	Data time: 2.4615, Total iter time: 6.3043
thomas 04/09 04:30:41 ===> Epoch[173](51960/301): Loss 0.2759	LR: 6.001e-02	Score 91.207	Data time: 2.4401, Total iter time: 6.0369
thomas 04/09 04:34:40 ===> Epoch[173](52000/301): Loss 0.2941	LR: 5.998e-02	Score 90.726	Data time: 2.3775, Total iter time: 5.9158
thomas 04/09 04:34:42 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/09 04:34:42 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/09 04:36:41 101/312: Data time: 0.0028, Iter time: 0.4072	Loss 0.274 (AVG: 0.600)	Score 88.096 (AVG: 84.187)	mIOU 55.718 mAP 69.192 mAcc 68.397
IOU: 77.469 95.646 54.748 66.622 85.429 73.983 67.019 43.429 37.192 70.137 20.966 60.724 53.553 59.738 34.487 43.987 45.444 54.808 26.699 42.273
mAP: 78.706 96.162 58.306 74.886 86.745 84.509 76.628 60.293 48.271 77.444 40.342 65.123 71.410 76.467 68.028 67.558 73.168 82.907 41.334 55.556
mAcc: 89.935 98.982 76.033 84.212 90.720 97.997 71.450 61.526 41.617 75.558 27.287 71.875 90.250 83.163 81.549 45.245 45.730 57.405 27.348 50.052

thomas 04/09 04:38:38 201/312: Data time: 0.0024, Iter time: 0.6045	Loss 0.576 (AVG: 0.585)	Score 77.003 (AVG: 84.216)	mIOU 57.963 mAP 71.051 mAcc 70.776
IOU: 77.936 95.451 51.379 67.875 86.775 77.514 65.455 43.269 43.212 64.741 17.376 56.374 51.795 64.125 29.151 55.733 53.522 44.982 75.366 37.236
mAP: 80.304 96.275 53.566 75.437 88.949 86.835 74.095 60.470 51.994 70.083 41.587 60.495 68.172 78.211 64.049 79.771 78.000 77.753 81.384 53.585
mAcc: 89.415 98.851 72.299 84.808 92.120 97.286 70.557 60.993 48.928 71.277 22.975 69.850 85.157 84.889 79.026 60.631 53.871 47.284 80.168 45.142

thomas 04/09 04:40:34 301/312: Data time: 0.0028, Iter time: 0.4659	Loss 0.229 (AVG: 0.564)	Score 91.243 (AVG: 84.627)	mIOU 58.694 mAP 70.867 mAcc 71.228
IOU: 78.024 95.584 52.977 68.922 87.598 77.005 67.374 43.583 45.676 66.558 15.065 55.646 55.758 61.119 32.844 55.373 51.980 49.331 74.597 38.856
mAP: 79.815 95.932 58.377 74.291 89.265 85.371 73.459 58.987 49.951 71.134 39.104 59.312 68.035 76.695 62.925 80.231 78.637 79.927 82.719 53.177
mAcc: 89.157 98.895 73.842 84.614 92.750 96.179 72.706 60.753 52.892 71.670 20.082 70.046 86.299 82.232 76.491 63.073 52.267 51.855 81.050 47.696

thomas 04/09 04:40:46 312/312: Data time: 0.0034, Iter time: 0.4530	Loss 0.703 (AVG: 0.565)	Score 74.124 (AVG: 84.468)	mIOU 58.792 mAP 70.884 mAcc 71.276
IOU: 77.678 95.622 52.676 69.282 87.478 76.112 67.421 43.373 45.149 66.465 15.439 55.928 56.262 62.677 33.043 55.339 52.724 49.844 74.488 38.849
mAP: 79.337 95.944 58.332 73.263 89.332 85.423 73.388 59.451 49.488 71.134 38.996 59.972 68.137 77.547 62.983 80.231 79.053 80.535 82.684 52.441
mAcc: 88.926 98.901 73.610 84.983 92.636 96.207 72.832 60.139 52.280 71.670 20.653 70.278 86.446 83.168 75.726 63.073 53.013 52.401 80.766 47.806

thomas 04/09 04:40:46 Finished test. Elapsed time: 364.5160
thomas 04/09 04:40:46 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/09 04:44:31 ===> Epoch[173](52040/301): Loss 0.2567	LR: 5.995e-02	Score 91.915	Data time: 2.1641, Total iter time: 5.5501
thomas 04/09 04:48:33 ===> Epoch[174](52080/301): Loss 0.2567	LR: 5.992e-02	Score 91.938	Data time: 2.3258, Total iter time: 5.9674
thomas 04/09 04:52:52 ===> Epoch[174](52120/301): Loss 0.2606	LR: 5.988e-02	Score 91.690	Data time: 2.5199, Total iter time: 6.3927
thomas 04/09 04:56:50 ===> Epoch[174](52160/301): Loss 0.2705	LR: 5.985e-02	Score 91.689	Data time: 2.3670, Total iter time: 5.8881
thomas 04/09 05:00:33 ===> Epoch[174](52200/301): Loss 0.2930	LR: 5.982e-02	Score 90.711	Data time: 2.1666, Total iter time: 5.4971
thomas 04/09 05:04:37 ===> Epoch[174](52240/301): Loss 0.3496	LR: 5.979e-02	Score 88.790	Data time: 2.3177, Total iter time: 6.0161
thomas 04/09 05:08:19 ===> Epoch[174](52280/301): Loss 0.2889	LR: 5.976e-02	Score 90.650	Data time: 2.1292, Total iter time: 5.4985
thomas 04/09 05:12:26 ===> Epoch[174](52320/301): Loss 0.2871	LR: 5.972e-02	Score 90.865	Data time: 2.3657, Total iter time: 6.0838
thomas 04/09 05:16:26 ===> Epoch[174](52360/301): Loss 0.2780	LR: 5.969e-02	Score 91.311	Data time: 2.3818, Total iter time: 5.9320
thomas 04/09 05:20:41 ===> Epoch[175](52400/301): Loss 0.2945	LR: 5.966e-02	Score 90.798	Data time: 2.4871, Total iter time: 6.2963
thomas 04/09 05:24:31 ===> Epoch[175](52440/301): Loss 0.2733	LR: 5.963e-02	Score 91.454	Data time: 2.2310, Total iter time: 5.6833
thomas 04/09 05:28:28 ===> Epoch[175](52480/301): Loss 0.2961	LR: 5.960e-02	Score 90.775	Data time: 2.2765, Total iter time: 5.8496
thomas 04/09 05:32:10 ===> Epoch[175](52520/301): Loss 0.3115	LR: 5.957e-02	Score 90.159	Data time: 2.1347, Total iter time: 5.4885
thomas 04/09 05:36:06 ===> Epoch[175](52560/301): Loss 0.2872	LR: 5.953e-02	Score 90.644	Data time: 2.2762, Total iter time: 5.8149
thomas 04/09 05:40:06 ===> Epoch[175](52600/301): Loss 0.2634	LR: 5.950e-02	Score 91.417	Data time: 2.3770, Total iter time: 5.9304
thomas 04/09 05:44:10 ===> Epoch[175](52640/301): Loss 0.2553	LR: 5.947e-02	Score 91.774	Data time: 2.4378, Total iter time: 6.0154
thomas 04/09 05:48:31 ===> Epoch[176](52680/301): Loss 0.3096	LR: 5.944e-02	Score 90.360	Data time: 2.5299, Total iter time: 6.4409
thomas 04/09 05:52:24 ===> Epoch[176](52720/301): Loss 0.2947	LR: 5.941e-02	Score 90.554	Data time: 2.2011, Total iter time: 5.7480
thomas 04/09 05:56:08 ===> Epoch[176](52760/301): Loss 0.2396	LR: 5.938e-02	Score 92.213	Data time: 2.1606, Total iter time: 5.5403
thomas 04/09 06:00:01 ===> Epoch[176](52800/301): Loss 0.2794	LR: 5.934e-02	Score 91.293	Data time: 2.2501, Total iter time: 5.7540
thomas 04/09 06:03:50 ===> Epoch[176](52840/301): Loss 0.2908	LR: 5.931e-02	Score 90.730	Data time: 2.2761, Total iter time: 5.6540
thomas 04/09 06:07:48 ===> Epoch[176](52880/301): Loss 0.2653	LR: 5.928e-02	Score 91.521	Data time: 2.3373, Total iter time: 5.8653
thomas 04/09 06:11:51 ===> Epoch[176](52920/301): Loss 0.2629	LR: 5.925e-02	Score 91.699	Data time: 2.3634, Total iter time: 6.0005
thomas 04/09 06:15:49 ===> Epoch[176](52960/301): Loss 0.2441	LR: 5.922e-02	Score 92.193	Data time: 2.2958, Total iter time: 5.8776
thomas 04/09 06:19:31 ===> Epoch[177](53000/301): Loss 0.2895	LR: 5.918e-02	Score 90.739	Data time: 2.1147, Total iter time: 5.4608
thomas 04/09 06:19:32 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/09 06:19:32 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/09 06:21:31 101/312: Data time: 0.0025, Iter time: 0.7994	Loss 0.163 (AVG: 0.652)	Score 95.082 (AVG: 83.355)	mIOU 58.151 mAP 69.711 mAcc 68.709
IOU: 75.422 96.277 54.850 63.362 80.949 64.307 68.083 41.980 32.859 70.359 5.797 59.953 52.937 65.019 15.664 48.467 79.454 65.447 86.347 35.494
mAP: 77.829 98.006 55.145 68.078 82.331 83.146 63.351 65.444 47.893 71.669 24.379 67.837 64.284 82.049 45.442 86.794 92.301 86.541 76.011 55.680
mAcc: 92.901 98.445 61.309 78.821 83.078 97.010 73.298 60.210 34.724 86.791 5.918 89.736 66.746 73.328 17.116 58.402 85.404 67.139 93.890 49.915

thomas 04/09 06:23:34 201/312: Data time: 0.0024, Iter time: 0.6950	Loss 0.348 (AVG: 0.665)	Score 89.736 (AVG: 82.983)	mIOU 57.011 mAP 69.544 mAcc 67.075
IOU: 74.943 96.005 52.607 65.237 80.374 65.941 67.231 41.130 26.514 69.653 11.300 53.822 56.331 66.377 21.073 42.747 79.947 55.725 76.921 36.352
mAP: 77.845 97.432 54.330 72.738 83.782 81.179 67.534 63.685 48.505 67.237 37.718 64.767 60.679 80.500 44.373 81.269 93.257 81.742 76.325 55.992
mAcc: 93.452 98.341 59.259 79.437 82.665 94.597 73.769 58.822 27.676 87.340 11.596 78.940 69.625 73.890 22.744 49.533 86.315 56.641 87.545 49.313

thomas 04/09 06:25:32 301/312: Data time: 0.0026, Iter time: 0.8522	Loss 0.346 (AVG: 0.660)	Score 91.461 (AVG: 82.898)	mIOU 56.490 mAP 70.014 mAcc 67.116
IOU: 75.045 95.926 52.738 60.913 79.364 64.697 66.542 40.645 26.631 69.218 11.385 53.651 54.096 64.661 31.670 41.967 76.970 50.333 76.436 36.920
mAP: 78.642 97.084 57.141 69.979 83.090 83.375 69.839 61.575 47.228 67.376 39.686 60.525 62.990 79.762 49.449 81.784 90.176 82.639 82.336 55.610
mAcc: 93.525 98.212 59.805 78.925 81.990 95.291 71.931 58.049 27.894 85.703 12.074 79.664 70.557 71.735 34.732 51.143 84.692 51.098 85.697 49.605

thomas 04/09 06:25:47 312/312: Data time: 0.0032, Iter time: 0.8232	Loss 1.120 (AVG: 0.664)	Score 71.778 (AVG: 82.785)	mIOU 56.407 mAP 69.844 mAcc 67.095
IOU: 75.024 95.853 52.483 60.701 78.279 63.074 65.566 40.494 26.863 68.961 11.866 53.364 54.189 63.564 30.957 45.044 77.881 49.948 76.937 37.103
mAP: 78.681 97.111 57.763 69.487 82.594 81.572 69.168 60.905 47.097 67.376 40.758 60.784 62.416 78.873 48.324 83.668 90.719 82.463 81.136 55.988
mAcc: 93.501 98.160 59.791 78.698 80.873 94.690 71.180 57.920 28.144 85.703 12.541 79.864 70.499 70.389 33.912 54.126 85.303 50.826 85.662 50.120

thomas 04/09 06:25:47 Finished test. Elapsed time: 374.8573
thomas 04/09 06:25:47 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/09 06:30:02 ===> Epoch[177](53040/301): Loss 0.3070	LR: 5.915e-02	Score 90.743	Data time: 2.4870, Total iter time: 6.2766
thomas 04/09 06:34:10 ===> Epoch[177](53080/301): Loss 0.2689	LR: 5.912e-02	Score 91.420	Data time: 2.4321, Total iter time: 6.1312
thomas 04/09 06:38:10 ===> Epoch[177](53120/301): Loss 0.2883	LR: 5.909e-02	Score 90.971	Data time: 2.3036, Total iter time: 5.9051
thomas 04/09 06:42:01 ===> Epoch[177](53160/301): Loss 0.2451	LR: 5.906e-02	Score 92.229	Data time: 2.2320, Total iter time: 5.7201
thomas 04/09 06:45:44 ===> Epoch[177](53200/301): Loss 0.2451	LR: 5.903e-02	Score 92.050	Data time: 2.1461, Total iter time: 5.4868
thomas 04/09 06:49:42 ===> Epoch[177](53240/301): Loss 0.2584	LR: 5.899e-02	Score 91.643	Data time: 2.3019, Total iter time: 5.8726
thomas 04/09 06:54:02 ===> Epoch[178](53280/301): Loss 0.2558	LR: 5.896e-02	Score 92.051	Data time: 2.5747, Total iter time: 6.4050
thomas 04/09 06:58:05 ===> Epoch[178](53320/301): Loss 0.2709	LR: 5.893e-02	Score 91.581	Data time: 2.3910, Total iter time: 6.0061
thomas 04/09 07:02:02 ===> Epoch[178](53360/301): Loss 0.2875	LR: 5.890e-02	Score 91.176	Data time: 2.2710, Total iter time: 5.8300
thomas 04/09 07:05:52 ===> Epoch[178](53400/301): Loss 0.2872	LR: 5.887e-02	Score 90.850	Data time: 2.2367, Total iter time: 5.6760
thomas 04/09 07:09:38 ===> Epoch[178](53440/301): Loss 0.2855	LR: 5.883e-02	Score 90.803	Data time: 2.1732, Total iter time: 5.5582
thomas 04/09 07:13:49 ===> Epoch[178](53480/301): Loss 0.2550	LR: 5.880e-02	Score 91.871	Data time: 2.4566, Total iter time: 6.1940
thomas 04/09 07:18:07 ===> Epoch[178](53520/301): Loss 0.2365	LR: 5.877e-02	Score 92.318	Data time: 2.5859, Total iter time: 6.3682
thomas 04/09 07:22:05 ===> Epoch[178](53560/301): Loss 0.2573	LR: 5.874e-02	Score 91.577	Data time: 2.3487, Total iter time: 5.8819
thomas 04/09 07:25:52 ===> Epoch[179](53600/301): Loss 0.2899	LR: 5.871e-02	Score 90.963	Data time: 2.2324, Total iter time: 5.6134
thomas 04/09 07:29:34 ===> Epoch[179](53640/301): Loss 0.2749	LR: 5.868e-02	Score 91.389	Data time: 2.1359, Total iter time: 5.4799
thomas 04/09 07:33:36 ===> Epoch[179](53680/301): Loss 0.2708	LR: 5.864e-02	Score 91.496	Data time: 2.3547, Total iter time: 5.9812
thomas 04/09 07:37:39 ===> Epoch[179](53720/301): Loss 0.2611	LR: 5.861e-02	Score 91.724	Data time: 2.4018, Total iter time: 6.0039
thomas 04/09 07:41:44 ===> Epoch[179](53760/301): Loss 0.2883	LR: 5.858e-02	Score 90.980	Data time: 2.4477, Total iter time: 6.0539
thomas 04/09 07:46:01 ===> Epoch[179](53800/301): Loss 0.2954	LR: 5.855e-02	Score 90.831	Data time: 2.5367, Total iter time: 6.3432
thomas 04/09 07:49:56 ===> Epoch[179](53840/301): Loss 0.2707	LR: 5.852e-02	Score 91.337	Data time: 2.2941, Total iter time: 5.8072
thomas 04/09 07:53:42 ===> Epoch[180](53880/301): Loss 0.3156	LR: 5.848e-02	Score 89.958	Data time: 2.1762, Total iter time: 5.5705
thomas 04/09 07:57:37 ===> Epoch[180](53920/301): Loss 0.2771	LR: 5.845e-02	Score 91.695	Data time: 2.2711, Total iter time: 5.7907
thomas 04/09 08:01:32 ===> Epoch[180](53960/301): Loss 0.2874	LR: 5.842e-02	Score 90.848	Data time: 2.2877, Total iter time: 5.8108
thomas 04/09 08:05:49 ===> Epoch[180](54000/301): Loss 0.2788	LR: 5.839e-02	Score 91.180	Data time: 2.5179, Total iter time: 6.3429
thomas 04/09 08:05:51 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/09 08:05:51 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/09 08:07:51 101/312: Data time: 0.0039, Iter time: 0.8462	Loss 0.617 (AVG: 0.582)	Score 84.458 (AVG: 83.383)	mIOU 59.914 mAP 71.050 mAcc 71.682
IOU: 75.054 95.914 55.551 71.052 87.148 73.472 56.593 43.528 39.538 69.174 10.175 58.326 61.146 67.524 64.383 67.426 50.286 34.180 83.632 34.179
mAP: 76.959 97.168 56.732 72.733 90.933 79.799 73.450 65.786 53.893 79.605 39.782 56.390 74.053 76.391 58.401 94.078 78.254 71.728 82.590 42.279
mAcc: 84.036 98.970 67.441 75.269 94.492 97.848 63.059 72.063 43.548 95.105 10.384 63.371 80.701 90.002 73.722 95.002 50.384 35.476 85.845 56.929

thomas 04/09 08:10:03 201/312: Data time: 0.0031, Iter time: 0.5741	Loss 0.812 (AVG: 0.644)	Score 77.989 (AVG: 82.549)	mIOU 57.553 mAP 68.861 mAcc 68.645
IOU: 74.575 95.952 54.904 67.162 86.489 77.050 58.751 43.741 31.590 70.462 8.871 55.406 57.493 55.104 50.487 66.116 53.498 32.151 80.853 30.402
mAP: 74.963 97.015 57.150 66.515 89.875 84.875 70.931 65.907 47.073 67.626 35.491 55.476 65.744 78.939 58.172 89.426 82.548 66.141 82.490 40.860
mAcc: 84.127 98.827 67.491 72.418 93.638 97.899 66.989 67.452 34.709 92.580 8.958 63.362 74.611 89.891 55.122 79.202 53.660 33.355 82.967 55.648

thomas 04/09 08:12:02 301/312: Data time: 0.0023, Iter time: 0.7557	Loss 1.309 (AVG: 0.641)	Score 70.156 (AVG: 82.599)	mIOU 57.244 mAP 68.639 mAcc 67.854
IOU: 74.584 96.046 55.219 68.266 85.976 78.495 60.758 43.222 35.450 69.095 7.242 58.243 58.448 52.197 42.217 61.946 50.891 39.907 76.010 30.675
mAP: 75.564 97.111 59.115 68.372 89.206 82.491 69.439 63.380 50.104 65.300 36.413 58.506 67.109 77.241 50.820 89.097 84.439 72.404 75.486 41.179
mAcc: 84.275 98.872 66.442 73.062 93.204 94.610 69.643 67.259 38.782 89.119 7.301 65.502 75.947 84.251 46.358 72.667 51.083 41.669 77.951 59.073

thomas 04/09 08:12:13 312/312: Data time: 0.0029, Iter time: 0.3173	Loss 0.245 (AVG: 0.640)	Score 89.117 (AVG: 82.643)	mIOU 57.369 mAP 68.715 mAcc 67.968
IOU: 74.640 96.015 55.188 67.271 86.058 78.772 61.540 42.919 35.166 69.182 7.111 58.243 57.543 54.031 41.893 63.530 51.739 39.935 76.085 30.514
mAP: 75.812 97.131 59.349 68.243 89.341 82.744 69.774 63.222 49.863 65.633 35.286 58.506 67.109 77.125 49.926 89.562 85.144 72.953 76.163 41.406
mAcc: 84.239 98.877 66.415 71.917 93.285 94.773 70.115 67.186 38.634 88.576 7.172 65.502 75.947 85.406 45.975 74.694 51.925 41.734 78.022 58.973

thomas 04/09 08:12:13 Finished test. Elapsed time: 382.6353
thomas 04/09 08:12:13 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/09 08:16:09 ===> Epoch[180](54040/301): Loss 0.2429	LR: 5.836e-02	Score 92.267	Data time: 2.2903, Total iter time: 5.8266
thomas 04/09 08:19:57 ===> Epoch[180](54080/301): Loss 0.2657	LR: 5.833e-02	Score 91.457	Data time: 2.2096, Total iter time: 5.6175
thomas 04/09 08:23:40 ===> Epoch[180](54120/301): Loss 0.2419	LR: 5.829e-02	Score 92.242	Data time: 2.1883, Total iter time: 5.5032
thomas 04/09 08:27:41 ===> Epoch[180](54160/301): Loss 0.2779	LR: 5.826e-02	Score 90.901	Data time: 2.3399, Total iter time: 5.9350
thomas 04/09 08:31:57 ===> Epoch[181](54200/301): Loss 0.2742	LR: 5.823e-02	Score 91.341	Data time: 2.4956, Total iter time: 6.3156
thomas 04/09 08:36:01 ===> Epoch[181](54240/301): Loss 0.2626	LR: 5.820e-02	Score 91.676	Data time: 2.4044, Total iter time: 6.0384
thomas 04/09 08:39:57 ===> Epoch[181](54280/301): Loss 0.2417	LR: 5.817e-02	Score 92.243	Data time: 2.2782, Total iter time: 5.8266
thomas 04/09 08:43:53 ===> Epoch[181](54320/301): Loss 0.2629	LR: 5.813e-02	Score 92.007	Data time: 2.3055, Total iter time: 5.8169
thomas 04/09 08:47:54 ===> Epoch[181](54360/301): Loss 0.2806	LR: 5.810e-02	Score 91.323	Data time: 2.3777, Total iter time: 5.9637
thomas 04/09 08:52:02 ===> Epoch[181](54400/301): Loss 0.2761	LR: 5.807e-02	Score 91.240	Data time: 2.4392, Total iter time: 6.1265
thomas 04/09 08:56:14 ===> Epoch[181](54440/301): Loss 0.2703	LR: 5.804e-02	Score 91.447	Data time: 2.4093, Total iter time: 6.2156
thomas 04/09 09:00:12 ===> Epoch[181](54480/301): Loss 0.2865	LR: 5.801e-02	Score 90.978	Data time: 2.3400, Total iter time: 5.8783
thomas 04/09 09:04:12 ===> Epoch[182](54520/301): Loss 0.2740	LR: 5.797e-02	Score 91.389	Data time: 2.3250, Total iter time: 5.9223
thomas 04/09 09:08:28 ===> Epoch[182](54560/301): Loss 0.2844	LR: 5.794e-02	Score 90.949	Data time: 2.4907, Total iter time: 6.3466
thomas 04/09 09:12:33 ===> Epoch[182](54600/301): Loss 0.2663	LR: 5.791e-02	Score 91.517	Data time: 2.3988, Total iter time: 6.0389
thomas 04/09 09:16:50 ===> Epoch[182](54640/301): Loss 0.3035	LR: 5.788e-02	Score 90.603	Data time: 2.5142, Total iter time: 6.3320
thomas 04/09 09:21:03 ===> Epoch[182](54680/301): Loss 0.2520	LR: 5.785e-02	Score 92.029	Data time: 2.5086, Total iter time: 6.2526
thomas 04/09 09:25:17 ===> Epoch[182](54720/301): Loss 0.2532	LR: 5.782e-02	Score 91.693	Data time: 2.4597, Total iter time: 6.2717
thomas 04/09 09:29:17 ===> Epoch[182](54760/301): Loss 0.2755	LR: 5.778e-02	Score 91.250	Data time: 2.2967, Total iter time: 5.9209
thomas 04/09 09:33:19 ===> Epoch[183](54800/301): Loss 0.2359	LR: 5.775e-02	Score 92.431	Data time: 2.3535, Total iter time: 5.9716
thomas 04/09 09:37:11 ===> Epoch[183](54840/301): Loss 0.2708	LR: 5.772e-02	Score 91.225	Data time: 2.2758, Total iter time: 5.7187
thomas 04/09 09:41:02 ===> Epoch[183](54880/301): Loss 0.2423	LR: 5.769e-02	Score 92.326	Data time: 2.2751, Total iter time: 5.7274
thomas 04/09 09:45:05 ===> Epoch[183](54920/301): Loss 0.3106	LR: 5.766e-02	Score 90.592	Data time: 2.3722, Total iter time: 5.9995
thomas 04/09 09:49:13 ===> Epoch[183](54960/301): Loss 0.2826	LR: 5.762e-02	Score 91.396	Data time: 2.4096, Total iter time: 6.1252
thomas 04/09 09:53:25 ===> Epoch[183](55000/301): Loss 0.2957	LR: 5.759e-02	Score 90.926	Data time: 2.4702, Total iter time: 6.2272
thomas 04/09 09:53:27 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/09 09:53:27 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/09 09:55:40 101/312: Data time: 0.0027, Iter time: 0.6916	Loss 0.728 (AVG: 0.606)	Score 85.780 (AVG: 83.852)	mIOU 58.389 mAP 69.282 mAcc 68.944
IOU: 75.979 96.286 54.595 58.508 88.720 69.695 73.037 42.592 28.105 62.027 6.207 47.487 56.814 45.236 49.641 53.967 90.471 53.983 74.795 39.626
mAP: 77.232 96.747 56.423 71.120 87.414 81.325 74.860 61.337 48.080 60.188 25.048 56.145 54.084 74.623 65.553 91.537 97.219 73.713 79.843 53.153
mAcc: 87.869 98.970 76.668 84.274 93.313 94.683 85.781 55.566 29.404 66.284 7.760 53.366 68.541 69.262 57.900 62.731 92.054 56.220 75.720 62.523

thomas 04/09 09:57:49 201/312: Data time: 0.2083, Iter time: 1.3872	Loss 0.545 (AVG: 0.600)	Score 84.895 (AVG: 83.920)	mIOU 58.280 mAP 70.346 mAcc 69.131
IOU: 77.100 96.389 53.625 57.801 86.899 69.163 68.872 42.744 30.259 64.595 9.301 45.793 55.964 49.938 42.858 58.948 84.092 49.479 84.010 37.772
mAP: 78.200 97.314 56.824 73.990 89.073 81.424 74.257 61.332 49.385 64.076 30.612 55.464 58.982 78.136 59.920 91.011 89.855 75.110 84.903 57.056
mAcc: 88.998 98.879 76.308 82.500 91.553 95.359 81.602 53.442 31.111 71.182 12.726 51.188 67.678 79.801 49.924 68.376 85.129 51.163 84.943 60.763

thomas 04/09 10:00:02 301/312: Data time: 0.0966, Iter time: 0.7286	Loss 0.695 (AVG: 0.602)	Score 78.841 (AVG: 83.722)	mIOU 58.660 mAP 69.552 mAcc 68.944
IOU: 76.288 96.277 53.328 60.716 88.108 70.779 69.745 40.648 27.464 67.493 10.942 46.982 56.611 56.076 45.024 59.468 83.562 44.673 80.804 38.217
mAP: 76.591 96.888 56.806 74.675 89.590 80.214 73.923 57.049 46.261 66.130 33.902 54.186 59.581 74.937 59.819 89.317 89.274 74.446 81.283 56.164
mAcc: 88.524 98.817 75.505 84.540 92.634 94.133 82.397 50.778 28.058 72.894 15.319 52.521 68.024 81.503 51.541 66.780 84.493 46.004 81.673 62.739

thomas 04/09 10:00:18 312/312: Data time: 0.0024, Iter time: 0.6753	Loss 0.586 (AVG: 0.612)	Score 81.471 (AVG: 83.443)	mIOU 58.489 mAP 69.434 mAcc 68.773
IOU: 76.097 96.285 52.828 60.495 88.052 71.286 69.051 40.131 27.138 67.384 11.060 45.966 56.243 56.979 44.581 59.464 83.759 44.576 80.776 37.627
mAP: 76.278 96.850 55.967 73.635 89.257 80.522 73.420 56.841 45.411 66.498 34.227 54.913 59.674 75.738 59.189 89.317 89.468 74.599 81.579 55.295
mAcc: 88.284 98.816 74.761 84.541 92.632 94.245 82.371 49.817 27.750 72.761 15.495 51.561 67.462 82.251 50.843 66.780 84.696 45.891 81.686 62.825

thomas 04/09 10:00:18 Finished test. Elapsed time: 411.1384
thomas 04/09 10:00:18 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/09 10:04:32 ===> Epoch[183](55040/301): Loss 0.2712	LR: 5.756e-02	Score 91.370	Data time: 2.4538, Total iter time: 6.2659
thomas 04/09 10:08:42 ===> Epoch[183](55080/301): Loss 0.2367	LR: 5.753e-02	Score 92.436	Data time: 2.4412, Total iter time: 6.1868
thomas 04/09 10:12:58 ===> Epoch[184](55120/301): Loss 0.2642	LR: 5.750e-02	Score 91.520	Data time: 2.5289, Total iter time: 6.3332
thomas 04/09 10:17:14 ===> Epoch[184](55160/301): Loss 0.2701	LR: 5.746e-02	Score 91.476	Data time: 2.4575, Total iter time: 6.3150
thomas 04/09 10:21:39 ===> Epoch[184](55200/301): Loss 0.2759	LR: 5.743e-02	Score 91.051	Data time: 2.6039, Total iter time: 6.5529
thomas 04/09 10:25:51 ===> Epoch[184](55240/301): Loss 0.2939	LR: 5.740e-02	Score 90.606	Data time: 2.4222, Total iter time: 6.2089
thomas 04/09 10:30:02 ===> Epoch[184](55280/301): Loss 0.2652	LR: 5.737e-02	Score 91.586	Data time: 2.4262, Total iter time: 6.1983
thomas 04/09 10:34:14 ===> Epoch[184](55320/301): Loss 0.2453	LR: 5.734e-02	Score 92.252	Data time: 2.4661, Total iter time: 6.2380
thomas 04/09 10:38:36 ===> Epoch[184](55360/301): Loss 0.2533	LR: 5.730e-02	Score 91.872	Data time: 2.5187, Total iter time: 6.4717
thomas 04/09 10:42:56 ===> Epoch[185](55400/301): Loss 0.2328	LR: 5.727e-02	Score 92.465	Data time: 2.5163, Total iter time: 6.4126
thomas 04/09 10:47:08 ===> Epoch[185](55440/301): Loss 0.2666	LR: 5.724e-02	Score 91.289	Data time: 2.4634, Total iter time: 6.2189
thomas 04/09 10:51:24 ===> Epoch[185](55480/301): Loss 0.2774	LR: 5.721e-02	Score 91.490	Data time: 2.5040, Total iter time: 6.3479
thomas 04/09 10:55:37 ===> Epoch[185](55520/301): Loss 0.2678	LR: 5.718e-02	Score 91.479	Data time: 2.4532, Total iter time: 6.2382
thomas 04/09 10:59:44 ===> Epoch[185](55560/301): Loss 0.2608	LR: 5.715e-02	Score 91.941	Data time: 2.4094, Total iter time: 6.0960
thomas 04/09 11:04:12 ===> Epoch[185](55600/301): Loss 0.2356	LR: 5.711e-02	Score 92.519	Data time: 2.5443, Total iter time: 6.6158
thomas 04/09 11:08:28 ===> Epoch[185](55640/301): Loss 0.2815	LR: 5.708e-02	Score 91.053	Data time: 2.5192, Total iter time: 6.3310
thomas 04/09 11:12:34 ===> Epoch[185](55680/301): Loss 0.2753	LR: 5.705e-02	Score 91.220	Data time: 2.4258, Total iter time: 6.0789
thomas 04/09 11:16:42 ===> Epoch[186](55720/301): Loss 0.2861	LR: 5.702e-02	Score 90.985	Data time: 2.3656, Total iter time: 6.1266
thomas 04/09 11:20:56 ===> Epoch[186](55760/301): Loss 0.2923	LR: 5.699e-02	Score 90.711	Data time: 2.4898, Total iter time: 6.2750
thomas 04/09 11:25:11 ===> Epoch[186](55800/301): Loss 0.2206	LR: 5.695e-02	Score 93.121	Data time: 2.4912, Total iter time: 6.3025
thomas 04/09 11:29:29 ===> Epoch[186](55840/301): Loss 0.2421	LR: 5.692e-02	Score 92.302	Data time: 2.5193, Total iter time: 6.3650
thomas 04/09 11:33:46 ===> Epoch[186](55880/301): Loss 0.2523	LR: 5.689e-02	Score 92.100	Data time: 2.5222, Total iter time: 6.3454
thomas 04/09 11:37:50 ===> Epoch[186](55920/301): Loss 0.2417	LR: 5.686e-02	Score 92.394	Data time: 2.3592, Total iter time: 6.0135
thomas 04/09 11:42:07 ===> Epoch[186](55960/301): Loss 0.2581	LR: 5.683e-02	Score 91.993	Data time: 2.4752, Total iter time: 6.3482
thomas 04/09 11:46:31 ===> Epoch[187](56000/301): Loss 0.2626	LR: 5.679e-02	Score 91.447	Data time: 2.5650, Total iter time: 6.5021
thomas 04/09 11:46:32 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/09 11:46:32 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/09 11:48:47 101/312: Data time: 0.0030, Iter time: 0.5725	Loss 1.606 (AVG: 0.636)	Score 67.609 (AVG: 83.475)	mIOU 60.756 mAP 70.940 mAcc 72.168
IOU: 73.563 96.823 44.512 71.429 88.669 80.099 68.630 48.389 9.328 69.227 20.724 57.846 57.958 65.674 44.361 54.490 90.776 62.970 71.016 38.626
mAP: 78.177 96.102 55.026 77.033 90.930 82.205 75.523 64.631 37.807 68.847 36.851 62.832 73.132 77.707 56.553 84.857 97.751 83.419 65.911 53.516
mAcc: 81.753 98.865 81.293 85.970 94.019 86.083 74.362 70.294 9.408 81.241 24.867 85.682 80.812 72.220 49.789 57.229 91.993 66.368 72.346 78.758

thomas 04/09 11:51:08 201/312: Data time: 0.0028, Iter time: 0.4998	Loss 0.131 (AVG: 0.703)	Score 96.102 (AVG: 81.988)	mIOU 59.514 mAP 69.333 mAcc 71.053
IOU: 72.706 96.667 38.698 71.643 89.354 80.908 68.272 45.548 12.599 61.803 12.043 56.936 59.355 54.773 46.737 50.919 84.254 63.375 83.958 39.734
mAP: 77.345 96.878 49.232 71.130 90.230 83.185 73.279 63.076 38.455 66.927 33.591 60.877 68.242 68.503 52.935 82.771 94.998 85.296 77.977 51.733
mAcc: 81.519 98.746 80.382 83.197 93.904 89.126 76.088 62.282 12.897 80.207 14.544 83.103 80.558 57.999 54.060 62.344 84.945 67.876 85.842 71.449

thomas 04/09 11:53:13 301/312: Data time: 0.0025, Iter time: 0.4859	Loss 1.126 (AVG: 0.706)	Score 65.104 (AVG: 81.928)	mIOU 59.431 mAP 69.251 mAcc 70.863
IOU: 72.887 96.335 38.344 71.686 89.313 79.744 68.437 43.861 14.991 65.378 12.401 56.350 55.996 57.298 49.217 52.770 84.853 60.006 83.554 35.209
mAP: 77.873 96.838 48.496 72.538 88.793 81.685 72.364 61.629 39.627 67.315 33.373 57.526 67.060 67.044 58.156 85.302 93.960 84.131 81.260 50.046
mAcc: 81.854 98.638 80.152 80.880 93.534 88.663 76.340 62.626 15.268 82.519 14.623 80.544 79.733 61.073 57.854 64.958 85.551 63.165 86.514 62.762

thomas 04/09 11:53:28 312/312: Data time: 0.0027, Iter time: 1.2908	Loss 0.786 (AVG: 0.706)	Score 70.067 (AVG: 81.840)	mIOU 59.436 mAP 69.368 mAcc 70.824
IOU: 72.878 96.322 37.229 72.045 89.466 79.744 68.353 44.152 15.201 65.480 13.286 56.329 55.925 57.548 48.247 53.913 83.183 59.246 84.122 36.054
mAP: 77.765 96.900 48.429 72.874 88.918 81.685 72.299 61.665 39.843 67.225 34.446 58.063 66.993 66.985 57.899 84.779 93.838 84.372 81.845 50.530
mAcc: 81.833 98.635 80.063 81.670 93.613 88.663 76.466 63.112 15.471 81.961 15.603 80.704 79.163 61.378 56.852 65.994 83.952 62.168 86.968 62.216

thomas 04/09 11:53:28 Finished test. Elapsed time: 415.7978
thomas 04/09 11:53:28 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/09 11:57:52 ===> Epoch[187](56040/301): Loss 0.2441	LR: 5.676e-02	Score 92.253	Data time: 2.5671, Total iter time: 6.5157
thomas 04/09 12:01:48 ===> Epoch[187](56080/301): Loss 0.2660	LR: 5.673e-02	Score 91.922	Data time: 2.2809, Total iter time: 5.8200
thomas 04/09 12:06:01 ===> Epoch[187](56120/301): Loss 0.2566	LR: 5.670e-02	Score 91.812	Data time: 2.4239, Total iter time: 6.2395
thomas 04/09 12:10:22 ===> Epoch[187](56160/301): Loss 0.2550	LR: 5.667e-02	Score 91.740	Data time: 2.5833, Total iter time: 6.4455
thomas 04/09 12:14:43 ===> Epoch[187](56200/301): Loss 0.2694	LR: 5.663e-02	Score 91.466	Data time: 2.5496, Total iter time: 6.4485
thomas 04/09 12:19:14 ===> Epoch[187](56240/301): Loss 0.2388	LR: 5.660e-02	Score 92.361	Data time: 2.6601, Total iter time: 6.6860
thomas 04/09 12:23:20 ===> Epoch[187](56280/301): Loss 0.2919	LR: 5.657e-02	Score 91.045	Data time: 2.4295, Total iter time: 6.0779
thomas 04/09 12:27:32 ===> Epoch[188](56320/301): Loss 0.2774	LR: 5.654e-02	Score 91.138	Data time: 2.3881, Total iter time: 6.2252
thomas 04/09 12:31:55 ===> Epoch[188](56360/301): Loss 0.2410	LR: 5.651e-02	Score 92.103	Data time: 2.5915, Total iter time: 6.5122
thomas 04/09 12:35:52 ===> Epoch[188](56400/301): Loss 0.2176	LR: 5.647e-02	Score 93.115	Data time: 2.2969, Total iter time: 5.8450
thomas 04/09 12:40:11 ===> Epoch[188](56440/301): Loss 0.2646	LR: 5.644e-02	Score 91.659	Data time: 2.5386, Total iter time: 6.3761
thomas 04/09 12:44:17 ===> Epoch[188](56480/301): Loss 0.2451	LR: 5.641e-02	Score 92.131	Data time: 2.4066, Total iter time: 6.0732
thomas 04/09 12:48:37 ===> Epoch[188](56520/301): Loss 0.2581	LR: 5.638e-02	Score 91.703	Data time: 2.5395, Total iter time: 6.4090
thomas 04/09 12:52:26 ===> Epoch[188](56560/301): Loss 0.2553	LR: 5.635e-02	Score 91.902	Data time: 2.1978, Total iter time: 5.6743
thomas 04/09 12:56:50 ===> Epoch[189](56600/301): Loss 0.2612	LR: 5.631e-02	Score 91.360	Data time: 2.5574, Total iter time: 6.5087
thomas 04/09 13:01:17 ===> Epoch[189](56640/301): Loss 0.2375	LR: 5.628e-02	Score 92.282	Data time: 2.5991, Total iter time: 6.6077
thomas 04/09 13:05:29 ===> Epoch[189](56680/301): Loss 0.2876	LR: 5.625e-02	Score 91.420	Data time: 2.4884, Total iter time: 6.2200
thomas 04/09 13:09:47 ===> Epoch[189](56720/301): Loss 0.2610	LR: 5.622e-02	Score 91.887	Data time: 2.5224, Total iter time: 6.3954
thomas 04/09 13:14:05 ===> Epoch[189](56760/301): Loss 0.2472	LR: 5.619e-02	Score 92.136	Data time: 2.4526, Total iter time: 6.3657
thomas 04/09 13:18:16 ===> Epoch[189](56800/301): Loss 0.2245	LR: 5.615e-02	Score 92.676	Data time: 2.3636, Total iter time: 6.2000
thomas 04/09 13:22:40 ===> Epoch[189](56840/301): Loss 0.2699	LR: 5.612e-02	Score 91.334	Data time: 2.5692, Total iter time: 6.5081
thomas 04/09 13:26:50 ===> Epoch[189](56880/301): Loss 0.2524	LR: 5.609e-02	Score 91.823	Data time: 2.4965, Total iter time: 6.1891
thomas 04/09 13:31:37 ===> Epoch[190](56920/301): Loss 0.2478	LR: 5.606e-02	Score 91.944	Data time: 2.8178, Total iter time: 7.0778
thomas 04/09 13:35:36 ===> Epoch[190](56960/301): Loss 0.2733	LR: 5.603e-02	Score 91.485	Data time: 2.3303, Total iter time: 5.9100
thomas 04/09 13:39:38 ===> Epoch[190](57000/301): Loss 0.2541	LR: 5.599e-02	Score 92.055	Data time: 2.3376, Total iter time: 5.9673
thomas 04/09 13:39:39 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/09 13:39:39 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/09 13:41:51 101/312: Data time: 0.0028, Iter time: 0.5927	Loss 0.384 (AVG: 0.568)	Score 91.218 (AVG: 85.527)	mIOU 59.441 mAP 69.498 mAcc 68.681
IOU: 81.242 96.189 54.347 74.694 84.945 83.796 68.754 50.116 36.398 57.750 7.680 46.504 54.544 68.594 35.975 57.135 77.823 30.160 73.389 48.785
mAP: 80.555 95.120 56.443 72.780 89.484 82.532 71.270 63.014 49.684 67.600 27.775 52.021 68.211 82.222 62.415 75.948 89.033 65.784 82.019 56.042
mAcc: 93.069 98.691 81.836 80.244 90.382 92.433 80.799 62.374 38.517 81.972 8.373 48.730 80.350 77.856 55.557 59.856 77.968 30.851 73.946 59.823

thomas 04/09 13:44:02 201/312: Data time: 0.1459, Iter time: 0.8371	Loss 0.191 (AVG: 0.564)	Score 94.653 (AVG: 85.306)	mIOU 59.334 mAP 69.385 mAcc 68.886
IOU: 80.347 95.995 50.439 76.699 87.495 82.580 68.409 44.527 38.028 67.890 11.228 38.053 55.056 70.759 37.093 53.603 78.442 36.495 67.764 45.779
mAP: 80.766 95.399 52.796 75.172 89.349 81.325 71.995 60.697 47.429 65.546 35.397 50.329 66.929 82.668 61.976 77.361 89.115 67.241 84.042 52.162
mAcc: 92.461 98.501 77.501 83.682 92.415 94.436 79.865 55.059 40.386 90.539 12.754 39.910 82.769 77.133 58.644 59.987 78.890 37.424 68.121 57.234

thomas 04/09 13:46:12 301/312: Data time: 0.0024, Iter time: 0.3256	Loss 0.448 (AVG: 0.574)	Score 85.118 (AVG: 85.285)	mIOU 58.972 mAP 69.978 mAcc 68.380
IOU: 80.023 95.852 50.381 74.553 89.027 82.130 67.835 43.799 36.506 70.145 11.432 41.273 53.266 68.968 37.768 47.664 80.781 34.722 70.612 42.709
mAP: 80.762 94.897 53.740 73.990 90.378 83.173 72.594 60.259 48.603 69.021 37.695 52.314 66.181 79.846 63.529 80.152 88.892 66.002 83.230 54.293
mAcc: 92.409 98.565 74.023 80.479 93.211 94.513 78.303 55.355 38.879 91.467 12.903 43.284 83.894 75.703 58.675 52.486 81.399 35.614 70.962 55.480

thomas 04/09 13:46:24 312/312: Data time: 0.0029, Iter time: 0.4751	Loss 0.530 (AVG: 0.585)	Score 87.784 (AVG: 85.040)	mIOU 58.418 mAP 69.502 mAcc 67.882
IOU: 79.865 95.851 50.016 74.611 88.831 82.017 67.537 44.086 35.603 69.263 12.019 41.252 52.855 67.987 36.720 42.647 79.217 35.928 69.217 42.830
mAP: 80.521 94.869 53.652 73.064 89.858 83.173 71.564 59.778 47.928 68.746 38.147 52.440 66.300 79.774 62.291 80.029 89.057 66.698 77.931 54.220
mAcc: 92.298 98.581 73.631 80.490 93.229 94.513 78.109 55.987 37.838 91.468 13.544 43.273 82.692 76.022 58.098 45.848 79.786 36.793 69.609 55.841

thomas 04/09 13:46:24 Finished test. Elapsed time: 404.9551
thomas 04/09 13:46:24 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/09 13:50:57 ===> Epoch[190](57040/301): Loss 0.2776	LR: 5.596e-02	Score 91.432	Data time: 2.6524, Total iter time: 6.7314
thomas 04/09 13:55:14 ===> Epoch[190](57080/301): Loss 0.2785	LR: 5.593e-02	Score 91.409	Data time: 2.5377, Total iter time: 6.3634
thomas 04/09 13:59:39 ===> Epoch[190](57120/301): Loss 0.2523	LR: 5.590e-02	Score 91.899	Data time: 2.5591, Total iter time: 6.5305
thomas 04/09 14:03:47 ===> Epoch[190](57160/301): Loss 0.2684	LR: 5.587e-02	Score 91.785	Data time: 2.3897, Total iter time: 6.1170
thomas 04/09 14:07:50 ===> Epoch[191](57200/301): Loss 0.2626	LR: 5.583e-02	Score 91.523	Data time: 2.3494, Total iter time: 6.0024
thomas 04/09 14:11:54 ===> Epoch[191](57240/301): Loss 0.2621	LR: 5.580e-02	Score 91.744	Data time: 2.3862, Total iter time: 6.0290
thomas 04/09 14:16:24 ===> Epoch[191](57280/301): Loss 0.2621	LR: 5.577e-02	Score 91.720	Data time: 2.7359, Total iter time: 6.6733
thomas 04/09 14:20:38 ===> Epoch[191](57320/301): Loss 0.2204	LR: 5.574e-02	Score 92.914	Data time: 2.4836, Total iter time: 6.2658
thomas 04/09 14:24:52 ===> Epoch[191](57360/301): Loss 0.2463	LR: 5.571e-02	Score 92.251	Data time: 2.4487, Total iter time: 6.2704
thomas 04/09 14:28:56 ===> Epoch[191](57400/301): Loss 0.2168	LR: 5.567e-02	Score 92.941	Data time: 2.3334, Total iter time: 6.0166
thomas 04/09 14:33:10 ===> Epoch[191](57440/301): Loss 0.2485	LR: 5.564e-02	Score 92.052	Data time: 2.4291, Total iter time: 6.2755
thomas 04/09 14:37:38 ===> Epoch[191](57480/301): Loss 0.2647	LR: 5.561e-02	Score 91.838	Data time: 2.6317, Total iter time: 6.6284
thomas 04/09 14:42:09 ===> Epoch[192](57520/301): Loss 0.2613	LR: 5.558e-02	Score 91.661	Data time: 2.7268, Total iter time: 6.6798
thomas 04/09 14:46:15 ===> Epoch[192](57560/301): Loss 0.2399	LR: 5.555e-02	Score 92.398	Data time: 2.4139, Total iter time: 6.0781
thomas 04/09 14:50:15 ===> Epoch[192](57600/301): Loss 0.2408	LR: 5.551e-02	Score 92.384	Data time: 2.2910, Total iter time: 5.9163
thomas 04/09 14:54:30 ===> Epoch[192](57640/301): Loss 0.2591	LR: 5.548e-02	Score 91.597	Data time: 2.4587, Total iter time: 6.3024
thomas 04/09 14:58:43 ===> Epoch[192](57680/301): Loss 0.2648	LR: 5.545e-02	Score 91.835	Data time: 2.4604, Total iter time: 6.2382
thomas 04/09 15:03:10 ===> Epoch[192](57720/301): Loss 0.2508	LR: 5.542e-02	Score 92.215	Data time: 2.6073, Total iter time: 6.5723
thomas 04/09 15:07:45 ===> Epoch[192](57760/301): Loss 0.2410	LR: 5.539e-02	Score 92.330	Data time: 2.7573, Total iter time: 6.7962
thomas 04/09 15:12:04 ===> Epoch[193](57800/301): Loss 0.2203	LR: 5.535e-02	Score 92.809	Data time: 2.4874, Total iter time: 6.3993
thomas 04/09 15:16:06 ===> Epoch[193](57840/301): Loss 0.2626	LR: 5.532e-02	Score 91.634	Data time: 2.3483, Total iter time: 5.9849
thomas 04/09 15:19:48 ===> Epoch[193](57880/301): Loss 0.2257	LR: 5.529e-02	Score 92.694	Data time: 2.1150, Total iter time: 5.4723
thomas 04/09 15:24:04 ===> Epoch[193](57920/301): Loss 0.2450	LR: 5.526e-02	Score 92.481	Data time: 2.5028, Total iter time: 6.3443
thomas 04/09 15:28:30 ===> Epoch[193](57960/301): Loss 0.2647	LR: 5.523e-02	Score 91.752	Data time: 2.6661, Total iter time: 6.5565
thomas 04/09 15:32:54 ===> Epoch[193](58000/301): Loss 0.2449	LR: 5.519e-02	Score 91.978	Data time: 2.6232, Total iter time: 6.5230
thomas 04/09 15:32:55 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/09 15:32:56 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/09 15:35:07 101/312: Data time: 0.0031, Iter time: 0.5755	Loss 0.251 (AVG: 0.612)	Score 91.858 (AVG: 83.153)	mIOU 56.302 mAP 69.773 mAcc 66.642
IOU: 74.424 96.396 47.054 69.341 91.822 78.291 63.577 43.166 45.543 77.511 12.874 46.993 56.241 49.200 14.405 10.396 84.423 54.243 70.247 39.885
mAP: 77.760 97.917 55.482 69.709 90.169 79.669 77.938 68.971 52.538 75.364 35.577 59.393 58.696 67.052 30.726 73.463 95.801 82.353 86.961 59.925
mAcc: 84.547 99.111 70.292 81.804 93.839 93.077 82.639 76.694 50.770 86.803 18.518 53.535 75.495 78.414 15.881 10.458 84.883 56.129 70.863 49.079

thomas 04/09 15:37:13 201/312: Data time: 0.0028, Iter time: 1.0008	Loss 0.899 (AVG: 0.604)	Score 77.083 (AVG: 83.634)	mIOU 57.927 mAP 70.909 mAcc 68.175
IOU: 74.786 96.087 51.015 69.048 90.078 81.519 65.778 43.594 38.936 73.917 16.825 48.865 55.369 54.822 35.416 10.523 84.702 52.429 75.002 39.836
mAP: 77.512 97.679 53.048 73.055 91.862 82.706 77.815 67.349 51.082 72.326 44.168 57.624 59.882 75.961 50.763 73.982 94.241 82.010 80.182 54.928
mAcc: 85.065 98.989 73.066 81.834 92.446 93.760 83.217 78.217 42.213 83.612 24.081 53.261 77.590 81.948 37.844 10.786 85.096 54.545 75.735 50.192

thomas 04/09 15:39:22 301/312: Data time: 0.0025, Iter time: 0.4600	Loss 0.274 (AVG: 0.595)	Score 91.675 (AVG: 83.610)	mIOU 57.351 mAP 69.890 mAcc 67.565
IOU: 75.089 96.126 51.528 67.666 89.447 79.859 66.378 41.415 38.867 69.217 13.802 52.591 57.024 54.506 34.684 10.055 79.769 51.710 77.124 40.171
mAP: 77.711 97.411 52.230 71.539 91.398 85.118 72.909 63.099 49.932 72.143 36.912 57.201 62.523 75.125 50.802 72.943 91.211 81.298 82.170 54.123
mAcc: 85.193 98.912 73.925 79.882 92.454 92.463 82.059 74.972 43.263 80.388 18.982 58.050 81.420 80.662 36.687 10.269 80.067 53.849 77.882 49.918

thomas 04/09 15:39:35 312/312: Data time: 0.0028, Iter time: 0.3291	Loss 0.231 (AVG: 0.588)	Score 93.587 (AVG: 83.715)	mIOU 57.364 mAP 69.624 mAcc 67.507
IOU: 75.150 96.141 50.964 68.588 89.612 80.206 66.410 41.471 38.352 69.815 13.823 52.247 57.334 54.500 35.263 10.055 78.365 51.691 77.124 40.181
mAP: 77.649 97.444 51.830 71.475 91.240 84.311 72.549 63.032 49.735 71.929 36.595 57.261 62.500 73.987 51.449 72.943 89.697 81.298 82.170 53.385
mAcc: 85.301 98.909 73.086 80.912 92.620 92.631 82.282 74.439 42.638 80.893 18.931 57.629 81.141 80.827 37.213 10.269 78.653 53.849 77.882 50.045

thomas 04/09 15:39:35 Finished test. Elapsed time: 399.0574
thomas 04/09 15:39:35 Current best mIoU: 61.872 at iter 38000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/09 15:43:53 ===> Epoch[193](58040/301): Loss 0.2508	LR: 5.516e-02	Score 91.891	Data time: 2.5182, Total iter time: 6.3869
thomas 04/09 15:48:00 ===> Epoch[193](58080/301): Loss 0.2436	LR: 5.513e-02	Score 92.191	Data time: 2.4093, Total iter time: 6.0973
thomas 04/09 15:52:17 ===> Epoch[194](58120/301): Loss 0.2928	LR: 5.510e-02	Score 90.996	Data time: 2.5403, Total iter time: 6.3614
thomas 04/09 15:55:54 ===> Epoch[194](58160/301): Loss 0.2557	LR: 5.507e-02	Score 91.881	Data time: 2.1237, Total iter time: 5.3401
thomas 04/09 15:59:39 ===> Epoch[194](58200/301): Loss 0.2622	LR: 5.503e-02	Score 91.526	Data time: 2.1970, Total iter time: 5.5498
thomas 04/09 16:03:21 ===> Epoch[194](58240/301): Loss 0.2927	LR: 5.500e-02	Score 90.914	Data time: 2.1702, Total iter time: 5.4912
thomas 04/09 16:07:06 ===> Epoch[194](58280/301): Loss 0.2740	LR: 5.497e-02	Score 91.314	Data time: 2.2053, Total iter time: 5.5502
thomas 04/09 16:10:52 ===> Epoch[194](58320/301): Loss 0.2547	LR: 5.494e-02	Score 91.875	Data time: 2.1815, Total iter time: 5.5750
thomas 04/09 16:14:42 ===> Epoch[194](58360/301): Loss 0.2465	LR: 5.491e-02	Score 92.117	Data time: 2.2630, Total iter time: 5.6600
thomas 04/09 16:18:32 ===> Epoch[195](58400/301): Loss 0.2579	LR: 5.487e-02	Score 91.785	Data time: 2.2704, Total iter time: 5.6903
thomas 04/09 16:22:24 ===> Epoch[195](58440/301): Loss 0.2456	LR: 5.484e-02	Score 92.130	Data time: 2.2591, Total iter time: 5.7074
thomas 04/09 16:25:58 ===> Epoch[195](58480/301): Loss 0.2480	LR: 5.481e-02	Score 92.183	Data time: 2.1071, Total iter time: 5.2865
thomas 04/09 16:30:48 ===> Epoch[195](58520/301): Loss 0.2698	LR: 5.478e-02	Score 91.304	Data time: 3.0345, Total iter time: 7.1781
thomas 04/09 16:35:59 ===> Epoch[195](58560/301): Loss 0.2807	LR: 5.475e-02	Score 91.299	Data time: 3.3450, Total iter time: 7.6556
thomas 04/09 16:41:19 ===> Epoch[195](58600/301): Loss 0.2518	LR: 5.471e-02	Score 92.046	Data time: 3.4792, Total iter time: 7.9182
thomas 04/09 16:46:24 ===> Epoch[195](58640/301): Loss 0.2349	LR: 5.468e-02	Score 92.503	Data time: 3.2795, Total iter time: 7.5469
thomas 04/09 16:51:13 ===> Epoch[195](58680/301): Loss 0.2272	LR: 5.465e-02	Score 92.523	Data time: 3.1277, Total iter time: 7.1485
thomas 04/09 16:56:16 ===> Epoch[196](58720/301): Loss 0.2722	LR: 5.462e-02	Score 91.403	Data time: 3.2789, Total iter time: 7.4699
thomas 04/09 17:01:23 ===> Epoch[196](58760/301): Loss 0.2768	LR: 5.458e-02	Score 91.157	Data time: 3.3223, Total iter time: 7.5877
thomas 04/09 17:06:25 ===> Epoch[196](58800/301): Loss 0.2405	LR: 5.455e-02	Score 92.221	Data time: 3.2767, Total iter time: 7.4688
thomas 04/09 17:11:08 ===> Epoch[196](58840/301): Loss 0.2269	LR: 5.452e-02	Score 92.858	Data time: 3.0386, Total iter time: 6.9973
thomas 04/09 17:15:42 ===> Epoch[196](58880/301): Loss 0.2180	LR: 5.449e-02	Score 93.062	Data time: 2.9253, Total iter time: 6.7762
thomas 04/09 17:20:36 ===> Epoch[196](58920/301): Loss 0.2336	LR: 5.446e-02	Score 92.522	Data time: 3.2041, Total iter time: 7.2818
thomas 04/09 17:25:31 ===> Epoch[196](58960/301): Loss 0.2389	LR: 5.442e-02	Score 92.183	Data time: 3.1962, Total iter time: 7.2828
thomas 04/09 17:30:44 ===> Epoch[197](59000/301): Loss 0.2543	LR: 5.439e-02	Score 91.951	Data time: 3.3932, Total iter time: 7.7170
thomas 04/09 17:30:46 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/09 17:30:46 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/09 17:33:35 101/312: Data time: 0.0025, Iter time: 0.4844	Loss 0.554 (AVG: 0.562)	Score 81.955 (AVG: 84.761)	mIOU 62.873 mAP 72.132 mAcc 71.991
IOU: 77.064 95.421 53.708 76.117 88.715 75.467 67.914 43.373 47.679 74.265 15.158 48.653 63.214 76.326 54.874 48.292 75.442 59.822 79.151 36.806
mAP: 74.617 97.463 63.748 70.910 90.022 80.750 72.924 58.542 51.531 65.234 50.156 56.980 69.481 84.700 74.922 86.171 88.868 87.269 68.967 49.376
mAcc: 92.140 98.868 78.636 84.615 91.609 93.413 78.672 57.803 50.763 78.635 17.045 64.340 84.040 88.988 57.161 54.774 75.635 62.529 83.849 46.306

thomas 04/09 17:36:11 201/312: Data time: 0.0023, Iter time: 0.8019	Loss 0.311 (AVG: 0.532)	Score 87.665 (AVG: 85.608)	mIOU 62.533 mAP 70.960 mAcc 71.669
IOU: 78.042 95.775 53.597 76.479 89.636 78.664 68.708 43.911 37.936 71.844 11.737 41.822 64.503 67.431 50.124 55.723 78.392 60.834 84.937 40.571
mAP: 76.382 97.253 60.096 71.094 90.821 82.549 73.581 61.040 49.681 61.932 42.337 55.497 69.481 75.145 68.505 83.250 90.615 85.770 74.537 49.636
mAcc: 92.666 98.900 77.909 83.448 92.967 94.272 78.572 57.865 40.366 76.146 13.843 62.168 83.116 80.557 52.727 64.479 78.531 64.207 89.139 51.513

thomas 04/09 17:38:43 301/312: Data time: 0.0024, Iter time: 1.6983	Loss 0.981 (AVG: 0.538)	Score 68.231 (AVG: 85.410)	mIOU 62.569 mAP 70.748 mAcc 71.921
IOU: 78.318 95.818 56.584 75.350 88.663 79.377 68.225 43.136 39.280 71.268 11.032 50.955 61.474 60.252 49.761 55.656 81.629 58.381 85.645 40.579
mAP: 76.830 97.185 59.471 72.953 90.378 83.169 71.276 60.393 49.804 64.877 38.233 57.637 69.090 70.241 65.940 83.583 92.028 83.004 78.309 50.563
mAcc: 92.377 98.951 78.572 82.248 92.099 93.990 77.462 57.233 42.124 76.569 13.468 67.208 82.467 77.454 53.070 66.656 81.746 62.361 90.152 52.207

thomas 04/09 17:38:59 312/312: Data time: 0.0049, Iter time: 0.4588	Loss 0.262 (AVG: 0.542)	Score 93.009 (AVG: 85.282)	mIOU 62.239 mAP 70.854 mAcc 71.654
IOU: 78.303 95.842 56.517 75.208 88.656 79.194 67.943 42.983 39.394 70.779 10.838 51.524 60.602 60.995 46.260 56.348 80.314 58.403 85.075 39.596
mAP: 77.071 97.259 60.010 73.352 90.272 83.153 70.156 60.292 49.392 64.882 37.833 59.597 69.216 70.885 65.244 84.125 92.027 83.072 78.926 50.317
mAcc: 92.364 98.963 79.584 82.457 92.132 94.012 77.332 57.018 42.285 76.044 13.181 67.215 82.577 78.218 49.183 67.327 80.433 62.793 89.446 50.508

thomas 04/09 17:38:59 Finished test. Elapsed time: 493.3108
thomas 04/09 17:39:01 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/09 17:39:01 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/09 17:43:46 ===> Epoch[197](59040/301): Loss 0.2683	LR: 5.436e-02	Score 91.555	Data time: 3.0487, Total iter time: 7.0419
thomas 04/09 17:48:55 ===> Epoch[197](59080/301): Loss 0.2368	LR: 5.433e-02	Score 92.400	Data time: 3.3910, Total iter time: 7.6467
thomas 04/09 17:54:00 ===> Epoch[197](59120/301): Loss 0.2415	LR: 5.430e-02	Score 92.117	Data time: 3.2703, Total iter time: 7.5300
thomas 04/09 17:58:30 ===> Epoch[197](59160/301): Loss 0.2855	LR: 5.426e-02	Score 90.860	Data time: 2.9053, Total iter time: 6.6900
thomas 04/09 18:03:36 ===> Epoch[197](59200/301): Loss 0.2303	LR: 5.423e-02	Score 92.595	Data time: 3.2900, Total iter time: 7.5528
thomas 04/09 18:08:35 ===> Epoch[197](59240/301): Loss 0.2439	LR: 5.420e-02	Score 92.037	Data time: 3.2181, Total iter time: 7.4019
thomas 04/09 18:13:44 ===> Epoch[197](59280/301): Loss 0.2424	LR: 5.417e-02	Score 92.230	Data time: 3.3654, Total iter time: 7.6282
thomas 04/09 18:18:50 ===> Epoch[198](59320/301): Loss 0.2601	LR: 5.414e-02	Score 91.983	Data time: 3.3075, Total iter time: 7.5596
thomas 04/09 18:23:50 ===> Epoch[198](59360/301): Loss 0.2562	LR: 5.410e-02	Score 91.806	Data time: 3.2104, Total iter time: 7.3900
thomas 04/09 18:28:37 ===> Epoch[198](59400/301): Loss 0.2569	LR: 5.407e-02	Score 91.745	Data time: 3.0960, Total iter time: 7.1114
thomas 04/09 18:34:02 ===> Epoch[198](59440/301): Loss 0.2758	LR: 5.404e-02	Score 91.397	Data time: 3.4591, Total iter time: 8.0316
thomas 04/09 18:39:13 ===> Epoch[198](59480/301): Loss 0.2711	LR: 5.401e-02	Score 91.347	Data time: 3.3229, Total iter time: 7.6638
thomas 04/09 18:44:11 ===> Epoch[198](59520/301): Loss 0.2375	LR: 5.397e-02	Score 92.474	Data time: 3.1434, Total iter time: 7.3657
thomas 04/09 18:49:20 ===> Epoch[198](59560/301): Loss 0.2471	LR: 5.394e-02	Score 92.079	Data time: 3.2652, Total iter time: 7.6270
thomas 04/09 18:54:02 ===> Epoch[199](59600/301): Loss 0.2680	LR: 5.391e-02	Score 91.173	Data time: 3.0302, Total iter time: 6.9645
thomas 04/09 18:58:55 ===> Epoch[199](59640/301): Loss 0.2782	LR: 5.388e-02	Score 90.990	Data time: 3.1905, Total iter time: 7.2385
thomas 04/09 19:03:40 ===> Epoch[199](59680/301): Loss 0.2991	LR: 5.385e-02	Score 90.777	Data time: 3.1220, Total iter time: 7.0330
thomas 04/09 19:08:28 ===> Epoch[199](59720/301): Loss 0.2579	LR: 5.381e-02	Score 91.729	Data time: 3.0792, Total iter time: 7.1275
thomas 04/09 19:13:24 ===> Epoch[199](59760/301): Loss 0.2507	LR: 5.378e-02	Score 91.705	Data time: 3.2471, Total iter time: 7.3327
thomas 04/09 19:18:20 ===> Epoch[199](59800/301): Loss 0.2378	LR: 5.375e-02	Score 92.394	Data time: 3.2209, Total iter time: 7.3119
thomas 04/09 19:23:10 ===> Epoch[199](59840/301): Loss 0.2471	LR: 5.372e-02	Score 92.114	Data time: 3.1519, Total iter time: 7.1935
thomas 04/09 19:27:29 ===> Epoch[199](59880/301): Loss 0.2598	LR: 5.369e-02	Score 91.446	Data time: 2.7763, Total iter time: 6.4022
thomas 04/09 19:32:44 ===> Epoch[200](59920/301): Loss 0.2618	LR: 5.365e-02	Score 91.650	Data time: 3.3483, Total iter time: 7.7741
thomas 04/09 19:37:36 ===> Epoch[200](59960/301): Loss 0.2478	LR: 5.362e-02	Score 92.208	Data time: 3.1081, Total iter time: 7.2029
thomas 04/09 19:42:47 ===> Epoch[200](60000/301): Loss 0.2641	LR: 5.359e-02	Score 91.397	Data time: 3.3704, Total iter time: 7.6938
thomas 04/09 19:42:48 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/09 19:42:48 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/09 19:45:34 101/312: Data time: 0.0100, Iter time: 0.5365	Loss 1.540 (AVG: 0.651)	Score 49.458 (AVG: 83.002)	mIOU 60.008 mAP 70.512 mAcc 70.632
IOU: 77.195 96.346 45.055 68.157 82.332 71.145 70.119 43.395 41.871 74.474 19.405 48.872 63.028 39.068 45.451 41.178 90.369 57.155 90.835 34.716
mAP: 79.361 96.120 59.592 60.019 85.074 79.296 69.165 59.595 49.817 73.982 49.082 55.928 63.289 69.132 59.174 79.774 94.481 84.351 92.883 50.130
mAcc: 87.316 98.608 77.960 78.514 90.184 94.112 81.181 65.172 55.457 80.711 22.512 66.361 79.196 39.517 59.482 44.653 91.909 61.432 92.761 45.602

thomas 04/09 19:48:12 201/312: Data time: 0.0031, Iter time: 1.5194	Loss 0.786 (AVG: 0.605)	Score 80.684 (AVG: 83.921)	mIOU 59.814 mAP 70.711 mAcc 69.987
IOU: 77.514 96.377 45.090 73.518 85.820 74.427 70.869 44.791 39.250 74.708 18.037 54.545 60.758 35.751 44.729 40.592 89.862 49.294 85.650 34.704
mAP: 79.054 96.319 56.457 71.726 88.005 78.999 68.101 59.119 53.009 68.643 44.035 56.307 68.870 70.581 53.509 84.513 94.816 79.826 90.251 52.073
mAcc: 88.292 98.748 79.064 83.425 93.493 93.198 81.576 64.511 49.751 81.168 21.379 75.918 77.628 36.308 54.370 44.588 91.329 53.022 87.592 44.385

thomas 04/09 19:50:39 301/312: Data time: 0.0175, Iter time: 0.8674	Loss 0.654 (AVG: 0.617)	Score 83.578 (AVG: 83.924)	mIOU 59.393 mAP 70.392 mAcc 69.333
IOU: 76.770 96.132 46.547 73.284 87.007 76.171 69.951 43.937 41.157 73.596 17.396 56.258 60.630 34.371 48.638 26.169 89.337 51.118 82.311 37.079
mAP: 78.002 96.726 58.682 73.390 88.552 80.960 69.191 59.613 52.399 69.644 41.075 59.817 66.666 68.447 58.863 78.582 94.995 78.595 80.566 53.076
mAcc: 88.313 98.665 78.981 84.107 93.969 93.039 80.924 65.039 50.609 81.378 20.558 76.434 77.280 35.087 58.718 27.403 90.936 54.790 84.330 46.101

thomas 04/09 19:50:54 312/312: Data time: 0.0024, Iter time: 0.3178	Loss 0.151 (AVG: 0.608)	Score 94.306 (AVG: 84.087)	mIOU 59.493 mAP 70.764 mAcc 69.381
IOU: 76.964 96.184 46.212 73.488 87.095 76.117 70.371 44.548 41.468 73.520 18.084 56.159 60.422 34.995 46.509 26.670 89.418 51.471 82.679 37.476
mAP: 78.481 96.791 58.384 73.802 88.807 80.960 70.181 60.415 52.743 69.644 42.364 60.318 66.608 69.018 59.968 78.947 94.617 78.586 81.017 53.620
mAcc: 88.313 98.678 78.593 84.314 93.974 93.039 81.266 65.824 50.972 81.378 21.359 76.537 76.860 35.727 55.381 27.897 90.969 55.084 84.737 46.728

thomas 04/09 19:50:54 Finished test. Elapsed time: 485.5568
thomas 04/09 19:50:54 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/09 19:55:55 ===> Epoch[200](60040/301): Loss 0.2514	LR: 5.356e-02	Score 92.289	Data time: 3.2098, Total iter time: 7.4511
thomas 04/09 20:00:46 ===> Epoch[200](60080/301): Loss 0.2471	LR: 5.352e-02	Score 92.146	Data time: 3.1495, Total iter time: 7.1818
thomas 04/09 20:05:48 ===> Epoch[200](60120/301): Loss 0.2767	LR: 5.349e-02	Score 91.242	Data time: 3.2771, Total iter time: 7.4571
thomas 04/09 20:10:34 ===> Epoch[200](60160/301): Loss 0.2532	LR: 5.346e-02	Score 92.083	Data time: 3.0948, Total iter time: 7.0748
thomas 04/09 20:15:32 ===> Epoch[200](60200/301): Loss 0.2467	LR: 5.343e-02	Score 91.966	Data time: 3.1727, Total iter time: 7.3550
thomas 04/09 20:20:25 ===> Epoch[201](60240/301): Loss 0.2548	LR: 5.340e-02	Score 91.959	Data time: 3.1831, Total iter time: 7.2388
thomas 04/09 20:25:23 ===> Epoch[201](60280/301): Loss 0.2299	LR: 5.336e-02	Score 92.730	Data time: 3.2439, Total iter time: 7.3312
thomas 04/09 20:30:03 ===> Epoch[201](60320/301): Loss 0.2348	LR: 5.333e-02	Score 92.511	Data time: 2.9939, Total iter time: 6.9283
thomas 04/09 20:35:09 ===> Epoch[201](60360/301): Loss 0.2458	LR: 5.330e-02	Score 92.255	Data time: 3.2913, Total iter time: 7.5505
thomas 04/09 20:40:02 ===> Epoch[201](60400/301): Loss 0.2358	LR: 5.327e-02	Score 92.473	Data time: 3.1975, Total iter time: 7.2409
thomas 04/09 20:45:00 ===> Epoch[201](60440/301): Loss 0.2566	LR: 5.324e-02	Score 92.038	Data time: 3.2421, Total iter time: 7.3683
thomas 04/09 20:49:52 ===> Epoch[201](60480/301): Loss 0.2508	LR: 5.320e-02	Score 91.904	Data time: 3.1170, Total iter time: 7.2045
thomas 04/09 20:54:26 ===> Epoch[202](60520/301): Loss 0.2428	LR: 5.317e-02	Score 92.119	Data time: 2.9613, Total iter time: 6.7838
thomas 04/09 20:59:28 ===> Epoch[202](60560/301): Loss 0.2877	LR: 5.314e-02	Score 91.266	Data time: 3.2162, Total iter time: 7.4555
thomas 04/09 21:04:19 ===> Epoch[202](60600/301): Loss 0.2512	LR: 5.311e-02	Score 92.009	Data time: 3.1556, Total iter time: 7.1704
thomas 04/09 21:09:28 ===> Epoch[202](60640/301): Loss 0.2686	LR: 5.307e-02	Score 91.523	Data time: 3.3639, Total iter time: 7.6450
thomas 04/09 21:13:56 ===> Epoch[202](60680/301): Loss 0.2215	LR: 5.304e-02	Score 92.706	Data time: 2.9025, Total iter time: 6.6331
thomas 04/09 21:18:51 ===> Epoch[202](60720/301): Loss 0.2264	LR: 5.301e-02	Score 92.627	Data time: 3.1648, Total iter time: 7.2760
thomas 04/09 21:23:43 ===> Epoch[202](60760/301): Loss 0.2365	LR: 5.298e-02	Score 92.565	Data time: 3.2049, Total iter time: 7.1928
thomas 04/09 21:28:52 ===> Epoch[202](60800/301): Loss 0.2433	LR: 5.295e-02	Score 92.330	Data time: 3.3976, Total iter time: 7.6446
thomas 04/09 21:33:54 ===> Epoch[203](60840/301): Loss 0.2351	LR: 5.291e-02	Score 92.468	Data time: 3.3071, Total iter time: 7.4670
thomas 04/09 21:38:48 ===> Epoch[203](60880/301): Loss 0.2560	LR: 5.288e-02	Score 91.819	Data time: 3.1310, Total iter time: 7.2416
thomas 04/09 21:43:52 ===> Epoch[203](60920/301): Loss 0.2798	LR: 5.285e-02	Score 91.115	Data time: 3.3235, Total iter time: 7.5092
thomas 04/09 21:48:38 ===> Epoch[203](60960/301): Loss 0.2434	LR: 5.282e-02	Score 92.044	Data time: 3.1654, Total iter time: 7.0819
thomas 04/09 21:53:40 ===> Epoch[203](61000/301): Loss 0.2276	LR: 5.278e-02	Score 92.595	Data time: 3.2207, Total iter time: 7.4493
thomas 04/09 21:53:42 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/09 21:53:42 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/09 21:56:26 101/312: Data time: 0.0026, Iter time: 0.8534	Loss 0.104 (AVG: 0.588)	Score 97.071 (AVG: 83.917)	mIOU 58.652 mAP 70.895 mAcc 70.029
IOU: 76.295 95.948 45.582 79.197 87.559 69.014 71.098 47.812 17.849 65.491 25.658 47.814 48.901 56.315 31.039 49.593 83.396 48.354 89.640 36.485
mAP: 80.311 97.854 53.242 81.095 86.076 88.116 69.164 64.791 41.067 61.503 50.020 44.591 71.360 75.144 60.786 87.751 92.697 76.892 80.764 54.684
mAcc: 87.974 98.854 74.265 83.454 91.954 95.247 79.039 66.873 18.210 75.776 30.941 56.520 81.639 78.919 41.948 57.688 88.532 50.987 90.745 51.014

thomas 04/09 21:58:59 201/312: Data time: 0.0046, Iter time: 0.8111	Loss 1.049 (AVG: 0.544)	Score 78.164 (AVG: 84.930)	mIOU 60.819 mAP 71.681 mAcc 71.508
IOU: 77.498 96.105 45.210 81.146 88.060 76.539 69.989 47.329 22.122 68.970 23.560 44.785 59.332 67.687 32.223 51.652 82.980 54.906 81.715 44.571
mAP: 80.149 97.760 55.009 83.165 88.143 83.184 69.619 62.214 46.297 66.517 43.182 49.567 74.106 80.522 59.844 86.926 91.669 80.503 81.983 53.264
mAcc: 88.320 98.932 74.573 88.216 92.013 94.886 78.192 68.614 22.544 80.626 29.731 52.859 85.356 88.451 45.162 56.601 85.910 57.471 83.075 58.618

thomas 04/09 22:01:35 301/312: Data time: 0.0028, Iter time: 1.1940	Loss 1.039 (AVG: 0.567)	Score 78.223 (AVG: 84.621)	mIOU 61.047 mAP 71.962 mAcc 71.521
IOU: 77.101 96.123 47.511 76.054 88.253 75.184 71.686 47.979 22.367 69.872 16.375 50.071 60.371 64.845 40.234 52.512 83.587 54.633 81.339 44.849
mAP: 79.650 97.564 58.321 76.212 89.221 83.351 71.210 65.053 47.650 67.333 40.987 54.534 73.252 80.392 62.012 86.499 90.651 81.797 80.392 53.167
mAcc: 88.272 98.982 78.581 82.440 92.129 93.955 80.571 68.057 23.010 81.519 19.795 57.772 85.035 85.959 53.626 56.529 85.842 57.485 82.632 58.218

thomas 04/09 22:01:57 312/312: Data time: 0.0030, Iter time: 0.6797	Loss 0.931 (AVG: 0.563)	Score 83.436 (AVG: 84.724)	mIOU 61.413 mAP 72.026 mAcc 71.880
IOU: 77.118 96.094 48.875 75.877 88.373 75.401 71.674 47.663 23.127 69.658 16.527 51.355 60.720 65.514 40.484 53.233 83.904 55.766 81.819 45.086
mAP: 79.662 97.590 58.670 75.327 88.978 83.583 71.160 65.004 47.179 67.333 40.602 54.701 72.965 80.880 62.650 86.500 91.108 82.181 80.971 53.485
mAcc: 88.284 98.951 79.418 82.175 92.257 94.113 80.710 67.729 23.757 81.519 19.901 59.008 84.913 86.486 54.474 57.462 86.153 58.570 83.140 58.573

thomas 04/09 22:01:57 Finished test. Elapsed time: 495.2446
thomas 04/09 22:01:57 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/09 22:06:58 ===> Epoch[203](61040/301): Loss 0.2134	LR: 5.275e-02	Score 93.082	Data time: 3.2666, Total iter time: 7.4277
thomas 04/09 22:12:10 ===> Epoch[203](61080/301): Loss 0.2480	LR: 5.272e-02	Score 91.946	Data time: 3.3969, Total iter time: 7.7173
thomas 04/09 22:17:11 ===> Epoch[204](61120/301): Loss 0.2181	LR: 5.269e-02	Score 93.048	Data time: 3.2831, Total iter time: 7.4259
thomas 04/09 22:22:06 ===> Epoch[204](61160/301): Loss 0.2321	LR: 5.266e-02	Score 92.587	Data time: 3.2279, Total iter time: 7.2670
thomas 04/09 22:26:46 ===> Epoch[204](61200/301): Loss 0.2479	LR: 5.262e-02	Score 92.108	Data time: 3.0463, Total iter time: 6.9318
thomas 04/09 22:31:46 ===> Epoch[204](61240/301): Loss 0.2682	LR: 5.259e-02	Score 91.662	Data time: 3.2216, Total iter time: 7.3995
thomas 04/09 22:37:13 ===> Epoch[204](61280/301): Loss 0.2582	LR: 5.256e-02	Score 91.940	Data time: 3.5274, Total iter time: 8.0827
thomas 04/09 22:42:06 ===> Epoch[204](61320/301): Loss 0.2511	LR: 5.253e-02	Score 91.989	Data time: 3.1559, Total iter time: 7.2509
thomas 04/09 22:47:13 ===> Epoch[204](61360/301): Loss 0.2471	LR: 5.249e-02	Score 92.116	Data time: 3.3057, Total iter time: 7.5688
thomas 04/09 22:52:23 ===> Epoch[204](61400/301): Loss 0.2599	LR: 5.246e-02	Score 91.785	Data time: 3.3628, Total iter time: 7.6758
thomas 04/09 22:57:17 ===> Epoch[205](61440/301): Loss 0.2541	LR: 5.243e-02	Score 92.037	Data time: 3.1950, Total iter time: 7.2663
thomas 04/09 23:02:10 ===> Epoch[205](61480/301): Loss 0.2447	LR: 5.240e-02	Score 92.065	Data time: 3.1868, Total iter time: 7.2409
thomas 04/09 23:06:57 ===> Epoch[205](61520/301): Loss 0.2709	LR: 5.237e-02	Score 91.652	Data time: 3.0986, Total iter time: 7.0675
thomas 04/09 23:11:19 ===> Epoch[205](61560/301): Loss 0.2409	LR: 5.233e-02	Score 92.423	Data time: 2.8252, Total iter time: 6.4878
thomas 04/09 23:16:09 ===> Epoch[205](61600/301): Loss 0.2423	LR: 5.230e-02	Score 92.185	Data time: 3.1364, Total iter time: 7.1427
thomas 04/09 23:20:55 ===> Epoch[205](61640/301): Loss 0.2352	LR: 5.227e-02	Score 92.476	Data time: 3.1299, Total iter time: 7.0841
thomas 04/09 23:25:45 ===> Epoch[205](61680/301): Loss 0.2665	LR: 5.224e-02	Score 91.466	Data time: 3.1227, Total iter time: 7.1573
thomas 04/09 23:30:50 ===> Epoch[206](61720/301): Loss 0.2810	LR: 5.220e-02	Score 91.160	Data time: 3.3411, Total iter time: 7.5335
thomas 04/09 23:35:53 ===> Epoch[206](61760/301): Loss 0.2662	LR: 5.217e-02	Score 91.660	Data time: 3.2944, Total iter time: 7.4818
thomas 04/09 23:40:45 ===> Epoch[206](61800/301): Loss 0.2271	LR: 5.214e-02	Score 92.767	Data time: 3.1603, Total iter time: 7.2154
thomas 04/09 23:46:00 ===> Epoch[206](61840/301): Loss 0.2523	LR: 5.211e-02	Score 92.167	Data time: 3.4256, Total iter time: 7.7830
thomas 04/09 23:50:55 ===> Epoch[206](61880/301): Loss 0.2380	LR: 5.208e-02	Score 92.529	Data time: 3.2637, Total iter time: 7.3117
thomas 04/09 23:55:37 ===> Epoch[206](61920/301): Loss 0.2391	LR: 5.204e-02	Score 92.465	Data time: 3.0278, Total iter time: 6.9599
thomas 04/10 00:00:31 ===> Epoch[206](61960/301): Loss 0.2340	LR: 5.201e-02	Score 92.628	Data time: 3.2048, Total iter time: 7.2538
thomas 04/10 00:05:22 ===> Epoch[206](62000/301): Loss 0.2688	LR: 5.198e-02	Score 91.598	Data time: 3.1799, Total iter time: 7.1789
thomas 04/10 00:05:23 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 00:05:23 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 00:07:58 101/312: Data time: 0.0050, Iter time: 0.5023	Loss 0.852 (AVG: 0.556)	Score 75.862 (AVG: 85.257)	mIOU 62.723 mAP 73.831 mAcc 73.421
IOU: 78.783 96.298 47.979 62.308 89.078 79.667 71.679 47.378 30.029 71.504 15.509 60.135 61.465 61.744 47.820 55.388 86.801 55.294 90.301 45.305
mAP: 78.625 97.059 61.985 63.625 90.492 84.720 73.835 65.983 49.773 69.386 52.796 58.449 63.118 91.499 55.550 97.178 90.768 82.851 91.866 57.067
mAcc: 91.921 98.815 71.835 67.443 92.832 94.240 86.125 52.671 33.434 87.540 16.851 69.279 83.232 84.742 65.672 73.994 88.134 60.348 91.322 57.989

thomas 04/10 00:10:38 201/312: Data time: 0.0231, Iter time: 0.5404	Loss 0.397 (AVG: 0.541)	Score 85.198 (AVG: 85.570)	mIOU 62.402 mAP 72.356 mAcc 72.373
IOU: 79.593 96.202 51.440 68.288 88.414 74.829 72.089 45.330 38.547 66.515 15.509 53.670 59.512 66.858 43.624 54.214 86.362 57.255 83.536 46.258
mAP: 80.593 97.581 60.160 68.107 90.852 81.646 71.057 62.801 50.809 69.064 48.653 54.850 64.832 87.802 60.837 92.138 92.268 80.622 81.123 51.335
mAcc: 92.063 98.798 76.533 76.977 92.597 92.862 84.908 50.351 42.528 85.148 16.497 62.924 78.721 87.223 54.440 60.113 87.285 63.832 84.595 59.068

thomas 04/10 00:13:18 301/312: Data time: 0.0139, Iter time: 0.4640	Loss 0.276 (AVG: 0.557)	Score 92.484 (AVG: 85.451)	mIOU 61.940 mAP 72.484 mAcc 71.807
IOU: 79.325 96.103 51.312 71.003 88.397 74.526 71.819 44.303 39.192 65.224 13.439 56.000 58.365 64.422 49.700 44.634 85.800 55.903 84.496 44.844
mAP: 80.469 97.267 61.482 72.368 90.538 81.249 72.698 61.158 49.498 66.877 44.138 57.329 65.054 85.086 67.202 90.918 93.033 81.259 81.241 50.808
mAcc: 92.160 98.734 76.810 80.224 93.112 91.145 83.510 49.153 42.660 85.963 14.226 63.491 79.348 85.859 60.378 48.141 86.798 61.891 85.582 56.946

thomas 04/10 00:13:39 312/312: Data time: 0.0033, Iter time: 1.0302	Loss 0.731 (AVG: 0.554)	Score 84.721 (AVG: 85.499)	mIOU 61.868 mAP 72.344 mAcc 71.668
IOU: 79.384 96.152 51.158 71.892 88.034 74.876 71.618 44.235 38.529 65.198 13.172 55.999 59.052 63.418 49.009 44.634 85.775 55.903 84.496 44.833
mAP: 80.354 97.284 61.487 71.740 90.135 81.766 72.578 60.710 49.455 67.107 43.639 57.329 65.851 83.659 66.741 90.918 93.033 81.259 81.241 50.591
mAcc: 92.202 98.727 76.848 81.109 92.886 91.114 83.296 49.222 41.828 86.090 14.102 63.491 79.101 84.224 59.470 48.141 86.798 61.891 85.582 57.237

thomas 04/10 00:13:39 Finished test. Elapsed time: 495.6021
thomas 04/10 00:13:39 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 00:18:27 ===> Epoch[207](62040/301): Loss 0.2524	LR: 5.195e-02	Score 91.855	Data time: 3.1169, Total iter time: 7.1270
thomas 04/10 00:23:36 ===> Epoch[207](62080/301): Loss 0.2670	LR: 5.191e-02	Score 91.774	Data time: 3.3079, Total iter time: 7.6271
thomas 04/10 00:28:39 ===> Epoch[207](62120/301): Loss 0.2733	LR: 5.188e-02	Score 91.376	Data time: 3.2932, Total iter time: 7.4938
thomas 04/10 00:33:34 ===> Epoch[207](62160/301): Loss 0.2573	LR: 5.185e-02	Score 91.757	Data time: 3.1837, Total iter time: 7.2965
thomas 04/10 00:38:06 ===> Epoch[207](62200/301): Loss 0.2141	LR: 5.182e-02	Score 92.920	Data time: 2.9419, Total iter time: 6.7172
thomas 04/10 00:43:18 ===> Epoch[207](62240/301): Loss 0.2538	LR: 5.179e-02	Score 91.930	Data time: 3.3769, Total iter time: 7.7034
thomas 04/10 00:48:23 ===> Epoch[207](62280/301): Loss 0.2570	LR: 5.175e-02	Score 92.007	Data time: 3.3190, Total iter time: 7.5433
thomas 04/10 00:53:27 ===> Epoch[208](62320/301): Loss 0.2489	LR: 5.172e-02	Score 92.007	Data time: 3.3007, Total iter time: 7.4989
thomas 04/10 00:58:26 ===> Epoch[208](62360/301): Loss 0.2443	LR: 5.169e-02	Score 92.206	Data time: 3.2785, Total iter time: 7.4045
thomas 04/10 01:03:16 ===> Epoch[208](62400/301): Loss 0.2566	LR: 5.166e-02	Score 91.883	Data time: 3.1519, Total iter time: 7.1691
thomas 04/10 01:08:08 ===> Epoch[208](62440/301): Loss 0.2488	LR: 5.162e-02	Score 92.184	Data time: 3.2046, Total iter time: 7.2211
thomas 04/10 01:12:55 ===> Epoch[208](62480/301): Loss 0.2373	LR: 5.159e-02	Score 92.472	Data time: 3.1316, Total iter time: 7.0915
thomas 04/10 01:17:56 ===> Epoch[208](62520/301): Loss 0.2422	LR: 5.156e-02	Score 92.292	Data time: 3.2556, Total iter time: 7.4506
thomas 04/10 01:22:24 ===> Epoch[208](62560/301): Loss 0.2367	LR: 5.153e-02	Score 92.524	Data time: 2.8807, Total iter time: 6.6069
thomas 04/10 01:27:41 ===> Epoch[208](62600/301): Loss 0.2518	LR: 5.149e-02	Score 92.113	Data time: 3.4277, Total iter time: 7.8352
thomas 04/10 01:32:42 ===> Epoch[209](62640/301): Loss 0.2729	LR: 5.146e-02	Score 91.274	Data time: 3.2553, Total iter time: 7.4526
thomas 04/10 01:37:30 ===> Epoch[209](62680/301): Loss 0.2434	LR: 5.143e-02	Score 91.979	Data time: 3.1096, Total iter time: 7.1063
thomas 04/10 01:42:29 ===> Epoch[209](62720/301): Loss 0.2487	LR: 5.140e-02	Score 92.152	Data time: 3.2676, Total iter time: 7.4044
thomas 04/10 01:47:12 ===> Epoch[209](62760/301): Loss 0.2403	LR: 5.137e-02	Score 92.368	Data time: 3.0161, Total iter time: 6.9919
thomas 04/10 01:51:39 ===> Epoch[209](62800/301): Loss 0.2507	LR: 5.133e-02	Score 92.059	Data time: 2.9106, Total iter time: 6.6026
thomas 04/10 01:56:57 ===> Epoch[209](62840/301): Loss 0.2422	LR: 5.130e-02	Score 92.069	Data time: 3.4279, Total iter time: 7.8468
thomas 04/10 02:02:07 ===> Epoch[209](62880/301): Loss 0.2363	LR: 5.127e-02	Score 92.480	Data time: 3.3745, Total iter time: 7.6721
thomas 04/10 02:07:04 ===> Epoch[210](62920/301): Loss 0.2361	LR: 5.124e-02	Score 92.247	Data time: 3.1801, Total iter time: 7.3324
thomas 04/10 02:12:01 ===> Epoch[210](62960/301): Loss 0.2234	LR: 5.120e-02	Score 92.903	Data time: 3.2110, Total iter time: 7.3229
thomas 04/10 02:17:01 ===> Epoch[210](63000/301): Loss 0.2237	LR: 5.117e-02	Score 92.623	Data time: 3.2847, Total iter time: 7.4323
thomas 04/10 02:17:03 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 02:17:03 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 02:19:40 101/312: Data time: 0.0033, Iter time: 0.7829	Loss 0.244 (AVG: 0.567)	Score 92.740 (AVG: 84.600)	mIOU 61.637 mAP 73.510 mAcc 72.400
IOU: 78.674 96.084 56.060 69.114 85.016 77.614 62.708 40.660 43.238 71.574 25.441 51.951 49.698 69.658 39.647 47.721 81.059 57.953 85.250 43.617
mAP: 80.953 97.450 59.033 73.552 88.001 84.742 67.437 59.564 55.552 80.330 44.099 56.328 71.748 79.183 65.406 87.234 89.979 84.446 88.497 56.663
mAcc: 91.515 98.764 73.882 87.066 88.509 96.591 68.577 49.745 51.129 95.471 35.144 63.186 90.505 73.274 46.684 51.124 81.435 63.243 88.232 53.918

thomas 04/10 02:22:32 201/312: Data time: 0.1071, Iter time: 1.7655	Loss 0.267 (AVG: 0.571)	Score 91.193 (AVG: 84.791)	mIOU 60.775 mAP 71.270 mAcc 71.178
IOU: 77.266 96.348 56.090 67.221 88.279 79.244 64.485 41.916 45.730 71.695 16.658 50.395 47.623 61.458 36.820 51.844 76.455 54.623 84.697 46.649
mAP: 77.976 98.008 58.696 70.571 88.303 83.626 69.050 57.416 53.951 71.976 36.756 54.546 69.335 72.059 61.212 87.760 88.900 82.734 85.561 56.969
mAcc: 90.903 98.875 75.192 84.686 91.947 93.447 69.509 52.149 54.067 93.827 22.735 64.701 90.239 64.107 43.698 56.121 76.886 57.944 87.549 54.971

thomas 04/10 02:25:02 301/312: Data time: 0.0025, Iter time: 0.6295	Loss 0.433 (AVG: 0.562)	Score 91.486 (AVG: 85.068)	mIOU 61.329 mAP 71.648 mAcc 71.939
IOU: 78.166 96.193 57.219 65.217 88.177 76.830 64.452 43.194 46.555 69.842 18.348 54.491 48.250 64.337 45.290 50.280 77.392 55.140 84.058 43.159
mAP: 79.338 97.578 58.349 71.906 89.306 83.717 69.029 58.492 52.942 70.201 39.911 54.806 67.906 76.077 64.946 89.390 90.096 82.359 81.811 54.797
mAcc: 90.850 98.754 76.666 84.460 91.499 93.487 69.335 54.693 54.407 93.276 25.081 67.771 90.680 68.331 53.704 52.902 77.752 58.381 86.516 50.238

thomas 04/10 02:25:17 312/312: Data time: 0.0025, Iter time: 0.9534	Loss 0.469 (AVG: 0.561)	Score 86.032 (AVG: 85.130)	mIOU 61.489 mAP 71.804 mAcc 71.967
IOU: 78.138 96.219 56.736 66.036 88.258 76.775 64.704 42.813 46.292 70.085 18.752 54.895 49.216 63.421 46.045 50.280 77.600 55.962 84.058 43.499
mAP: 79.122 97.623 57.921 72.550 89.541 83.346 69.285 58.221 53.100 70.690 40.399 54.801 68.400 76.370 65.314 89.390 90.288 82.571 81.811 55.348
mAcc: 90.918 98.760 75.592 85.136 91.550 93.330 69.631 54.675 53.860 92.594 25.630 68.094 90.685 67.220 54.431 52.902 77.955 59.221 86.516 50.641

thomas 04/10 02:25:17 Finished test. Elapsed time: 494.2968
thomas 04/10 02:25:18 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 02:30:15 ===> Epoch[210](63040/301): Loss 0.2397	LR: 5.114e-02	Score 92.120	Data time: 3.2045, Total iter time: 7.3575
thomas 04/10 02:35:23 ===> Epoch[210](63080/301): Loss 0.2433	LR: 5.111e-02	Score 92.284	Data time: 3.3774, Total iter time: 7.5942
thomas 04/10 02:40:35 ===> Epoch[210](63120/301): Loss 0.2511	LR: 5.107e-02	Score 92.221	Data time: 3.3914, Total iter time: 7.7211
thomas 04/10 02:45:38 ===> Epoch[210](63160/301): Loss 0.2183	LR: 5.104e-02	Score 93.115	Data time: 3.2639, Total iter time: 7.4854
thomas 04/10 02:50:27 ===> Epoch[210](63200/301): Loss 0.2596	LR: 5.101e-02	Score 91.899	Data time: 3.1197, Total iter time: 7.1541
thomas 04/10 02:55:34 ===> Epoch[211](63240/301): Loss 0.2764	LR: 5.098e-02	Score 90.872	Data time: 3.3619, Total iter time: 7.5932
thomas 04/10 03:00:32 ===> Epoch[211](63280/301): Loss 0.2820	LR: 5.095e-02	Score 91.175	Data time: 3.2937, Total iter time: 7.3834
thomas 04/10 03:05:42 ===> Epoch[211](63320/301): Loss 0.2427	LR: 5.091e-02	Score 92.421	Data time: 3.3059, Total iter time: 7.6533
thomas 04/10 03:10:44 ===> Epoch[211](63360/301): Loss 0.2260	LR: 5.088e-02	Score 92.545	Data time: 3.3036, Total iter time: 7.4684
thomas 04/10 03:15:59 ===> Epoch[211](63400/301): Loss 0.2059	LR: 5.085e-02	Score 93.264	Data time: 3.3967, Total iter time: 7.7983
thomas 04/10 03:21:04 ===> Epoch[211](63440/301): Loss 0.2316	LR: 5.082e-02	Score 92.751	Data time: 3.2806, Total iter time: 7.5508
thomas 04/10 03:26:38 ===> Epoch[211](63480/301): Loss 0.2227	LR: 5.078e-02	Score 92.923	Data time: 3.5505, Total iter time: 8.2520
thomas 04/10 03:31:25 ===> Epoch[212](63520/301): Loss 0.2278	LR: 5.075e-02	Score 92.898	Data time: 3.1241, Total iter time: 7.1215
thomas 04/10 03:36:11 ===> Epoch[212](63560/301): Loss 0.2341	LR: 5.072e-02	Score 92.384	Data time: 3.0288, Total iter time: 7.0476
thomas 04/10 03:41:20 ===> Epoch[212](63600/301): Loss 0.2599	LR: 5.069e-02	Score 91.470	Data time: 3.3033, Total iter time: 7.6427
thomas 04/10 03:46:21 ===> Epoch[212](63640/301): Loss 0.2529	LR: 5.065e-02	Score 91.927	Data time: 3.2893, Total iter time: 7.4650
thomas 04/10 03:51:21 ===> Epoch[212](63680/301): Loss 0.2308	LR: 5.062e-02	Score 92.727	Data time: 3.2316, Total iter time: 7.4210
thomas 04/10 03:56:24 ===> Epoch[212](63720/301): Loss 0.2488	LR: 5.059e-02	Score 92.190	Data time: 3.3136, Total iter time: 7.4745
thomas 04/10 04:01:25 ===> Epoch[212](63760/301): Loss 0.2346	LR: 5.056e-02	Score 92.501	Data time: 3.2141, Total iter time: 7.4563
thomas 04/10 04:06:34 ===> Epoch[212](63800/301): Loss 0.2082	LR: 5.052e-02	Score 93.407	Data time: 3.3549, Total iter time: 7.6350
thomas 04/10 04:11:53 ===> Epoch[213](63840/301): Loss 0.2171	LR: 5.049e-02	Score 92.962	Data time: 3.4373, Total iter time: 7.8872
thomas 04/10 04:17:10 ===> Epoch[213](63880/301): Loss 0.2353	LR: 5.046e-02	Score 92.369	Data time: 3.4288, Total iter time: 7.8355
thomas 04/10 04:21:56 ===> Epoch[213](63920/301): Loss 0.2691	LR: 5.043e-02	Score 91.574	Data time: 3.0750, Total iter time: 7.0648
thomas 04/10 04:26:55 ===> Epoch[213](63960/301): Loss 0.2362	LR: 5.040e-02	Score 92.195	Data time: 3.1962, Total iter time: 7.3918
thomas 04/10 04:31:37 ===> Epoch[213](64000/301): Loss 0.2228	LR: 5.036e-02	Score 92.898	Data time: 3.0574, Total iter time: 6.9639
thomas 04/10 04:31:38 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 04:31:39 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 04:34:25 101/312: Data time: 0.0503, Iter time: 1.3241	Loss 0.232 (AVG: 0.525)	Score 94.386 (AVG: 86.398)	mIOU 63.222 mAP 73.547 mAcc 73.325
IOU: 80.601 95.893 59.720 73.263 88.285 73.511 64.821 37.941 35.167 74.711 15.977 56.404 54.764 69.069 57.303 42.025 84.718 58.057 86.379 55.843
mAP: 82.348 97.358 58.188 78.826 88.856 79.582 73.141 57.440 56.445 69.905 41.531 50.425 61.181 84.833 74.760 90.803 93.761 86.628 87.266 57.652
mAcc: 93.757 98.507 75.187 79.636 92.999 94.391 83.466 44.284 36.521 97.099 18.391 73.018 65.785 84.585 75.129 48.436 86.035 62.142 88.339 68.785

thomas 04/10 04:37:05 201/312: Data time: 0.0029, Iter time: 0.5870	Loss 0.547 (AVG: 0.543)	Score 87.410 (AVG: 85.973)	mIOU 62.034 mAP 73.315 mAcc 71.808
IOU: 80.059 96.213 56.572 73.344 89.476 75.131 66.120 39.342 37.511 69.442 11.893 54.287 54.232 65.823 43.648 44.284 85.800 58.780 87.419 51.302
mAP: 80.846 97.822 57.285 77.898 90.605 82.398 72.605 61.967 53.536 67.818 44.333 55.284 60.404 86.701 62.242 87.394 94.263 84.099 89.847 58.958
mAcc: 93.404 98.723 71.274 81.620 94.067 95.131 85.291 45.323 39.072 91.494 13.958 69.200 63.660 87.580 52.526 49.021 87.659 63.765 89.004 64.399

thomas 04/10 04:39:58 301/312: Data time: 0.0036, Iter time: 1.0083	Loss 0.900 (AVG: 0.552)	Score 77.854 (AVG: 85.866)	mIOU 61.323 mAP 72.089 mAcc 71.011
IOU: 79.902 96.285 57.426 71.889 88.311 71.477 66.001 41.881 36.614 73.266 14.628 55.145 54.247 62.427 44.058 34.826 85.120 58.617 84.544 49.788
mAP: 79.813 97.754 58.725 74.572 90.442 83.308 69.624 59.828 51.441 67.411 43.597 55.629 60.674 83.582 61.403 86.573 94.176 83.852 83.554 55.827
mAcc: 93.561 98.744 72.839 80.254 92.953 94.445 85.853 48.519 37.923 90.990 16.879 70.588 62.883 85.753 53.594 36.856 86.568 62.424 86.264 62.335

thomas 04/10 04:40:11 312/312: Data time: 0.0028, Iter time: 0.7417	Loss 0.504 (AVG: 0.550)	Score 85.891 (AVG: 85.909)	mIOU 61.335 mAP 72.229 mAcc 70.984
IOU: 80.058 96.228 56.936 72.370 88.532 71.355 65.650 42.022 36.344 72.758 15.485 54.934 53.662 62.172 43.104 35.162 85.736 58.615 85.873 49.708
mAP: 80.126 97.728 58.408 75.033 90.553 83.192 69.992 60.465 51.698 67.411 44.071 55.647 60.590 83.095 60.704 87.071 94.400 83.852 84.520 56.028
mAcc: 93.655 98.749 72.342 80.354 93.105 93.901 86.104 48.646 37.657 90.990 17.847 70.320 61.773 85.265 52.045 37.626 87.143 62.424 87.499 62.228

thomas 04/10 04:40:11 Finished test. Elapsed time: 512.9025
thomas 04/10 04:40:11 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 04:45:29 ===> Epoch[213](64040/301): Loss 0.2434	LR: 5.033e-02	Score 92.056	Data time: 3.4127, Total iter time: 7.8355
thomas 04/10 04:50:23 ===> Epoch[213](64080/301): Loss 0.2738	LR: 5.030e-02	Score 91.624	Data time: 3.1484, Total iter time: 7.2757
thomas 04/10 04:55:37 ===> Epoch[214](64120/301): Loss 0.2415	LR: 5.027e-02	Score 92.171	Data time: 3.4347, Total iter time: 7.7676
thomas 04/10 05:00:35 ===> Epoch[214](64160/301): Loss 0.2210	LR: 5.023e-02	Score 92.925	Data time: 3.1911, Total iter time: 7.3729
thomas 04/10 05:05:19 ===> Epoch[214](64200/301): Loss 0.2340	LR: 5.020e-02	Score 92.260	Data time: 3.0470, Total iter time: 7.0347
thomas 04/10 05:10:26 ===> Epoch[214](64240/301): Loss 0.2571	LR: 5.017e-02	Score 91.904	Data time: 3.3046, Total iter time: 7.5840
thomas 04/10 05:15:32 ===> Epoch[214](64280/301): Loss 0.2390	LR: 5.014e-02	Score 92.472	Data time: 3.3032, Total iter time: 7.5763
thomas 04/10 05:20:48 ===> Epoch[214](64320/301): Loss 0.2007	LR: 5.010e-02	Score 93.474	Data time: 3.3401, Total iter time: 7.8032
thomas 04/10 05:25:46 ===> Epoch[214](64360/301): Loss 0.2311	LR: 5.007e-02	Score 92.738	Data time: 3.1842, Total iter time: 7.3694
thomas 04/10 05:30:48 ===> Epoch[214](64400/301): Loss 0.2466	LR: 5.004e-02	Score 91.967	Data time: 3.2947, Total iter time: 7.4732
thomas 04/10 05:35:34 ===> Epoch[215](64440/301): Loss 0.2258	LR: 5.001e-02	Score 92.993	Data time: 3.0667, Total iter time: 7.0879
thomas 04/10 05:40:23 ===> Epoch[215](64480/301): Loss 0.2383	LR: 4.997e-02	Score 92.949	Data time: 3.1584, Total iter time: 7.1495
thomas 04/10 05:45:21 ===> Epoch[215](64520/301): Loss 0.2534	LR: 4.994e-02	Score 91.883	Data time: 3.1967, Total iter time: 7.3417
thomas 04/10 05:50:06 ===> Epoch[215](64560/301): Loss 0.2345	LR: 4.991e-02	Score 92.494	Data time: 3.0575, Total iter time: 7.0529
thomas 04/10 05:55:03 ===> Epoch[215](64600/301): Loss 0.2202	LR: 4.988e-02	Score 92.852	Data time: 3.2110, Total iter time: 7.3273
thomas 04/10 06:00:12 ===> Epoch[215](64640/301): Loss 0.2133	LR: 4.984e-02	Score 93.138	Data time: 3.3912, Total iter time: 7.6548
thomas 04/10 06:05:14 ===> Epoch[215](64680/301): Loss 0.2338	LR: 4.981e-02	Score 92.593	Data time: 3.2800, Total iter time: 7.4733
thomas 04/10 06:10:33 ===> Epoch[216](64720/301): Loss 0.2005	LR: 4.978e-02	Score 93.619	Data time: 3.3813, Total iter time: 7.8742
thomas 04/10 06:15:37 ===> Epoch[216](64760/301): Loss 0.2340	LR: 4.975e-02	Score 92.556	Data time: 3.3337, Total iter time: 7.5220
thomas 04/10 06:20:21 ===> Epoch[216](64800/301): Loss 0.2317	LR: 4.971e-02	Score 92.563	Data time: 3.0945, Total iter time: 7.0180
thomas 04/10 06:25:03 ===> Epoch[216](64840/301): Loss 0.2522	LR: 4.968e-02	Score 92.216	Data time: 3.0447, Total iter time: 6.9687
thomas 04/10 06:30:07 ===> Epoch[216](64880/301): Loss 0.2823	LR: 4.965e-02	Score 91.263	Data time: 3.3231, Total iter time: 7.5049
thomas 04/10 06:34:57 ===> Epoch[216](64920/301): Loss 0.2738	LR: 4.962e-02	Score 91.366	Data time: 3.1293, Total iter time: 7.1456
thomas 04/10 06:40:00 ===> Epoch[216](64960/301): Loss 0.2580	LR: 4.959e-02	Score 91.765	Data time: 3.2389, Total iter time: 7.4914
thomas 04/10 06:44:52 ===> Epoch[216](65000/301): Loss 0.2631	LR: 4.955e-02	Score 91.778	Data time: 3.1941, Total iter time: 7.2174
thomas 04/10 06:44:53 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 06:44:53 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 06:47:40 101/312: Data time: 0.0027, Iter time: 0.4425	Loss 1.382 (AVG: 0.750)	Score 58.013 (AVG: 80.816)	mIOU 49.859 mAP 66.358 mAcc 61.492
IOU: 76.410 95.955 44.704 47.056 75.465 55.563 58.059 52.132 31.294 65.849 11.197 52.085 23.420 71.992 31.749 42.650 48.765 26.668 56.585 29.584
mAP: 81.379 98.139 57.410 69.055 81.802 73.952 72.581 69.404 41.713 62.725 37.010 53.805 53.142 80.134 49.485 86.875 65.109 71.409 71.551 50.473
mAcc: 87.512 98.181 73.673 81.494 78.330 96.254 70.787 66.348 33.535 89.388 13.400 71.927 24.576 74.145 41.639 47.832 48.889 26.789 56.936 48.200

thomas 04/10 06:50:15 201/312: Data time: 0.0030, Iter time: 0.6785	Loss 0.185 (AVG: 0.747)	Score 94.654 (AVG: 81.557)	mIOU 49.964 mAP 66.620 mAcc 61.517
IOU: 77.846 95.532 48.664 51.876 79.413 55.180 60.806 46.137 26.893 67.571 12.550 56.471 24.158 68.189 40.534 18.901 54.089 31.247 55.060 28.163
mAP: 80.910 97.564 55.314 70.358 85.148 75.222 72.667 62.906 37.917 70.935 34.868 57.051 54.733 77.892 56.417 79.478 77.486 74.963 62.553 48.018
mAcc: 89.152 98.280 73.521 83.729 82.177 96.627 73.552 58.599 28.699 92.847 15.483 76.833 25.427 70.528 57.542 19.460 54.249 31.501 55.464 46.663

thomas 04/10 06:52:53 301/312: Data time: 0.0034, Iter time: 0.9214	Loss 0.103 (AVG: 0.761)	Score 97.043 (AVG: 81.058)	mIOU 49.546 mAP 66.704 mAcc 61.171
IOU: 76.869 95.568 48.633 50.056 79.880 53.731 61.481 46.563 25.599 67.725 12.552 52.863 23.845 63.478 40.056 22.698 49.916 30.261 60.865 28.279
mAP: 79.117 97.457 55.808 70.615 85.075 75.290 72.327 62.552 38.686 70.332 34.811 55.999 54.565 75.520 56.322 77.954 77.169 75.119 70.912 48.457
mAcc: 88.531 98.298 71.724 85.410 82.609 94.707 74.293 60.698 27.253 91.269 14.889 75.928 24.815 66.159 53.223 23.508 50.146 30.476 61.421 48.066

thomas 04/10 06:53:07 312/312: Data time: 0.0046, Iter time: 1.6137	Loss 0.734 (AVG: 0.759)	Score 79.659 (AVG: 81.129)	mIOU 49.687 mAP 66.841 mAcc 61.317
IOU: 76.885 95.566 49.139 50.679 80.058 54.066 61.400 46.335 24.877 68.122 12.527 53.443 23.891 62.066 42.056 23.565 50.131 29.801 60.621 28.515
mAP: 78.968 97.448 56.656 71.138 85.336 75.824 72.231 62.723 37.874 70.552 34.552 56.466 54.227 75.394 58.106 77.770 76.954 75.656 71.028 47.915
mAcc: 88.549 98.287 72.253 85.925 82.852 94.802 73.904 60.411 26.620 91.389 14.996 76.742 24.992 64.642 55.524 24.394 50.351 30.007 61.168 48.532

thomas 04/10 06:53:07 Finished test. Elapsed time: 493.4850
thomas 04/10 06:53:07 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 06:58:07 ===> Epoch[217](65040/301): Loss 0.2525	LR: 4.952e-02	Score 92.131	Data time: 3.2580, Total iter time: 7.4162
thomas 04/10 07:03:08 ===> Epoch[217](65080/301): Loss 0.2316	LR: 4.949e-02	Score 92.269	Data time: 3.2712, Total iter time: 7.4384
thomas 04/10 07:07:53 ===> Epoch[217](65120/301): Loss 0.2393	LR: 4.946e-02	Score 92.204	Data time: 3.1356, Total iter time: 7.0553
thomas 04/10 07:12:58 ===> Epoch[217](65160/301): Loss 0.2226	LR: 4.942e-02	Score 92.985	Data time: 3.2982, Total iter time: 7.5307
thomas 04/10 07:17:57 ===> Epoch[217](65200/301): Loss 0.2391	LR: 4.939e-02	Score 92.129	Data time: 3.1992, Total iter time: 7.3992
thomas 04/10 07:23:12 ===> Epoch[217](65240/301): Loss 0.2164	LR: 4.936e-02	Score 92.853	Data time: 3.3777, Total iter time: 7.7821
thomas 04/10 07:28:17 ===> Epoch[217](65280/301): Loss 0.2128	LR: 4.933e-02	Score 93.517	Data time: 3.3087, Total iter time: 7.5259
thomas 04/10 07:32:58 ===> Epoch[218](65320/301): Loss 0.2177	LR: 4.929e-02	Score 93.050	Data time: 3.0682, Total iter time: 6.9535
thomas 04/10 07:38:05 ===> Epoch[218](65360/301): Loss 0.2296	LR: 4.926e-02	Score 92.441	Data time: 3.3281, Total iter time: 7.6118
thomas 04/10 07:42:50 ===> Epoch[218](65400/301): Loss 0.2827	LR: 4.923e-02	Score 91.405	Data time: 3.0681, Total iter time: 7.0333
thomas 04/10 07:47:48 ===> Epoch[218](65440/301): Loss 0.2761	LR: 4.920e-02	Score 91.071	Data time: 3.2017, Total iter time: 7.3671
thomas 04/10 07:53:06 ===> Epoch[218](65480/301): Loss 0.2515	LR: 4.916e-02	Score 92.159	Data time: 3.4484, Total iter time: 7.8513
thomas 04/10 07:57:58 ===> Epoch[218](65520/301): Loss 0.2397	LR: 4.913e-02	Score 92.152	Data time: 3.1627, Total iter time: 7.2070
thomas 04/10 08:02:34 ===> Epoch[218](65560/301): Loss 0.2571	LR: 4.910e-02	Score 91.880	Data time: 2.9622, Total iter time: 6.8171
thomas 04/10 08:07:40 ===> Epoch[218](65600/301): Loss 0.2504	LR: 4.907e-02	Score 92.252	Data time: 3.3224, Total iter time: 7.5707
thomas 04/10 08:12:37 ===> Epoch[219](65640/301): Loss 0.2268	LR: 4.903e-02	Score 92.657	Data time: 3.2041, Total iter time: 7.3481
thomas 04/10 08:17:39 ===> Epoch[219](65680/301): Loss 0.2095	LR: 4.900e-02	Score 92.999	Data time: 3.2767, Total iter time: 7.4850
thomas 04/10 08:22:20 ===> Epoch[219](65720/301): Loss 0.2431	LR: 4.897e-02	Score 92.355	Data time: 3.0676, Total iter time: 6.9349
thomas 04/10 08:27:28 ===> Epoch[219](65760/301): Loss 0.2304	LR: 4.894e-02	Score 92.664	Data time: 3.3129, Total iter time: 7.6201
thomas 04/10 08:32:40 ===> Epoch[219](65800/301): Loss 0.2221	LR: 4.890e-02	Score 92.756	Data time: 3.3395, Total iter time: 7.7107
thomas 04/10 08:37:38 ===> Epoch[219](65840/301): Loss 0.2304	LR: 4.887e-02	Score 92.609	Data time: 3.2441, Total iter time: 7.3646
thomas 04/10 08:42:42 ===> Epoch[219](65880/301): Loss 0.2460	LR: 4.884e-02	Score 92.014	Data time: 3.3030, Total iter time: 7.5209
thomas 04/10 08:47:44 ===> Epoch[220](65920/301): Loss 0.2461	LR: 4.881e-02	Score 92.106	Data time: 3.2675, Total iter time: 7.4606
thomas 04/10 08:52:31 ===> Epoch[220](65960/301): Loss 0.2364	LR: 4.877e-02	Score 92.619	Data time: 3.1329, Total iter time: 7.0842
thomas 04/10 08:57:34 ===> Epoch[220](66000/301): Loss 0.2494	LR: 4.874e-02	Score 91.842	Data time: 3.2456, Total iter time: 7.4760
thomas 04/10 08:57:35 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 08:57:35 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 09:00:10 101/312: Data time: 0.0030, Iter time: 0.8922	Loss 0.458 (AVG: 0.569)	Score 88.526 (AVG: 85.173)	mIOU 63.038 mAP 71.995 mAcc 72.325
IOU: 76.326 96.263 61.938 59.291 86.303 71.164 72.913 46.391 37.497 74.463 9.513 61.990 52.460 52.299 60.802 58.986 91.991 61.298 85.621 43.255
mAP: 75.413 97.805 64.792 68.227 90.077 84.210 73.684 62.309 46.876 68.046 33.213 53.152 61.131 74.689 57.086 92.587 97.924 86.811 91.509 60.368
mAcc: 89.127 98.784 77.262 79.571 94.128 95.694 83.276 68.398 43.410 84.218 10.061 67.706 61.711 69.828 65.411 60.471 93.475 62.985 86.832 54.159

thomas 04/10 09:02:42 201/312: Data time: 0.0043, Iter time: 1.1507	Loss 0.902 (AVG: 0.576)	Score 79.170 (AVG: 84.810)	mIOU 60.794 mAP 70.498 mAcc 70.393
IOU: 77.495 96.142 54.592 68.884 84.179 67.777 70.761 49.814 37.514 70.897 9.883 57.417 52.961 56.470 44.292 40.799 88.072 61.610 83.584 42.744
mAP: 75.769 97.548 60.862 77.201 89.377 82.351 74.101 65.171 47.353 61.911 34.342 56.124 61.404 73.744 49.426 86.407 93.302 82.113 82.586 58.876
mAcc: 88.863 98.688 68.311 85.479 91.776 94.935 82.406 71.563 43.758 81.572 11.087 65.609 62.496 72.561 47.590 43.280 89.367 63.510 84.664 60.336

thomas 04/10 09:05:34 301/312: Data time: 0.0029, Iter time: 0.4961	Loss 0.603 (AVG: 0.603)	Score 86.993 (AVG: 84.435)	mIOU 58.856 mAP 69.712 mAcc 68.674
IOU: 77.219 96.271 55.138 66.239 84.565 67.132 68.218 47.605 36.348 69.272 11.899 56.132 54.854 56.899 43.555 30.729 84.728 49.781 77.933 42.614
mAP: 75.756 97.689 58.567 75.971 88.662 82.653 72.426 63.258 48.728 66.192 36.900 53.716 64.889 75.289 47.770 85.160 91.367 74.236 78.573 56.442
mAcc: 88.709 98.710 68.285 86.408 92.314 95.016 79.779 67.838 42.861 80.502 12.854 62.846 64.687 78.765 45.968 32.115 86.268 50.984 78.955 59.619

thomas 04/10 09:05:53 312/312: Data time: 0.0100, Iter time: 0.7106	Loss 1.335 (AVG: 0.605)	Score 67.696 (AVG: 84.372)	mIOU 59.127 mAP 69.842 mAcc 69.057
IOU: 77.230 96.269 55.647 65.700 84.303 66.897 67.394 47.595 37.089 68.299 12.452 55.827 55.229 59.464 43.633 33.465 85.241 49.021 79.798 41.988
mAP: 75.886 97.706 58.166 75.139 88.598 81.721 72.377 63.486 49.131 66.192 37.732 52.190 64.781 76.687 48.485 86.447 91.688 74.413 80.490 55.525
mAcc: 88.533 98.691 68.773 86.585 92.469 94.378 79.112 67.451 43.799 80.502 13.432 62.915 64.968 80.525 47.158 34.875 86.855 50.204 80.978 58.930

thomas 04/10 09:05:53 Finished test. Elapsed time: 497.9512
thomas 04/10 09:05:53 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 09:10:35 ===> Epoch[220](66040/301): Loss 0.2533	LR: 4.871e-02	Score 91.898	Data time: 3.0663, Total iter time: 6.9566
thomas 04/10 09:15:26 ===> Epoch[220](66080/301): Loss 0.2443	LR: 4.868e-02	Score 92.105	Data time: 3.1187, Total iter time: 7.2095
thomas 04/10 09:20:37 ===> Epoch[220](66120/301): Loss 0.2435	LR: 4.864e-02	Score 92.228	Data time: 3.3615, Total iter time: 7.6671
thomas 04/10 09:25:36 ===> Epoch[220](66160/301): Loss 0.2336	LR: 4.861e-02	Score 92.372	Data time: 3.2434, Total iter time: 7.4070
thomas 04/10 09:30:30 ===> Epoch[220](66200/301): Loss 0.2106	LR: 4.858e-02	Score 93.040	Data time: 3.2339, Total iter time: 7.2556
thomas 04/10 09:35:21 ===> Epoch[221](66240/301): Loss 0.2436	LR: 4.855e-02	Score 92.478	Data time: 3.1044, Total iter time: 7.1967
thomas 04/10 09:40:23 ===> Epoch[221](66280/301): Loss 0.2239	LR: 4.851e-02	Score 92.820	Data time: 3.2687, Total iter time: 7.4479
thomas 04/10 09:45:09 ===> Epoch[221](66320/301): Loss 0.2752	LR: 4.848e-02	Score 91.735	Data time: 3.0544, Total iter time: 7.0720
thomas 04/10 09:50:12 ===> Epoch[221](66360/301): Loss 0.2363	LR: 4.845e-02	Score 92.592	Data time: 3.3435, Total iter time: 7.4747
thomas 04/10 09:55:34 ===> Epoch[221](66400/301): Loss 0.2326	LR: 4.842e-02	Score 92.731	Data time: 3.5439, Total iter time: 7.9456
thomas 04/10 10:00:21 ===> Epoch[221](66440/301): Loss 0.2275	LR: 4.838e-02	Score 92.569	Data time: 3.1419, Total iter time: 7.0852
thomas 04/10 10:04:44 ===> Epoch[221](66480/301): Loss 0.2409	LR: 4.835e-02	Score 92.218	Data time: 2.6320, Total iter time: 6.5016
thomas 04/10 10:09:10 ===> Epoch[221](66520/301): Loss 0.2252	LR: 4.832e-02	Score 92.826	Data time: 2.7141, Total iter time: 6.5590
thomas 04/10 10:13:41 ===> Epoch[222](66560/301): Loss 0.2051	LR: 4.829e-02	Score 93.245	Data time: 2.8345, Total iter time: 6.6810
thomas 04/10 10:18:03 ===> Epoch[222](66600/301): Loss 0.2360	LR: 4.825e-02	Score 92.557	Data time: 2.7232, Total iter time: 6.4621
thomas 04/10 10:22:47 ===> Epoch[222](66640/301): Loss 0.2322	LR: 4.822e-02	Score 92.554	Data time: 2.9241, Total iter time: 7.0028
thomas 04/10 10:27:17 ===> Epoch[222](66680/301): Loss 0.2138	LR: 4.819e-02	Score 93.038	Data time: 2.8542, Total iter time: 6.6676
thomas 04/10 10:31:51 ===> Epoch[222](66720/301): Loss 0.2354	LR: 4.816e-02	Score 92.371	Data time: 2.8418, Total iter time: 6.7575
thomas 04/10 10:36:14 ===> Epoch[222](66760/301): Loss 0.2100	LR: 4.812e-02	Score 93.088	Data time: 2.7921, Total iter time: 6.4893
thomas 04/10 10:40:36 ===> Epoch[222](66800/301): Loss 0.2135	LR: 4.809e-02	Score 93.075	Data time: 2.7089, Total iter time: 6.4724
thomas 04/10 10:44:07 ===> Epoch[223](66840/301): Loss 0.2105	LR: 4.806e-02	Score 93.070	Data time: 2.0407, Total iter time: 5.1869
thomas 04/10 10:47:42 ===> Epoch[223](66880/301): Loss 0.2230	LR: 4.803e-02	Score 92.642	Data time: 2.0917, Total iter time: 5.3145
thomas 04/10 10:51:15 ===> Epoch[223](66920/301): Loss 0.2239	LR: 4.799e-02	Score 92.825	Data time: 2.0808, Total iter time: 5.2340
thomas 04/10 10:54:59 ===> Epoch[223](66960/301): Loss 0.2403	LR: 4.796e-02	Score 92.153	Data time: 2.1624, Total iter time: 5.5244
thomas 04/10 10:58:53 ===> Epoch[223](67000/301): Loss 0.2103	LR: 4.793e-02	Score 92.975	Data time: 2.2413, Total iter time: 5.7647
thomas 04/10 10:58:54 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 10:58:54 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 11:00:45 101/312: Data time: 0.0036, Iter time: 0.6213	Loss 0.471 (AVG: 0.578)	Score 86.438 (AVG: 85.007)	mIOU 59.725 mAP 71.469 mAcc 69.857
IOU: 77.756 96.106 52.861 60.771 86.908 66.777 70.637 45.165 38.526 64.627 9.194 36.624 65.972 62.071 36.016 57.834 72.958 58.167 85.041 50.497
mAP: 78.359 96.980 64.043 63.769 88.164 79.382 73.553 61.210 51.389 64.175 35.505 52.187 76.748 80.046 46.377 93.319 85.226 87.899 96.661 54.380
mAcc: 89.861 98.688 79.558 64.422 90.135 91.703 83.396 70.561 39.592 95.386 11.334 39.357 81.184 76.492 38.421 70.587 73.490 58.855 85.637 58.472

thomas 04/10 11:02:28 201/312: Data time: 0.0036, Iter time: 0.5166	Loss 0.681 (AVG: 0.572)	Score 79.603 (AVG: 85.188)	mIOU 60.903 mAP 71.544 mAcc 69.985
IOU: 77.795 96.011 54.774 67.567 86.461 67.035 70.194 45.317 34.104 70.255 10.092 46.757 61.517 66.537 53.130 45.973 74.489 58.075 80.857 51.121
mAP: 78.690 96.843 63.312 68.678 90.490 78.822 76.247 63.159 52.508 64.545 33.000 56.309 71.542 79.491 55.398 86.221 86.870 87.008 88.753 53.001
mAcc: 91.103 98.569 75.785 71.870 89.036 94.186 83.754 68.801 35.263 89.833 13.119 49.575 76.539 79.335 56.766 50.190 74.872 59.322 81.372 60.410

thomas 04/10 11:04:11 301/312: Data time: 0.0036, Iter time: 0.9936	Loss 0.862 (AVG: 0.567)	Score 72.445 (AVG: 85.508)	mIOU 60.734 mAP 71.247 mAcc 69.590
IOU: 78.492 96.246 55.174 72.244 87.105 71.513 70.207 48.764 31.651 70.451 12.907 50.436 59.257 69.904 44.211 41.525 76.335 52.386 76.595 49.280
mAP: 79.723 97.005 62.327 68.925 90.537 80.298 75.186 64.749 49.785 65.773 34.850 58.840 70.827 78.887 54.919 84.313 90.409 82.866 79.740 54.986
mAcc: 91.199 98.645 76.780 76.994 89.564 95.167 83.071 72.202 33.045 89.880 16.566 53.123 75.429 81.652 47.262 43.789 76.725 53.797 77.125 59.791

thomas 04/10 11:04:21 312/312: Data time: 0.0026, Iter time: 0.2529	Loss 0.365 (AVG: 0.565)	Score 88.807 (AVG: 85.567)	mIOU 60.812 mAP 71.353 mAcc 69.638
IOU: 78.642 96.163 55.528 71.554 87.326 72.289 70.247 49.167 31.200 69.953 13.325 51.021 59.253 70.089 43.676 41.038 76.837 52.386 77.648 48.908
mAP: 79.888 97.022 62.466 68.901 90.489 80.570 75.422 65.135 49.975 65.773 35.552 59.516 70.673 79.639 52.740 84.313 90.595 82.866 80.391 55.134
mAcc: 91.388 98.592 77.153 76.252 89.760 95.436 83.218 71.711 32.625 89.880 17.097 53.652 75.268 81.724 46.694 43.789 77.233 53.797 78.166 59.335

thomas 04/10 11:04:21 Finished test. Elapsed time: 326.5783
thomas 04/10 11:04:21 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 11:07:44 ===> Epoch[223](67040/301): Loss 0.2244	LR: 4.790e-02	Score 92.724	Data time: 1.9223, Total iter time: 4.9939
thomas 04/10 11:11:12 ===> Epoch[223](67080/301): Loss 0.2198	LR: 4.786e-02	Score 93.051	Data time: 1.9893, Total iter time: 5.1213
thomas 04/10 11:14:46 ===> Epoch[223](67120/301): Loss 0.2307	LR: 4.783e-02	Score 92.871	Data time: 2.0367, Total iter time: 5.2610
thomas 04/10 11:18:19 ===> Epoch[224](67160/301): Loss 0.2189	LR: 4.780e-02	Score 92.800	Data time: 2.0504, Total iter time: 5.2472
thomas 04/10 11:21:49 ===> Epoch[224](67200/301): Loss 0.2530	LR: 4.777e-02	Score 91.817	Data time: 2.0134, Total iter time: 5.1921
thomas 04/10 11:25:16 ===> Epoch[224](67240/301): Loss 0.2623	LR: 4.773e-02	Score 91.756	Data time: 1.9607, Total iter time: 5.1031
thomas 04/10 11:28:48 ===> Epoch[224](67280/301): Loss 0.2330	LR: 4.770e-02	Score 92.581	Data time: 2.0165, Total iter time: 5.2376
thomas 04/10 11:32:29 ===> Epoch[224](67320/301): Loss 0.2318	LR: 4.767e-02	Score 92.564	Data time: 2.1105, Total iter time: 5.4447
thomas 04/10 11:36:18 ===> Epoch[224](67360/301): Loss 0.2199	LR: 4.763e-02	Score 93.003	Data time: 2.2080, Total iter time: 5.6542
thomas 04/10 11:39:48 ===> Epoch[224](67400/301): Loss 0.2085	LR: 4.760e-02	Score 93.600	Data time: 2.0161, Total iter time: 5.1668
thomas 04/10 11:43:22 ===> Epoch[225](67440/301): Loss 0.2147	LR: 4.757e-02	Score 93.090	Data time: 2.0600, Total iter time: 5.2939
thomas 04/10 11:46:46 ===> Epoch[225](67480/301): Loss 0.2178	LR: 4.754e-02	Score 92.922	Data time: 1.9901, Total iter time: 5.0496
thomas 04/10 11:50:23 ===> Epoch[225](67520/301): Loss 0.2138	LR: 4.750e-02	Score 93.030	Data time: 2.0737, Total iter time: 5.3615
thomas 04/10 11:53:56 ===> Epoch[225](67560/301): Loss 0.2354	LR: 4.747e-02	Score 92.298	Data time: 2.0594, Total iter time: 5.2661
thomas 04/10 11:57:30 ===> Epoch[225](67600/301): Loss 0.2419	LR: 4.744e-02	Score 92.318	Data time: 2.0689, Total iter time: 5.2612
thomas 04/10 12:00:59 ===> Epoch[225](67640/301): Loss 0.2291	LR: 4.741e-02	Score 92.625	Data time: 2.0336, Total iter time: 5.1736
thomas 04/10 12:04:50 ===> Epoch[225](67680/301): Loss 0.2328	LR: 4.737e-02	Score 92.602	Data time: 2.2135, Total iter time: 5.6824
thomas 04/10 12:08:35 ===> Epoch[225](67720/301): Loss 0.2229	LR: 4.734e-02	Score 92.749	Data time: 2.1779, Total iter time: 5.5704
thomas 04/10 12:12:13 ===> Epoch[226](67760/301): Loss 0.2332	LR: 4.731e-02	Score 92.617	Data time: 2.0812, Total iter time: 5.3583
thomas 04/10 12:15:47 ===> Epoch[226](67800/301): Loss 0.2107	LR: 4.728e-02	Score 93.056	Data time: 2.0667, Total iter time: 5.2867
thomas 04/10 12:19:16 ===> Epoch[226](67840/301): Loss 0.2129	LR: 4.724e-02	Score 92.881	Data time: 2.0195, Total iter time: 5.1634
thomas 04/10 12:23:05 ===> Epoch[226](67880/301): Loss 0.2502	LR: 4.721e-02	Score 92.062	Data time: 2.2010, Total iter time: 5.6487
thomas 04/10 12:26:46 ===> Epoch[226](67920/301): Loss 0.2132	LR: 4.718e-02	Score 93.064	Data time: 2.1029, Total iter time: 5.4342
thomas 04/10 12:30:39 ===> Epoch[226](67960/301): Loss 0.2154	LR: 4.715e-02	Score 93.156	Data time: 2.2410, Total iter time: 5.7627
thomas 04/10 12:34:08 ===> Epoch[226](68000/301): Loss 0.2147	LR: 4.711e-02	Score 92.713	Data time: 2.0186, Total iter time: 5.1544
thomas 04/10 12:34:09 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 12:34:10 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 12:36:01 101/312: Data time: 0.0038, Iter time: 0.3230	Loss 1.351 (AVG: 0.634)	Score 68.006 (AVG: 83.375)	mIOU 58.881 mAP 71.524 mAcc 70.397
IOU: 75.409 96.621 47.929 57.298 90.707 75.792 65.299 43.281 25.566 65.874 7.091 59.302 53.436 62.672 60.066 35.595 75.546 66.425 62.398 51.323
mAP: 78.884 97.032 53.628 62.269 89.312 82.650 74.119 62.542 47.322 70.361 29.097 71.866 60.512 76.019 70.626 85.872 90.910 89.326 81.184 56.954
mAcc: 86.425 98.684 76.558 70.289 95.340 94.804 75.357 58.143 28.288 90.749 14.319 85.013 87.123 64.054 70.131 36.792 76.070 72.717 62.988 64.095

thomas 04/10 12:37:49 201/312: Data time: 0.0025, Iter time: 0.3613	Loss 0.462 (AVG: 0.627)	Score 82.183 (AVG: 84.022)	mIOU 59.676 mAP 70.422 mAcc 70.538
IOU: 76.153 96.304 51.031 70.262 89.897 75.947 70.167 43.607 28.592 68.136 12.113 57.579 57.369 68.736 50.413 27.021 79.174 59.878 65.635 45.513
mAP: 77.371 96.622 52.405 69.360 90.096 79.181 74.419 63.464 45.154 70.233 36.454 63.698 63.902 81.568 63.761 76.320 89.316 85.971 75.254 53.897
mAcc: 87.424 98.540 77.029 79.913 94.047 93.329 80.497 60.813 30.813 92.912 16.440 80.290 84.833 72.681 60.606 28.268 79.719 63.995 66.182 62.430

thomas 04/10 12:39:35 301/312: Data time: 0.0022, Iter time: 0.5623	Loss 0.382 (AVG: 0.612)	Score 90.719 (AVG: 84.516)	mIOU 59.929 mAP 70.768 mAcc 70.637
IOU: 76.719 96.334 49.511 72.065 90.584 76.000 70.467 44.800 27.340 70.499 13.502 55.665 57.286 66.350 52.333 33.129 73.864 61.356 65.838 44.929
mAP: 78.173 97.012 54.358 72.900 91.198 79.820 74.598 64.288 43.579 70.934 35.447 62.072 64.355 77.529 68.301 76.521 90.025 85.858 76.114 52.283
mAcc: 87.558 98.585 76.294 83.119 94.754 93.289 80.906 63.348 29.438 93.386 18.399 79.293 83.125 70.001 60.523 34.653 74.313 65.308 66.352 60.105

thomas 04/10 12:39:46 312/312: Data time: 0.0029, Iter time: 0.4208	Loss 1.988 (AVG: 0.620)	Score 67.405 (AVG: 84.418)	mIOU 59.765 mAP 70.669 mAcc 70.509
IOU: 76.771 96.267 49.826 71.894 90.076 76.284 70.439 44.866 26.572 70.376 13.266 56.335 58.215 65.821 50.171 33.591 73.174 61.100 65.899 44.348
mAP: 78.350 96.948 53.854 72.159 90.910 79.657 74.585 64.357 43.383 70.946 35.693 60.525 65.020 76.732 69.202 77.126 90.046 85.218 76.784 51.881
mAcc: 87.524 98.586 77.013 82.560 94.225 93.354 80.957 63.961 28.579 93.439 17.991 78.992 83.454 69.339 60.481 35.121 73.611 65.068 66.411 59.523

thomas 04/10 12:39:46 Finished test. Elapsed time: 336.9201
thomas 04/10 12:39:46 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 12:43:29 ===> Epoch[227](68040/301): Loss 0.2079	LR: 4.708e-02	Score 93.377	Data time: 2.1399, Total iter time: 5.4889
thomas 04/10 12:46:58 ===> Epoch[227](68080/301): Loss 0.2355	LR: 4.705e-02	Score 92.526	Data time: 2.0134, Total iter time: 5.1442
thomas 04/10 12:50:37 ===> Epoch[227](68120/301): Loss 0.2585	LR: 4.702e-02	Score 91.935	Data time: 2.1204, Total iter time: 5.4190
thomas 04/10 12:54:02 ===> Epoch[227](68160/301): Loss 0.2309	LR: 4.698e-02	Score 92.771	Data time: 1.9804, Total iter time: 5.0334
thomas 04/10 12:58:31 ===> Epoch[227](68200/301): Loss 0.2186	LR: 4.695e-02	Score 92.840	Data time: 2.8888, Total iter time: 6.6619
thomas 04/10 13:03:07 ===> Epoch[227](68240/301): Loss 0.1980	LR: 4.692e-02	Score 93.657	Data time: 2.9478, Total iter time: 6.8236
thomas 04/10 13:07:43 ===> Epoch[227](68280/301): Loss 0.2056	LR: 4.688e-02	Score 93.518	Data time: 3.0767, Total iter time: 6.8138
thomas 04/10 13:12:35 ===> Epoch[227](68320/301): Loss 0.1969	LR: 4.685e-02	Score 93.581	Data time: 3.2174, Total iter time: 7.2114
thomas 04/10 13:17:15 ===> Epoch[228](68360/301): Loss 0.2163	LR: 4.682e-02	Score 92.815	Data time: 3.0223, Total iter time: 6.9184
thomas 04/10 13:21:34 ===> Epoch[228](68400/301): Loss 0.2011	LR: 4.679e-02	Score 93.539	Data time: 2.7151, Total iter time: 6.3798
thomas 04/10 13:25:41 ===> Epoch[228](68440/301): Loss 0.2237	LR: 4.675e-02	Score 92.999	Data time: 2.3921, Total iter time: 6.0936
thomas 04/10 13:29:43 ===> Epoch[228](68480/301): Loss 0.2158	LR: 4.672e-02	Score 93.141	Data time: 2.3110, Total iter time: 5.9870
thomas 04/10 13:33:39 ===> Epoch[228](68520/301): Loss 0.2298	LR: 4.669e-02	Score 92.762	Data time: 2.2579, Total iter time: 5.8192
thomas 04/10 13:37:29 ===> Epoch[228](68560/301): Loss 0.1988	LR: 4.666e-02	Score 93.536	Data time: 2.2127, Total iter time: 5.6606
thomas 04/10 13:41:05 ===> Epoch[228](68600/301): Loss 0.2367	LR: 4.662e-02	Score 92.754	Data time: 2.1228, Total iter time: 5.3480
thomas 04/10 13:44:58 ===> Epoch[229](68640/301): Loss 0.2467	LR: 4.659e-02	Score 92.290	Data time: 2.2448, Total iter time: 5.7481
thomas 04/10 13:48:45 ===> Epoch[229](68680/301): Loss 0.2346	LR: 4.656e-02	Score 92.663	Data time: 2.1821, Total iter time: 5.5966
thomas 04/10 13:52:26 ===> Epoch[229](68720/301): Loss 0.2587	LR: 4.653e-02	Score 91.596	Data time: 2.1275, Total iter time: 5.4657
thomas 04/10 13:56:19 ===> Epoch[229](68760/301): Loss 0.2633	LR: 4.649e-02	Score 91.622	Data time: 2.2173, Total iter time: 5.7515
thomas 04/10 14:00:15 ===> Epoch[229](68800/301): Loss 0.2312	LR: 4.646e-02	Score 92.620	Data time: 2.2651, Total iter time: 5.8118
thomas 04/10 14:04:03 ===> Epoch[229](68840/301): Loss 0.2267	LR: 4.643e-02	Score 92.860	Data time: 2.1986, Total iter time: 5.6280
thomas 04/10 14:07:47 ===> Epoch[229](68880/301): Loss 0.2584	LR: 4.640e-02	Score 91.721	Data time: 2.1268, Total iter time: 5.5105
thomas 04/10 14:11:24 ===> Epoch[229](68920/301): Loss 0.2738	LR: 4.636e-02	Score 91.412	Data time: 2.1020, Total iter time: 5.3511
thomas 04/10 14:15:26 ===> Epoch[230](68960/301): Loss 0.2619	LR: 4.633e-02	Score 91.687	Data time: 2.3262, Total iter time: 5.9736
thomas 04/10 14:19:15 ===> Epoch[230](69000/301): Loss 0.2774	LR: 4.630e-02	Score 91.484	Data time: 2.2178, Total iter time: 5.6560
thomas 04/10 14:19:16 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 14:19:16 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 14:21:13 101/312: Data time: 0.1076, Iter time: 0.5082	Loss 1.794 (AVG: 0.573)	Score 64.377 (AVG: 84.248)	mIOU 55.645 mAP 67.759 mAcc 64.786
IOU: 78.119 96.319 49.028 69.091 87.183 80.108 62.642 42.622 28.481 75.594 12.271 6.858 40.942 60.452 49.843 35.842 79.695 50.258 69.500 38.047
mAP: 76.295 97.836 55.484 67.242 90.534 88.298 72.079 57.334 38.183 69.491 33.419 55.012 62.435 77.082 50.241 83.263 86.648 79.458 64.996 49.846
mAcc: 93.280 98.182 66.079 78.547 92.412 96.045 70.028 54.157 30.642 85.812 14.468 6.905 87.271 68.575 52.643 39.455 80.083 52.351 69.907 58.876

thomas 04/10 14:23:04 201/312: Data time: 0.0025, Iter time: 0.6566	Loss 0.408 (AVG: 0.590)	Score 90.947 (AVG: 84.101)	mIOU 56.204 mAP 68.468 mAcc 64.894
IOU: 77.830 96.175 47.090 66.148 88.238 78.113 67.428 41.069 26.486 73.575 10.323 9.386 49.238 55.422 45.703 41.887 86.754 53.130 72.146 37.947
mAP: 78.209 97.122 54.427 64.486 89.840 85.336 73.653 58.853 41.831 65.814 29.486 51.913 66.042 71.768 56.567 85.277 91.505 78.699 75.606 52.917
mAcc: 94.193 98.240 63.882 76.714 93.369 94.911 75.462 52.305 28.294 84.589 12.727 9.566 88.810 62.647 48.162 45.583 87.581 55.862 72.614 52.373

thomas 04/10 14:24:57 301/312: Data time: 0.0029, Iter time: 0.9469	Loss 1.123 (AVG: 0.604)	Score 72.593 (AVG: 84.071)	mIOU 56.566 mAP 68.300 mAcc 65.050
IOU: 77.696 96.167 49.307 64.952 88.608 75.736 68.427 41.781 27.302 67.980 10.829 7.615 53.954 59.058 44.098 42.685 86.638 56.198 74.354 37.935
mAP: 78.117 97.379 55.182 62.725 90.106 82.048 71.608 60.425 41.253 64.782 31.569 51.278 66.090 73.344 53.503 85.872 91.288 79.530 77.229 52.673
mAcc: 94.417 98.268 66.932 75.506 93.814 94.665 76.762 52.539 29.166 79.423 13.100 7.744 86.093 66.816 46.583 46.378 87.437 58.956 74.824 51.573

thomas 04/10 14:25:08 312/312: Data time: 0.0029, Iter time: 0.3885	Loss 0.823 (AVG: 0.605)	Score 82.430 (AVG: 84.034)	mIOU 56.642 mAP 68.470 mAcc 65.117
IOU: 77.686 96.177 49.030 64.949 88.737 76.690 68.057 41.503 27.216 67.944 10.945 7.615 53.268 59.045 42.708 43.843 86.885 56.918 75.155 38.471
mAP: 78.333 97.439 55.036 63.580 90.336 82.649 71.554 59.985 41.755 64.782 31.440 51.278 65.915 73.593 52.366 86.055 91.604 79.978 77.914 53.805
mAcc: 94.437 98.292 66.315 76.371 93.936 94.921 76.370 52.066 29.008 79.423 13.234 7.744 84.884 66.846 45.554 47.745 87.705 59.644 75.620 52.228

thomas 04/10 14:25:08 Finished test. Elapsed time: 351.5044
thomas 04/10 14:25:08 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 14:28:51 ===> Epoch[230](69040/301): Loss 0.2110	LR: 4.626e-02	Score 93.137	Data time: 2.1513, Total iter time: 5.5094
thomas 04/10 14:32:42 ===> Epoch[230](69080/301): Loss 0.2267	LR: 4.623e-02	Score 92.798	Data time: 2.2477, Total iter time: 5.7078
thomas 04/10 14:36:35 ===> Epoch[230](69120/301): Loss 0.2154	LR: 4.620e-02	Score 93.006	Data time: 2.2504, Total iter time: 5.7491
thomas 04/10 14:40:14 ===> Epoch[230](69160/301): Loss 0.2319	LR: 4.617e-02	Score 92.643	Data time: 2.1061, Total iter time: 5.4027
thomas 04/10 14:44:07 ===> Epoch[230](69200/301): Loss 0.2383	LR: 4.613e-02	Score 92.398	Data time: 2.2237, Total iter time: 5.7532
thomas 04/10 14:47:54 ===> Epoch[231](69240/301): Loss 0.2136	LR: 4.610e-02	Score 93.263	Data time: 2.2098, Total iter time: 5.6016
thomas 04/10 14:51:29 ===> Epoch[231](69280/301): Loss 0.2007	LR: 4.607e-02	Score 93.357	Data time: 2.0557, Total iter time: 5.2846
thomas 04/10 14:55:11 ===> Epoch[231](69320/301): Loss 0.2511	LR: 4.604e-02	Score 92.061	Data time: 2.1279, Total iter time: 5.4862
thomas 04/10 14:59:09 ===> Epoch[231](69360/301): Loss 0.2432	LR: 4.600e-02	Score 92.364	Data time: 2.3062, Total iter time: 5.8611
thomas 04/10 15:02:43 ===> Epoch[231](69400/301): Loss 0.1994	LR: 4.597e-02	Score 93.683	Data time: 2.0737, Total iter time: 5.2635
thomas 04/10 15:06:32 ===> Epoch[231](69440/301): Loss 0.2340	LR: 4.594e-02	Score 92.494	Data time: 2.2230, Total iter time: 5.6574
thomas 04/10 15:10:22 ===> Epoch[231](69480/301): Loss 0.2381	LR: 4.590e-02	Score 92.335	Data time: 2.2379, Total iter time: 5.6874
thomas 04/10 15:13:58 ===> Epoch[231](69520/301): Loss 0.2197	LR: 4.587e-02	Score 92.946	Data time: 2.0804, Total iter time: 5.3125
thomas 04/10 15:18:03 ===> Epoch[232](69560/301): Loss 0.2276	LR: 4.584e-02	Score 92.787	Data time: 2.3526, Total iter time: 6.0637
thomas 04/10 15:21:55 ===> Epoch[232](69600/301): Loss 0.2187	LR: 4.581e-02	Score 92.909	Data time: 2.2363, Total iter time: 5.7216
thomas 04/10 15:25:42 ===> Epoch[232](69640/301): Loss 0.2245	LR: 4.577e-02	Score 92.858	Data time: 2.2216, Total iter time: 5.5964
thomas 04/10 15:29:25 ===> Epoch[232](69680/301): Loss 0.2424	LR: 4.574e-02	Score 92.431	Data time: 2.1712, Total iter time: 5.5176
thomas 04/10 15:33:02 ===> Epoch[232](69720/301): Loss 0.2390	LR: 4.571e-02	Score 92.503	Data time: 2.0824, Total iter time: 5.3586
thomas 04/10 15:36:59 ===> Epoch[232](69760/301): Loss 0.2527	LR: 4.568e-02	Score 91.853	Data time: 2.2759, Total iter time: 5.8407
thomas 04/10 15:40:50 ===> Epoch[232](69800/301): Loss 0.2155	LR: 4.564e-02	Score 92.836	Data time: 2.2457, Total iter time: 5.6939
thomas 04/10 15:44:25 ===> Epoch[233](69840/301): Loss 0.2237	LR: 4.561e-02	Score 92.883	Data time: 2.0873, Total iter time: 5.3140
thomas 04/10 15:48:28 ===> Epoch[233](69880/301): Loss 0.2153	LR: 4.558e-02	Score 92.967	Data time: 2.3311, Total iter time: 5.9965
thomas 04/10 15:52:13 ===> Epoch[233](69920/301): Loss 0.2205	LR: 4.554e-02	Score 92.881	Data time: 2.1733, Total iter time: 5.5391
thomas 04/10 15:56:06 ===> Epoch[233](69960/301): Loss 0.2429	LR: 4.551e-02	Score 92.404	Data time: 2.2448, Total iter time: 5.7403
thomas 04/10 15:59:46 ===> Epoch[233](70000/301): Loss 0.2432	LR: 4.548e-02	Score 92.310	Data time: 2.1149, Total iter time: 5.4471
thomas 04/10 15:59:48 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 15:59:48 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 16:01:36 101/312: Data time: 0.0025, Iter time: 0.3418	Loss 0.446 (AVG: 0.662)	Score 86.623 (AVG: 82.703)	mIOU 59.453 mAP 70.353 mAcc 71.133
IOU: 72.689 95.616 54.986 64.935 87.043 73.659 68.890 40.351 25.702 67.182 17.221 53.438 52.981 56.764 44.286 44.087 92.607 59.847 74.876 41.909
mAP: 73.448 97.349 65.112 69.686 90.220 81.585 75.725 63.378 43.219 58.215 35.033 58.337 66.186 69.179 58.609 88.990 97.313 87.881 72.401 55.203
mAcc: 86.648 97.873 64.456 81.250 90.015 92.613 86.124 65.394 27.393 89.862 22.935 75.102 77.280 64.155 58.153 44.641 93.970 72.101 78.126 54.566

thomas 04/10 16:03:32 201/312: Data time: 0.0024, Iter time: 0.3679	Loss 0.177 (AVG: 0.671)	Score 93.201 (AVG: 82.486)	mIOU 58.076 mAP 68.585 mAcc 68.967
IOU: 72.428 95.782 52.564 62.904 87.328 72.883 68.133 41.193 26.251 65.823 8.567 52.257 56.588 60.978 38.649 43.426 78.454 59.132 77.229 40.953
mAP: 74.456 97.417 60.233 61.879 89.488 81.237 74.490 60.462 42.568 60.554 29.223 58.829 65.826 71.622 52.638 84.455 89.396 85.632 75.502 55.801
mAcc: 86.175 97.979 62.756 77.948 90.567 92.370 84.440 66.908 28.278 87.407 10.622 71.562 78.079 66.996 49.064 47.274 78.967 64.270 81.360 56.309

thomas 04/10 16:05:29 301/312: Data time: 0.0027, Iter time: 0.4873	Loss 0.480 (AVG: 0.648)	Score 86.954 (AVG: 82.924)	mIOU 58.806 mAP 68.973 mAcc 69.689
IOU: 72.850 95.769 55.478 65.059 87.072 75.809 67.548 40.043 27.666 64.476 7.301 56.284 55.780 65.398 39.569 46.619 76.860 57.630 78.599 40.312
mAP: 74.896 97.378 60.681 65.708 88.855 81.647 73.326 59.976 45.185 63.979 27.067 60.384 64.899 75.899 54.352 83.200 88.057 81.796 77.134 55.052
mAcc: 85.734 97.849 65.471 78.271 90.708 92.722 82.813 69.159 29.653 86.190 8.563 74.129 78.399 72.085 51.928 51.053 77.429 62.512 82.015 57.096

thomas 04/10 16:05:40 312/312: Data time: 0.0030, Iter time: 0.4191	Loss 0.525 (AVG: 0.651)	Score 82.717 (AVG: 82.901)	mIOU 58.915 mAP 69.314 mAcc 69.947
IOU: 72.972 95.733 55.801 66.304 87.234 74.674 67.719 39.878 28.217 62.705 7.388 56.366 55.619 65.648 40.296 47.390 77.534 57.848 79.614 39.358
mAP: 75.202 97.203 61.001 66.911 89.181 81.684 73.749 59.224 45.124 63.979 27.395 61.092 65.503 76.179 55.388 83.338 88.500 82.249 78.363 55.016
mAcc: 85.670 97.839 65.580 79.388 90.880 92.771 83.028 69.222 30.202 86.190 8.667 74.525 78.195 72.416 53.125 52.147 78.119 62.787 82.890 55.301

thomas 04/10 16:05:40 Finished test. Elapsed time: 351.7977
thomas 04/10 16:05:40 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 16:09:32 ===> Epoch[233](70040/301): Loss 0.2181	LR: 4.545e-02	Score 93.042	Data time: 2.2313, Total iter time: 5.7354
thomas 04/10 16:13:23 ===> Epoch[233](70080/301): Loss 0.2285	LR: 4.541e-02	Score 92.863	Data time: 2.2313, Total iter time: 5.6974
thomas 04/10 16:17:16 ===> Epoch[233](70120/301): Loss 0.2122	LR: 4.538e-02	Score 93.147	Data time: 2.2285, Total iter time: 5.7410
thomas 04/10 16:20:54 ===> Epoch[234](70160/301): Loss 0.2126	LR: 4.535e-02	Score 93.066	Data time: 2.1147, Total iter time: 5.3801
thomas 04/10 16:24:46 ===> Epoch[234](70200/301): Loss 0.2265	LR: 4.532e-02	Score 92.831	Data time: 2.2353, Total iter time: 5.7353
thomas 04/10 16:28:40 ===> Epoch[234](70240/301): Loss 0.2118	LR: 4.528e-02	Score 93.191	Data time: 2.2629, Total iter time: 5.7723
thomas 04/10 16:32:20 ===> Epoch[234](70280/301): Loss 0.2216	LR: 4.525e-02	Score 92.939	Data time: 2.1211, Total iter time: 5.4370
thomas 04/10 16:36:25 ===> Epoch[234](70320/301): Loss 0.2063	LR: 4.522e-02	Score 93.073	Data time: 2.3276, Total iter time: 6.0466
thomas 04/10 16:40:04 ===> Epoch[234](70360/301): Loss 0.2302	LR: 4.518e-02	Score 92.626	Data time: 2.1288, Total iter time: 5.4070
thomas 04/10 16:43:53 ===> Epoch[234](70400/301): Loss 0.2232	LR: 4.515e-02	Score 92.934	Data time: 2.2016, Total iter time: 5.6569
thomas 04/10 16:47:14 ===> Epoch[235](70440/301): Loss 0.2212	LR: 4.512e-02	Score 92.759	Data time: 1.9400, Total iter time: 4.9509
thomas 04/10 16:50:49 ===> Epoch[235](70480/301): Loss 0.2323	LR: 4.509e-02	Score 92.527	Data time: 2.0711, Total iter time: 5.2879
thomas 04/10 16:54:36 ===> Epoch[235](70520/301): Loss 0.2088	LR: 4.505e-02	Score 93.351	Data time: 2.1855, Total iter time: 5.6025
thomas 04/10 16:58:11 ===> Epoch[235](70560/301): Loss 0.1975	LR: 4.502e-02	Score 93.671	Data time: 2.0790, Total iter time: 5.3093
thomas 04/10 17:01:47 ===> Epoch[235](70600/301): Loss 0.1807	LR: 4.499e-02	Score 94.196	Data time: 2.0544, Total iter time: 5.3164
thomas 04/10 17:05:48 ===> Epoch[235](70640/301): Loss 0.2265	LR: 4.496e-02	Score 92.824	Data time: 2.3444, Total iter time: 5.9355
thomas 04/10 17:09:38 ===> Epoch[235](70680/301): Loss 0.2050	LR: 4.492e-02	Score 93.285	Data time: 2.2918, Total iter time: 5.6856
thomas 04/10 17:13:08 ===> Epoch[235](70720/301): Loss 0.2013	LR: 4.489e-02	Score 93.327	Data time: 2.0420, Total iter time: 5.1892
thomas 04/10 17:16:37 ===> Epoch[236](70760/301): Loss 0.2406	LR: 4.486e-02	Score 92.290	Data time: 1.9895, Total iter time: 5.1629
thomas 04/10 17:20:09 ===> Epoch[236](70800/301): Loss 0.1997	LR: 4.482e-02	Score 93.548	Data time: 2.0215, Total iter time: 5.2251
thomas 04/10 17:23:35 ===> Epoch[236](70840/301): Loss 0.2046	LR: 4.479e-02	Score 93.586	Data time: 2.0223, Total iter time: 5.0817
thomas 04/10 17:27:07 ===> Epoch[236](70880/301): Loss 0.2251	LR: 4.476e-02	Score 92.680	Data time: 2.0388, Total iter time: 5.2263
thomas 04/10 17:31:05 ===> Epoch[236](70920/301): Loss 0.2089	LR: 4.473e-02	Score 93.209	Data time: 2.2646, Total iter time: 5.8585
thomas 04/10 17:34:41 ===> Epoch[236](70960/301): Loss 0.2217	LR: 4.469e-02	Score 92.884	Data time: 2.0600, Total iter time: 5.3255
thomas 04/10 17:38:16 ===> Epoch[236](71000/301): Loss 0.2306	LR: 4.466e-02	Score 92.576	Data time: 2.0706, Total iter time: 5.2833
thomas 04/10 17:38:17 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 17:38:17 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 17:40:07 101/312: Data time: 0.0273, Iter time: 0.5422	Loss 2.104 (AVG: 0.621)	Score 71.658 (AVG: 85.178)	mIOU 58.480 mAP 69.891 mAcc 68.160
IOU: 79.500 96.380 56.978 64.727 81.778 52.339 71.243 43.150 42.207 73.872 10.564 34.373 56.514 72.711 25.159 53.178 77.898 50.435 84.461 42.121
mAP: 79.358 97.134 61.167 68.506 86.735 84.813 74.444 55.047 43.075 65.191 35.801 48.454 71.794 84.073 37.107 84.737 85.158 86.197 94.421 54.614
mAcc: 92.117 98.595 74.918 75.856 84.381 94.088 82.877 60.170 46.733 86.974 10.803 35.781 73.410 88.547 25.464 60.936 78.654 51.510 85.908 55.478

thomas 04/10 17:41:55 201/312: Data time: 0.0030, Iter time: 0.3683	Loss 0.342 (AVG: 0.594)	Score 88.701 (AVG: 85.426)	mIOU 59.128 mAP 70.326 mAcc 68.572
IOU: 79.693 96.456 54.858 66.907 84.117 62.579 69.314 45.663 48.414 72.420 9.547 32.732 62.085 62.232 34.583 42.480 84.087 47.599 81.063 45.731
mAP: 79.934 97.441 61.875 69.948 86.478 78.238 71.989 58.755 51.160 65.187 29.989 54.945 67.372 81.490 51.296 85.341 90.581 84.091 85.747 54.661
mAcc: 92.236 98.531 76.320 80.606 86.872 95.769 81.610 59.597 55.420 84.672 9.882 33.997 77.188 84.502 35.349 45.408 84.994 48.753 82.609 57.134

thomas 04/10 17:43:53 301/312: Data time: 0.0028, Iter time: 0.6154	Loss 0.652 (AVG: 0.605)	Score 81.175 (AVG: 85.168)	mIOU 58.941 mAP 70.176 mAcc 68.166
IOU: 78.734 96.223 56.436 68.913 84.621 66.413 70.397 44.054 42.228 72.469 8.239 36.744 59.428 63.003 33.186 38.667 84.007 50.318 79.715 45.032
mAP: 79.161 97.445 58.756 70.107 87.372 80.478 72.491 58.762 49.884 71.825 28.466 52.088 66.241 80.427 53.710 83.147 91.273 83.521 81.591 56.779
mAcc: 91.819 98.358 76.130 81.705 87.673 96.283 83.430 59.085 47.513 84.808 8.447 38.483 72.373 85.660 33.975 40.679 84.895 51.903 81.386 58.718

thomas 04/10 17:44:06 312/312: Data time: 0.0034, Iter time: 1.1875	Loss 0.396 (AVG: 0.598)	Score 89.712 (AVG: 85.321)	mIOU 59.293 mAP 70.281 mAcc 68.539
IOU: 78.937 96.286 56.520 69.457 84.909 67.633 70.889 45.019 41.649 72.321 8.158 36.307 59.628 62.011 36.022 38.045 83.954 53.431 79.715 44.968
mAP: 78.874 97.480 58.721 71.143 87.585 80.859 72.804 58.763 50.018 71.571 28.240 52.533 66.151 80.226 53.857 82.128 91.735 84.096 81.591 57.239
mAcc: 91.796 98.369 76.456 82.226 87.938 96.527 83.787 60.555 46.702 84.870 8.361 37.959 72.432 85.614 36.850 39.992 85.432 55.007 81.386 58.520

thomas 04/10 17:44:06 Finished test. Elapsed time: 349.3334
thomas 04/10 17:44:06 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 17:47:41 ===> Epoch[237](71040/301): Loss 0.2111	LR: 4.463e-02	Score 93.213	Data time: 2.0779, Total iter time: 5.2838
thomas 04/10 17:51:26 ===> Epoch[237](71080/301): Loss 0.2414	LR: 4.459e-02	Score 92.046	Data time: 2.1435, Total iter time: 5.5461
thomas 04/10 17:55:05 ===> Epoch[237](71120/301): Loss 0.2436	LR: 4.456e-02	Score 92.135	Data time: 2.0838, Total iter time: 5.4174
thomas 04/10 17:58:39 ===> Epoch[237](71160/301): Loss 0.2060	LR: 4.453e-02	Score 93.245	Data time: 2.0610, Total iter time: 5.2644
thomas 04/10 18:02:17 ===> Epoch[237](71200/301): Loss 0.1951	LR: 4.450e-02	Score 93.630	Data time: 2.0796, Total iter time: 5.3940
thomas 04/10 18:05:53 ===> Epoch[237](71240/301): Loss 0.1918	LR: 4.446e-02	Score 93.697	Data time: 2.0723, Total iter time: 5.3188
thomas 04/10 18:09:29 ===> Epoch[237](71280/301): Loss 0.1988	LR: 4.443e-02	Score 93.264	Data time: 2.0665, Total iter time: 5.3339
thomas 04/10 18:13:10 ===> Epoch[237](71320/301): Loss 0.2163	LR: 4.440e-02	Score 92.748	Data time: 2.1120, Total iter time: 5.4441
thomas 04/10 18:16:39 ===> Epoch[238](71360/301): Loss 0.2111	LR: 4.436e-02	Score 93.516	Data time: 2.0184, Total iter time: 5.1454
thomas 04/10 18:20:20 ===> Epoch[238](71400/301): Loss 0.2354	LR: 4.433e-02	Score 92.510	Data time: 2.1045, Total iter time: 5.4409
thomas 04/10 18:24:00 ===> Epoch[238](71440/301): Loss 0.2699	LR: 4.430e-02	Score 91.414	Data time: 2.1116, Total iter time: 5.4464
thomas 04/10 18:27:32 ===> Epoch[238](71480/301): Loss 0.2122	LR: 4.427e-02	Score 93.207	Data time: 2.0219, Total iter time: 5.2186
thomas 04/10 18:30:55 ===> Epoch[238](71520/301): Loss 0.2062	LR: 4.423e-02	Score 93.505	Data time: 1.9675, Total iter time: 5.0040
thomas 04/10 18:34:41 ===> Epoch[238](71560/301): Loss 0.1880	LR: 4.420e-02	Score 93.816	Data time: 2.1681, Total iter time: 5.5732
thomas 04/10 18:38:13 ===> Epoch[238](71600/301): Loss 0.1997	LR: 4.417e-02	Score 93.486	Data time: 2.0418, Total iter time: 5.2249
thomas 04/10 18:41:54 ===> Epoch[239](71640/301): Loss 0.2195	LR: 4.413e-02	Score 92.742	Data time: 2.1062, Total iter time: 5.4345
thomas 04/10 18:45:34 ===> Epoch[239](71680/301): Loss 0.2157	LR: 4.410e-02	Score 93.027	Data time: 2.0962, Total iter time: 5.4236
thomas 04/10 18:49:14 ===> Epoch[239](71720/301): Loss 0.2215	LR: 4.407e-02	Score 92.978	Data time: 2.0916, Total iter time: 5.4294
thomas 04/10 18:52:45 ===> Epoch[239](71760/301): Loss 0.2103	LR: 4.404e-02	Score 93.042	Data time: 2.0112, Total iter time: 5.1994
thomas 04/10 18:56:29 ===> Epoch[239](71800/301): Loss 0.2040	LR: 4.400e-02	Score 93.412	Data time: 2.1044, Total iter time: 5.5209
thomas 04/10 19:00:11 ===> Epoch[239](71840/301): Loss 0.1885	LR: 4.397e-02	Score 93.832	Data time: 2.1295, Total iter time: 5.4753
thomas 04/10 19:03:39 ===> Epoch[239](71880/301): Loss 0.2165	LR: 4.394e-02	Score 93.125	Data time: 2.0107, Total iter time: 5.1293
thomas 04/10 19:07:15 ===> Epoch[239](71920/301): Loss 0.2499	LR: 4.390e-02	Score 91.927	Data time: 2.0308, Total iter time: 5.3061
thomas 04/10 19:11:00 ===> Epoch[240](71960/301): Loss 0.2270	LR: 4.387e-02	Score 92.716	Data time: 2.1549, Total iter time: 5.5613
thomas 04/10 19:14:24 ===> Epoch[240](72000/301): Loss 0.2037	LR: 4.384e-02	Score 93.513	Data time: 1.9483, Total iter time: 5.0372
thomas 04/10 19:14:26 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 19:14:26 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 19:16:14 101/312: Data time: 0.0023, Iter time: 0.4822	Loss 1.933 (AVG: 0.643)	Score 57.884 (AVG: 84.038)	mIOU 59.020 mAP 69.691 mAcc 69.853
IOU: 75.542 96.701 51.671 51.828 88.244 62.419 73.000 43.975 26.447 75.744 11.110 60.779 52.042 52.095 48.924 36.325 86.575 53.304 92.019 41.647
mAP: 75.412 97.951 60.160 51.044 86.834 87.193 69.129 64.147 43.322 69.116 31.021 56.528 62.858 62.539 63.477 84.621 94.762 86.043 93.031 54.641
mAcc: 87.793 98.519 60.694 66.532 96.417 83.822 78.040 59.831 27.371 97.174 15.351 73.958 74.980 66.877 65.070 39.749 87.226 55.076 94.803 67.782

thomas 04/10 19:18:07 201/312: Data time: 0.0028, Iter time: 0.5128	Loss 1.241 (AVG: 0.588)	Score 73.804 (AVG: 85.097)	mIOU 61.698 mAP 71.303 mAcc 72.447
IOU: 77.829 96.631 54.308 69.528 88.146 72.652 68.675 48.945 31.817 70.376 13.732 63.348 58.186 65.100 42.436 39.418 87.511 56.780 85.805 42.745
mAP: 78.656 97.305 59.094 70.752 89.430 82.249 70.281 65.016 43.121 68.432 36.502 60.356 68.781 76.656 54.430 86.933 92.647 85.277 85.517 54.622
mAcc: 88.690 98.495 62.868 83.794 96.483 88.468 74.589 63.587 33.169 95.507 20.537 75.854 79.368 77.653 57.232 45.207 88.323 58.568 89.779 70.766

thomas 04/10 19:19:43 301/312: Data time: 0.0031, Iter time: 0.2692	Loss 0.442 (AVG: 0.618)	Score 88.615 (AVG: 84.600)	mIOU 61.066 mAP 71.399 mAcc 71.877
IOU: 77.564 96.201 55.179 67.286 86.959 69.670 68.399 47.689 33.338 67.832 14.650 59.683 59.031 67.862 44.673 41.741 86.517 50.503 85.705 40.832
mAP: 78.909 97.279 59.550 67.627 89.880 80.627 70.532 63.825 45.693 68.733 37.396 57.641 69.784 80.888 58.649 90.075 89.410 84.836 82.075 54.568
mAcc: 88.552 98.450 64.966 80.032 95.374 90.071 74.587 61.830 34.944 94.319 20.072 72.686 80.228 81.961 60.308 44.983 87.296 51.843 89.232 65.798

thomas 04/10 19:19:53 312/312: Data time: 0.0028, Iter time: 0.6217	Loss 1.023 (AVG: 0.613)	Score 81.824 (AVG: 84.737)	mIOU 61.176 mAP 71.416 mAcc 72.006
IOU: 77.812 96.234 55.688 67.107 87.067 69.588 68.528 47.956 34.606 67.804 14.229 60.675 59.462 67.834 45.190 40.870 86.956 49.071 85.650 41.181
mAP: 79.080 97.153 59.883 67.627 90.037 80.736 70.659 63.481 46.035 69.371 36.616 56.421 69.820 80.888 59.407 89.226 89.902 84.566 82.432 54.979
mAcc: 88.674 98.445 65.412 80.032 95.448 90.197 74.658 62.319 36.199 94.359 19.963 73.704 80.613 81.961 61.015 43.974 87.725 50.371 89.113 65.945

thomas 04/10 19:19:53 Finished test. Elapsed time: 326.9093
thomas 04/10 19:19:53 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 19:23:12 ===> Epoch[240](72040/301): Loss 0.2366	LR: 4.381e-02	Score 92.571	Data time: 1.8876, Total iter time: 4.9088
thomas 04/10 19:26:42 ===> Epoch[240](72080/301): Loss 0.2329	LR: 4.377e-02	Score 92.761	Data time: 2.0020, Total iter time: 5.1761
thomas 04/10 19:30:19 ===> Epoch[240](72120/301): Loss 0.1976	LR: 4.374e-02	Score 93.833	Data time: 2.0393, Total iter time: 5.3600
thomas 04/10 19:33:51 ===> Epoch[240](72160/301): Loss 0.1998	LR: 4.371e-02	Score 93.376	Data time: 2.0215, Total iter time: 5.2304
thomas 04/10 19:37:18 ===> Epoch[240](72200/301): Loss 0.2077	LR: 4.367e-02	Score 93.321	Data time: 1.9680, Total iter time: 5.1038
thomas 04/10 19:40:51 ===> Epoch[240](72240/301): Loss 0.2236	LR: 4.364e-02	Score 92.695	Data time: 2.0328, Total iter time: 5.2476
thomas 04/10 19:44:26 ===> Epoch[241](72280/301): Loss 0.2464	LR: 4.361e-02	Score 92.026	Data time: 2.0856, Total iter time: 5.3166
thomas 04/10 19:48:12 ===> Epoch[241](72320/301): Loss 0.2269	LR: 4.358e-02	Score 92.700	Data time: 2.1633, Total iter time: 5.5913
thomas 04/10 19:52:05 ===> Epoch[241](72360/301): Loss 0.2164	LR: 4.354e-02	Score 92.956	Data time: 2.2263, Total iter time: 5.7416
thomas 04/10 19:55:59 ===> Epoch[241](72400/301): Loss 0.1867	LR: 4.351e-02	Score 93.875	Data time: 2.2230, Total iter time: 5.7837
thomas 04/10 19:59:40 ===> Epoch[241](72440/301): Loss 0.2034	LR: 4.348e-02	Score 93.494	Data time: 2.1177, Total iter time: 5.4416
thomas 04/10 20:03:27 ===> Epoch[241](72480/301): Loss 0.2072	LR: 4.344e-02	Score 93.473	Data time: 2.1623, Total iter time: 5.6018
thomas 04/10 20:07:06 ===> Epoch[241](72520/301): Loss 0.1923	LR: 4.341e-02	Score 93.741	Data time: 2.0827, Total iter time: 5.4026
thomas 04/10 20:10:55 ===> Epoch[242](72560/301): Loss 0.2217	LR: 4.338e-02	Score 92.889	Data time: 2.1870, Total iter time: 5.6511
thomas 04/10 20:14:44 ===> Epoch[242](72600/301): Loss 0.2057	LR: 4.335e-02	Score 93.438	Data time: 2.1782, Total iter time: 5.6609
thomas 04/10 20:18:30 ===> Epoch[242](72640/301): Loss 0.2137	LR: 4.331e-02	Score 93.025	Data time: 2.1451, Total iter time: 5.5583
thomas 04/10 20:21:54 ===> Epoch[242](72680/301): Loss 0.2054	LR: 4.328e-02	Score 93.440	Data time: 1.9549, Total iter time: 5.0292
thomas 04/10 20:25:52 ===> Epoch[242](72720/301): Loss 0.2334	LR: 4.325e-02	Score 92.419	Data time: 2.2651, Total iter time: 5.8832
thomas 04/10 20:29:35 ===> Epoch[242](72760/301): Loss 0.2784	LR: 4.321e-02	Score 91.403	Data time: 2.1277, Total iter time: 5.5051
thomas 04/10 20:33:10 ===> Epoch[242](72800/301): Loss 0.3130	LR: 4.318e-02	Score 90.133	Data time: 2.0535, Total iter time: 5.3222
thomas 04/10 20:37:05 ===> Epoch[242](72840/301): Loss 0.2601	LR: 4.315e-02	Score 92.092	Data time: 2.2340, Total iter time: 5.7872
thomas 04/10 20:40:37 ===> Epoch[243](72880/301): Loss 0.2360	LR: 4.311e-02	Score 92.350	Data time: 2.0210, Total iter time: 5.2334
thomas 04/10 20:44:22 ===> Epoch[243](72920/301): Loss 0.2534	LR: 4.308e-02	Score 92.203	Data time: 2.1313, Total iter time: 5.5378
thomas 04/10 20:48:18 ===> Epoch[243](72960/301): Loss 0.2470	LR: 4.305e-02	Score 92.198	Data time: 2.2426, Total iter time: 5.8350
thomas 04/10 20:52:12 ===> Epoch[243](73000/301): Loss 0.1974	LR: 4.302e-02	Score 93.606	Data time: 2.2239, Total iter time: 5.7614
thomas 04/10 20:52:14 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 20:52:14 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 20:54:15 101/312: Data time: 0.0037, Iter time: 0.9659	Loss 0.525 (AVG: 0.558)	Score 83.713 (AVG: 84.991)	mIOU 59.493 mAP 69.709 mAcc 70.969
IOU: 79.442 95.756 46.753 67.023 87.610 69.868 60.198 47.867 46.190 76.908 21.228 58.972 46.418 62.474 34.784 34.383 95.584 44.736 66.163 47.508
mAP: 78.294 96.649 51.102 68.880 89.283 80.543 68.619 58.769 50.154 67.404 41.931 57.629 67.379 78.526 52.308 82.534 98.238 77.394 74.340 54.199
mAcc: 87.710 98.857 71.145 76.157 96.065 95.337 64.501 79.389 51.246 90.947 25.694 66.142 80.054 74.123 50.604 35.302 96.651 46.333 74.707 58.418

thomas 04/10 20:56:05 201/312: Data time: 0.0029, Iter time: 0.3121	Loss 0.121 (AVG: 0.590)	Score 96.823 (AVG: 84.188)	mIOU 60.066 mAP 70.823 mAcc 71.495
IOU: 76.153 96.127 49.729 69.397 86.628 68.853 63.975 44.396 38.011 76.271 16.025 61.897 52.617 57.992 40.904 37.427 92.846 51.920 73.473 46.674
mAP: 76.910 97.013 56.596 72.611 89.012 79.625 68.029 62.492 46.940 72.369 36.978 64.014 69.368 71.494 54.993 84.714 97.139 78.294 82.880 54.995
mAcc: 85.637 98.799 71.102 78.263 94.654 95.204 67.489 76.825 43.197 91.918 18.154 68.117 85.105 69.275 58.980 39.749 94.718 53.788 80.013 58.919

thomas 04/10 20:57:54 301/312: Data time: 0.0022, Iter time: 0.6331	Loss 0.719 (AVG: 0.567)	Score 72.690 (AVG: 84.594)	mIOU 61.119 mAP 71.310 mAcc 72.564
IOU: 76.806 96.150 56.533 71.786 87.296 71.410 63.750 44.467 38.703 74.057 16.635 62.451 56.904 56.745 44.229 32.983 92.863 58.806 74.780 45.018
mAP: 78.193 97.232 59.434 74.434 89.918 81.314 68.793 63.299 48.151 70.728 37.202 60.538 70.556 72.754 60.510 77.791 97.263 82.222 80.489 55.382
mAcc: 85.646 98.819 74.940 81.010 95.289 95.154 67.530 76.558 45.160 90.843 19.290 72.653 84.950 70.782 63.973 35.347 94.542 61.268 79.983 57.537

thomas 04/10 20:58:01 312/312: Data time: 0.0031, Iter time: 0.2062	Loss 0.184 (AVG: 0.563)	Score 92.603 (AVG: 84.651)	mIOU 61.307 mAP 71.585 mAcc 72.767
IOU: 76.864 96.152 57.499 71.771 87.550 71.295 63.736 44.404 38.255 73.926 16.590 63.030 56.458 56.180 46.293 33.881 92.853 58.979 75.331 45.091
mAP: 78.184 97.293 59.934 74.906 90.069 81.314 69.649 63.439 47.865 70.728 36.795 61.407 70.625 73.297 61.309 78.539 97.304 82.381 81.094 55.567
mAcc: 85.643 98.829 75.726 81.279 95.364 95.154 67.463 76.248 44.639 90.843 19.230 72.780 84.684 71.135 65.989 36.213 94.513 61.507 80.426 57.668

thomas 04/10 20:58:01 Finished test. Elapsed time: 347.3332
thomas 04/10 20:58:01 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 21:01:28 ===> Epoch[243](73040/301): Loss 0.2067	LR: 4.298e-02	Score 93.192	Data time: 2.0110, Total iter time: 5.1044
thomas 04/10 21:05:19 ===> Epoch[243](73080/301): Loss 0.2388	LR: 4.295e-02	Score 92.311	Data time: 2.2398, Total iter time: 5.6925
thomas 04/10 21:09:09 ===> Epoch[243](73120/301): Loss 0.3065	LR: 4.292e-02	Score 90.644	Data time: 2.1974, Total iter time: 5.6717
thomas 04/10 21:12:55 ===> Epoch[244](73160/301): Loss 0.2788	LR: 4.288e-02	Score 91.215	Data time: 2.1475, Total iter time: 5.5744
thomas 04/10 21:16:38 ===> Epoch[244](73200/301): Loss 0.2553	LR: 4.285e-02	Score 92.061	Data time: 2.1572, Total iter time: 5.5124
thomas 04/10 21:20:40 ===> Epoch[244](73240/301): Loss 0.2578	LR: 4.282e-02	Score 91.817	Data time: 2.3079, Total iter time: 5.9564
thomas 04/10 21:24:34 ===> Epoch[244](73280/301): Loss 0.2502	LR: 4.279e-02	Score 92.249	Data time: 2.2485, Total iter time: 5.7812
thomas 04/10 21:28:41 ===> Epoch[244](73320/301): Loss 0.2285	LR: 4.275e-02	Score 92.658	Data time: 2.3143, Total iter time: 6.0967
thomas 04/10 21:32:19 ===> Epoch[244](73360/301): Loss 0.2081	LR: 4.272e-02	Score 93.025	Data time: 2.0710, Total iter time: 5.3747
thomas 04/10 21:36:04 ===> Epoch[244](73400/301): Loss 0.2062	LR: 4.269e-02	Score 93.321	Data time: 2.1542, Total iter time: 5.5636
thomas 04/10 21:39:39 ===> Epoch[244](73440/301): Loss 0.2099	LR: 4.265e-02	Score 93.356	Data time: 2.0264, Total iter time: 5.2915
thomas 04/10 21:43:24 ===> Epoch[245](73480/301): Loss 0.2257	LR: 4.262e-02	Score 93.078	Data time: 2.1396, Total iter time: 5.5719
thomas 04/10 21:47:02 ===> Epoch[245](73520/301): Loss 0.1908	LR: 4.259e-02	Score 93.835	Data time: 2.0698, Total iter time: 5.3759
thomas 04/10 21:50:45 ===> Epoch[245](73560/301): Loss 0.2086	LR: 4.255e-02	Score 92.910	Data time: 2.1308, Total iter time: 5.4916
thomas 04/10 21:54:28 ===> Epoch[245](73600/301): Loss 0.1899	LR: 4.252e-02	Score 93.756	Data time: 2.1286, Total iter time: 5.5091
thomas 04/10 21:58:21 ===> Epoch[245](73640/301): Loss 0.2333	LR: 4.249e-02	Score 92.469	Data time: 2.2020, Total iter time: 5.7461
thomas 04/10 22:02:05 ===> Epoch[245](73680/301): Loss 0.2034	LR: 4.246e-02	Score 93.410	Data time: 2.1415, Total iter time: 5.5279
thomas 04/10 22:05:52 ===> Epoch[245](73720/301): Loss 0.2070	LR: 4.242e-02	Score 93.076	Data time: 2.1483, Total iter time: 5.5842
thomas 04/10 22:09:48 ===> Epoch[246](73760/301): Loss 0.1937	LR: 4.239e-02	Score 93.637	Data time: 2.2549, Total iter time: 5.8427
thomas 04/10 22:13:35 ===> Epoch[246](73800/301): Loss 0.2104	LR: 4.236e-02	Score 93.323	Data time: 2.1589, Total iter time: 5.5763
thomas 04/10 22:17:13 ===> Epoch[246](73840/301): Loss 0.2097	LR: 4.232e-02	Score 93.347	Data time: 2.0849, Total iter time: 5.3901
thomas 04/10 22:20:40 ===> Epoch[246](73880/301): Loss 0.2116	LR: 4.229e-02	Score 93.125	Data time: 2.0005, Total iter time: 5.0963
thomas 04/10 22:24:13 ===> Epoch[246](73920/301): Loss 0.1944	LR: 4.226e-02	Score 93.692	Data time: 2.0406, Total iter time: 5.2441
thomas 04/10 22:28:03 ===> Epoch[246](73960/301): Loss 0.2078	LR: 4.222e-02	Score 93.063	Data time: 2.1995, Total iter time: 5.6858
thomas 04/10 22:31:50 ===> Epoch[246](74000/301): Loss 0.2202	LR: 4.219e-02	Score 92.802	Data time: 2.1518, Total iter time: 5.5954
thomas 04/10 22:31:52 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/10 22:31:52 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/10 22:33:48 101/312: Data time: 0.0027, Iter time: 0.4721	Loss 0.205 (AVG: 0.590)	Score 91.744 (AVG: 84.705)	mIOU 61.863 mAP 70.575 mAcc 73.445
IOU: 76.799 95.931 54.587 80.064 87.288 69.038 68.713 44.369 32.384 82.266 4.956 60.020 58.651 68.657 43.243 57.437 85.221 41.455 80.086 46.099
mAP: 76.598 97.422 54.028 79.440 90.436 80.372 70.702 61.709 48.192 69.475 26.498 61.890 63.521 80.595 66.656 93.276 90.540 69.252 75.969 54.941
mAcc: 87.660 98.757 74.320 90.940 91.166 94.946 75.957 69.967 34.396 92.532 5.118 70.217 85.090 81.547 68.778 63.351 85.712 54.870 85.296 58.281

thomas 04/10 22:35:39 201/312: Data time: 0.0027, Iter time: 0.7781	Loss 0.641 (AVG: 0.572)	Score 82.771 (AVG: 85.148)	mIOU 62.887 mAP 71.594 mAcc 74.307
IOU: 77.273 95.909 56.450 77.504 86.327 68.102 71.775 44.170 39.473 80.802 7.777 56.316 59.651 62.579 44.382 60.628 89.587 48.122 81.976 48.936
mAP: 76.704 97.338 59.089 77.742 89.605 81.366 70.940 58.020 52.255 72.211 32.082 57.260 64.084 77.556 64.874 90.523 94.837 77.886 78.954 58.550
mAcc: 88.206 98.680 72.875 88.723 89.982 94.845 78.736 68.738 41.864 91.609 8.124 66.014 85.764 77.449 66.943 64.085 90.345 63.388 86.028 63.746

thomas 04/10 22:37:25 301/312: Data time: 0.0030, Iter time: 0.3049	Loss 0.226 (AVG: 0.571)	Score 90.777 (AVG: 85.168)	mIOU 62.216 mAP 71.691 mAcc 73.788
IOU: 77.705 96.094 54.873 74.739 86.220 67.386 70.966 44.749 37.912 76.905 9.195 54.812 55.952 68.066 45.035 57.880 84.631 49.011 83.854 48.325
mAP: 76.525 97.260 56.884 77.313 89.988 81.878 72.093 59.721 49.799 72.146 33.829 59.572 64.888 82.167 65.056 89.974 89.623 79.019 78.629 57.448
mAcc: 88.776 98.748 71.182 85.445 89.842 95.396 78.607 67.602 39.961 89.200 9.565 63.675 85.023 81.712 69.340 62.930 85.438 63.058 87.916 62.337

thomas 04/10 22:37:35 312/312: Data time: 0.0025, Iter time: 0.4496	Loss 0.555 (AVG: 0.570)	Score 86.870 (AVG: 85.186)	mIOU 62.140 mAP 71.393 mAcc 73.623
IOU: 77.712 96.130 54.279 74.726 86.384 68.059 71.234 45.452 37.435 77.259 9.078 54.702 56.401 67.421 45.168 56.979 83.455 49.070 83.854 47.998
mAP: 76.621 97.308 56.230 77.709 89.950 82.098 72.078 60.569 48.836 71.637 33.098 59.895 64.474 80.141 65.175 87.527 89.901 79.285 78.629 56.706
mAcc: 88.816 98.755 70.260 85.710 90.005 95.654 78.827 68.107 39.621 89.493 9.487 63.467 85.045 80.918 69.528 61.866 84.217 62.697 87.916 62.079

thomas 04/10 22:37:35 Finished test. Elapsed time: 342.9827
thomas 04/10 22:37:35 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/10 22:41:19 ===> Epoch[246](74040/301): Loss 0.2203	LR: 4.216e-02	Score 93.026	Data time: 2.1458, Total iter time: 5.5344
thomas 04/10 22:45:07 ===> Epoch[247](74080/301): Loss 0.2046	LR: 4.213e-02	Score 93.386	Data time: 2.1739, Total iter time: 5.6129
thomas 04/10 22:49:03 ===> Epoch[247](74120/301): Loss 0.2351	LR: 4.209e-02	Score 92.387	Data time: 2.2543, Total iter time: 5.8104
thomas 04/10 22:52:44 ===> Epoch[247](74160/301): Loss 0.2232	LR: 4.206e-02	Score 92.997	Data time: 2.1148, Total iter time: 5.4685
thomas 04/10 22:56:29 ===> Epoch[247](74200/301): Loss 0.2171	LR: 4.203e-02	Score 93.033	Data time: 2.1580, Total iter time: 5.5458
thomas 04/10 23:00:41 ===> Epoch[247](74240/301): Loss 0.2364	LR: 4.199e-02	Score 92.590	Data time: 2.4774, Total iter time: 6.2189
thomas 04/10 23:04:04 ===> Epoch[247](74280/301): Loss 0.2528	LR: 4.196e-02	Score 91.917	Data time: 1.9527, Total iter time: 5.0308
thomas 04/10 23:07:37 ===> Epoch[247](74320/301): Loss 0.2008	LR: 4.193e-02	Score 93.619	Data time: 2.0226, Total iter time: 5.2293
thomas 04/10 23:11:04 ===> Epoch[248](74360/301): Loss 0.2144	LR: 4.189e-02	Score 93.009	Data time: 1.9540, Total iter time: 5.1182
thomas 04/10 23:14:41 ===> Epoch[248](74400/301): Loss 0.2253	LR: 4.186e-02	Score 92.625	Data time: 2.0180, Total iter time: 5.3227
thomas 04/10 23:18:08 ===> Epoch[248](74440/301): Loss 0.1962	LR: 4.183e-02	Score 93.602	Data time: 1.9771, Total iter time: 5.1087
thomas 04/10 23:21:40 ===> Epoch[248](74480/301): Loss 0.1934	LR: 4.179e-02	Score 93.678	Data time: 1.9654, Total iter time: 5.2164
thomas 04/10 23:25:10 ===> Epoch[248](74520/301): Loss 0.1915	LR: 4.176e-02	Score 93.726	Data time: 1.9794, Total iter time: 5.1935
thomas 04/10 23:28:37 ===> Epoch[248](74560/301): Loss 0.1821	LR: 4.173e-02	Score 93.990	Data time: 1.9696, Total iter time: 5.0875
thomas 04/10 23:32:13 ===> Epoch[248](74600/301): Loss 0.1851	LR: 4.170e-02	Score 93.937	Data time: 2.0489, Total iter time: 5.3298
thomas 04/10 23:35:40 ===> Epoch[248](74640/301): Loss 0.2178	LR: 4.166e-02	Score 93.013	Data time: 1.9493, Total iter time: 5.1006
thomas 04/10 23:39:16 ===> Epoch[249](74680/301): Loss 0.1983	LR: 4.163e-02	Score 93.532	Data time: 2.0465, Total iter time: 5.3191
thomas 04/10 23:42:41 ===> Epoch[249](74720/301): Loss 0.2173	LR: 4.160e-02	Score 93.269	Data time: 1.9269, Total iter time: 5.0501
thomas 04/10 23:46:16 ===> Epoch[249](74760/301): Loss 0.2236	LR: 4.156e-02	Score 92.539	Data time: 2.0416, Total iter time: 5.3081
thomas 04/10 23:49:48 ===> Epoch[249](74800/301): Loss 0.1947	LR: 4.153e-02	Score 93.552	Data time: 2.0099, Total iter time: 5.2398
thomas 04/10 23:53:25 ===> Epoch[249](74840/301): Loss 0.1929	LR: 4.150e-02	Score 93.494	Data time: 2.0359, Total iter time: 5.3411
thomas 04/10 23:57:01 ===> Epoch[249](74880/301): Loss 0.1905	LR: 4.146e-02	Score 93.710	Data time: 2.0519, Total iter time: 5.3255
thomas 04/11 00:00:38 ===> Epoch[249](74920/301): Loss 0.1902	LR: 4.143e-02	Score 93.711	Data time: 2.0503, Total iter time: 5.3441
thomas 04/11 00:04:05 ===> Epoch[250](74960/301): Loss 0.2349	LR: 4.140e-02	Score 92.740	Data time: 1.9532, Total iter time: 5.0911
thomas 04/11 00:07:27 ===> Epoch[250](75000/301): Loss 0.2326	LR: 4.137e-02	Score 92.621	Data time: 1.9285, Total iter time: 4.9780
thomas 04/11 00:07:28 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 00:07:28 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 00:09:15 101/312: Data time: 0.0025, Iter time: 0.3609	Loss 1.269 (AVG: 0.594)	Score 66.670 (AVG: 85.830)	mIOU 63.959 mAP 72.766 mAcc 74.383
IOU: 78.476 95.525 62.693 71.569 88.588 78.978 70.212 46.290 33.513 76.213 23.049 60.518 59.955 61.616 43.705 64.711 92.625 53.215 76.006 41.726
mAP: 77.780 97.075 66.679 75.555 92.152 77.550 75.305 66.868 49.395 52.555 49.579 61.429 62.207 81.353 52.015 94.142 96.352 87.554 82.569 57.206
mAcc: 92.929 98.954 75.054 77.760 93.404 94.050 77.565 68.549 34.433 90.154 26.428 93.567 83.584 77.945 54.287 71.820 94.323 53.660 82.818 46.374

thomas 04/11 00:11:02 201/312: Data time: 0.0023, Iter time: 0.5203	Loss 0.421 (AVG: 0.605)	Score 91.062 (AVG: 85.049)	mIOU 61.409 mAP 71.805 mAcc 71.848
IOU: 76.990 95.828 56.241 74.740 88.071 78.110 69.013 45.995 29.993 75.133 16.738 59.600 59.770 57.378 35.761 53.863 88.165 45.507 80.179 41.111
mAP: 75.365 97.192 64.070 78.346 90.561 81.206 73.965 66.525 44.672 60.854 43.609 57.562 60.949 79.620 55.332 91.519 93.033 85.111 80.268 56.349
mAcc: 92.254 98.906 70.681 82.167 92.697 93.205 77.973 65.470 31.151 85.194 19.090 84.451 83.717 81.466 48.088 59.929 91.933 45.973 85.737 46.876

thomas 04/11 00:12:51 301/312: Data time: 0.0023, Iter time: 0.5830	Loss 0.724 (AVG: 0.596)	Score 72.091 (AVG: 85.129)	mIOU 61.327 mAP 71.503 mAcc 71.897
IOU: 77.282 95.814 56.758 73.843 88.852 81.917 69.034 45.171 29.926 75.574 15.540 58.060 57.665 60.462 34.003 53.414 88.241 43.762 78.907 42.307
mAP: 75.115 97.149 61.285 75.872 90.570 81.606 72.843 64.616 48.257 64.391 41.998 58.207 59.777 81.509 52.788 89.003 93.269 82.798 80.646 58.369
mAcc: 92.023 98.950 70.751 79.849 92.997 94.456 77.935 64.100 31.149 86.375 17.402 84.867 82.933 85.186 46.326 60.292 92.363 44.126 87.222 48.642

thomas 04/11 00:13:02 312/312: Data time: 0.0025, Iter time: 0.4363	Loss 0.748 (AVG: 0.588)	Score 81.073 (AVG: 85.303)	mIOU 61.548 mAP 71.560 mAcc 72.120
IOU: 77.408 95.864 57.519 73.762 89.122 81.592 69.833 45.181 29.697 75.468 15.539 58.588 57.149 60.876 36.658 53.414 88.239 43.888 78.907 42.253
mAP: 75.149 97.209 60.769 75.105 90.494 82.064 73.071 64.571 48.323 65.059 41.998 58.430 59.777 81.564 53.769 89.003 93.269 82.842 80.646 58.081
mAcc: 92.012 98.978 70.983 79.631 93.152 94.547 78.323 64.398 30.897 86.312 17.402 84.933 82.933 85.739 49.280 60.292 92.363 44.280 87.222 48.716

thomas 04/11 00:13:02 Finished test. Elapsed time: 333.7607
thomas 04/11 00:13:02 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 00:16:38 ===> Epoch[250](75040/301): Loss 0.2132	LR: 4.133e-02	Score 93.174	Data time: 2.0599, Total iter time: 5.3184
thomas 04/11 00:20:01 ===> Epoch[250](75080/301): Loss 0.1996	LR: 4.130e-02	Score 93.484	Data time: 1.9219, Total iter time: 5.0148
thomas 04/11 00:23:30 ===> Epoch[250](75120/301): Loss 0.2095	LR: 4.127e-02	Score 93.432	Data time: 1.9687, Total iter time: 5.1522
thomas 04/11 00:27:02 ===> Epoch[250](75160/301): Loss 0.2338	LR: 4.123e-02	Score 92.634	Data time: 1.9934, Total iter time: 5.2167
thomas 04/11 00:30:33 ===> Epoch[250](75200/301): Loss 0.2185	LR: 4.120e-02	Score 93.071	Data time: 2.0221, Total iter time: 5.1945
thomas 04/11 00:34:19 ===> Epoch[250](75240/301): Loss 0.2446	LR: 4.117e-02	Score 92.522	Data time: 2.1656, Total iter time: 5.5816
thomas 04/11 00:37:55 ===> Epoch[251](75280/301): Loss 0.1985	LR: 4.113e-02	Score 93.524	Data time: 2.0615, Total iter time: 5.3319
thomas 04/11 00:41:28 ===> Epoch[251](75320/301): Loss 0.1883	LR: 4.110e-02	Score 93.585	Data time: 2.0225, Total iter time: 5.2434
thomas 04/11 00:45:00 ===> Epoch[251](75360/301): Loss 0.1992	LR: 4.107e-02	Score 93.398	Data time: 2.0248, Total iter time: 5.2185
thomas 04/11 00:48:35 ===> Epoch[251](75400/301): Loss 0.1862	LR: 4.103e-02	Score 94.081	Data time: 2.0429, Total iter time: 5.3048
thomas 04/11 00:52:14 ===> Epoch[251](75440/301): Loss 0.1981	LR: 4.100e-02	Score 93.584	Data time: 2.0951, Total iter time: 5.4070
thomas 04/11 00:55:45 ===> Epoch[251](75480/301): Loss 0.1824	LR: 4.097e-02	Score 93.986	Data time: 2.0270, Total iter time: 5.1794
thomas 04/11 00:59:11 ===> Epoch[251](75520/301): Loss 0.1918	LR: 4.093e-02	Score 93.589	Data time: 1.9616, Total iter time: 5.0765
thomas 04/11 01:02:35 ===> Epoch[252](75560/301): Loss 0.2151	LR: 4.090e-02	Score 93.258	Data time: 1.9631, Total iter time: 5.0480
thomas 04/11 01:06:02 ===> Epoch[252](75600/301): Loss 0.2221	LR: 4.087e-02	Score 92.845	Data time: 1.9571, Total iter time: 5.0800
thomas 04/11 01:09:55 ===> Epoch[252](75640/301): Loss 0.2276	LR: 4.084e-02	Score 92.725	Data time: 2.2279, Total iter time: 5.7522
thomas 04/11 01:13:18 ===> Epoch[252](75680/301): Loss 0.2269	LR: 4.080e-02	Score 92.755	Data time: 1.9450, Total iter time: 5.0132
thomas 04/11 01:16:50 ===> Epoch[252](75720/301): Loss 0.1949	LR: 4.077e-02	Score 93.624	Data time: 2.0252, Total iter time: 5.2147
thomas 04/11 01:20:16 ===> Epoch[252](75760/301): Loss 0.1879	LR: 4.074e-02	Score 93.723	Data time: 1.9927, Total iter time: 5.0889
thomas 04/11 01:24:00 ===> Epoch[252](75800/301): Loss 0.2066	LR: 4.070e-02	Score 93.326	Data time: 2.1602, Total iter time: 5.5332
thomas 04/11 01:27:23 ===> Epoch[252](75840/301): Loss 0.2253	LR: 4.067e-02	Score 92.847	Data time: 1.9507, Total iter time: 4.9992
thomas 04/11 01:31:08 ===> Epoch[253](75880/301): Loss 0.2165	LR: 4.064e-02	Score 92.926	Data time: 2.1117, Total iter time: 5.5349
thomas 04/11 01:34:38 ===> Epoch[253](75920/301): Loss 0.2146	LR: 4.060e-02	Score 93.056	Data time: 1.9897, Total iter time: 5.1617
thomas 04/11 01:38:12 ===> Epoch[253](75960/301): Loss 0.2158	LR: 4.057e-02	Score 93.002	Data time: 2.0376, Total iter time: 5.2646
thomas 04/11 01:41:48 ===> Epoch[253](76000/301): Loss 0.1851	LR: 4.054e-02	Score 93.950	Data time: 2.0551, Total iter time: 5.3302
thomas 04/11 01:41:49 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 01:41:49 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 01:43:36 101/312: Data time: 0.0023, Iter time: 0.4961	Loss 0.881 (AVG: 0.613)	Score 80.048 (AVG: 83.657)	mIOU 58.923 mAP 71.021 mAcc 71.220
IOU: 73.794 96.531 52.784 70.879 90.299 65.091 74.533 40.947 39.731 63.441 11.900 67.884 57.192 67.029 45.146 29.325 86.249 42.876 66.803 36.025
mAP: 76.083 97.886 61.674 67.981 91.944 75.476 72.328 55.946 46.421 67.184 32.968 68.313 66.239 87.245 73.426 88.676 91.169 78.029 72.684 48.750
mAcc: 83.062 99.062 69.180 74.961 94.786 92.370 83.896 51.578 47.112 95.002 12.808 88.413 85.189 82.944 79.233 29.537 86.966 43.259 67.961 57.071

thomas 04/11 01:45:22 201/312: Data time: 0.0025, Iter time: 0.6239	Loss 1.168 (AVG: 0.616)	Score 75.154 (AVG: 83.578)	mIOU 59.013 mAP 71.635 mAcc 71.917
IOU: 75.075 96.373 50.730 66.823 88.328 65.649 70.116 42.518 41.385 57.394 14.989 59.356 55.019 66.120 39.936 45.066 81.588 44.818 78.083 40.899
mAP: 77.050 97.720 62.715 69.874 90.523 74.020 71.259 57.651 50.122 68.702 38.973 62.464 66.804 81.087 66.431 87.127 90.785 80.828 84.366 54.193
mAcc: 84.496 98.995 69.873 71.640 93.327 89.927 81.240 54.127 47.816 94.071 16.345 87.586 81.259 79.956 74.375 46.467 82.390 45.246 79.346 59.852

thomas 04/11 01:47:02 301/312: Data time: 0.0024, Iter time: 0.2638	Loss 0.300 (AVG: 0.613)	Score 89.187 (AVG: 83.519)	mIOU 58.203 mAP 71.617 mAcc 71.554
IOU: 75.667 96.190 51.114 67.821 88.027 69.732 66.970 41.499 43.397 56.159 16.005 54.830 54.854 68.119 38.238 33.191 82.162 40.884 78.498 40.699
mAP: 78.307 97.397 61.210 69.897 90.690 80.344 69.036 58.138 50.845 70.448 41.245 60.372 66.409 81.063 69.179 85.130 89.482 81.699 78.203 53.242
mAcc: 85.434 98.874 69.932 72.282 92.948 92.540 77.590 52.708 49.079 94.498 18.107 88.667 83.845 80.138 77.694 34.751 82.987 41.330 79.654 58.015

thomas 04/11 01:47:14 312/312: Data time: 0.0024, Iter time: 0.2669	Loss 0.212 (AVG: 0.616)	Score 92.652 (AVG: 83.506)	mIOU 58.042 mAP 71.503 mAcc 71.258
IOU: 75.527 96.235 51.021 67.820 88.118 70.141 66.668 41.501 42.192 56.273 15.675 54.776 53.505 68.130 39.459 32.479 81.739 40.521 78.498 40.571
mAP: 78.086 97.455 61.052 69.897 90.831 80.835 69.755 58.031 49.804 70.426 41.186 59.932 66.195 81.101 70.081 82.895 89.660 81.480 78.203 53.150
mAcc: 85.417 98.888 69.865 72.282 93.057 92.804 77.047 52.656 47.608 94.739 17.686 87.107 83.667 80.071 77.624 33.972 82.558 40.950 79.654 57.502

thomas 04/11 01:47:14 Finished test. Elapsed time: 324.5964
thomas 04/11 01:47:14 Current best mIoU: 62.239 at iter 59000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 01:50:38 ===> Epoch[253](76040/301): Loss 0.1963	LR: 4.050e-02	Score 93.799	Data time: 1.9488, Total iter time: 5.0238
thomas 04/11 01:54:07 ===> Epoch[253](76080/301): Loss 0.2080	LR: 4.047e-02	Score 93.273	Data time: 2.0257, Total iter time: 5.1676
thomas 04/11 01:58:00 ===> Epoch[253](76120/301): Loss 0.1941	LR: 4.044e-02	Score 93.553	Data time: 2.2450, Total iter time: 5.7339
thomas 04/11 02:01:52 ===> Epoch[254](76160/301): Loss 0.1932	LR: 4.040e-02	Score 93.808	Data time: 2.2323, Total iter time: 5.7258
thomas 04/11 02:05:37 ===> Epoch[254](76200/301): Loss 0.2140	LR: 4.037e-02	Score 93.104	Data time: 2.1313, Total iter time: 5.5347
thomas 04/11 02:08:56 ===> Epoch[254](76240/301): Loss 0.2101	LR: 4.034e-02	Score 93.056	Data time: 1.9030, Total iter time: 4.9165
thomas 04/11 02:12:13 ===> Epoch[254](76280/301): Loss 0.1872	LR: 4.030e-02	Score 93.891	Data time: 1.8895, Total iter time: 4.8575
thomas 04/11 02:15:43 ===> Epoch[254](76320/301): Loss 0.1829	LR: 4.027e-02	Score 93.913	Data time: 1.9913, Total iter time: 5.1747
thomas 04/11 02:19:15 ===> Epoch[254](76360/301): Loss 0.2012	LR: 4.024e-02	Score 93.719	Data time: 1.9987, Total iter time: 5.2209
thomas 04/11 02:22:44 ===> Epoch[254](76400/301): Loss 0.1922	LR: 4.021e-02	Score 93.788	Data time: 1.9798, Total iter time: 5.1503
thomas 04/11 02:26:13 ===> Epoch[254](76440/301): Loss 0.1924	LR: 4.017e-02	Score 93.704	Data time: 1.9963, Total iter time: 5.1506
thomas 04/11 02:29:50 ===> Epoch[255](76480/301): Loss 0.2190	LR: 4.014e-02	Score 92.914	Data time: 2.0928, Total iter time: 5.3533
thomas 04/11 02:33:31 ===> Epoch[255](76520/301): Loss 0.1958	LR: 4.011e-02	Score 93.637	Data time: 2.1178, Total iter time: 5.4701
thomas 04/11 02:37:12 ===> Epoch[255](76560/301): Loss 0.2099	LR: 4.007e-02	Score 93.404	Data time: 2.1167, Total iter time: 5.4459
thomas 04/11 02:40:33 ===> Epoch[255](76600/301): Loss 0.1748	LR: 4.004e-02	Score 94.161	Data time: 1.9402, Total iter time: 4.9467
thomas 04/11 02:44:06 ===> Epoch[255](76640/301): Loss 0.1875	LR: 4.001e-02	Score 93.889	Data time: 2.0633, Total iter time: 5.2632
thomas 04/11 02:47:49 ===> Epoch[255](76680/301): Loss 0.1968	LR: 3.997e-02	Score 93.585	Data time: 2.1285, Total iter time: 5.4929
thomas 04/11 02:51:37 ===> Epoch[255](76720/301): Loss 0.1878	LR: 3.994e-02	Score 93.736	Data time: 2.1664, Total iter time: 5.6187
thomas 04/11 02:55:07 ===> Epoch[256](76760/301): Loss 0.1966	LR: 3.991e-02	Score 93.794	Data time: 2.0084, Total iter time: 5.1833
thomas 04/11 02:58:46 ===> Epoch[256](76800/301): Loss 0.1838	LR: 3.987e-02	Score 93.937	Data time: 2.0941, Total iter time: 5.3845
thomas 04/11 03:02:07 ===> Epoch[256](76840/301): Loss 0.2190	LR: 3.984e-02	Score 93.047	Data time: 1.9206, Total iter time: 4.9734
thomas 04/11 03:05:16 ===> Epoch[256](76880/301): Loss 0.2205	LR: 3.981e-02	Score 92.908	Data time: 1.8162, Total iter time: 4.6469
thomas 04/11 03:08:52 ===> Epoch[256](76920/301): Loss 0.2194	LR: 3.977e-02	Score 93.102	Data time: 2.0540, Total iter time: 5.3240
thomas 04/11 03:12:24 ===> Epoch[256](76960/301): Loss 0.1876	LR: 3.974e-02	Score 93.937	Data time: 2.0417, Total iter time: 5.2362
thomas 04/11 03:15:42 ===> Epoch[256](77000/301): Loss 0.2007	LR: 3.971e-02	Score 93.423	Data time: 1.8971, Total iter time: 4.8859
thomas 04/11 03:15:44 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 03:15:44 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 03:17:28 101/312: Data time: 0.0025, Iter time: 0.4016	Loss 0.803 (AVG: 0.581)	Score 82.004 (AVG: 85.191)	mIOU 62.539 mAP 72.429 mAcc 73.072
IOU: 77.047 96.085 62.178 68.597 79.131 71.883 71.747 49.248 25.398 79.298 18.774 65.305 59.204 71.239 29.969 49.168 91.273 51.083 84.096 50.058
mAP: 77.824 97.022 57.052 75.637 90.209 78.122 71.254 62.749 48.598 75.664 45.545 61.802 69.123 85.088 54.244 84.037 93.095 84.065 83.926 53.528
mAcc: 87.623 98.275 76.128 84.585 85.080 95.422 83.914 73.426 26.716 94.669 29.858 77.575 73.424 90.599 36.086 51.583 92.524 52.019 85.652 66.281

thomas 04/11 03:19:13 201/312: Data time: 0.0028, Iter time: 0.3945	Loss 0.349 (AVG: 0.566)	Score 88.972 (AVG: 85.317)	mIOU 62.936 mAP 72.100 mAcc 73.320
IOU: 77.843 96.263 61.768 68.685 85.446 72.250 70.481 48.546 31.148 76.540 19.394 65.492 59.313 66.867 37.823 53.580 88.399 45.560 85.611 47.709
mAP: 78.914 97.574 57.107 76.730 91.761 79.443 69.079 64.043 48.815 72.752 45.905 59.494 66.903 81.976 55.949 88.856 90.239 77.682 81.299 57.475
mAcc: 88.287 98.543 74.459 87.561 90.370 94.238 82.039 69.018 32.961 92.140 26.164 77.358 71.830 87.074 44.262 57.646 89.761 47.033 87.298 68.361

thomas 04/11 03:21:01 301/312: Data time: 0.0035, Iter time: 0.5929	Loss 0.155 (AVG: 0.546)	Score 95.702 (AVG: 85.596)	mIOU 62.665 mAP 72.385 mAcc 73.480
IOU: 78.547 96.385 61.257 67.041 87.441 73.167 71.279 47.451 30.708 75.753 18.696 61.885 58.879 62.822 40.694 50.663 88.865 47.178 84.911 49.684
mAP: 78.951 97.621 58.393 75.133 91.756 78.603 72.579 64.211 49.102 73.835 45.025 58.266 65.136 83.542 59.409 87.446 91.897 79.148 81.242 56.413
mAcc: 88.582 98.636 74.569 87.957 92.228 94.011 83.342 66.196 33.212 92.465 26.798 73.510 71.058 88.871 50.104 53.777 90.298 48.622 86.912 68.445

thomas 04/11 03:21:11 312/312: Data time: 0.0029, Iter time: 0.2816	Loss 0.873 (AVG: 0.544)	Score 78.402 (AVG: 85.679)	mIOU 62.662 mAP 72.363 mAcc 73.477
IOU: 78.553 96.420 60.808 66.957 87.627 73.592 71.893 47.466 30.405 76.780 18.487 60.371 58.864 62.786 40.611 50.657 88.984 47.031 85.126 49.820
mAP: 78.778 97.560 58.176 75.133 91.762 78.895 72.719 64.064 48.861 73.514 44.044 58.202 65.136 83.641 59.409 87.446 92.051 79.375 81.706 56.781
mAcc: 88.692 98.652 73.772 87.957 92.364 94.133 83.672 66.077 32.821 92.909 26.654 73.509 71.058 88.721 50.104 53.777 90.429 48.467 87.115 68.666

thomas 04/11 03:21:11 Finished test. Elapsed time: 327.4835
thomas 04/11 03:21:13 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/11 03:21:13 Current best mIoU: 62.662 at iter 77000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 03:24:42 ===> Epoch[256](77040/301): Loss 0.2056	LR: 3.967e-02	Score 93.053	Data time: 1.9800, Total iter time: 5.1492
thomas 04/11 03:28:23 ===> Epoch[257](77080/301): Loss 0.2154	LR: 3.964e-02	Score 93.096	Data time: 2.1355, Total iter time: 5.4582
thomas 04/11 03:32:01 ===> Epoch[257](77120/301): Loss 0.1986	LR: 3.961e-02	Score 93.351	Data time: 2.0734, Total iter time: 5.3646
thomas 04/11 03:35:50 ===> Epoch[257](77160/301): Loss 0.2061	LR: 3.957e-02	Score 93.533	Data time: 2.1911, Total iter time: 5.6701
thomas 04/11 03:39:33 ===> Epoch[257](77200/301): Loss 0.2069	LR: 3.954e-02	Score 93.500	Data time: 2.1413, Total iter time: 5.5032
thomas 04/11 03:43:08 ===> Epoch[257](77240/301): Loss 0.1801	LR: 3.951e-02	Score 94.151	Data time: 2.0683, Total iter time: 5.2798
thomas 04/11 03:46:47 ===> Epoch[257](77280/301): Loss 0.1847	LR: 3.947e-02	Score 93.746	Data time: 2.1208, Total iter time: 5.4059
thomas 04/11 03:50:27 ===> Epoch[257](77320/301): Loss 0.1840	LR: 3.944e-02	Score 94.007	Data time: 2.1332, Total iter time: 5.4299
thomas 04/11 03:54:04 ===> Epoch[258](77360/301): Loss 0.1995	LR: 3.941e-02	Score 93.649	Data time: 2.1112, Total iter time: 5.3577
thomas 04/11 03:57:44 ===> Epoch[258](77400/301): Loss 0.2099	LR: 3.937e-02	Score 93.178	Data time: 2.1344, Total iter time: 5.4304
thomas 04/11 04:01:17 ===> Epoch[258](77440/301): Loss 0.1925	LR: 3.934e-02	Score 93.725	Data time: 2.0600, Total iter time: 5.2490
thomas 04/11 04:04:45 ===> Epoch[258](77480/301): Loss 0.2152	LR: 3.931e-02	Score 92.885	Data time: 1.9866, Total iter time: 5.1324
thomas 04/11 04:08:18 ===> Epoch[258](77520/301): Loss 0.1967	LR: 3.927e-02	Score 93.569	Data time: 2.0582, Total iter time: 5.2700
thomas 04/11 04:12:07 ===> Epoch[258](77560/301): Loss 0.1713	LR: 3.924e-02	Score 94.465	Data time: 2.2088, Total iter time: 5.6325
thomas 04/11 04:15:48 ===> Epoch[258](77600/301): Loss 0.1920	LR: 3.921e-02	Score 93.667	Data time: 2.1250, Total iter time: 5.4563
thomas 04/11 04:19:02 ===> Epoch[258](77640/301): Loss 0.1814	LR: 3.917e-02	Score 94.054	Data time: 1.9041, Total iter time: 4.7887
thomas 04/11 04:22:44 ===> Epoch[259](77680/301): Loss 0.2120	LR: 3.914e-02	Score 93.035	Data time: 2.1530, Total iter time: 5.4809
thomas 04/11 04:26:32 ===> Epoch[259](77720/301): Loss 0.1964	LR: 3.911e-02	Score 93.760	Data time: 2.2308, Total iter time: 5.6320
thomas 04/11 04:30:14 ===> Epoch[259](77760/301): Loss 0.1908	LR: 3.907e-02	Score 93.877	Data time: 2.1435, Total iter time: 5.4614
thomas 04/11 04:33:47 ===> Epoch[259](77800/301): Loss 0.1780	LR: 3.904e-02	Score 94.205	Data time: 2.0505, Total iter time: 5.2476
thomas 04/11 04:37:26 ===> Epoch[259](77840/301): Loss 0.1936	LR: 3.901e-02	Score 93.723	Data time: 2.1110, Total iter time: 5.4107
thomas 04/11 04:41:09 ===> Epoch[259](77880/301): Loss 0.1810	LR: 3.897e-02	Score 93.893	Data time: 2.1582, Total iter time: 5.5041
thomas 04/11 04:44:32 ===> Epoch[259](77920/301): Loss 0.2020	LR: 3.894e-02	Score 93.490	Data time: 1.9688, Total iter time: 4.9957
thomas 04/11 04:48:05 ===> Epoch[260](77960/301): Loss 0.1931	LR: 3.891e-02	Score 93.591	Data time: 2.0680, Total iter time: 5.2613
thomas 04/11 04:51:55 ===> Epoch[260](78000/301): Loss 0.1886	LR: 3.887e-02	Score 93.870	Data time: 2.2466, Total iter time: 5.6889
thomas 04/11 04:51:57 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 04:51:57 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 04:53:47 101/312: Data time: 0.0023, Iter time: 0.3381	Loss 0.236 (AVG: 0.584)	Score 91.336 (AVG: 85.744)	mIOU 64.006 mAP 72.611 mAcc 73.790
IOU: 78.722 96.244 59.336 74.190 86.846 71.624 74.663 46.965 36.457 63.040 22.364 61.272 70.211 69.865 45.955 58.488 81.698 53.390 87.130 41.658
mAP: 81.154 97.233 52.537 69.103 88.524 88.803 69.856 63.324 52.369 72.739 44.244 55.780 73.382 82.849 69.080 86.815 84.745 82.942 82.235 54.498
mAcc: 92.350 98.864 72.666 78.746 92.312 92.923 83.271 57.290 41.599 74.134 33.216 74.087 82.199 87.506 63.268 62.484 83.823 58.595 89.877 56.601

thomas 04/11 04:55:39 201/312: Data time: 0.0026, Iter time: 0.6626	Loss 0.158 (AVG: 0.574)	Score 95.084 (AVG: 85.929)	mIOU 63.730 mAP 71.617 mAcc 73.234
IOU: 79.114 96.199 54.583 72.979 88.320 76.852 72.810 46.371 36.282 68.843 17.214 56.940 63.352 67.274 37.130 63.128 84.644 60.939 85.476 46.152
mAP: 80.146 97.161 50.814 71.295 89.157 81.282 72.629 59.919 51.292 75.735 39.269 57.290 67.249 80.121 54.594 88.877 88.717 83.858 85.903 57.031
mAcc: 93.003 98.869 70.407 78.009 92.952 93.328 83.254 58.023 39.665 77.946 24.026 73.802 72.708 84.473 50.563 68.150 86.063 67.351 90.846 61.245

thomas 04/11 04:57:24 301/312: Data time: 0.0026, Iter time: 0.7239	Loss 0.302 (AVG: 0.572)	Score 90.089 (AVG: 86.062)	mIOU 63.929 mAP 71.899 mAcc 73.700
IOU: 79.063 96.159 57.653 70.158 89.399 74.115 72.182 45.865 36.367 69.493 16.624 60.233 60.230 69.322 44.020 63.086 85.772 57.954 85.447 45.430
mAP: 80.185 97.333 54.536 68.337 89.898 78.845 75.605 59.903 50.770 73.057 39.381 61.748 66.715 81.852 60.465 84.713 89.872 83.047 82.970 58.743
mAcc: 92.991 98.920 74.274 75.304 94.164 93.320 82.205 58.154 39.223 79.845 23.664 77.552 71.322 87.721 59.677 66.801 87.356 64.863 89.760 56.893

thomas 04/11 04:57:37 312/312: Data time: 0.0034, Iter time: 0.3776	Loss 0.673 (AVG: 0.576)	Score 85.878 (AVG: 85.982)	mIOU 63.885 mAP 71.833 mAcc 73.672
IOU: 78.895 96.183 57.521 71.123 89.231 74.229 71.692 46.359 36.081 69.097 16.891 59.379 59.604 68.383 44.731 63.086 85.772 57.503 85.447 46.488
mAP: 80.293 97.381 55.047 68.954 89.428 79.155 75.080 60.314 50.986 71.855 39.677 61.417 65.959 80.643 61.884 84.713 89.872 82.485 82.970 58.542
mAcc: 93.018 98.917 74.631 76.206 94.186 93.023 81.712 58.656 38.862 79.895 24.165 77.733 70.613 85.473 60.690 66.801 87.356 64.341 89.760 57.400

thomas 04/11 04:57:37 Finished test. Elapsed time: 340.5245
thomas 04/11 04:57:39 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/11 04:57:39 Current best mIoU: 63.885 at iter 78000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 05:01:19 ===> Epoch[260](78040/301): Loss 0.1892	LR: 3.884e-02	Score 93.961	Data time: 2.1229, Total iter time: 5.4414
thomas 04/11 05:04:46 ===> Epoch[260](78080/301): Loss 0.2034	LR: 3.881e-02	Score 93.455	Data time: 1.9955, Total iter time: 5.1085
thomas 04/11 05:08:10 ===> Epoch[260](78120/301): Loss 0.1905	LR: 3.877e-02	Score 93.858	Data time: 1.9609, Total iter time: 5.0224
thomas 04/11 05:11:48 ===> Epoch[260](78160/301): Loss 0.2107	LR: 3.874e-02	Score 93.137	Data time: 2.0960, Total iter time: 5.3817
thomas 04/11 05:15:30 ===> Epoch[260](78200/301): Loss 0.1979	LR: 3.871e-02	Score 93.618	Data time: 2.1400, Total iter time: 5.4587
thomas 04/11 05:19:09 ===> Epoch[260](78240/301): Loss 0.1911	LR: 3.867e-02	Score 93.867	Data time: 2.1057, Total iter time: 5.4050
thomas 04/11 05:22:28 ===> Epoch[261](78280/301): Loss 0.2034	LR: 3.864e-02	Score 93.528	Data time: 1.9046, Total iter time: 4.8987
thomas 04/11 05:26:13 ===> Epoch[261](78320/301): Loss 0.2077	LR: 3.861e-02	Score 93.192	Data time: 2.1577, Total iter time: 5.5344
thomas 04/11 05:29:48 ===> Epoch[261](78360/301): Loss 0.2063	LR: 3.857e-02	Score 93.399	Data time: 2.0720, Total iter time: 5.2974
thomas 04/11 05:33:30 ===> Epoch[261](78400/301): Loss 0.1862	LR: 3.854e-02	Score 93.881	Data time: 2.1163, Total iter time: 5.4841
thomas 04/11 05:37:07 ===> Epoch[261](78440/301): Loss 0.1933	LR: 3.851e-02	Score 93.567	Data time: 2.0487, Total iter time: 5.3418
thomas 04/11 05:40:26 ===> Epoch[261](78480/301): Loss 0.1772	LR: 3.847e-02	Score 94.197	Data time: 1.9123, Total iter time: 4.9020
thomas 04/11 05:44:03 ===> Epoch[261](78520/301): Loss 0.2151	LR: 3.844e-02	Score 93.231	Data time: 2.0730, Total iter time: 5.3313
thomas 04/11 05:47:31 ===> Epoch[261](78560/301): Loss 0.1887	LR: 3.841e-02	Score 93.665	Data time: 2.0017, Total iter time: 5.1334
thomas 04/11 05:50:59 ===> Epoch[262](78600/301): Loss 0.1851	LR: 3.837e-02	Score 93.913	Data time: 1.9946, Total iter time: 5.1292
thomas 04/11 05:54:39 ===> Epoch[262](78640/301): Loss 0.1967	LR: 3.834e-02	Score 93.696	Data time: 2.1113, Total iter time: 5.4191
thomas 04/11 05:58:18 ===> Epoch[262](78680/301): Loss 0.2253	LR: 3.831e-02	Score 92.517	Data time: 2.1085, Total iter time: 5.4118
thomas 04/11 06:01:43 ===> Epoch[262](78720/301): Loss 0.1983	LR: 3.827e-02	Score 93.579	Data time: 1.9724, Total iter time: 5.0407
thomas 04/11 06:05:19 ===> Epoch[262](78760/301): Loss 0.1957	LR: 3.824e-02	Score 93.698	Data time: 2.0678, Total iter time: 5.3251
thomas 04/11 06:08:42 ===> Epoch[262](78800/301): Loss 0.1989	LR: 3.821e-02	Score 93.683	Data time: 1.9449, Total iter time: 5.0102
thomas 04/11 06:12:40 ===> Epoch[262](78840/301): Loss 0.1953	LR: 3.817e-02	Score 93.529	Data time: 2.2829, Total iter time: 5.8719
thomas 04/11 06:16:12 ===> Epoch[263](78880/301): Loss 0.1745	LR: 3.814e-02	Score 94.346	Data time: 2.0428, Total iter time: 5.2256
thomas 04/11 06:19:42 ===> Epoch[263](78920/301): Loss 0.1993	LR: 3.811e-02	Score 93.535	Data time: 2.0251, Total iter time: 5.1829
thomas 04/11 06:23:18 ===> Epoch[263](78960/301): Loss 0.2263	LR: 3.807e-02	Score 92.635	Data time: 2.0600, Total iter time: 5.3200
thomas 04/11 06:26:54 ===> Epoch[263](79000/301): Loss 0.1900	LR: 3.804e-02	Score 93.900	Data time: 2.0942, Total iter time: 5.3334
thomas 04/11 06:26:55 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 06:26:55 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 06:28:46 101/312: Data time: 0.0158, Iter time: 0.5250	Loss 0.336 (AVG: 0.768)	Score 89.820 (AVG: 82.238)	mIOU 58.101 mAP 69.087 mAcc 69.369
IOU: 74.592 94.875 42.882 72.463 86.491 56.222 65.166 42.733 33.196 55.963 23.327 51.405 49.995 68.125 36.283 62.446 73.648 63.045 77.319 31.841
mAP: 74.898 97.123 58.697 77.190 88.855 77.062 67.610 59.004 41.902 68.800 33.083 62.724 65.050 70.239 61.952 83.514 83.326 85.539 77.222 47.937
mAcc: 88.198 98.723 58.264 79.218 92.023 93.869 71.215 56.314 36.333 95.892 26.393 70.658 71.591 77.311 44.674 68.219 74.325 65.836 78.302 40.013

thomas 04/11 06:30:32 201/312: Data time: 0.0029, Iter time: 0.3229	Loss 0.206 (AVG: 0.767)	Score 95.680 (AVG: 82.296)	mIOU 56.547 mAP 69.623 mAcc 67.337
IOU: 75.382 95.200 45.065 66.086 86.382 56.577 65.947 43.733 37.718 53.821 13.671 49.423 53.841 66.295 36.972 37.432 72.211 60.707 78.892 35.589
mAP: 77.249 97.459 60.048 70.579 89.936 78.145 70.209 58.839 47.361 65.916 32.403 59.463 64.372 76.438 63.971 84.643 84.888 87.669 71.793 51.078
mAcc: 88.848 98.776 62.656 74.699 92.031 95.826 74.375 55.328 42.444 92.486 14.655 62.639 69.171 80.879 42.163 38.817 72.633 62.893 80.168 45.258

thomas 04/11 06:32:17 301/312: Data time: 0.0024, Iter time: 0.2769	Loss 0.153 (AVG: 0.742)	Score 96.140 (AVG: 82.753)	mIOU 56.711 mAP 69.418 mAcc 67.326
IOU: 75.696 95.501 46.380 63.530 85.530 60.104 66.219 44.247 36.512 53.823 11.722 50.510 51.199 63.912 38.256 41.550 74.216 57.013 81.666 36.638
mAP: 77.795 97.305 57.807 70.114 89.139 79.494 71.448 60.160 46.108 67.068 29.924 57.738 61.376 76.165 62.387 85.231 85.080 83.988 78.992 51.046
mAcc: 89.144 98.878 64.478 72.710 90.520 95.232 74.852 54.567 40.841 92.666 12.408 63.168 67.291 78.548 44.069 44.579 74.613 58.940 82.857 46.163

thomas 04/11 06:32:27 312/312: Data time: 0.0026, Iter time: 0.2794	Loss 0.203 (AVG: 0.737)	Score 94.016 (AVG: 82.838)	mIOU 57.151 mAP 69.682 mAcc 67.778
IOU: 75.852 95.500 48.272 63.623 85.634 59.870 65.959 44.750 36.004 53.566 11.656 52.228 51.016 64.888 42.433 42.623 74.287 57.700 80.485 36.674
mAP: 77.924 97.158 58.135 69.736 89.176 79.172 71.460 60.657 46.053 66.786 29.337 58.250 61.693 77.071 65.281 85.665 85.574 83.975 79.461 51.071
mAcc: 89.206 98.869 66.029 72.508 90.641 95.256 74.533 55.142 40.245 92.620 12.335 64.200 67.742 79.462 48.332 45.697 74.669 59.928 81.711 46.432

thomas 04/11 06:32:27 Finished test. Elapsed time: 331.9839
thomas 04/11 06:32:27 Current best mIoU: 63.885 at iter 78000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 06:36:19 ===> Epoch[263](79040/301): Loss 0.1950	LR: 3.801e-02	Score 93.688	Data time: 2.2157, Total iter time: 5.7018
thomas 04/11 06:39:32 ===> Epoch[263](79080/301): Loss 0.2593	LR: 3.797e-02	Score 91.960	Data time: 1.8645, Total iter time: 4.7838
thomas 04/11 06:43:00 ===> Epoch[263](79120/301): Loss 0.2228	LR: 3.794e-02	Score 92.704	Data time: 1.9932, Total iter time: 5.1169
thomas 04/11 06:46:37 ===> Epoch[263](79160/301): Loss 0.2175	LR: 3.791e-02	Score 92.961	Data time: 2.0879, Total iter time: 5.3641
thomas 04/11 06:50:08 ===> Epoch[264](79200/301): Loss 0.2190	LR: 3.787e-02	Score 92.762	Data time: 2.0311, Total iter time: 5.2007
thomas 04/11 06:53:48 ===> Epoch[264](79240/301): Loss 0.1853	LR: 3.784e-02	Score 94.010	Data time: 2.1142, Total iter time: 5.4205
thomas 04/11 06:57:28 ===> Epoch[264](79280/301): Loss 0.1967	LR: 3.781e-02	Score 93.609	Data time: 2.1233, Total iter time: 5.4384
thomas 04/11 07:01:08 ===> Epoch[264](79320/301): Loss 0.1844	LR: 3.777e-02	Score 93.920	Data time: 2.1120, Total iter time: 5.4101
thomas 04/11 07:04:44 ===> Epoch[264](79360/301): Loss 0.1902	LR: 3.774e-02	Score 93.820	Data time: 2.1018, Total iter time: 5.3467
thomas 04/11 07:09:44 ===> Epoch[264](79400/301): Loss 0.2040	LR: 3.771e-02	Score 93.172	Data time: 3.1570, Total iter time: 7.4034
thomas 04/11 07:13:59 ===> Epoch[264](79440/301): Loss 0.2234	LR: 3.767e-02	Score 92.971	Data time: 2.6416, Total iter time: 6.2847
thomas 04/11 07:18:21 ===> Epoch[265](79480/301): Loss 0.1960	LR: 3.764e-02	Score 93.393	Data time: 2.7051, Total iter time: 6.4725
thomas 04/11 07:23:31 ===> Epoch[265](79520/301): Loss 0.1821	LR: 3.761e-02	Score 94.063	Data time: 3.3008, Total iter time: 7.6531
thomas 04/11 07:28:00 ===> Epoch[265](79560/301): Loss 0.1936	LR: 3.757e-02	Score 93.608	Data time: 2.8353, Total iter time: 6.6467
thomas 04/11 07:32:09 ===> Epoch[265](79600/301): Loss 0.1813	LR: 3.754e-02	Score 94.113	Data time: 2.4874, Total iter time: 6.1504
thomas 04/11 07:36:35 ===> Epoch[265](79640/301): Loss 0.1725	LR: 3.751e-02	Score 94.097	Data time: 2.7615, Total iter time: 6.5756
thomas 04/11 07:41:37 ===> Epoch[265](79680/301): Loss 0.1932	LR: 3.747e-02	Score 93.412	Data time: 3.1966, Total iter time: 7.4771
thomas 04/11 07:46:06 ===> Epoch[265](79720/301): Loss 0.1888	LR: 3.744e-02	Score 93.755	Data time: 2.7520, Total iter time: 6.6431
thomas 04/11 07:50:14 ===> Epoch[265](79760/301): Loss 0.1618	LR: 3.741e-02	Score 94.768	Data time: 2.4552, Total iter time: 6.1189
thomas 04/11 07:54:59 ===> Epoch[266](79800/301): Loss 0.2146	LR: 3.737e-02	Score 93.131	Data time: 3.0408, Total iter time: 7.0302
thomas 04/11 07:59:27 ===> Epoch[266](79840/301): Loss 0.2113	LR: 3.734e-02	Score 93.275	Data time: 2.8182, Total iter time: 6.6041
thomas 04/11 08:03:54 ===> Epoch[266](79880/301): Loss 0.2134	LR: 3.731e-02	Score 93.332	Data time: 2.6673, Total iter time: 6.6057
thomas 04/11 08:08:03 ===> Epoch[266](79920/301): Loss 0.2093	LR: 3.727e-02	Score 93.252	Data time: 2.4833, Total iter time: 6.1379
thomas 04/11 08:12:45 ===> Epoch[266](79960/301): Loss 0.1945	LR: 3.724e-02	Score 93.524	Data time: 3.0209, Total iter time: 6.9777
thomas 04/11 08:17:27 ===> Epoch[266](80000/301): Loss 0.1956	LR: 3.720e-02	Score 93.716	Data time: 2.9665, Total iter time: 6.9483
thomas 04/11 08:17:28 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 08:17:28 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 08:19:31 101/312: Data time: 0.0036, Iter time: 0.6152	Loss 0.324 (AVG: 0.672)	Score 87.481 (AVG: 83.603)	mIOU 56.185 mAP 69.923 mAcc 66.599
IOU: 76.517 95.782 53.985 67.972 81.618 57.838 71.750 48.308 22.467 71.207 20.483 48.755 56.410 63.076 36.666 17.081 69.084 48.234 81.889 34.585
mAP: 78.766 97.120 52.387 66.268 87.883 73.171 75.696 60.428 40.137 64.613 42.327 62.403 70.670 74.424 55.396 84.029 94.719 83.938 80.173 53.903
mAcc: 93.473 98.682 70.956 79.733 84.627 93.851 80.617 59.908 25.260 81.762 27.076 78.035 67.908 79.369 45.261 17.559 69.164 50.194 82.329 46.216

thomas 04/11 08:21:40 201/312: Data time: 0.0024, Iter time: 0.5389	Loss 0.555 (AVG: 0.638)	Score 77.190 (AVG: 84.544)	mIOU 58.200 mAP 70.762 mAcc 67.774
IOU: 78.225 96.030 55.902 68.942 82.710 65.288 69.013 44.474 29.949 71.677 15.277 54.805 58.656 65.390 41.364 26.828 65.975 50.557 80.461 42.477
mAP: 81.599 97.490 55.553 68.469 89.209 77.976 73.675 59.456 48.179 70.724 38.490 63.387 68.311 75.812 55.798 80.820 89.473 83.414 83.288 54.116
mAcc: 94.076 98.690 71.205 80.669 85.920 95.040 81.451 54.517 33.047 84.829 18.912 79.100 68.431 78.792 50.446 27.373 66.129 52.521 80.994 53.345

thomas 04/11 08:23:50 301/312: Data time: 0.0027, Iter time: 0.4311	Loss 0.434 (AVG: 0.628)	Score 84.648 (AVG: 84.973)	mIOU 58.443 mAP 70.829 mAcc 68.159
IOU: 78.578 96.006 57.282 67.802 84.533 64.034 71.016 46.960 27.551 70.161 15.010 51.634 55.901 67.486 44.308 26.330 67.125 51.815 78.857 46.480
mAP: 80.723 97.606 57.243 69.286 88.986 79.751 76.465 62.341 46.007 72.917 37.658 59.229 65.553 78.694 60.563 79.300 87.708 82.713 78.259 55.582
mAcc: 94.048 98.649 73.495 79.740 87.692 95.432 82.108 56.883 29.880 83.391 19.291 75.017 65.471 80.682 53.647 27.530 67.277 54.708 79.410 58.832

thomas 04/11 08:24:07 312/312: Data time: 0.0025, Iter time: 0.7672	Loss 0.238 (AVG: 0.622)	Score 93.909 (AVG: 85.112)	mIOU 58.727 mAP 70.799 mAcc 68.351
IOU: 78.758 95.965 58.276 67.882 84.511 64.382 70.798 47.075 26.760 70.220 14.515 53.024 57.111 67.382 44.061 28.756 67.541 52.104 79.000 46.423
mAP: 80.947 97.606 57.594 69.388 89.019 79.924 75.770 61.945 44.588 72.935 37.144 59.024 65.515 78.549 59.465 80.748 88.063 82.588 79.496 55.666
mAcc: 94.102 98.645 74.540 79.885 88.053 94.958 81.148 57.048 29.066 83.587 18.749 75.653 66.634 80.597 53.416 30.002 67.689 54.938 79.540 58.770

thomas 04/11 08:24:07 Finished test. Elapsed time: 398.7426
thomas 04/11 08:24:07 Current best mIoU: 63.885 at iter 78000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 08:29:09 ===> Epoch[266](80040/301): Loss 0.1953	LR: 3.717e-02	Score 93.764	Data time: 3.1928, Total iter time: 7.4652
thomas 04/11 08:33:36 ===> Epoch[267](80080/301): Loss 0.1791	LR: 3.714e-02	Score 94.248	Data time: 2.7732, Total iter time: 6.5799
thomas 04/11 08:38:14 ===> Epoch[267](80120/301): Loss 0.2089	LR: 3.710e-02	Score 93.142	Data time: 2.8053, Total iter time: 6.8650
thomas 04/11 08:42:36 ===> Epoch[267](80160/301): Loss 0.2047	LR: 3.707e-02	Score 93.187	Data time: 2.6361, Total iter time: 6.4590
thomas 04/11 08:47:33 ===> Epoch[267](80200/301): Loss 0.2016	LR: 3.704e-02	Score 93.421	Data time: 3.0874, Total iter time: 7.3442
thomas 04/11 08:52:23 ===> Epoch[267](80240/301): Loss 0.1976	LR: 3.700e-02	Score 93.681	Data time: 2.9679, Total iter time: 7.1629
thomas 04/11 08:56:25 ===> Epoch[267](80280/301): Loss 0.2051	LR: 3.697e-02	Score 93.415	Data time: 2.4125, Total iter time: 5.9916
thomas 04/11 09:01:06 ===> Epoch[267](80320/301): Loss 0.2050	LR: 3.694e-02	Score 93.380	Data time: 2.9720, Total iter time: 6.9504
thomas 04/11 09:05:52 ===> Epoch[267](80360/301): Loss 0.2166	LR: 3.690e-02	Score 93.157	Data time: 3.1784, Total iter time: 7.0685
thomas 04/11 09:10:29 ===> Epoch[268](80400/301): Loss 0.2231	LR: 3.687e-02	Score 92.977	Data time: 2.9565, Total iter time: 6.8482
thomas 04/11 09:15:08 ===> Epoch[268](80440/301): Loss 0.1995	LR: 3.684e-02	Score 93.713	Data time: 2.8012, Total iter time: 6.9020
thomas 04/11 09:20:53 ===> Epoch[268](80480/301): Loss 0.2000	LR: 3.680e-02	Score 93.431	Data time: 3.8734, Total iter time: 8.5182
thomas 04/11 09:26:07 ===> Epoch[268](80520/301): Loss 0.1844	LR: 3.677e-02	Score 93.958	Data time: 3.4963, Total iter time: 7.7527
thomas 04/11 09:30:30 ===> Epoch[268](80560/301): Loss 0.1903	LR: 3.674e-02	Score 93.751	Data time: 2.7233, Total iter time: 6.4671
thomas 04/11 09:34:53 ===> Epoch[268](80600/301): Loss 0.1980	LR: 3.670e-02	Score 93.508	Data time: 2.6915, Total iter time: 6.5009
thomas 04/11 09:39:48 ===> Epoch[268](80640/301): Loss 0.1811	LR: 3.667e-02	Score 94.007	Data time: 3.1817, Total iter time: 7.3046
thomas 04/11 09:44:44 ===> Epoch[269](80680/301): Loss 0.1777	LR: 3.663e-02	Score 94.104	Data time: 3.0683, Total iter time: 7.3013
thomas 04/11 09:49:02 ===> Epoch[269](80720/301): Loss 0.1692	LR: 3.660e-02	Score 94.363	Data time: 2.5440, Total iter time: 6.3851
thomas 04/11 09:53:39 ===> Epoch[269](80760/301): Loss 0.1766	LR: 3.657e-02	Score 94.202	Data time: 2.8604, Total iter time: 6.8408
thomas 04/11 09:58:29 ===> Epoch[269](80800/301): Loss 0.1893	LR: 3.653e-02	Score 93.763	Data time: 3.0775, Total iter time: 7.1641
thomas 04/11 10:03:14 ===> Epoch[269](80840/301): Loss 0.1815	LR: 3.650e-02	Score 93.919	Data time: 2.9187, Total iter time: 7.0370
thomas 04/11 10:07:30 ===> Epoch[269](80880/301): Loss 0.1737	LR: 3.647e-02	Score 94.121	Data time: 2.5510, Total iter time: 6.3427
thomas 04/11 10:12:26 ===> Epoch[269](80920/301): Loss 0.2015	LR: 3.643e-02	Score 93.568	Data time: 3.1611, Total iter time: 7.3109
thomas 04/11 10:16:55 ===> Epoch[269](80960/301): Loss 0.1979	LR: 3.640e-02	Score 93.515	Data time: 2.8773, Total iter time: 6.6343
thomas 04/11 10:21:25 ===> Epoch[270](81000/301): Loss 0.1919	LR: 3.637e-02	Score 93.682	Data time: 2.7528, Total iter time: 6.6902
thomas 04/11 10:21:27 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 10:21:27 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 10:23:33 101/312: Data time: 0.0027, Iter time: 1.3886	Loss 1.183 (AVG: 0.582)	Score 67.907 (AVG: 85.080)	mIOU 59.748 mAP 69.670 mAcc 69.593
IOU: 79.283 96.316 59.056 73.170 90.154 70.239 67.726 45.738 28.726 69.756 12.478 50.910 59.857 69.243 53.797 18.707 74.625 65.603 72.806 36.766
mAP: 79.060 97.866 61.115 76.063 91.132 84.873 73.542 64.016 43.375 63.092 28.537 61.259 60.788 73.958 67.585 66.129 87.551 84.100 69.220 60.129
mAcc: 89.841 98.514 72.608 81.782 95.041 85.724 83.446 67.570 31.352 90.594 16.549 65.054 82.027 75.554 62.640 19.451 75.199 69.570 74.125 55.219

thomas 04/11 10:25:36 201/312: Data time: 0.0032, Iter time: 0.6396	Loss 0.369 (AVG: 0.584)	Score 90.114 (AVG: 85.550)	mIOU 59.758 mAP 70.021 mAcc 69.344
IOU: 79.599 96.261 55.585 70.469 90.621 73.179 71.306 47.816 27.262 68.169 16.546 51.488 60.667 76.353 48.288 23.023 66.707 60.932 69.245 41.653
mAP: 79.093 97.515 60.982 71.007 91.733 82.410 76.067 65.591 41.411 67.285 39.935 55.392 63.086 80.945 62.989 65.522 83.698 85.644 72.745 57.375
mAcc: 89.110 98.697 73.111 79.473 95.008 88.963 85.094 72.357 29.930 89.429 20.253 60.518 79.887 81.569 55.434 24.477 67.176 65.133 70.186 61.068

thomas 04/11 10:28:30 301/312: Data time: 0.0040, Iter time: 0.9783	Loss 0.594 (AVG: 0.594)	Score 82.080 (AVG: 85.310)	mIOU 60.541 mAP 70.046 mAcc 69.860
IOU: 78.431 96.413 55.102 70.510 90.389 77.046 70.607 44.113 26.654 72.493 13.975 53.072 59.266 70.223 45.447 32.308 73.285 56.946 76.308 48.229
mAP: 79.128 97.761 59.522 70.671 90.953 83.465 73.427 63.084 42.402 66.932 38.205 57.128 62.422 75.526 61.713 74.571 86.844 82.730 76.938 57.500
mAcc: 88.796 98.752 72.698 79.868 94.790 88.259 84.166 71.105 29.100 90.550 16.118 61.758 77.811 75.182 53.805 34.449 73.876 61.261 77.405 67.458

thomas 04/11 10:28:47 312/312: Data time: 0.0037, Iter time: 0.7616	Loss 0.454 (AVG: 0.601)	Score 87.516 (AVG: 85.216)	mIOU 60.500 mAP 69.914 mAcc 69.867
IOU: 78.493 96.293 55.489 71.190 89.901 77.055 70.600 43.532 26.642 71.341 14.461 54.650 60.054 70.971 43.514 31.620 72.693 57.370 76.300 47.832
mAP: 79.000 97.489 59.560 71.665 90.859 83.397 72.901 62.854 42.564 66.130 38.753 57.869 63.277 76.019 60.459 72.301 87.281 82.096 76.938 56.867
mAcc: 88.784 98.755 73.138 79.956 94.230 88.311 84.216 70.960 29.015 90.544 16.617 62.894 78.420 76.081 52.500 33.668 73.259 61.821 77.405 66.760

thomas 04/11 10:28:47 Finished test. Elapsed time: 439.7340
thomas 04/11 10:28:47 Current best mIoU: 63.885 at iter 78000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 10:33:29 ===> Epoch[270](81040/301): Loss 0.1820	LR: 3.633e-02	Score 94.081	Data time: 2.9403, Total iter time: 6.9787
thomas 04/11 10:36:58 ===> Epoch[270](81080/301): Loss 0.1756	LR: 3.630e-02	Score 94.104	Data time: 2.0447, Total iter time: 5.1609
thomas 04/11 10:42:11 ===> Epoch[270](81120/301): Loss 0.1764	LR: 3.627e-02	Score 94.186	Data time: 3.4253, Total iter time: 7.7456
thomas 04/11 10:47:03 ===> Epoch[270](81160/301): Loss 0.1757	LR: 3.623e-02	Score 94.452	Data time: 3.0659, Total iter time: 7.2204
thomas 04/11 10:51:09 ===> Epoch[270](81200/301): Loss 0.2041	LR: 3.620e-02	Score 93.284	Data time: 2.4548, Total iter time: 6.0734
thomas 04/11 10:55:01 ===> Epoch[270](81240/301): Loss 0.1788	LR: 3.617e-02	Score 94.077	Data time: 2.3280, Total iter time: 5.7159
thomas 04/11 11:00:16 ===> Epoch[271](81280/301): Loss 0.1969	LR: 3.613e-02	Score 93.518	Data time: 3.3660, Total iter time: 7.8014
thomas 04/11 11:05:02 ===> Epoch[271](81320/301): Loss 0.1738	LR: 3.610e-02	Score 94.302	Data time: 2.9610, Total iter time: 7.0496
thomas 04/11 11:09:15 ===> Epoch[271](81360/301): Loss 0.1917	LR: 3.606e-02	Score 93.743	Data time: 2.5314, Total iter time: 6.2527
thomas 04/11 11:13:50 ===> Epoch[271](81400/301): Loss 0.1953	LR: 3.603e-02	Score 93.600	Data time: 2.8685, Total iter time: 6.7753
thomas 04/11 11:18:44 ===> Epoch[271](81440/301): Loss 0.1886	LR: 3.600e-02	Score 93.818	Data time: 3.1671, Total iter time: 7.2870
thomas 04/11 11:23:10 ===> Epoch[271](81480/301): Loss 0.1642	LR: 3.596e-02	Score 94.581	Data time: 2.7563, Total iter time: 6.5627
thomas 04/11 11:27:28 ===> Epoch[271](81520/301): Loss 0.1721	LR: 3.593e-02	Score 94.405	Data time: 2.5658, Total iter time: 6.3680
thomas 04/11 11:32:36 ===> Epoch[271](81560/301): Loss 0.1942	LR: 3.590e-02	Score 93.737	Data time: 3.2717, Total iter time: 7.6209
thomas 04/11 11:37:28 ===> Epoch[272](81600/301): Loss 0.1988	LR: 3.586e-02	Score 93.551	Data time: 3.1228, Total iter time: 7.2093
thomas 04/11 11:41:38 ===> Epoch[272](81640/301): Loss 0.1984	LR: 3.583e-02	Score 93.673	Data time: 2.4762, Total iter time: 6.1584
thomas 04/11 11:45:29 ===> Epoch[272](81680/301): Loss 0.2097	LR: 3.580e-02	Score 93.149	Data time: 2.3262, Total iter time: 5.7158
thomas 04/11 11:50:57 ===> Epoch[272](81720/301): Loss 0.1904	LR: 3.576e-02	Score 93.827	Data time: 3.5514, Total iter time: 8.0996
thomas 04/11 11:55:41 ===> Epoch[272](81760/301): Loss 0.1657	LR: 3.573e-02	Score 94.567	Data time: 2.8544, Total iter time: 6.9821
thomas 04/11 11:59:58 ===> Epoch[272](81800/301): Loss 0.1700	LR: 3.569e-02	Score 94.201	Data time: 2.5789, Total iter time: 6.3484
thomas 04/11 12:04:41 ===> Epoch[272](81840/301): Loss 0.1823	LR: 3.566e-02	Score 94.008	Data time: 2.9764, Total iter time: 7.0030
thomas 04/11 12:09:32 ===> Epoch[273](81880/301): Loss 0.1886	LR: 3.563e-02	Score 93.929	Data time: 3.1061, Total iter time: 7.1999
thomas 04/11 12:13:59 ===> Epoch[273](81920/301): Loss 0.1862	LR: 3.559e-02	Score 93.864	Data time: 2.7799, Total iter time: 6.6225
thomas 04/11 12:17:52 ===> Epoch[273](81960/301): Loss 0.2191	LR: 3.556e-02	Score 92.902	Data time: 2.3089, Total iter time: 5.7538
thomas 04/11 12:22:28 ===> Epoch[273](82000/301): Loss 0.2075	LR: 3.553e-02	Score 93.059	Data time: 2.9243, Total iter time: 6.8108
thomas 04/11 12:22:29 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 12:22:29 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 12:25:10 101/312: Data time: 0.1669, Iter time: 0.7045	Loss 0.357 (AVG: 0.664)	Score 84.352 (AVG: 84.215)	mIOU 57.430 mAP 68.836 mAcc 66.527
IOU: 76.486 96.643 52.162 77.414 87.744 69.167 73.009 40.601 30.317 63.926 10.251 48.700 57.634 33.060 43.625 27.895 88.911 47.718 79.151 44.177
mAP: 78.500 98.128 52.257 75.829 89.043 76.435 74.043 60.723 44.838 71.586 25.388 51.865 69.774 62.710 64.615 71.667 95.921 84.019 77.498 51.880
mAcc: 93.585 98.808 73.466 89.645 90.382 96.206 86.452 55.496 32.464 72.890 10.320 66.778 66.059 34.433 61.676 27.919 89.520 49.145 79.911 55.390

thomas 04/11 12:27:50 201/312: Data time: 0.0025, Iter time: 0.3406	Loss 0.407 (AVG: 0.711)	Score 87.745 (AVG: 83.240)	mIOU 56.954 mAP 68.454 mAcc 65.995
IOU: 75.054 96.431 52.155 67.540 84.720 63.802 70.473 39.581 31.769 64.485 4.629 55.885 57.767 30.641 41.380 41.490 90.670 46.119 84.522 39.966
mAP: 78.667 98.095 56.255 70.163 87.627 78.674 70.342 58.425 44.876 68.221 21.480 57.117 67.424 64.358 58.936 76.486 95.922 78.475 84.553 52.987
mAcc: 93.490 98.607 78.402 82.495 87.048 95.871 83.115 51.851 33.772 73.308 4.644 69.121 66.950 31.721 53.586 42.578 91.169 47.480 85.632 49.072

thomas 04/11 12:30:02 301/312: Data time: 0.0377, Iter time: 0.6907	Loss 0.675 (AVG: 0.680)	Score 80.353 (AVG: 83.787)	mIOU 57.409 mAP 69.043 mAcc 66.123
IOU: 75.898 96.288 51.329 70.509 85.876 67.228 70.974 38.408 31.108 74.142 4.303 57.906 55.860 34.356 42.128 32.115 84.350 51.307 84.325 39.776
mAP: 78.741 97.894 56.034 73.353 89.474 80.428 71.749 57.565 46.991 71.321 20.130 57.862 66.487 66.085 59.120 76.354 89.981 81.383 85.133 54.776
mAcc: 93.444 98.642 75.913 83.195 88.009 96.264 83.003 51.984 32.784 82.187 4.317 70.544 65.812 35.422 54.190 33.485 84.862 52.809 86.210 49.379

thomas 04/11 12:30:17 312/312: Data time: 0.0042, Iter time: 0.4673	Loss 0.176 (AVG: 0.680)	Score 93.680 (AVG: 83.883)	mIOU 57.183 mAP 69.107 mAcc 66.005
IOU: 76.131 96.316 51.065 70.712 85.333 66.582 71.455 39.161 30.772 73.934 4.940 57.678 55.784 34.355 41.764 28.089 84.567 51.805 83.578 39.641
mAP: 78.816 97.909 56.868 73.913 89.466 80.107 72.556 57.743 47.383 70.875 21.788 58.510 66.712 66.085 58.824 75.379 90.163 81.769 82.413 54.861
mAcc: 93.427 98.654 75.816 83.757 87.422 96.208 83.500 53.057 32.367 82.363 4.957 70.676 65.484 35.422 54.518 29.131 85.076 53.396 85.449 49.421

thomas 04/11 12:30:17 Finished test. Elapsed time: 467.6924
thomas 04/11 12:30:17 Current best mIoU: 63.885 at iter 78000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 12:34:20 ===> Epoch[273](82040/301): Loss 0.2026	LR: 3.549e-02	Score 93.447	Data time: 2.4299, Total iter time: 5.9948
thomas 04/11 12:38:59 ===> Epoch[273](82080/301): Loss 0.2194	LR: 3.546e-02	Score 93.112	Data time: 2.9327, Total iter time: 6.8815
thomas 04/11 12:44:00 ===> Epoch[273](82120/301): Loss 0.2114	LR: 3.543e-02	Score 93.132	Data time: 3.1769, Total iter time: 7.4445
thomas 04/11 12:48:44 ===> Epoch[273](82160/301): Loss 0.1842	LR: 3.539e-02	Score 93.803	Data time: 2.8753, Total iter time: 7.0113
thomas 04/11 12:52:37 ===> Epoch[274](82200/301): Loss 0.1759	LR: 3.536e-02	Score 94.095	Data time: 2.3046, Total iter time: 5.7767
thomas 04/11 12:57:35 ===> Epoch[274](82240/301): Loss 0.1772	LR: 3.532e-02	Score 94.218	Data time: 3.1388, Total iter time: 7.3690
thomas 04/11 13:02:19 ===> Epoch[274](82280/301): Loss 0.1873	LR: 3.529e-02	Score 94.019	Data time: 3.0043, Total iter time: 7.0123
thomas 04/11 13:06:35 ===> Epoch[274](82320/301): Loss 0.1926	LR: 3.526e-02	Score 93.914	Data time: 2.6267, Total iter time: 6.3277
thomas 04/11 13:11:04 ===> Epoch[274](82360/301): Loss 0.1882	LR: 3.522e-02	Score 93.985	Data time: 2.6886, Total iter time: 6.6278
thomas 04/11 13:15:46 ===> Epoch[274](82400/301): Loss 0.1806	LR: 3.519e-02	Score 93.957	Data time: 3.0121, Total iter time: 6.9496
thomas 04/11 13:20:40 ===> Epoch[274](82440/301): Loss 0.1916	LR: 3.516e-02	Score 93.742	Data time: 3.1199, Total iter time: 7.2773
thomas 04/11 13:25:02 ===> Epoch[275](82480/301): Loss 0.2224	LR: 3.512e-02	Score 92.764	Data time: 2.6115, Total iter time: 6.4539
thomas 04/11 13:29:27 ===> Epoch[275](82520/301): Loss 0.2318	LR: 3.509e-02	Score 92.684	Data time: 2.7740, Total iter time: 6.5667
thomas 04/11 13:34:27 ===> Epoch[275](82560/301): Loss 0.2044	LR: 3.505e-02	Score 93.139	Data time: 3.1817, Total iter time: 7.4142
thomas 04/11 13:38:52 ===> Epoch[275](82600/301): Loss 0.1902	LR: 3.502e-02	Score 93.774	Data time: 2.7202, Total iter time: 6.5421
thomas 04/11 13:43:15 ===> Epoch[275](82640/301): Loss 0.1943	LR: 3.499e-02	Score 93.649	Data time: 2.6161, Total iter time: 6.4964
thomas 04/11 13:48:13 ===> Epoch[275](82680/301): Loss 0.1925	LR: 3.495e-02	Score 93.718	Data time: 3.2170, Total iter time: 7.3620
thomas 04/11 13:53:07 ===> Epoch[275](82720/301): Loss 0.1763	LR: 3.492e-02	Score 94.233	Data time: 3.0596, Total iter time: 7.2610
thomas 04/11 13:57:13 ===> Epoch[275](82760/301): Loss 0.1957	LR: 3.489e-02	Score 93.518	Data time: 2.4472, Total iter time: 6.0939
thomas 04/11 14:01:26 ===> Epoch[276](82800/301): Loss 0.1916	LR: 3.485e-02	Score 93.613	Data time: 2.5409, Total iter time: 6.2507
thomas 04/11 14:06:13 ===> Epoch[276](82840/301): Loss 0.1806	LR: 3.482e-02	Score 94.094	Data time: 3.0487, Total iter time: 7.0786
thomas 04/11 14:10:41 ===> Epoch[276](82880/301): Loss 0.1705	LR: 3.478e-02	Score 94.342	Data time: 2.8527, Total iter time: 6.6057
thomas 04/11 14:14:43 ===> Epoch[276](82920/301): Loss 0.1788	LR: 3.475e-02	Score 94.185	Data time: 2.4093, Total iter time: 5.9681
thomas 04/11 14:19:47 ===> Epoch[276](82960/301): Loss 0.1911	LR: 3.472e-02	Score 93.854	Data time: 3.1840, Total iter time: 7.5205
thomas 04/11 14:24:42 ===> Epoch[276](83000/301): Loss 0.1806	LR: 3.468e-02	Score 93.759	Data time: 3.0611, Total iter time: 7.2858
thomas 04/11 14:24:43 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 14:24:43 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 14:27:08 101/312: Data time: 0.0039, Iter time: 0.8604	Loss 0.113 (AVG: 0.558)	Score 97.353 (AVG: 86.890)	mIOU 64.167 mAP 72.483 mAcc 72.441
IOU: 79.841 96.615 62.583 77.420 91.772 92.294 71.157 42.942 23.593 79.983 15.345 66.117 58.260 75.824 47.571 36.934 72.450 61.787 84.098 46.753
mAP: 78.926 98.056 59.849 85.809 90.242 93.682 76.142 58.839 44.245 78.991 35.395 66.719 69.004 77.527 60.037 75.010 87.678 80.394 69.983 63.142
mAcc: 93.989 98.488 78.151 90.936 95.827 98.398 78.895 54.807 24.536 95.767 16.388 77.098 80.850 84.903 57.678 37.117 73.105 64.940 85.504 61.452

thomas 04/11 14:29:20 201/312: Data time: 0.0024, Iter time: 0.6839	Loss 0.327 (AVG: 0.594)	Score 88.411 (AVG: 86.485)	mIOU 63.230 mAP 71.739 mAcc 71.512
IOU: 79.465 96.272 61.590 71.422 91.153 90.220 71.352 45.229 31.673 79.088 15.573 61.655 57.176 71.302 46.657 42.574 77.196 52.034 80.488 42.489
mAP: 79.496 97.680 62.456 77.534 91.497 89.605 75.718 62.664 48.230 73.384 32.708 63.818 68.250 76.333 59.765 74.368 87.920 78.377 75.768 59.217
mAcc: 94.074 98.481 78.887 87.253 95.713 97.426 80.618 57.910 33.253 94.457 16.821 73.768 77.880 80.297 55.678 42.864 77.959 54.621 81.413 50.861

thomas 04/11 14:31:22 301/312: Data time: 0.0028, Iter time: 0.6634	Loss 0.763 (AVG: 0.629)	Score 85.793 (AVG: 85.904)	mIOU 62.212 mAP 70.909 mAcc 70.781
IOU: 78.988 95.993 58.474 71.400 89.498 86.850 69.647 45.021 31.722 72.781 14.719 60.772 57.066 70.555 44.135 43.054 80.238 49.108 83.078 41.139
mAP: 78.966 97.537 60.829 76.409 90.562 85.067 75.053 61.577 47.486 71.410 32.813 60.687 66.776 74.858 54.487 79.746 89.408 78.158 79.309 57.045
mAcc: 93.565 98.403 77.930 85.673 94.440 95.810 78.655 56.930 33.139 88.684 16.346 73.391 78.128 79.314 53.403 45.230 80.896 51.083 84.048 50.546

thomas 04/11 14:31:40 312/312: Data time: 0.0026, Iter time: 0.7140	Loss 0.962 (AVG: 0.640)	Score 77.348 (AVG: 85.730)	mIOU 62.038 mAP 70.814 mAcc 70.691
IOU: 78.457 95.993 57.658 69.497 89.868 86.935 70.267 45.035 32.099 73.210 12.701 60.203 57.455 70.832 43.681 43.054 79.993 49.428 83.127 41.257
mAP: 78.740 97.532 61.226 76.463 90.621 84.682 75.445 61.466 47.262 70.312 32.315 60.687 66.084 75.428 53.461 79.746 89.595 78.535 79.766 56.918
mAcc: 93.575 98.376 78.025 85.733 94.629 95.864 79.107 56.726 33.572 88.860 13.904 73.391 78.658 79.570 52.930 45.230 80.629 51.344 84.078 49.613

thomas 04/11 14:31:40 Finished test. Elapsed time: 416.3014
thomas 04/11 14:31:40 Current best mIoU: 63.885 at iter 78000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 14:35:46 ===> Epoch[276](83040/301): Loss 0.1972	LR: 3.465e-02	Score 93.616	Data time: 2.5439, Total iter time: 6.0752
thomas 04/11 14:40:59 ===> Epoch[277](83080/301): Loss 0.1781	LR: 3.462e-02	Score 94.117	Data time: 3.3221, Total iter time: 7.7484
thomas 04/11 14:45:09 ===> Epoch[277](83120/301): Loss 0.1929	LR: 3.458e-02	Score 93.663	Data time: 2.5664, Total iter time: 6.1757
thomas 04/11 14:49:16 ===> Epoch[277](83160/301): Loss 0.2166	LR: 3.455e-02	Score 92.961	Data time: 2.4631, Total iter time: 6.1067
thomas 04/11 14:53:49 ===> Epoch[277](83200/301): Loss 0.2010	LR: 3.451e-02	Score 93.467	Data time: 2.8701, Total iter time: 6.7160
thomas 04/11 14:58:46 ===> Epoch[277](83240/301): Loss 0.1765	LR: 3.448e-02	Score 94.161	Data time: 3.2243, Total iter time: 7.3421
thomas 04/11 15:02:55 ===> Epoch[277](83280/301): Loss 0.2073	LR: 3.445e-02	Score 93.253	Data time: 2.5501, Total iter time: 6.1447
thomas 04/11 15:07:09 ===> Epoch[277](83320/301): Loss 0.2312	LR: 3.441e-02	Score 92.575	Data time: 2.5594, Total iter time: 6.2726
thomas 04/11 15:11:37 ===> Epoch[277](83360/301): Loss 0.1967	LR: 3.438e-02	Score 93.591	Data time: 2.8282, Total iter time: 6.5917
thomas 04/11 15:16:35 ===> Epoch[278](83400/301): Loss 0.2001	LR: 3.435e-02	Score 93.381	Data time: 3.0858, Total iter time: 7.3669
thomas 04/11 15:21:01 ===> Epoch[278](83440/301): Loss 0.1943	LR: 3.431e-02	Score 93.625	Data time: 2.6757, Total iter time: 6.5423
thomas 04/11 15:25:13 ===> Epoch[278](83480/301): Loss 0.1807	LR: 3.428e-02	Score 93.951	Data time: 2.4954, Total iter time: 6.2349
thomas 04/11 15:30:17 ===> Epoch[278](83520/301): Loss 0.1779	LR: 3.424e-02	Score 94.093	Data time: 3.3010, Total iter time: 7.4924
thomas 04/11 15:34:58 ===> Epoch[278](83560/301): Loss 0.1903	LR: 3.421e-02	Score 93.783	Data time: 2.9552, Total iter time: 6.9516
thomas 04/11 15:39:03 ===> Epoch[278](83600/301): Loss 0.2061	LR: 3.418e-02	Score 93.226	Data time: 2.4477, Total iter time: 6.0428
thomas 04/11 15:43:40 ===> Epoch[278](83640/301): Loss 0.2040	LR: 3.414e-02	Score 93.410	Data time: 2.8694, Total iter time: 6.8530
thomas 04/11 15:48:25 ===> Epoch[279](83680/301): Loss 0.2247	LR: 3.411e-02	Score 92.818	Data time: 3.0672, Total iter time: 7.0442
thomas 04/11 15:52:50 ===> Epoch[279](83720/301): Loss 0.1772	LR: 3.408e-02	Score 94.193	Data time: 2.7421, Total iter time: 6.5661
thomas 04/11 15:56:41 ===> Epoch[279](83760/301): Loss 0.1645	LR: 3.404e-02	Score 94.473	Data time: 2.3323, Total iter time: 5.7228
thomas 04/11 16:01:10 ===> Epoch[279](83800/301): Loss 0.1563	LR: 3.401e-02	Score 94.785	Data time: 2.8697, Total iter time: 6.6344
thomas 04/11 16:05:56 ===> Epoch[279](83840/301): Loss 0.1793	LR: 3.397e-02	Score 94.053	Data time: 3.0068, Total iter time: 7.0630
thomas 04/11 16:10:13 ===> Epoch[279](83880/301): Loss 0.1739	LR: 3.394e-02	Score 94.262	Data time: 2.6215, Total iter time: 6.3661
thomas 04/11 16:14:11 ===> Epoch[279](83920/301): Loss 0.1973	LR: 3.391e-02	Score 93.654	Data time: 2.3444, Total iter time: 5.8578
thomas 04/11 16:18:56 ===> Epoch[279](83960/301): Loss 0.1842	LR: 3.387e-02	Score 94.111	Data time: 3.0129, Total iter time: 7.0601
thomas 04/11 16:23:33 ===> Epoch[280](84000/301): Loss 0.1914	LR: 3.384e-02	Score 93.929	Data time: 2.8815, Total iter time: 6.8362
thomas 04/11 16:23:35 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 16:23:35 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 16:26:04 101/312: Data time: 0.0028, Iter time: 0.8824	Loss 1.332 (AVG: 0.594)	Score 71.337 (AVG: 84.350)	mIOU 62.216 mAP 72.209 mAcc 74.138
IOU: 76.469 96.546 50.257 67.423 88.823 75.088 68.908 47.129 42.248 66.116 17.091 56.277 56.740 64.202 47.704 49.591 91.245 56.547 79.152 46.761
mAP: 79.131 97.054 63.169 72.153 89.485 81.075 68.475 64.458 50.499 70.437 39.131 49.105 62.121 78.585 63.077 93.791 95.865 81.893 85.336 59.333
mAcc: 85.784 98.160 83.640 86.344 92.535 90.968 87.367 67.036 49.987 94.115 23.681 82.080 73.859 72.576 54.526 50.335 92.294 61.915 80.551 55.002

thomas 04/11 16:28:08 201/312: Data time: 0.0053, Iter time: 0.6450	Loss 0.228 (AVG: 0.585)	Score 91.500 (AVG: 84.805)	mIOU 61.997 mAP 71.874 mAcc 73.130
IOU: 76.868 96.411 47.247 72.147 88.615 79.977 69.906 46.730 43.888 71.439 15.972 58.369 57.507 65.972 48.744 30.730 87.379 56.638 80.531 44.874
mAP: 79.896 96.837 61.381 73.982 91.399 85.271 72.592 62.998 52.635 69.091 36.791 54.911 63.848 78.827 62.002 88.769 90.893 78.535 78.019 58.797
mAcc: 86.369 98.272 81.492 86.513 92.391 92.934 89.265 68.016 51.658 92.591 21.820 80.210 72.200 73.345 58.966 32.712 88.259 61.766 81.776 52.048

thomas 04/11 16:30:05 301/312: Data time: 0.0027, Iter time: 0.6586	Loss 0.688 (AVG: 0.575)	Score 81.910 (AVG: 85.246)	mIOU 63.112 mAP 72.020 mAcc 74.029
IOU: 77.413 96.320 49.661 72.932 89.360 81.063 70.166 47.783 41.897 71.402 15.795 59.281 57.442 65.766 55.246 38.153 86.214 59.103 82.732 44.520
mAP: 79.915 96.918 57.829 73.961 90.749 85.231 74.522 61.978 52.481 71.217 35.962 57.418 61.584 77.962 64.511 85.825 91.510 81.887 80.633 58.311
mAcc: 86.725 98.232 80.897 85.863 93.139 93.487 90.267 67.756 48.969 92.810 22.865 81.987 68.568 74.194 65.766 40.004 87.118 65.168 83.968 52.803

thomas 04/11 16:30:16 312/312: Data time: 0.0024, Iter time: 0.2877	Loss 0.258 (AVG: 0.575)	Score 91.414 (AVG: 85.248)	mIOU 63.022 mAP 71.970 mAcc 73.774
IOU: 77.412 96.343 49.786 72.877 89.082 80.955 70.496 47.991 41.452 71.552 15.725 59.625 57.317 65.745 53.548 38.153 86.214 58.898 82.732 44.529
mAP: 80.060 97.009 57.052 73.961 90.692 84.193 74.594 62.099 52.213 70.921 36.129 57.457 61.584 77.962 65.552 85.825 91.510 81.482 80.633 58.461
mAcc: 86.803 98.236 81.258 85.863 92.971 93.454 90.379 67.931 48.407 92.949 22.257 80.790 68.568 74.194 62.923 40.004 87.118 64.717 83.968 52.692

thomas 04/11 16:30:16 Finished test. Elapsed time: 401.1708
thomas 04/11 16:30:16 Current best mIoU: 63.885 at iter 78000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 16:35:18 ===> Epoch[280](84040/301): Loss 0.1746	LR: 3.381e-02	Score 94.120	Data time: 3.1516, Total iter time: 7.4511
thomas 04/11 16:40:10 ===> Epoch[280](84080/301): Loss 0.1957	LR: 3.377e-02	Score 93.488	Data time: 3.0768, Total iter time: 7.2123
thomas 04/11 16:44:41 ===> Epoch[280](84120/301): Loss 0.1768	LR: 3.374e-02	Score 94.170	Data time: 2.7645, Total iter time: 6.7002
thomas 04/11 16:48:46 ===> Epoch[280](84160/301): Loss 0.1623	LR: 3.370e-02	Score 94.717	Data time: 2.4656, Total iter time: 6.0598
thomas 04/11 16:53:32 ===> Epoch[280](84200/301): Loss 0.1802	LR: 3.367e-02	Score 93.828	Data time: 3.1297, Total iter time: 7.0539
thomas 04/11 16:58:18 ===> Epoch[280](84240/301): Loss 0.1963	LR: 3.364e-02	Score 93.453	Data time: 3.0320, Total iter time: 7.0822
thomas 04/11 17:02:23 ===> Epoch[280](84280/301): Loss 0.2051	LR: 3.360e-02	Score 93.357	Data time: 2.4221, Total iter time: 6.0353
thomas 04/11 17:06:33 ===> Epoch[281](84320/301): Loss 0.2027	LR: 3.357e-02	Score 93.433	Data time: 2.5543, Total iter time: 6.1839
thomas 04/11 17:11:27 ===> Epoch[281](84360/301): Loss 0.2310	LR: 3.353e-02	Score 92.676	Data time: 3.1353, Total iter time: 7.2564
thomas 04/11 17:16:02 ===> Epoch[281](84400/301): Loss 0.1938	LR: 3.350e-02	Score 93.817	Data time: 2.8229, Total iter time: 6.7830
thomas 04/11 17:20:08 ===> Epoch[281](84440/301): Loss 0.2067	LR: 3.347e-02	Score 93.325	Data time: 2.4428, Total iter time: 6.0441
thomas 04/11 17:24:46 ===> Epoch[281](84480/301): Loss 0.2058	LR: 3.343e-02	Score 93.432	Data time: 2.8914, Total iter time: 6.8699
thomas 04/11 17:29:27 ===> Epoch[281](84520/301): Loss 0.1993	LR: 3.340e-02	Score 93.482	Data time: 2.9512, Total iter time: 6.9347
thomas 04/11 17:33:50 ===> Epoch[281](84560/301): Loss 0.1968	LR: 3.336e-02	Score 93.677	Data time: 2.7071, Total iter time: 6.4860
thomas 04/11 17:38:09 ===> Epoch[282](84600/301): Loss 0.2106	LR: 3.333e-02	Score 93.186	Data time: 2.5670, Total iter time: 6.3988
thomas 04/11 17:42:42 ===> Epoch[282](84640/301): Loss 0.1880	LR: 3.330e-02	Score 93.939	Data time: 2.8849, Total iter time: 6.7195
thomas 04/11 17:47:30 ===> Epoch[282](84680/301): Loss 0.1924	LR: 3.326e-02	Score 93.847	Data time: 3.0602, Total iter time: 7.1328
thomas 04/11 17:51:52 ===> Epoch[282](84720/301): Loss 0.1721	LR: 3.323e-02	Score 94.279	Data time: 2.6353, Total iter time: 6.4474
thomas 04/11 17:55:58 ===> Epoch[282](84760/301): Loss 0.1656	LR: 3.320e-02	Score 94.368	Data time: 2.4735, Total iter time: 6.0663
thomas 04/11 18:01:01 ===> Epoch[282](84800/301): Loss 0.1620	LR: 3.316e-02	Score 94.702	Data time: 3.2072, Total iter time: 7.4787
thomas 04/11 18:05:24 ===> Epoch[282](84840/301): Loss 0.1774	LR: 3.313e-02	Score 94.160	Data time: 2.7846, Total iter time: 6.4963
thomas 04/11 18:09:28 ===> Epoch[282](84880/301): Loss 0.1766	LR: 3.309e-02	Score 94.321	Data time: 2.4721, Total iter time: 6.0326
thomas 04/11 18:14:05 ===> Epoch[283](84920/301): Loss 0.1920	LR: 3.306e-02	Score 93.863	Data time: 2.8794, Total iter time: 6.8265
thomas 04/11 18:18:47 ===> Epoch[283](84960/301): Loss 0.1837	LR: 3.303e-02	Score 94.026	Data time: 2.9772, Total iter time: 6.9765
thomas 04/11 18:23:13 ===> Epoch[283](85000/301): Loss 0.1799	LR: 3.299e-02	Score 94.087	Data time: 2.7481, Total iter time: 6.5555
thomas 04/11 18:23:14 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 18:23:14 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 18:25:26 101/312: Data time: 0.0032, Iter time: 1.0586	Loss 0.806 (AVG: 0.624)	Score 83.800 (AVG: 84.841)	mIOU 61.435 mAP 72.438 mAcc 73.113
IOU: 77.909 96.212 53.983 69.942 90.954 81.878 69.427 46.125 36.418 50.195 14.612 49.539 46.417 70.246 43.986 63.287 83.803 61.104 83.951 38.707
mAP: 78.726 97.290 56.795 69.225 90.855 85.289 76.104 62.313 56.182 63.985 37.875 51.349 65.157 84.752 56.218 96.254 87.670 83.492 91.372 57.848
mAcc: 89.530 98.964 72.910 78.763 96.092 95.083 76.563 59.378 38.026 91.473 16.072 73.979 77.219 86.922 49.992 76.788 85.223 66.027 84.758 48.505

thomas 04/11 18:27:26 201/312: Data time: 0.0025, Iter time: 0.3932	Loss 0.177 (AVG: 0.640)	Score 93.402 (AVG: 84.681)	mIOU 61.048 mAP 71.703 mAcc 71.838
IOU: 77.109 96.373 54.603 72.266 89.396 78.818 68.119 46.900 30.309 66.949 11.783 55.549 52.027 67.551 51.592 37.383 84.640 58.613 79.018 41.970
mAP: 77.255 97.231 61.050 75.377 89.135 85.144 72.694 59.174 51.325 67.849 33.051 55.330 67.819 80.057 62.254 86.849 89.345 83.208 81.356 58.555
mAcc: 90.208 98.899 73.417 84.879 95.407 91.233 75.726 62.939 31.444 91.895 12.756 81.025 79.741 87.132 61.163 40.530 86.610 61.545 79.780 50.427

thomas 04/11 18:29:28 301/312: Data time: 0.0041, Iter time: 0.5105	Loss 0.460 (AVG: 0.626)	Score 83.295 (AVG: 85.177)	mIOU 61.377 mAP 71.865 mAcc 72.323
IOU: 78.444 96.153 55.356 70.766 88.961 79.788 68.660 48.324 30.108 62.756 10.192 56.089 54.148 66.702 52.413 41.726 85.141 60.090 79.232 42.483
mAP: 78.827 97.201 63.597 68.576 89.607 81.646 72.306 61.779 50.908 68.203 34.577 58.016 69.556 82.151 62.721 86.616 90.457 82.825 79.466 58.258
mAcc: 90.581 98.854 75.359 81.101 94.093 92.443 76.480 64.943 31.528 89.338 10.879 83.173 81.604 86.890 62.933 44.221 86.705 63.880 80.098 51.366

thomas 04/11 18:29:46 312/312: Data time: 0.0037, Iter time: 0.9136	Loss 1.324 (AVG: 0.630)	Score 74.188 (AVG: 85.125)	mIOU 61.074 mAP 71.870 mAcc 72.032
IOU: 78.287 96.132 53.748 71.738 88.917 79.257 69.209 48.437 29.824 63.072 11.439 55.401 54.486 66.872 51.344 40.454 85.338 58.320 76.957 42.246
mAP: 78.902 97.255 63.220 69.790 89.610 81.533 72.902 61.960 51.123 67.783 35.490 58.016 70.917 80.409 62.318 84.929 90.477 82.401 79.933 58.422
mAcc: 90.308 98.853 75.108 81.766 94.089 91.883 76.962 65.136 31.193 89.443 12.199 83.173 82.035 85.872 62.102 42.794 86.871 61.855 77.761 51.239

thomas 04/11 18:29:46 Finished test. Elapsed time: 391.5528
thomas 04/11 18:29:46 Current best mIoU: 63.885 at iter 78000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 18:34:35 ===> Epoch[283](85040/301): Loss 0.1831	LR: 3.296e-02	Score 93.935	Data time: 3.0792, Total iter time: 7.1451
thomas 04/11 18:39:16 ===> Epoch[283](85080/301): Loss 0.1908	LR: 3.292e-02	Score 93.700	Data time: 2.9043, Total iter time: 6.9519
thomas 04/11 18:43:15 ===> Epoch[283](85120/301): Loss 0.1832	LR: 3.289e-02	Score 93.905	Data time: 2.3876, Total iter time: 5.9052
thomas 04/11 18:47:31 ===> Epoch[283](85160/301): Loss 0.1829	LR: 3.286e-02	Score 94.007	Data time: 2.6490, Total iter time: 6.3039
thomas 04/11 18:52:04 ===> Epoch[284](85200/301): Loss 0.1942	LR: 3.282e-02	Score 93.612	Data time: 2.8729, Total iter time: 6.7460
thomas 04/11 18:56:40 ===> Epoch[284](85240/301): Loss 0.1998	LR: 3.279e-02	Score 93.451	Data time: 2.8677, Total iter time: 6.8308
thomas 04/11 19:00:54 ===> Epoch[284](85280/301): Loss 0.1787	LR: 3.275e-02	Score 94.277	Data time: 2.5220, Total iter time: 6.2721
thomas 04/11 19:05:48 ===> Epoch[284](85320/301): Loss 0.1643	LR: 3.272e-02	Score 94.344	Data time: 3.0826, Total iter time: 7.2533
thomas 04/11 19:10:27 ===> Epoch[284](85360/301): Loss 0.1627	LR: 3.269e-02	Score 94.730	Data time: 2.9484, Total iter time: 6.8852
thomas 04/11 19:14:50 ===> Epoch[284](85400/301): Loss 0.1821	LR: 3.265e-02	Score 93.911	Data time: 2.6872, Total iter time: 6.4821
thomas 04/11 19:18:49 ===> Epoch[284](85440/301): Loss 0.1699	LR: 3.262e-02	Score 94.261	Data time: 2.3717, Total iter time: 5.8941
thomas 04/11 19:23:59 ===> Epoch[284](85480/301): Loss 0.1755	LR: 3.258e-02	Score 94.215	Data time: 3.3452, Total iter time: 7.6532
thomas 04/11 19:28:57 ===> Epoch[285](85520/301): Loss 0.1633	LR: 3.255e-02	Score 94.687	Data time: 3.1322, Total iter time: 7.3782
thomas 04/11 19:32:50 ===> Epoch[285](85560/301): Loss 0.1755	LR: 3.252e-02	Score 94.032	Data time: 2.3279, Total iter time: 5.7437
thomas 04/11 19:36:51 ===> Epoch[285](85600/301): Loss 0.1633	LR: 3.248e-02	Score 94.627	Data time: 2.3972, Total iter time: 5.9397
thomas 04/11 19:42:05 ===> Epoch[285](85640/301): Loss 0.1731	LR: 3.245e-02	Score 94.144	Data time: 3.3783, Total iter time: 7.7588
thomas 04/11 19:46:46 ===> Epoch[285](85680/301): Loss 0.1875	LR: 3.241e-02	Score 93.770	Data time: 2.9559, Total iter time: 6.9422
thomas 04/11 19:51:02 ===> Epoch[285](85720/301): Loss 0.1981	LR: 3.238e-02	Score 93.682	Data time: 2.5860, Total iter time: 6.3230
thomas 04/11 19:55:12 ===> Epoch[285](85760/301): Loss 0.1896	LR: 3.235e-02	Score 93.966	Data time: 2.5970, Total iter time: 6.1732
thomas 04/11 20:00:15 ===> Epoch[286](85800/301): Loss 0.1855	LR: 3.231e-02	Score 93.920	Data time: 3.2455, Total iter time: 7.4834
thomas 04/11 20:04:42 ===> Epoch[286](85840/301): Loss 0.2061	LR: 3.228e-02	Score 93.485	Data time: 2.7569, Total iter time: 6.6074
thomas 04/11 20:08:50 ===> Epoch[286](85880/301): Loss 0.2012	LR: 3.224e-02	Score 93.634	Data time: 2.4674, Total iter time: 6.1065
thomas 04/11 20:13:19 ===> Epoch[286](85920/301): Loss 0.1814	LR: 3.221e-02	Score 93.953	Data time: 2.8385, Total iter time: 6.6526
thomas 04/11 20:18:29 ===> Epoch[286](85960/301): Loss 0.1858	LR: 3.218e-02	Score 93.923	Data time: 3.3073, Total iter time: 7.6642
thomas 04/11 20:22:51 ===> Epoch[286](86000/301): Loss 0.1557	LR: 3.214e-02	Score 94.895	Data time: 2.7000, Total iter time: 6.4646
thomas 04/11 20:22:52 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 20:22:52 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 20:25:01 101/312: Data time: 0.0024, Iter time: 0.6928	Loss 0.591 (AVG: 0.565)	Score 85.265 (AVG: 86.532)	mIOU 66.195 mAP 73.160 mAcc 75.840
IOU: 79.040 95.959 59.640 69.668 91.062 78.417 70.621 42.843 38.351 79.606 15.633 63.891 65.189 63.840 56.336 76.918 81.225 57.445 91.394 46.828
mAP: 78.978 97.697 53.679 66.393 91.210 75.908 73.954 55.846 54.861 74.642 37.614 54.579 66.464 87.138 69.500 94.567 92.373 85.418 96.160 56.227
mAcc: 92.608 98.788 78.647 73.417 95.369 95.781 78.298 51.837 41.947 92.674 20.501 78.058 76.403 91.431 71.553 88.960 81.917 58.770 92.603 57.230

thomas 04/11 20:26:57 201/312: Data time: 0.0026, Iter time: 0.5830	Loss 0.522 (AVG: 0.576)	Score 86.444 (AVG: 86.401)	mIOU 64.759 mAP 73.290 mAcc 74.454
IOU: 79.737 96.174 61.560 74.818 90.600 73.474 67.294 47.883 34.309 74.844 14.816 67.399 60.041 68.813 54.493 60.921 85.940 55.087 83.573 43.398
mAP: 79.125 97.978 59.757 73.900 90.884 79.273 73.059 63.021 52.692 73.007 37.213 59.116 63.677 85.504 69.182 87.096 94.640 82.761 87.129 56.787
mAcc: 92.661 98.820 80.686 79.606 95.167 96.753 75.130 55.607 36.978 89.936 22.313 82.364 72.667 89.459 68.260 67.467 86.916 56.693 84.653 56.938

thomas 04/11 20:29:34 301/312: Data time: 0.0038, Iter time: 0.7098	Loss 0.289 (AVG: 0.576)	Score 89.000 (AVG: 86.289)	mIOU 64.237 mAP 73.485 mAcc 73.803
IOU: 79.431 96.369 61.481 74.206 89.802 71.981 70.569 49.012 34.887 73.542 12.836 63.175 61.514 67.481 52.256 56.102 88.806 53.398 82.747 45.137
mAP: 79.249 97.642 61.528 72.626 90.231 79.801 74.120 65.239 52.122 73.981 38.561 61.113 64.887 84.939 70.449 88.886 96.012 81.085 79.500 57.728
mAcc: 93.031 98.807 81.766 79.714 94.090 95.656 78.509 56.492 37.417 87.471 17.551 77.513 74.570 89.273 67.806 60.760 89.554 55.016 83.897 57.162

thomas 04/11 20:29:50 312/312: Data time: 0.0038, Iter time: 1.5234	Loss 0.472 (AVG: 0.579)	Score 87.931 (AVG: 86.272)	mIOU 64.095 mAP 73.235 mAcc 73.652
IOU: 79.294 96.378 61.260 74.138 89.645 71.404 71.113 48.599 34.004 73.505 12.906 63.152 61.428 65.845 51.108 56.643 88.960 53.644 83.433 45.433
mAP: 78.824 97.668 61.104 72.626 89.911 79.800 74.054 65.031 51.756 72.633 38.018 61.527 64.887 83.303 68.974 88.932 96.089 81.468 80.158 57.931
mAcc: 93.062 98.800 81.367 79.714 94.150 94.997 78.957 56.042 36.663 87.473 17.579 77.501 74.570 87.009 66.866 61.285 89.703 55.312 84.567 57.422

thomas 04/11 20:29:50 Finished test. Elapsed time: 417.5216
thomas 04/11 20:29:52 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34Cbest_val.pth
thomas 04/11 20:29:52 Current best mIoU: 64.095 at iter 86000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 20:34:23 ===> Epoch[286](86040/301): Loss 0.1720	LR: 3.211e-02	Score 94.448	Data time: 2.8915, Total iter time: 6.6978
thomas 04/11 20:38:48 ===> Epoch[286](86080/301): Loss 0.1751	LR: 3.207e-02	Score 94.187	Data time: 2.7316, Total iter time: 6.5428
thomas 04/11 20:43:01 ===> Epoch[287](86120/301): Loss 0.1711	LR: 3.204e-02	Score 94.210	Data time: 2.5483, Total iter time: 6.2647
thomas 04/11 20:47:41 ===> Epoch[287](86160/301): Loss 0.1672	LR: 3.201e-02	Score 94.482	Data time: 2.9753, Total iter time: 6.9048
thomas 04/11 20:52:22 ===> Epoch[287](86200/301): Loss 0.1623	LR: 3.197e-02	Score 94.700	Data time: 2.9977, Total iter time: 6.9504
thomas 04/11 20:57:00 ===> Epoch[287](86240/301): Loss 0.1675	LR: 3.194e-02	Score 94.367	Data time: 2.8484, Total iter time: 6.8594
thomas 04/11 21:00:49 ===> Epoch[287](86280/301): Loss 0.1586	LR: 3.190e-02	Score 94.727	Data time: 2.3070, Total iter time: 5.6614
thomas 04/11 21:06:12 ===> Epoch[287](86320/301): Loss 0.1626	LR: 3.187e-02	Score 94.662	Data time: 3.6625, Total iter time: 7.9940
thomas 04/11 21:10:59 ===> Epoch[287](86360/301): Loss 0.1516	LR: 3.184e-02	Score 94.869	Data time: 3.0028, Total iter time: 7.1008
thomas 04/11 21:15:19 ===> Epoch[288](86400/301): Loss 0.1660	LR: 3.180e-02	Score 94.441	Data time: 2.6032, Total iter time: 6.4067
thomas 04/11 21:19:41 ===> Epoch[288](86440/301): Loss 0.1589	LR: 3.177e-02	Score 94.786	Data time: 2.6899, Total iter time: 6.4686
thomas 04/11 21:24:30 ===> Epoch[288](86480/301): Loss 0.1826	LR: 3.173e-02	Score 93.797	Data time: 3.1118, Total iter time: 7.1476
thomas 04/11 21:28:58 ===> Epoch[288](86520/301): Loss 0.1801	LR: 3.170e-02	Score 93.965	Data time: 2.8280, Total iter time: 6.6230
thomas 04/11 21:33:07 ===> Epoch[288](86560/301): Loss 0.1707	LR: 3.167e-02	Score 94.455	Data time: 2.4677, Total iter time: 6.1459
thomas 04/11 21:37:32 ===> Epoch[288](86600/301): Loss 0.2573	LR: 3.163e-02	Score 91.947	Data time: 2.7542, Total iter time: 6.5603
thomas 04/11 21:42:26 ===> Epoch[288](86640/301): Loss 0.2899	LR: 3.160e-02	Score 91.024	Data time: 3.2725, Total iter time: 7.2424
thomas 04/11 21:47:05 ===> Epoch[288](86680/301): Loss 0.1997	LR: 3.156e-02	Score 93.559	Data time: 2.9015, Total iter time: 6.9016
thomas 04/11 21:51:25 ===> Epoch[289](86720/301): Loss 0.2127	LR: 3.153e-02	Score 93.279	Data time: 2.6009, Total iter time: 6.4166
thomas 04/11 21:56:25 ===> Epoch[289](86760/301): Loss 0.2076	LR: 3.149e-02	Score 93.248	Data time: 3.1966, Total iter time: 7.4191
thomas 04/11 22:01:08 ===> Epoch[289](86800/301): Loss 0.1860	LR: 3.146e-02	Score 94.076	Data time: 3.0281, Total iter time: 7.0032
thomas 04/11 22:05:30 ===> Epoch[289](86840/301): Loss 0.1584	LR: 3.143e-02	Score 94.633	Data time: 2.6727, Total iter time: 6.4884
thomas 04/11 22:09:26 ===> Epoch[289](86880/301): Loss 0.1736	LR: 3.139e-02	Score 94.318	Data time: 2.3603, Total iter time: 5.8073
thomas 04/11 22:14:32 ===> Epoch[289](86920/301): Loss 0.1933	LR: 3.136e-02	Score 93.549	Data time: 3.3006, Total iter time: 7.5671
thomas 04/11 22:19:31 ===> Epoch[289](86960/301): Loss 0.1683	LR: 3.132e-02	Score 94.434	Data time: 3.1526, Total iter time: 7.4034
thomas 04/11 22:24:00 ===> Epoch[290](87000/301): Loss 0.1728	LR: 3.129e-02	Score 94.317	Data time: 2.7230, Total iter time: 6.6466
thomas 04/11 22:24:02 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/11 22:24:02 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/11 22:26:06 101/312: Data time: 0.0041, Iter time: 0.9134	Loss 0.853 (AVG: 0.605)	Score 76.647 (AVG: 84.926)	mIOU 62.630 mAP 73.232 mAcc 73.991
IOU: 78.796 96.625 52.263 73.006 91.397 73.237 68.343 45.840 31.128 80.869 18.011 44.860 55.536 51.342 50.002 51.991 88.617 65.995 88.264 46.483
mAP: 79.843 97.342 64.925 76.233 89.040 83.008 72.740 61.877 45.520 72.490 39.469 67.063 60.866 87.624 58.393 91.112 91.166 88.784 77.043 60.101
mAcc: 91.365 98.765 71.020 83.630 95.375 90.266 88.406 57.037 32.662 91.520 21.937 80.955 66.359 90.214 60.799 52.088 89.519 69.830 90.265 57.808

thomas 04/11 22:28:23 201/312: Data time: 0.1271, Iter time: 0.5478	Loss 0.043 (AVG: 0.561)	Score 98.990 (AVG: 86.088)	mIOU 64.240 mAP 72.981 mAcc 74.866
IOU: 79.282 96.250 58.157 74.463 90.246 77.722 72.089 45.515 30.942 79.448 15.081 50.012 59.934 55.627 49.975 57.993 87.952 64.123 91.573 48.412
mAP: 79.463 96.918 61.617 73.903 89.916 84.491 72.153 60.427 45.395 71.972 38.329 62.281 63.638 83.305 61.694 91.629 92.657 86.425 84.146 59.263
mAcc: 91.669 98.678 75.121 84.796 94.223 93.057 86.593 58.253 32.497 91.558 18.596 86.128 70.315 86.082 60.935 59.727 88.538 67.163 93.201 60.183

thomas 04/11 22:31:13 301/312: Data time: 0.0031, Iter time: 0.4956	Loss 0.200 (AVG: 0.566)	Score 93.668 (AVG: 85.909)	mIOU 62.668 mAP 72.199 mAcc 73.549
IOU: 79.301 96.412 56.176 71.302 89.999 79.515 72.589 47.295 31.792 74.309 15.910 50.477 60.284 56.314 43.881 47.826 86.566 58.334 88.161 46.915
mAP: 79.959 97.240 56.843 69.228 90.475 83.079 73.080 64.065 46.960 71.135 39.420 63.181 63.948 82.947 55.717 90.159 91.613 85.127 81.257 58.540
mAcc: 91.358 98.713 71.558 82.692 94.182 94.533 86.929 60.843 33.336 87.944 20.364 87.090 69.460 86.649 54.119 50.257 87.195 61.769 90.225 61.765

thomas 04/11 22:31:33 312/312: Data time: 0.0040, Iter time: 0.9913	Loss 0.223 (AVG: 0.563)	Score 90.463 (AVG: 85.946)	mIOU 62.990 mAP 72.141 mAcc 73.777
IOU: 79.323 96.402 57.172 70.911 90.022 79.469 72.756 47.066 31.719 75.138 16.079 50.856 59.799 58.550 45.367 48.588 86.377 59.333 88.158 46.721
mAP: 79.858 97.128 56.361 68.708 90.550 83.326 73.193 63.806 46.635 71.388 39.546 61.947 63.790 83.814 56.310 90.136 91.786 85.254 81.257 58.032
mAcc: 91.270 98.710 72.521 81.654 94.138 94.754 87.109 60.793 33.255 88.067 20.394 87.121 69.344 87.848 55.661 51.177 86.983 62.814 90.225 61.702

thomas 04/11 22:31:33 Finished test. Elapsed time: 451.4857
thomas 04/11 22:31:33 Current best mIoU: 64.095 at iter 86000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/11 22:36:19 ===> Epoch[290](87040/301): Loss 0.1925	LR: 3.126e-02	Score 93.714	Data time: 3.0477, Total iter time: 7.0810
thomas 04/11 22:40:21 ===> Epoch[290](87080/301): Loss 0.1803	LR: 3.122e-02	Score 94.035	Data time: 2.4757, Total iter time: 5.9728
thomas 04/11 22:44:19 ===> Epoch[290](87120/301): Loss 0.1672	LR: 3.119e-02	Score 94.598	Data time: 2.3530, Total iter time: 5.8693
thomas 04/11 22:49:01 ===> Epoch[290](87160/301): Loss 0.1837	LR: 3.115e-02	Score 94.079	Data time: 2.9734, Total iter time: 6.9488
thomas 04/11 22:53:56 ===> Epoch[290](87200/301): Loss 0.1810	LR: 3.112e-02	Score 93.995	Data time: 3.1135, Total iter time: 7.2983
thomas 04/11 22:58:17 ===> Epoch[290](87240/301): Loss 0.1758	LR: 3.109e-02	Score 94.160	Data time: 2.5761, Total iter time: 6.4279
thomas 04/11 23:02:39 ===> Epoch[290](87280/301): Loss 0.1658	LR: 3.105e-02	Score 94.373	Data time: 2.7232, Total iter time: 6.4822
thomas 04/11 23:07:21 ===> Epoch[291](87320/301): Loss 0.1891	LR: 3.102e-02	Score 93.813	Data time: 3.0005, Total iter time: 6.9579
thomas 04/11 23:11:29 ===> Epoch[291](87360/301): Loss 0.1707	LR: 3.098e-02	Score 94.382	Data time: 2.5923, Total iter time: 6.1219
thomas 04/11 23:15:35 ===> Epoch[291](87400/301): Loss 0.1698	LR: 3.095e-02	Score 94.650	Data time: 2.4530, Total iter time: 6.0744
thomas 04/11 23:19:48 ===> Epoch[291](87440/301): Loss 0.1623	LR: 3.091e-02	Score 94.704	Data time: 2.6165, Total iter time: 6.2512
thomas 04/11 23:24:54 ===> Epoch[291](87480/301): Loss 0.1703	LR: 3.088e-02	Score 94.366	Data time: 3.2869, Total iter time: 7.5580
thomas 04/11 23:29:02 ===> Epoch[291](87520/301): Loss 0.1647	LR: 3.085e-02	Score 94.474	Data time: 2.5751, Total iter time: 6.1448
thomas 04/11 23:33:15 ===> Epoch[291](87560/301): Loss 0.1943	LR: 3.081e-02	Score 93.617	Data time: 2.4969, Total iter time: 6.2500
thomas 04/11 23:37:42 ===> Epoch[292](87600/301): Loss 0.1794	LR: 3.078e-02	Score 93.937	Data time: 2.8665, Total iter time: 6.5998
thomas 04/11 23:42:35 ===> Epoch[292](87640/301): Loss 0.1717	LR: 3.074e-02	Score 94.279	Data time: 3.1153, Total iter time: 7.2255
thomas 04/11 23:46:52 ===> Epoch[292](87680/301): Loss 0.1719	LR: 3.071e-02	Score 94.224	Data time: 2.6285, Total iter time: 6.3597
thomas 04/11 23:50:59 ===> Epoch[292](87720/301): Loss 0.1496	LR: 3.068e-02	Score 94.931	Data time: 2.4281, Total iter time: 6.0765
thomas 04/11 23:55:43 ===> Epoch[292](87760/301): Loss 0.1794	LR: 3.064e-02	Score 94.048	Data time: 3.0611, Total iter time: 7.0135
thomas 04/12 00:00:20 ===> Epoch[292](87800/301): Loss 0.1764	LR: 3.061e-02	Score 94.070	Data time: 2.9299, Total iter time: 6.8504
thomas 04/12 00:04:31 ===> Epoch[292](87840/301): Loss 0.1810	LR: 3.057e-02	Score 94.213	Data time: 2.4883, Total iter time: 6.1912
thomas 04/12 00:08:21 ===> Epoch[292](87880/301): Loss 0.1706	LR: 3.054e-02	Score 94.285	Data time: 2.3098, Total iter time: 5.6788
thomas 04/12 00:13:26 ===> Epoch[293](87920/301): Loss 0.1726	LR: 3.050e-02	Score 94.531	Data time: 3.2612, Total iter time: 7.5554
thomas 04/12 00:17:50 ===> Epoch[293](87960/301): Loss 0.1805	LR: 3.047e-02	Score 94.193	Data time: 2.7589, Total iter time: 6.5168
thomas 04/12 00:22:02 ===> Epoch[293](88000/301): Loss 0.1771	LR: 3.044e-02	Score 94.158	Data time: 2.4919, Total iter time: 6.2041
thomas 04/12 00:22:03 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/12 00:22:03 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/12 00:24:06 101/312: Data time: 0.0025, Iter time: 0.6308	Loss 0.221 (AVG: 0.572)	Score 92.715 (AVG: 85.942)	mIOU 65.480 mAP 74.085 mAcc 75.086
IOU: 78.879 96.665 57.919 67.726 89.931 81.370 66.669 47.606 22.829 74.714 18.247 58.672 61.279 84.033 55.156 69.659 83.534 54.253 88.749 51.718
mAP: 78.627 98.018 56.986 65.663 90.436 86.713 71.056 59.245 46.054 79.951 43.291 62.996 71.419 89.409 70.922 93.024 84.876 83.592 95.273 54.159
mAcc: 91.173 98.418 80.293 83.130 94.667 89.601 81.069 62.687 24.387 88.983 19.479 82.096 80.414 85.952 59.702 82.623 85.383 55.199 90.616 65.857

thomas 04/12 00:26:45 201/312: Data time: 0.0038, Iter time: 0.6399	Loss 0.274 (AVG: 0.546)	Score 91.796 (AVG: 86.881)	mIOU 65.428 mAP 73.320 mAcc 74.701
IOU: 79.317 96.719 58.068 73.371 90.481 79.807 73.870 48.080 25.995 77.762 16.677 59.895 62.867 75.177 54.276 61.861 85.107 59.131 78.205 51.888
mAP: 79.399 97.965 59.619 70.477 92.016 83.669 76.062 59.666 44.266 72.386 40.809 63.510 71.653 84.491 72.977 86.583 91.628 83.688 77.517 58.025
mAcc: 91.618 98.473 77.300 88.328 94.524 89.532 85.489 64.544 27.309 91.311 20.873 84.795 79.012 79.114 60.910 66.781 86.484 60.137 80.272 67.204

thomas 04/12 00:29:17 301/312: Data time: 0.0033, Iter time: 0.3833	Loss 0.105 (AVG: 0.582)	Score 96.210 (AVG: 86.228)	mIOU 63.950 mAP 72.344 mAcc 73.591
IOU: 79.520 96.486 56.352 72.000 89.405 78.885 70.785 48.749 27.190 74.232 16.386 56.929 59.896 71.839 48.644 62.406 85.248 52.595 80.977 50.481
mAP: 79.075 97.678 60.390 71.396 90.999 83.608 71.327 58.179 43.589 74.839 41.864 62.331 70.241 79.793 65.463 89.183 91.521 79.188 79.356 56.858
mAcc: 92.157 98.399 76.945 85.237 93.300 88.862 83.959 63.264 28.777 90.633 20.751 83.773 77.660 76.604 58.069 66.322 86.443 53.515 82.911 64.246

thomas 04/12 00:29:31 312/312: Data time: 0.0030, Iter time: 0.6506	Loss 2.335 (AVG: 0.591)	Score 68.134 (AVG: 86.159)	mIOU 63.901 mAP 72.312 mAcc 73.490
IOU: 79.459 96.451 56.114 71.986 89.399 78.724 70.758 49.201 26.848 74.069 16.509 57.037 60.172 73.039 48.371 61.087 85.383 52.349 80.977 50.086
mAP: 79.223 97.662 60.518 71.296 91.072 83.375 71.736 58.789 43.536 74.803 42.468 62.197 69.417 80.157 65.636 88.137 91.680 79.028 79.356 56.154
mAcc: 92.189 98.421 76.462 84.893 93.347 88.853 84.065 63.801 28.364 90.836 21.064 83.660 77.431 77.716 57.336 64.834 86.573 53.273 82.911 63.764

thomas 04/12 00:29:31 Finished test. Elapsed time: 447.7503
thomas 04/12 00:29:31 Current best mIoU: 64.095 at iter 86000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/12 00:33:15 ===> Epoch[293](88040/301): Loss 0.1465	LR: 3.040e-02	Score 95.134	Data time: 2.1904, Total iter time: 5.5346
thomas 04/12 00:36:49 ===> Epoch[293](88080/301): Loss 0.1539	LR: 3.037e-02	Score 95.037	Data time: 2.0671, Total iter time: 5.2635
thomas 04/12 00:40:17 ===> Epoch[293](88120/301): Loss 0.1622	LR: 3.033e-02	Score 94.588	Data time: 2.0010, Total iter time: 5.1246
thomas 04/12 00:43:38 ===> Epoch[293](88160/301): Loss 0.1705	LR: 3.030e-02	Score 94.381	Data time: 1.9289, Total iter time: 4.9420
thomas 04/12 00:47:06 ===> Epoch[294](88200/301): Loss 0.1682	LR: 3.026e-02	Score 94.338	Data time: 2.0027, Total iter time: 5.1378
thomas 04/12 00:50:25 ===> Epoch[294](88240/301): Loss 0.1561	LR: 3.023e-02	Score 94.963	Data time: 1.9098, Total iter time: 4.8819
thomas 04/12 00:53:55 ===> Epoch[294](88280/301): Loss 0.1550	LR: 3.020e-02	Score 94.896	Data time: 2.0127, Total iter time: 5.1688
thomas 04/12 00:57:23 ===> Epoch[294](88320/301): Loss 0.1565	LR: 3.016e-02	Score 94.854	Data time: 2.0219, Total iter time: 5.1488
thomas 04/12 01:00:53 ===> Epoch[294](88360/301): Loss 0.1667	LR: 3.013e-02	Score 94.291	Data time: 2.0028, Total iter time: 5.1670
thomas 04/12 01:04:32 ===> Epoch[294](88400/301): Loss 0.1745	LR: 3.009e-02	Score 94.309	Data time: 2.0959, Total iter time: 5.4084
thomas 04/12 01:08:04 ===> Epoch[294](88440/301): Loss 0.1804	LR: 3.006e-02	Score 94.080	Data time: 2.0358, Total iter time: 5.2169
thomas 04/12 01:11:39 ===> Epoch[294](88480/301): Loss 0.2101	LR: 3.002e-02	Score 93.273	Data time: 2.0759, Total iter time: 5.2920
thomas 04/12 01:14:49 ===> Epoch[295](88520/301): Loss 0.1930	LR: 2.999e-02	Score 93.824	Data time: 1.8149, Total iter time: 4.6887
thomas 04/12 01:18:14 ===> Epoch[295](88560/301): Loss 0.1785	LR: 2.996e-02	Score 94.250	Data time: 1.9474, Total iter time: 5.0359
thomas 04/12 01:21:33 ===> Epoch[295](88600/301): Loss 0.2075	LR: 2.992e-02	Score 93.289	Data time: 1.9109, Total iter time: 4.8978
thomas 04/12 01:25:03 ===> Epoch[295](88640/301): Loss 0.1615	LR: 2.989e-02	Score 94.671	Data time: 2.0205, Total iter time: 5.1751
thomas 04/12 01:28:40 ===> Epoch[295](88680/301): Loss 0.1743	LR: 2.985e-02	Score 94.486	Data time: 2.0880, Total iter time: 5.3351
thomas 04/12 01:32:13 ===> Epoch[295](88720/301): Loss 0.1701	LR: 2.982e-02	Score 94.207	Data time: 2.0405, Total iter time: 5.2467
thomas 04/12 01:35:42 ===> Epoch[295](88760/301): Loss 0.1741	LR: 2.978e-02	Score 94.165	Data time: 2.0263, Total iter time: 5.1540
thomas 04/12 01:39:10 ===> Epoch[296](88800/301): Loss 0.1785	LR: 2.975e-02	Score 94.064	Data time: 1.9942, Total iter time: 5.1367
thomas 04/12 01:42:53 ===> Epoch[296](88840/301): Loss 0.1870	LR: 2.972e-02	Score 93.862	Data time: 2.1439, Total iter time: 5.4945
thomas 04/12 01:46:24 ===> Epoch[296](88880/301): Loss 0.1454	LR: 2.968e-02	Score 95.196	Data time: 2.0396, Total iter time: 5.2009
thomas 04/12 01:50:02 ===> Epoch[296](88920/301): Loss 0.1442	LR: 2.965e-02	Score 95.241	Data time: 2.1150, Total iter time: 5.3749
thomas 04/12 01:53:32 ===> Epoch[296](88960/301): Loss 0.1679	LR: 2.961e-02	Score 94.508	Data time: 2.0261, Total iter time: 5.2031
thomas 04/12 01:57:11 ===> Epoch[296](89000/301): Loss 0.1697	LR: 2.958e-02	Score 94.137	Data time: 2.0855, Total iter time: 5.3881
thomas 04/12 01:57:12 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/12 01:57:12 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/12 01:59:02 101/312: Data time: 0.0034, Iter time: 0.4705	Loss 1.101 (AVG: 0.621)	Score 77.502 (AVG: 85.254)	mIOU 61.854 mAP 70.858 mAcc 71.537
IOU: 78.930 96.332 60.908 74.680 90.139 70.658 70.778 42.668 26.733 71.943 11.070 47.053 59.191 64.469 36.401 66.904 87.182 51.238 86.036 43.772
mAP: 79.445 97.416 67.846 77.488 90.642 77.639 72.867 59.953 45.126 57.011 38.081 52.310 69.746 85.395 38.312 91.993 88.480 80.406 88.593 58.403
mAcc: 93.308 98.700 79.658 85.630 93.478 86.360 80.539 52.759 27.884 94.288 11.923 60.585 79.639 84.163 40.842 73.592 88.428 52.372 87.649 58.954

thomas 04/12 02:00:44 201/312: Data time: 0.0029, Iter time: 0.4580	Loss 0.161 (AVG: 0.604)	Score 94.817 (AVG: 85.804)	mIOU 62.483 mAP 72.224 mAcc 72.174
IOU: 78.994 96.293 59.779 78.192 90.493 78.158 71.990 46.019 25.075 71.625 10.974 56.746 54.846 64.807 35.215 55.277 88.183 55.207 86.639 45.158
mAP: 77.959 97.636 65.995 79.837 91.776 81.052 74.205 62.854 45.603 71.049 32.950 59.587 67.350 86.161 46.027 87.535 91.289 81.477 86.559 57.577
mAcc: 92.669 98.628 76.633 89.215 93.432 91.745 80.962 57.675 25.888 90.364 12.346 67.883 76.224 87.019 45.218 59.859 89.958 56.655 89.499 61.606

thomas 04/12 02:02:28 301/312: Data time: 0.0032, Iter time: 0.3791	Loss 0.201 (AVG: 0.595)	Score 94.969 (AVG: 86.170)	mIOU 63.696 mAP 72.633 mAcc 73.066
IOU: 79.209 96.244 61.239 77.016 89.682 78.858 71.891 47.192 27.605 73.824 12.009 59.115 59.378 67.301 44.362 56.780 86.442 56.974 83.915 44.883
mAP: 78.351 97.621 64.763 78.017 91.114 82.353 73.918 63.233 47.048 70.988 34.631 59.041 69.535 83.896 53.571 88.161 90.893 84.259 83.715 57.543
mAcc: 92.601 98.617 77.669 86.546 92.691 91.584 81.984 59.609 28.446 92.238 14.419 69.553 78.999 87.132 55.540 60.372 87.793 58.261 87.648 59.626

thomas 04/12 02:02:40 312/312: Data time: 0.0027, Iter time: 0.8685	Loss 1.509 (AVG: 0.604)	Score 69.497 (AVG: 85.993)	mIOU 63.173 mAP 72.580 mAcc 72.634
IOU: 78.926 96.267 60.729 76.022 89.118 78.727 71.964 46.931 27.170 73.439 12.122 59.220 58.805 66.455 44.438 53.456 86.609 54.959 82.689 45.408
mAP: 78.096 97.632 65.166 77.255 91.118 82.640 74.435 63.413 47.230 70.601 34.942 59.700 69.291 84.028 54.441 88.001 90.876 84.059 81.098 57.576
mAcc: 92.690 98.634 77.892 85.367 92.086 91.622 82.151 58.769 28.141 92.257 14.538 70.023 79.088 87.231 55.933 56.442 87.943 56.132 86.619 59.123

thomas 04/12 02:02:40 Finished test. Elapsed time: 327.5651
thomas 04/12 02:02:40 Current best mIoU: 64.095 at iter 86000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/12 02:06:05 ===> Epoch[296](89040/301): Loss 0.2005	LR: 2.954e-02	Score 93.369	Data time: 1.9757, Total iter time: 5.0454
thomas 04/12 02:09:35 ===> Epoch[296](89080/301): Loss 0.1940	LR: 2.951e-02	Score 93.677	Data time: 2.0307, Total iter time: 5.1920
thomas 04/12 02:13:08 ===> Epoch[297](89120/301): Loss 0.1781	LR: 2.948e-02	Score 93.937	Data time: 2.0306, Total iter time: 5.2322
thomas 04/12 02:16:28 ===> Epoch[297](89160/301): Loss 0.1717	LR: 2.944e-02	Score 94.420	Data time: 1.9426, Total iter time: 4.9336
thomas 04/12 02:20:01 ===> Epoch[297](89200/301): Loss 0.1823	LR: 2.941e-02	Score 94.099	Data time: 2.0406, Total iter time: 5.2472
thomas 04/12 02:23:44 ===> Epoch[297](89240/301): Loss 0.1549	LR: 2.937e-02	Score 94.773	Data time: 2.1520, Total iter time: 5.4982
thomas 04/12 02:27:17 ===> Epoch[297](89280/301): Loss 0.1560	LR: 2.934e-02	Score 94.775	Data time: 2.0532, Total iter time: 5.2408
thomas 04/12 02:30:50 ===> Epoch[297](89320/301): Loss 0.1710	LR: 2.930e-02	Score 94.427	Data time: 2.0673, Total iter time: 5.2479
thomas 04/12 02:34:24 ===> Epoch[297](89360/301): Loss 0.1933	LR: 2.927e-02	Score 93.718	Data time: 2.0535, Total iter time: 5.2921
thomas 04/12 02:37:59 ===> Epoch[298](89400/301): Loss 0.1533	LR: 2.923e-02	Score 95.119	Data time: 2.0707, Total iter time: 5.2812
thomas 04/12 02:41:15 ===> Epoch[298](89440/301): Loss 0.1561	LR: 2.920e-02	Score 94.804	Data time: 1.8983, Total iter time: 4.8241
thomas 04/12 02:44:51 ===> Epoch[298](89480/301): Loss 0.1681	LR: 2.917e-02	Score 94.466	Data time: 2.0966, Total iter time: 5.3185
thomas 04/12 02:48:15 ===> Epoch[298](89520/301): Loss 0.1563	LR: 2.913e-02	Score 94.789	Data time: 1.9844, Total iter time: 5.0403
thomas 04/12 02:51:51 ===> Epoch[298](89560/301): Loss 0.1575	LR: 2.910e-02	Score 94.845	Data time: 2.0699, Total iter time: 5.3323
thomas 04/12 02:55:20 ===> Epoch[298](89600/301): Loss 0.1902	LR: 2.906e-02	Score 93.871	Data time: 2.0345, Total iter time: 5.1471
thomas 04/12 02:58:36 ===> Epoch[298](89640/301): Loss 0.1761	LR: 2.903e-02	Score 94.093	Data time: 1.8994, Total iter time: 4.8518
thomas 04/12 03:02:09 ===> Epoch[298](89680/301): Loss 0.1592	LR: 2.899e-02	Score 94.696	Data time: 2.0586, Total iter time: 5.2404
thomas 04/12 03:05:47 ===> Epoch[299](89720/301): Loss 0.1838	LR: 2.896e-02	Score 93.873	Data time: 2.0985, Total iter time: 5.3774
thomas 04/12 03:09:28 ===> Epoch[299](89760/301): Loss 0.1678	LR: 2.892e-02	Score 94.388	Data time: 2.1545, Total iter time: 5.4480
thomas 04/12 03:12:53 ===> Epoch[299](89800/301): Loss 0.1542	LR: 2.889e-02	Score 94.840	Data time: 1.9972, Total iter time: 5.0586
thomas 04/12 03:16:18 ===> Epoch[299](89840/301): Loss 0.1605	LR: 2.886e-02	Score 94.670	Data time: 1.9696, Total iter time: 5.0453
thomas 04/12 03:19:56 ===> Epoch[299](89880/301): Loss 0.1662	LR: 2.882e-02	Score 94.479	Data time: 2.1057, Total iter time: 5.3654
thomas 04/12 03:23:27 ===> Epoch[299](89920/301): Loss 0.1615	LR: 2.879e-02	Score 94.626	Data time: 2.0557, Total iter time: 5.2240
thomas 04/12 03:27:01 ===> Epoch[299](89960/301): Loss 0.1477	LR: 2.875e-02	Score 95.026	Data time: 2.0619, Total iter time: 5.2625
thomas 04/12 03:30:35 ===> Epoch[300](90000/301): Loss 0.1584	LR: 2.872e-02	Score 94.758	Data time: 2.0511, Total iter time: 5.2733
thomas 04/12 03:30:36 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/12 03:30:36 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/12 03:32:28 101/312: Data time: 0.0026, Iter time: 0.3729	Loss 0.329 (AVG: 0.736)	Score 90.086 (AVG: 84.122)	mIOU 60.853 mAP 69.009 mAcc 69.398
IOU: 74.734 96.369 59.098 58.983 90.140 82.967 72.270 43.165 26.677 74.478 4.291 55.798 54.593 59.461 50.078 42.988 89.378 60.714 77.449 43.433
mAP: 74.861 97.822 48.928 63.675 87.018 78.608 75.635 60.003 46.188 70.441 27.099 57.625 63.001 73.136 57.938 93.766 95.758 81.060 70.645 56.977
mAcc: 95.163 98.608 67.557 72.781 94.299 94.502 86.645 51.297 28.817 87.941 4.636 80.267 67.397 70.087 55.747 43.090 91.142 64.276 78.990 54.724

thomas 04/12 03:34:07 201/312: Data time: 0.0025, Iter time: 0.2553	Loss 0.080 (AVG: 0.691)	Score 98.008 (AVG: 85.140)	mIOU 62.043 mAP 70.315 mAcc 70.361
IOU: 77.062 96.264 58.427 66.212 90.199 81.872 71.496 43.922 24.764 75.551 7.702 54.402 59.521 70.587 48.891 44.240 87.492 56.114 82.210 43.930
mAP: 77.785 97.729 54.367 68.654 89.995 82.201 73.957 58.588 45.103 72.809 29.564 59.322 67.066 77.576 58.515 83.496 91.673 82.175 78.017 57.701
mAcc: 95.270 98.661 67.478 79.066 94.079 94.175 85.069 52.889 26.558 90.039 8.441 76.814 72.453 79.459 54.031 46.654 88.672 58.983 83.318 55.112

thomas 04/12 03:35:50 301/312: Data time: 0.0025, Iter time: 0.9732	Loss 0.211 (AVG: 0.649)	Score 93.466 (AVG: 85.929)	mIOU 63.003 mAP 70.536 mAcc 71.103
IOU: 78.354 96.353 58.646 70.273 90.289 84.249 71.517 44.186 24.764 75.672 8.215 57.250 55.393 72.229 50.582 46.904 85.376 59.249 84.575 45.980
mAP: 77.324 97.662 55.677 71.695 90.340 82.441 74.752 59.564 46.303 71.737 26.118 61.531 63.277 78.542 58.803 82.319 90.715 83.032 81.123 57.775
mAcc: 95.197 98.671 67.275 83.038 94.129 95.215 84.822 54.076 26.966 88.069 9.124 79.040 69.654 80.124 55.299 49.252 86.440 62.483 85.604 57.592

thomas 04/12 03:36:04 312/312: Data time: 0.0031, Iter time: 0.4787	Loss 0.858 (AVG: 0.648)	Score 80.457 (AVG: 85.976)	mIOU 63.044 mAP 70.592 mAcc 71.168
IOU: 78.531 96.362 59.133 70.527 90.148 83.004 71.567 44.618 25.650 76.643 8.765 56.988 56.245 72.395 48.476 48.123 85.518 58.386 84.986 44.809
mAP: 77.551 97.696 55.658 72.084 90.473 82.363 74.658 59.960 46.757 71.167 27.565 61.514 63.604 78.987 56.661 82.879 90.578 82.692 81.525 57.468
mAcc: 95.260 98.685 67.676 83.369 94.139 94.688 84.841 54.604 27.844 89.385 9.722 79.193 70.158 80.456 52.792 50.474 86.572 61.500 86.000 56.008

thomas 04/12 03:36:04 Finished test. Elapsed time: 328.0745
thomas 04/12 03:36:04 Current best mIoU: 64.095 at iter 86000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/12 03:39:30 ===> Epoch[300](90040/301): Loss 0.1452	LR: 2.868e-02	Score 95.031	Data time: 1.9855, Total iter time: 5.0756
thomas 04/12 03:43:17 ===> Epoch[300](90080/301): Loss 0.1521	LR: 2.865e-02	Score 94.923	Data time: 2.2045, Total iter time: 5.5724
thomas 04/12 03:46:52 ===> Epoch[300](90120/301): Loss 0.1506	LR: 2.861e-02	Score 95.029	Data time: 2.0644, Total iter time: 5.2863
thomas 04/12 03:50:16 ===> Epoch[300](90160/301): Loss 0.1527	LR: 2.858e-02	Score 94.884	Data time: 1.9878, Total iter time: 5.0387
thomas 04/12 03:53:57 ===> Epoch[300](90200/301): Loss 0.1711	LR: 2.855e-02	Score 94.384	Data time: 2.1082, Total iter time: 5.4318
thomas 04/12 03:57:33 ===> Epoch[300](90240/301): Loss 0.1392	LR: 2.851e-02	Score 95.348	Data time: 2.0836, Total iter time: 5.3442
thomas 04/12 04:01:06 ===> Epoch[300](90280/301): Loss 0.1680	LR: 2.848e-02	Score 94.440	Data time: 2.0530, Total iter time: 5.2464
thomas 04/12 04:04:26 ===> Epoch[301](90320/301): Loss 0.1585	LR: 2.844e-02	Score 94.881	Data time: 1.9171, Total iter time: 4.9142
thomas 04/12 04:07:40 ===> Epoch[301](90360/301): Loss 0.1530	LR: 2.841e-02	Score 94.791	Data time: 1.8622, Total iter time: 4.7715
thomas 04/12 04:11:17 ===> Epoch[301](90400/301): Loss 0.1513	LR: 2.837e-02	Score 94.793	Data time: 2.0873, Total iter time: 5.3569
thomas 04/12 04:14:48 ===> Epoch[301](90440/301): Loss 0.1699	LR: 2.834e-02	Score 94.397	Data time: 2.0184, Total iter time: 5.2180
thomas 04/12 04:18:16 ===> Epoch[301](90480/301): Loss 0.1481	LR: 2.830e-02	Score 95.151	Data time: 1.9682, Total iter time: 5.1211
thomas 04/12 04:21:35 ===> Epoch[301](90520/301): Loss 0.1599	LR: 2.827e-02	Score 94.746	Data time: 1.8949, Total iter time: 4.8987
thomas 04/12 04:25:09 ===> Epoch[301](90560/301): Loss 0.1519	LR: 2.824e-02	Score 94.811	Data time: 2.0410, Total iter time: 5.2823
thomas 04/12 04:28:38 ===> Epoch[301](90600/301): Loss 0.1667	LR: 2.820e-02	Score 94.508	Data time: 1.9865, Total iter time: 5.1365
thomas 04/12 04:32:03 ===> Epoch[302](90640/301): Loss 0.1917	LR: 2.817e-02	Score 93.670	Data time: 1.9659, Total iter time: 5.0660
thomas 04/12 04:35:29 ===> Epoch[302](90680/301): Loss 0.1908	LR: 2.813e-02	Score 94.019	Data time: 1.9644, Total iter time: 5.0689
thomas 04/12 04:39:08 ===> Epoch[302](90720/301): Loss 0.1521	LR: 2.810e-02	Score 94.961	Data time: 2.0860, Total iter time: 5.4013
thomas 04/12 04:42:38 ===> Epoch[302](90760/301): Loss 0.1436	LR: 2.806e-02	Score 95.287	Data time: 1.9900, Total iter time: 5.1724
thomas 04/12 04:46:06 ===> Epoch[302](90800/301): Loss 0.1622	LR: 2.803e-02	Score 94.609	Data time: 1.9934, Total iter time: 5.1271
thomas 04/12 04:49:40 ===> Epoch[302](90840/301): Loss 0.1620	LR: 2.799e-02	Score 94.457	Data time: 2.0645, Total iter time: 5.2873
thomas 04/12 04:52:56 ===> Epoch[302](90880/301): Loss 0.1661	LR: 2.796e-02	Score 94.458	Data time: 1.8977, Total iter time: 4.8194
thomas 04/12 04:56:41 ===> Epoch[303](90920/301): Loss 0.1659	LR: 2.792e-02	Score 94.413	Data time: 2.1369, Total iter time: 5.5340
thomas 04/12 04:59:59 ===> Epoch[303](90960/301): Loss 0.1659	LR: 2.789e-02	Score 94.453	Data time: 1.8844, Total iter time: 4.9000
thomas 04/12 05:03:31 ===> Epoch[303](91000/301): Loss 0.1610	LR: 2.786e-02	Score 94.554	Data time: 2.0416, Total iter time: 5.2153
thomas 04/12 05:03:32 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/12 05:03:32 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/12 05:05:28 101/312: Data time: 0.0030, Iter time: 0.5286	Loss 1.016 (AVG: 0.799)	Score 83.985 (AVG: 84.212)	mIOU 61.776 mAP 70.895 mAcc 69.521
IOU: 74.793 95.771 64.021 71.377 89.714 89.204 63.609 48.995 19.020 73.014 10.827 57.808 60.713 69.552 40.168 42.588 77.343 57.587 84.568 44.859
mAP: 75.230 97.078 58.175 85.308 92.503 83.927 62.498 61.126 43.828 69.945 27.075 51.999 67.054 83.742 60.707 86.961 82.664 81.434 88.438 58.201
mAcc: 95.336 98.677 72.861 86.293 95.345 94.164 76.553 63.043 19.555 91.632 12.212 65.724 79.728 75.654 42.287 46.582 78.065 59.348 88.490 48.874

thomas 04/12 05:07:07 201/312: Data time: 0.0027, Iter time: 0.9220	Loss 0.464 (AVG: 0.720)	Score 93.088 (AVG: 84.971)	mIOU 61.325 mAP 70.492 mAcc 69.256
IOU: 76.804 96.273 61.763 68.364 89.699 87.273 65.029 46.240 20.866 72.349 10.457 59.089 56.478 62.113 48.159 41.515 82.019 53.764 83.887 44.351
mAP: 76.488 97.781 61.994 79.433 91.119 84.143 68.704 59.897 42.522 71.070 28.351 54.741 63.755 75.306 57.421 89.270 87.174 80.489 82.468 57.710
mAcc: 95.683 98.670 70.375 83.326 94.659 93.193 77.623 57.256 21.512 92.613 11.996 69.153 78.289 69.736 50.540 43.757 82.949 56.119 87.796 49.867

thomas 04/12 05:08:48 301/312: Data time: 0.0023, Iter time: 0.5315	Loss 0.093 (AVG: 0.681)	Score 97.221 (AVG: 85.709)	mIOU 60.960 mAP 69.952 mAcc 68.900
IOU: 78.012 96.320 61.542 70.236 90.915 85.250 69.583 46.897 18.183 71.876 11.805 58.320 59.099 65.036 34.847 41.275 81.367 54.349 82.532 41.749
mAP: 78.044 97.510 62.878 75.555 91.663 81.846 72.387 60.272 41.442 71.510 27.887 57.112 66.249 75.131 48.610 83.707 88.359 80.491 80.694 57.693
mAcc: 95.768 98.633 71.211 83.652 95.469 93.904 81.433 57.791 18.760 93.396 14.053 69.462 79.518 72.026 36.541 43.444 82.421 57.243 85.716 47.569

thomas 04/12 05:08:59 312/312: Data time: 0.0025, Iter time: 0.4837	Loss 0.469 (AVG: 0.681)	Score 86.263 (AVG: 85.765)	mIOU 61.357 mAP 70.273 mAcc 69.293
IOU: 77.969 96.362 62.661 70.356 90.487 84.722 69.940 47.212 18.581 71.745 11.088 58.819 59.484 64.347 41.148 41.275 81.100 55.150 82.522 42.171
mAP: 78.118 97.564 63.566 76.011 91.425 80.976 73.102 60.943 41.795 71.510 28.179 57.868 66.176 74.334 51.893 83.707 88.486 80.938 80.694 58.183
mAcc: 95.738 98.642 72.485 83.955 94.926 93.287 81.833 58.123 19.164 93.396 12.932 69.565 79.738 71.490 43.094 43.444 82.122 58.079 85.716 48.126

thomas 04/12 05:08:59 Finished test. Elapsed time: 326.8688
thomas 04/12 05:08:59 Current best mIoU: 64.095 at iter 86000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/12 05:12:33 ===> Epoch[303](91040/301): Loss 0.1734	LR: 2.782e-02	Score 94.319	Data time: 2.0475, Total iter time: 5.2644
thomas 04/12 05:16:05 ===> Epoch[303](91080/301): Loss 0.1587	LR: 2.779e-02	Score 94.661	Data time: 2.0379, Total iter time: 5.2343
thomas 04/12 05:19:25 ===> Epoch[303](91120/301): Loss 0.1493	LR: 2.775e-02	Score 95.188	Data time: 1.9067, Total iter time: 4.9324
thomas 04/12 05:22:48 ===> Epoch[303](91160/301): Loss 0.1526	LR: 2.772e-02	Score 94.856	Data time: 1.9396, Total iter time: 5.0008
thomas 04/12 05:26:23 ===> Epoch[303](91200/301): Loss 0.1513	LR: 2.768e-02	Score 95.041	Data time: 2.0753, Total iter time: 5.3025
thomas 04/12 05:29:56 ===> Epoch[304](91240/301): Loss 0.1457	LR: 2.765e-02	Score 95.022	Data time: 2.0274, Total iter time: 5.2406
thomas 04/12 05:33:22 ===> Epoch[304](91280/301): Loss 0.1510	LR: 2.761e-02	Score 94.997	Data time: 1.9423, Total iter time: 5.0727
thomas 04/12 05:36:54 ===> Epoch[304](91320/301): Loss 0.1394	LR: 2.758e-02	Score 95.233	Data time: 2.0236, Total iter time: 5.2401
thomas 04/12 05:40:24 ===> Epoch[304](91360/301): Loss 0.1464	LR: 2.754e-02	Score 95.159	Data time: 2.0015, Total iter time: 5.1588
thomas 04/12 05:43:53 ===> Epoch[304](91400/301): Loss 0.1405	LR: 2.751e-02	Score 95.410	Data time: 2.0008, Total iter time: 5.1503
thomas 04/12 05:47:25 ===> Epoch[304](91440/301): Loss 0.1507	LR: 2.747e-02	Score 94.856	Data time: 2.0106, Total iter time: 5.2257
thomas 04/12 05:50:55 ===> Epoch[304](91480/301): Loss 0.1615	LR: 2.744e-02	Score 94.591	Data time: 2.0069, Total iter time: 5.1691
thomas 04/12 05:54:24 ===> Epoch[305](91520/301): Loss 0.1542	LR: 2.741e-02	Score 94.978	Data time: 2.0147, Total iter time: 5.1566
thomas 04/12 05:58:01 ===> Epoch[305](91560/301): Loss 0.1554	LR: 2.737e-02	Score 94.966	Data time: 2.0546, Total iter time: 5.3520
thomas 04/12 06:01:19 ===> Epoch[305](91600/301): Loss 0.1435	LR: 2.734e-02	Score 95.189	Data time: 1.8901, Total iter time: 4.8797
thomas 04/12 06:04:50 ===> Epoch[305](91640/301): Loss 0.1617	LR: 2.730e-02	Score 94.535	Data time: 2.0183, Total iter time: 5.2211
thomas 04/12 06:08:17 ===> Epoch[305](91680/301): Loss 0.1539	LR: 2.727e-02	Score 94.866	Data time: 1.9773, Total iter time: 5.0967
thomas 04/12 06:11:37 ===> Epoch[305](91720/301): Loss 0.1397	LR: 2.723e-02	Score 95.406	Data time: 1.9037, Total iter time: 4.9326
thomas 04/12 06:14:54 ===> Epoch[305](91760/301): Loss 0.1395	LR: 2.720e-02	Score 95.219	Data time: 1.8808, Total iter time: 4.8438
thomas 04/12 06:18:36 ===> Epoch[305](91800/301): Loss 0.1608	LR: 2.716e-02	Score 94.624	Data time: 2.1170, Total iter time: 5.4837
thomas 04/12 06:22:02 ===> Epoch[306](91840/301): Loss 0.1460	LR: 2.713e-02	Score 95.052	Data time: 1.9770, Total iter time: 5.0764
thomas 04/12 06:25:52 ===> Epoch[306](91880/301): Loss 0.1774	LR: 2.709e-02	Score 93.914	Data time: 2.1795, Total iter time: 5.6605
thomas 04/12 06:29:24 ===> Epoch[306](91920/301): Loss 0.1412	LR: 2.706e-02	Score 95.266	Data time: 2.0264, Total iter time: 5.2253
thomas 04/12 06:32:52 ===> Epoch[306](91960/301): Loss 0.1647	LR: 2.702e-02	Score 94.404	Data time: 2.0123, Total iter time: 5.1356
thomas 04/12 06:36:32 ===> Epoch[306](92000/301): Loss 0.1610	LR: 2.699e-02	Score 94.626	Data time: 2.1812, Total iter time: 5.4216
thomas 04/12 06:36:33 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/12 06:36:33 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/12 06:38:08 101/312: Data time: 0.0025, Iter time: 0.3408	Loss 0.079 (AVG: 0.538)	Score 97.531 (AVG: 86.255)	mIOU 65.457 mAP 73.658 mAcc 74.238
IOU: 80.190 95.635 60.766 66.173 89.451 79.041 69.060 46.299 40.018 79.659 16.300 51.954 51.009 56.009 43.161 94.592 88.485 61.870 89.979 49.493
mAP: 80.424 97.215 66.403 59.583 91.559 86.487 78.976 62.316 47.127 68.235 36.333 60.246 60.342 86.889 67.805 98.959 95.273 83.242 85.745 60.007
mAcc: 91.976 99.283 77.453 76.864 92.329 89.946 87.121 58.747 46.471 87.424 18.768 58.948 61.316 85.157 53.389 96.068 89.131 62.964 90.713 60.683

thomas 04/12 06:39:53 201/312: Data time: 0.0024, Iter time: 0.5145	Loss 0.249 (AVG: 0.583)	Score 89.475 (AVG: 85.834)	mIOU 62.947 mAP 72.261 mAcc 72.055
IOU: 78.413 95.396 59.793 70.838 90.076 84.305 69.479 46.203 40.423 78.394 8.496 58.752 51.266 58.940 52.451 51.014 84.173 57.113 79.486 43.931
mAP: 79.238 96.838 63.798 67.831 90.783 84.607 76.262 62.046 50.707 75.530 30.928 58.433 59.523 84.224 71.342 82.272 89.927 81.650 83.623 55.651
mAcc: 90.860 99.165 75.567 80.634 93.319 93.037 86.969 61.036 46.465 89.422 9.198 68.439 62.477 89.411 64.820 52.242 85.283 59.235 80.278 53.238

thomas 04/12 06:41:48 301/312: Data time: 0.0032, Iter time: 1.2231	Loss 0.394 (AVG: 0.610)	Score 89.870 (AVG: 85.371)	mIOU 61.460 mAP 71.454 mAcc 70.788
IOU: 78.257 95.325 58.326 72.682 89.131 80.526 68.639 47.196 40.305 75.340 9.425 57.333 49.799 57.715 46.659 42.982 83.548 55.414 78.567 42.027
mAP: 78.863 97.081 63.280 70.887 89.771 79.576 74.463 63.319 51.202 72.821 34.090 56.807 60.243 82.168 66.517 83.387 88.784 82.768 78.743 54.316
mAcc: 90.562 99.154 74.596 82.148 93.570 89.083 88.033 64.668 46.107 89.965 10.283 66.493 58.216 85.176 60.700 45.605 84.871 57.233 79.263 50.035

thomas 04/12 06:41:59 312/312: Data time: 0.0025, Iter time: 0.5179	Loss 0.400 (AVG: 0.605)	Score 86.827 (AVG: 85.458)	mIOU 61.466 mAP 71.291 mAcc 70.791
IOU: 78.455 95.348 58.597 72.397 89.078 81.094 68.733 46.995 39.989 75.761 9.379 56.924 50.278 57.432 46.386 42.982 83.540 55.230 78.567 42.165
mAP: 78.852 97.125 62.797 70.432 89.833 80.502 73.437 62.967 51.586 72.995 33.369 56.807 60.490 81.719 65.124 83.387 88.784 82.768 78.743 54.095
mAcc: 90.588 99.163 74.833 81.932 93.653 89.237 88.052 63.979 46.302 90.292 10.227 66.493 58.841 84.763 60.416 45.605 84.871 57.233 79.263 50.075

thomas 04/12 06:41:59 Finished test. Elapsed time: 325.8540
thomas 04/12 06:41:59 Current best mIoU: 64.095 at iter 86000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/12 06:45:28 ===> Epoch[306](92040/301): Loss 0.1632	LR: 2.695e-02	Score 94.550	Data time: 1.9855, Total iter time: 5.1481
thomas 04/12 06:48:56 ===> Epoch[306](92080/301): Loss 0.1540	LR: 2.692e-02	Score 94.848	Data time: 1.9904, Total iter time: 5.1187
thomas 04/12 06:52:14 ===> Epoch[307](92120/301): Loss 0.1519	LR: 2.689e-02	Score 95.015	Data time: 1.9167, Total iter time: 4.8816
thomas 04/12 06:55:41 ===> Epoch[307](92160/301): Loss 0.1627	LR: 2.685e-02	Score 94.562	Data time: 1.9803, Total iter time: 5.1209
thomas 04/12 06:59:10 ===> Epoch[307](92200/301): Loss 0.1651	LR: 2.682e-02	Score 94.651	Data time: 2.0124, Total iter time: 5.1542
thomas 04/12 07:02:54 ===> Epoch[307](92240/301): Loss 0.1410	LR: 2.678e-02	Score 95.293	Data time: 2.1554, Total iter time: 5.5073
thomas 04/12 07:06:37 ===> Epoch[307](92280/301): Loss 0.1620	LR: 2.675e-02	Score 94.520	Data time: 2.1159, Total iter time: 5.4837
thomas 04/12 07:10:07 ===> Epoch[307](92320/301): Loss 0.1606	LR: 2.671e-02	Score 94.535	Data time: 2.0165, Total iter time: 5.1718
thomas 04/12 07:13:44 ===> Epoch[307](92360/301): Loss 0.1547	LR: 2.668e-02	Score 94.760	Data time: 2.0949, Total iter time: 5.3622
thomas 04/12 07:17:22 ===> Epoch[307](92400/301): Loss 0.1451	LR: 2.664e-02	Score 95.057	Data time: 2.0790, Total iter time: 5.3766
thomas 04/12 07:20:28 ===> Epoch[308](92440/301): Loss 0.1410	LR: 2.661e-02	Score 95.351	Data time: 1.7986, Total iter time: 4.5920
thomas 04/12 07:23:49 ===> Epoch[308](92480/301): Loss 0.1504	LR: 2.657e-02	Score 94.960	Data time: 1.9222, Total iter time: 4.9449
thomas 04/12 07:27:16 ===> Epoch[308](92520/301): Loss 0.1527	LR: 2.654e-02	Score 94.847	Data time: 1.9753, Total iter time: 5.0833
thomas 04/12 07:30:37 ===> Epoch[308](92560/301): Loss 0.1406	LR: 2.650e-02	Score 95.222	Data time: 1.9335, Total iter time: 4.9585
thomas 04/12 07:34:10 ===> Epoch[308](92600/301): Loss 0.1636	LR: 2.647e-02	Score 94.607	Data time: 2.0446, Total iter time: 5.2460
thomas 04/12 07:37:46 ===> Epoch[308](92640/301): Loss 0.1493	LR: 2.643e-02	Score 95.078	Data time: 2.0795, Total iter time: 5.3229
thomas 04/12 07:41:10 ===> Epoch[308](92680/301): Loss 0.1499	LR: 2.640e-02	Score 94.943	Data time: 1.9702, Total iter time: 5.0212
thomas 04/12 07:44:53 ===> Epoch[309](92720/301): Loss 0.1599	LR: 2.636e-02	Score 94.723	Data time: 2.1360, Total iter time: 5.5052
thomas 04/12 07:48:28 ===> Epoch[309](92760/301): Loss 0.1330	LR: 2.633e-02	Score 95.485	Data time: 2.0579, Total iter time: 5.2888
thomas 04/12 07:51:56 ===> Epoch[309](92800/301): Loss 0.1509	LR: 2.629e-02	Score 94.991	Data time: 2.0037, Total iter time: 5.1464
thomas 04/12 07:55:32 ===> Epoch[309](92840/301): Loss 0.1419	LR: 2.626e-02	Score 95.074	Data time: 2.0614, Total iter time: 5.3153
thomas 04/12 07:59:04 ===> Epoch[309](92880/301): Loss 0.1503	LR: 2.622e-02	Score 94.966	Data time: 2.0436, Total iter time: 5.2098
thomas 04/12 08:02:45 ===> Epoch[309](92920/301): Loss 0.1618	LR: 2.619e-02	Score 94.721	Data time: 2.1347, Total iter time: 5.4627
thomas 04/12 08:06:18 ===> Epoch[309](92960/301): Loss 0.1470	LR: 2.615e-02	Score 95.063	Data time: 2.0593, Total iter time: 5.2366
thomas 04/12 08:09:45 ===> Epoch[309](93000/301): Loss 0.1488	LR: 2.612e-02	Score 94.996	Data time: 2.0074, Total iter time: 5.1215
thomas 04/12 08:09:47 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/12 08:09:47 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/12 08:11:28 101/312: Data time: 0.0027, Iter time: 0.3554	Loss 0.252 (AVG: 0.751)	Score 91.777 (AVG: 84.842)	mIOU 61.027 mAP 71.109 mAcc 69.709
IOU: 78.540 95.954 58.871 69.738 90.836 69.676 65.439 43.135 27.450 68.298 9.554 54.781 52.679 76.135 53.828 40.268 85.816 60.219 81.152 38.168
mAP: 79.586 97.681 63.645 64.353 92.521 76.479 75.256 60.858 39.894 67.064 37.148 63.021 62.371 88.230 57.385 89.331 92.778 82.143 77.099 55.329
mAcc: 95.497 98.810 74.447 74.077 95.567 88.303 89.364 51.515 29.813 81.875 9.628 80.321 60.795 80.608 59.098 42.305 89.743 62.738 82.085 47.589

thomas 04/12 08:13:22 201/312: Data time: 0.0029, Iter time: 0.7810	Loss 0.527 (AVG: 0.712)	Score 87.755 (AVG: 85.446)	mIOU 61.124 mAP 70.856 mAcc 69.569
IOU: 78.022 96.034 56.044 75.057 88.939 73.245 69.290 44.984 25.290 69.538 8.117 55.708 53.299 73.756 45.069 46.458 86.929 59.167 75.255 42.284
mAP: 78.266 97.562 63.193 69.755 89.547 77.731 76.534 61.609 41.807 70.168 28.921 62.503 63.029 84.457 53.999 87.833 92.754 82.501 79.856 55.086
mAcc: 94.634 98.702 72.194 79.400 92.815 91.010 88.472 56.084 26.509 82.568 8.162 81.495 62.874 77.535 48.994 48.445 91.045 61.655 75.951 52.840

thomas 04/12 08:15:06 301/312: Data time: 0.0024, Iter time: 0.4414	Loss 0.371 (AVG: 0.732)	Score 89.494 (AVG: 85.278)	mIOU 61.151 mAP 70.491 mAcc 69.398
IOU: 77.830 96.213 55.918 75.604 89.131 74.808 68.050 45.797 23.082 71.866 9.682 56.082 50.796 69.654 43.704 47.899 87.714 58.552 78.069 42.579
mAP: 76.977 97.750 61.229 71.843 90.027 78.467 75.617 61.792 40.773 70.418 30.477 61.065 60.911 77.105 54.129 88.371 94.323 82.526 78.646 57.384
mAcc: 94.886 98.707 69.918 80.708 92.934 91.357 88.656 56.389 23.980 84.876 9.845 79.397 59.033 73.896 47.789 49.977 91.986 61.163 78.831 53.632

thomas 04/12 08:15:19 312/312: Data time: 0.0026, Iter time: 0.1709	Loss 0.236 (AVG: 0.732)	Score 93.312 (AVG: 85.365)	mIOU 61.264 mAP 70.341 mAcc 69.541
IOU: 77.958 96.255 56.691 76.317 89.182 74.238 68.127 46.264 22.542 72.202 9.418 56.277 50.847 68.022 43.085 50.312 87.964 58.351 78.436 42.796
mAP: 76.971 97.782 61.858 71.514 90.216 78.859 74.807 62.449 40.483 71.056 29.228 60.572 61.873 76.921 54.357 88.308 94.493 81.593 76.335 57.152
mAcc: 94.961 98.710 70.506 81.488 93.007 91.555 88.375 56.953 23.455 85.211 9.568 79.913 59.203 72.186 47.073 52.436 92.115 60.980 79.234 53.881

thomas 04/12 08:15:19 Finished test. Elapsed time: 332.2539
thomas 04/12 08:15:19 Current best mIoU: 64.095 at iter 86000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/12 08:19:10 ===> Epoch[310](93040/301): Loss 0.1562	LR: 2.609e-02	Score 94.596	Data time: 2.2190, Total iter time: 5.6995
thomas 04/12 08:22:31 ===> Epoch[310](93080/301): Loss 0.1459	LR: 2.605e-02	Score 94.950	Data time: 1.9242, Total iter time: 4.9434
thomas 04/12 08:26:16 ===> Epoch[310](93120/301): Loss 0.1485	LR: 2.602e-02	Score 94.940	Data time: 2.1619, Total iter time: 5.5331
thomas 04/12 08:29:53 ===> Epoch[310](93160/301): Loss 0.1297	LR: 2.598e-02	Score 95.726	Data time: 2.1027, Total iter time: 5.3683
thomas 04/12 08:33:17 ===> Epoch[310](93200/301): Loss 0.1414	LR: 2.595e-02	Score 95.130	Data time: 1.9603, Total iter time: 5.0245
thomas 04/12 08:36:47 ===> Epoch[310](93240/301): Loss 0.1789	LR: 2.591e-02	Score 93.871	Data time: 2.0498, Total iter time: 5.1905
thomas 04/12 08:40:33 ===> Epoch[310](93280/301): Loss 0.1787	LR: 2.588e-02	Score 94.109	Data time: 2.1965, Total iter time: 5.5620
thomas 04/12 08:44:10 ===> Epoch[311](93320/301): Loss 0.1462	LR: 2.584e-02	Score 95.177	Data time: 2.0980, Total iter time: 5.3446
thomas 04/12 08:47:26 ===> Epoch[311](93360/301): Loss 0.1563	LR: 2.581e-02	Score 94.782	Data time: 1.9166, Total iter time: 4.8490
thomas 04/12 08:50:54 ===> Epoch[311](93400/301): Loss 0.1546	LR: 2.577e-02	Score 94.927	Data time: 2.0157, Total iter time: 5.1224
thomas 04/12 08:54:21 ===> Epoch[311](93440/301): Loss 0.1478	LR: 2.574e-02	Score 95.124	Data time: 1.9787, Total iter time: 5.1077
thomas 04/12 08:57:58 ===> Epoch[311](93480/301): Loss 0.1656	LR: 2.570e-02	Score 94.679	Data time: 2.0918, Total iter time: 5.3412
thomas 04/12 09:01:28 ===> Epoch[311](93520/301): Loss 0.1631	LR: 2.567e-02	Score 94.642	Data time: 2.0228, Total iter time: 5.1615
thomas 04/12 09:05:03 ===> Epoch[311](93560/301): Loss 0.1485	LR: 2.563e-02	Score 94.893	Data time: 2.0646, Total iter time: 5.3012
thomas 04/12 09:08:40 ===> Epoch[311](93600/301): Loss 0.1510	LR: 2.560e-02	Score 94.928	Data time: 2.0928, Total iter time: 5.3588
thomas 04/12 09:12:20 ===> Epoch[312](93640/301): Loss 0.1643	LR: 2.556e-02	Score 94.422	Data time: 2.1257, Total iter time: 5.4260
thomas 04/12 09:15:49 ===> Epoch[312](93680/301): Loss 0.1663	LR: 2.553e-02	Score 94.502	Data time: 1.9843, Total iter time: 5.1437
thomas 04/12 09:19:15 ===> Epoch[312](93720/301): Loss 0.1371	LR: 2.549e-02	Score 95.412	Data time: 1.9885, Total iter time: 5.0845
thomas 04/12 09:22:45 ===> Epoch[312](93760/301): Loss 0.1394	LR: 2.546e-02	Score 95.293	Data time: 2.0174, Total iter time: 5.1992
thomas 04/12 09:26:23 ===> Epoch[312](93800/301): Loss 0.1473	LR: 2.542e-02	Score 94.976	Data time: 2.0928, Total iter time: 5.3539
thomas 04/12 09:29:46 ===> Epoch[312](93840/301): Loss 0.1482	LR: 2.539e-02	Score 95.045	Data time: 1.9598, Total iter time: 5.0025
thomas 04/12 09:33:14 ===> Epoch[312](93880/301): Loss 0.1439	LR: 2.535e-02	Score 95.121	Data time: 1.9930, Total iter time: 5.1411
thomas 04/12 09:36:43 ===> Epoch[313](93920/301): Loss 0.1434	LR: 2.532e-02	Score 95.201	Data time: 2.0050, Total iter time: 5.1381
thomas 04/12 09:40:26 ===> Epoch[313](93960/301): Loss 0.1601	LR: 2.528e-02	Score 94.656	Data time: 2.1408, Total iter time: 5.5004
thomas 04/12 09:44:08 ===> Epoch[313](94000/301): Loss 0.1432	LR: 2.525e-02	Score 95.175	Data time: 2.1276, Total iter time: 5.4672
thomas 04/12 09:44:10 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/12 09:44:10 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/12 09:45:55 101/312: Data time: 0.0026, Iter time: 0.4981	Loss 1.530 (AVG: 0.606)	Score 71.377 (AVG: 86.765)	mIOU 64.080 mAP 72.869 mAcc 73.115
IOU: 80.199 95.748 63.587 77.993 89.253 77.417 69.111 44.037 23.183 75.536 17.430 64.088 50.740 71.832 59.416 55.908 84.461 53.111 85.834 42.708
mAP: 80.235 95.495 72.269 78.885 88.096 77.658 71.628 60.367 47.148 76.606 41.001 56.651 66.879 78.728 61.509 79.219 92.340 81.457 95.153 56.060
mAcc: 91.658 98.774 84.369 84.973 95.068 94.114 82.864 62.717 24.644 85.869 21.096 78.011 70.253 83.220 65.103 55.950 85.447 57.846 86.593 53.737

thomas 04/12 09:47:39 201/312: Data time: 0.0031, Iter time: 0.4990	Loss 0.325 (AVG: 0.619)	Score 88.683 (AVG: 86.138)	mIOU 62.733 mAP 72.244 mAcc 71.964
IOU: 78.725 96.091 58.512 78.060 89.539 79.290 70.513 48.830 25.920 75.661 18.722 60.619 54.578 66.815 48.121 38.538 82.771 56.007 82.287 45.063
mAP: 78.524 96.277 66.645 81.002 90.024 79.471 75.123 65.166 45.938 69.855 41.592 52.962 66.362 78.983 63.120 83.797 92.119 83.936 74.169 59.826
mAcc: 90.978 98.729 80.457 86.535 94.812 94.278 85.378 66.383 27.538 85.679 22.813 73.068 70.549 79.144 56.228 39.823 83.619 60.082 85.270 57.912

thomas 04/12 09:49:27 301/312: Data time: 0.0029, Iter time: 0.7071	Loss 0.101 (AVG: 0.610)	Score 96.657 (AVG: 85.982)	mIOU 63.788 mAP 72.237 mAcc 73.109
IOU: 79.043 96.114 56.037 76.463 89.135 77.912 68.658 49.241 28.726 74.968 21.162 57.743 54.783 73.118 48.458 51.321 82.357 57.937 87.198 45.388
mAP: 78.261 95.972 61.668 74.647 90.246 81.880 72.483 64.978 46.186 69.492 42.157 54.969 61.873 82.240 64.677 87.875 90.229 85.121 82.064 57.722
mAcc: 91.117 98.706 76.071 85.238 94.197 94.676 84.266 68.521 30.378 83.703 25.233 72.703 70.246 83.540 56.930 53.760 83.271 61.272 90.130 58.225

thomas 04/12 09:49:40 312/312: Data time: 0.0025, Iter time: 0.3021	Loss 0.190 (AVG: 0.618)	Score 93.281 (AVG: 85.795)	mIOU 63.521 mAP 72.133 mAcc 72.849
IOU: 79.039 96.064 55.431 75.714 89.096 77.806 68.084 49.356 29.146 74.372 18.849 57.791 54.454 73.033 46.805 51.321 82.926 58.420 87.198 45.513
mAP: 78.219 95.909 61.107 74.090 90.137 81.599 72.267 65.176 46.576 69.492 42.572 55.520 61.558 82.240 63.261 87.875 90.269 84.442 82.064 58.278
mAcc: 91.119 98.714 75.346 84.011 94.207 94.462 83.816 68.417 31.014 83.703 21.967 73.111 69.833 83.540 55.644 53.760 84.017 61.616 90.130 58.549

thomas 04/12 09:49:40 Finished test. Elapsed time: 330.0536
thomas 04/12 09:49:40 Current best mIoU: 64.095 at iter 86000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/12 09:53:10 ===> Epoch[313](94040/301): Loss 0.1483	LR: 2.521e-02	Score 95.169	Data time: 2.0371, Total iter time: 5.1714
thomas 04/12 09:56:55 ===> Epoch[313](94080/301): Loss 0.1531	LR: 2.518e-02	Score 94.896	Data time: 2.1551, Total iter time: 5.5419
thomas 04/12 10:00:24 ===> Epoch[313](94120/301): Loss 0.1700	LR: 2.514e-02	Score 94.346	Data time: 2.0186, Total iter time: 5.1642
thomas 04/12 10:03:52 ===> Epoch[313](94160/301): Loss 0.1526	LR: 2.511e-02	Score 94.787	Data time: 2.0101, Total iter time: 5.1055
thomas 04/12 10:07:28 ===> Epoch[313](94200/301): Loss 0.1572	LR: 2.507e-02	Score 94.722	Data time: 2.0892, Total iter time: 5.3215
thomas 04/12 10:10:56 ===> Epoch[314](94240/301): Loss 0.1387	LR: 2.504e-02	Score 95.390	Data time: 2.0072, Total iter time: 5.1211
thomas 04/12 10:14:37 ===> Epoch[314](94280/301): Loss 0.1540	LR: 2.500e-02	Score 94.884	Data time: 2.1377, Total iter time: 5.4537
thomas 04/12 10:18:24 ===> Epoch[314](94320/301): Loss 0.1525	LR: 2.497e-02	Score 94.926	Data time: 2.2236, Total iter time: 5.6090
thomas 04/12 10:22:12 ===> Epoch[314](94360/301): Loss 0.1419	LR: 2.493e-02	Score 95.210	Data time: 2.2136, Total iter time: 5.6143
thomas 04/12 10:25:46 ===> Epoch[314](94400/301): Loss 0.1488	LR: 2.490e-02	Score 95.098	Data time: 2.0503, Total iter time: 5.2648
thomas 04/12 10:29:22 ===> Epoch[314](94440/301): Loss 0.1416	LR: 2.486e-02	Score 95.346	Data time: 2.0897, Total iter time: 5.3208
thomas 04/12 10:32:43 ===> Epoch[314](94480/301): Loss 0.1380	LR: 2.483e-02	Score 95.308	Data time: 1.9480, Total iter time: 4.9647
thomas 04/12 10:36:36 ===> Epoch[315](94520/301): Loss 0.1482	LR: 2.479e-02	Score 94.968	Data time: 2.2958, Total iter time: 5.7463
thomas 04/12 10:40:10 ===> Epoch[315](94560/301): Loss 0.1639	LR: 2.476e-02	Score 94.498	Data time: 2.0605, Total iter time: 5.2637
thomas 04/12 10:43:44 ===> Epoch[315](94600/301): Loss 0.1509	LR: 2.472e-02	Score 95.044	Data time: 2.0593, Total iter time: 5.2880
thomas 04/12 10:47:23 ===> Epoch[315](94640/301): Loss 0.1610	LR: 2.469e-02	Score 94.477	Data time: 2.1494, Total iter time: 5.4043
thomas 04/12 10:51:13 ===> Epoch[315](94680/301): Loss 0.1379	LR: 2.465e-02	Score 95.397	Data time: 2.2275, Total iter time: 5.6723
thomas 04/12 10:54:51 ===> Epoch[315](94720/301): Loss 0.1434	LR: 2.462e-02	Score 95.183	Data time: 2.1058, Total iter time: 5.3694
thomas 04/12 10:58:22 ===> Epoch[315](94760/301): Loss 0.1422	LR: 2.458e-02	Score 95.138	Data time: 2.0286, Total iter time: 5.1907
thomas 04/12 11:02:00 ===> Epoch[315](94800/301): Loss 0.1338	LR: 2.455e-02	Score 95.520	Data time: 2.1061, Total iter time: 5.3768
thomas 04/12 11:05:43 ===> Epoch[316](94840/301): Loss 0.1458	LR: 2.451e-02	Score 95.162	Data time: 2.2112, Total iter time: 5.5046
thomas 04/12 11:09:18 ===> Epoch[316](94880/301): Loss 0.1394	LR: 2.448e-02	Score 95.231	Data time: 2.0560, Total iter time: 5.2913
thomas 04/12 11:12:47 ===> Epoch[316](94920/301): Loss 0.1355	LR: 2.444e-02	Score 95.302	Data time: 2.0312, Total iter time: 5.1566
thomas 04/12 11:16:26 ===> Epoch[316](94960/301): Loss 0.1476	LR: 2.441e-02	Score 95.029	Data time: 2.0941, Total iter time: 5.3985
thomas 04/12 11:19:53 ===> Epoch[316](95000/301): Loss 0.1450	LR: 2.437e-02	Score 95.199	Data time: 1.9578, Total iter time: 5.1094
thomas 04/12 11:19:55 Checkpoint saved to ./outputs/ScanNet-default/2020-04-05_08-43-59/checkpoint_NoneRes16UNet34C.pth
thomas 04/12 11:19:55 ===> Start testing
/home/tcn02/SpatioTemporalSegmentation/lib/datasets
thomas 04/12 11:21:47 101/312: Data time: 0.0027, Iter time: 0.5435	Loss 0.573 (AVG: 0.631)	Score 84.120 (AVG: 85.508)	mIOU 62.009 mAP 69.912 mAcc 71.615
IOU: 77.097 96.101 59.345 72.161 89.380 70.878 73.893 49.467 35.878 72.321 10.312 62.089 65.382 62.103 35.727 54.556 87.501 45.522 85.957 34.517
mAP: 78.130 97.496 59.661 68.529 91.947 80.139 74.268 65.959 47.455 67.267 28.438 44.357 64.394 83.666 55.665 85.989 87.172 73.501 87.569 56.642
mAcc: 88.578 98.947 75.404 76.812 92.709 95.195 87.334 73.711 38.262 92.197 11.951 75.863 76.378 81.745 42.624 57.854 88.314 46.934 87.674 43.819

thomas 04/12 11:23:34 201/312: Data time: 0.0024, Iter time: 0.2636	Loss 0.148 (AVG: 0.653)	Score 95.419 (AVG: 85.012)	mIOU 60.720 mAP 69.834 mAcc 70.536
IOU: 77.267 96.176 56.774 71.401 89.293 72.949 70.070 45.809 33.283 70.539 10.090 57.909 58.555 63.480 37.898 41.055 86.148 50.501 82.370 42.826
mAP: 77.883 97.970 57.906 71.590 90.921 81.645 71.489 63.450 47.992 69.319 31.374 54.422 59.599 77.888 51.078 82.167 88.171 78.580 83.226 60.011
mAcc: 88.422 98.819 75.537 75.894 92.816 95.939 86.357 71.628 36.066 91.835 12.182 70.854 70.792 79.291 42.870 44.707 87.276 52.088 83.804 53.544

thomas 04/12 11:25:13 301/312: Data time: 0.0029, Iter time: 0.5490	Loss 0.321 (AVG: 0.633)	Score 91.109 (AVG: 85.266)	mIOU 61.146 mAP 70.317 mAcc 70.837
IOU: 77.201 96.134 55.123 72.055 90.222 71.154 72.152 44.468 34.481 75.044 10.714 56.639 58.014 68.648 40.671 38.113 86.710 49.439 81.165 44.768
mAP: 78.736 97.564 56.506 70.365 91.787 82.360 73.433 61.499 48.420 70.134 33.019 56.088 61.790 81.460 53.959 81.913 90.075 79.046 79.756 58.436
mAcc: 88.375 98.799 73.673 76.860 93.693 96.652 87.002 71.097 37.264 91.238 12.646 71.269 70.671 85.594 45.143 39.976 87.759 51.021 82.582 55.426

thomas 04/12 11:25:26 312/312: Data time: 0.0030, Iter time: 1.1892	Loss 0.616 (AVG: 0.636)	Score 86.992 (AVG: 85.213)	mIOU 61.281 mAP 70.442 mAcc 71.016
IOU: 77.141 96.175 54.945 72.373 90.225 71.566 71.972 44.449 34.617 74.284 10.371 57.415 58.655 67.362 39.893 39.460 86.735 50.580 81.633 45.770
mAP: 78.718 97.614 56.677 71.551 91.732 82.498 72.670 61.705 48.608 71.283 33.469 55.805 62.090 81.500 52.798 82.582 90.015 78.661 80.392 58.470
mAcc: 88.433 98.813 74.234 77.370 93.768 96.718 86.829 70.127 37.471 91.126 12.356 72.223 70.998 85.530 44.215 41.345 87.759 52.182 83.037 55.781

thomas 04/12 11:25:26 Finished test. Elapsed time: 331.6059
thomas 04/12 11:25:26 Current best mIoU: 64.095 at iter 86000
/home/tcn02/.cache/pypoetry/virtualenvs/spatiotemporalsegmentation-m5BOK7Dg-py3.6/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:224: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.
  warnings.warn("To get the last learning rate computed by the scheduler, "
thomas 04/12 11:28:43 ===> Epoch[316](95040/301): Loss 0.1375	LR: 2.434e-02	Score 95.428	Data time: 1.9131, Total iter time: 4.8573
thomas 04/12 11:32:38 ===> Epoch[316](95080/301): Loss 0.1512	LR: 2.430e-02	Score 94.931	Data time: 2.2681, Total iter time: 5.7911
thomas 04/12 11:36:07 ===> Epoch[317](95120/301): Loss 0.1528	LR: 2.427e-02	Score 94.713	Data time: 2.0007, Total iter time: 5.1522
thomas 04/12 11:39:42 ===> Epoch[317](95160/301): Loss 0.1581	LR: 2.423e-02	Score 94.682	Data time: 2.0849, Total iter time: 5.2940
thomas 04/12 11:43:03 ===> Epoch[317](95200/301): Loss 0.1501	LR: 2.420e-02	Score 95.291	Data time: 1.9539, Total iter time: 4.9789
thomas 04/12 11:46:29 ===> Epoch[317](95240/301): Loss 0.1458	LR: 2.416e-02	Score 95.363	Data time: 2.0192, Total iter time: 5.0625
thomas 04/12 11:50:15 ===> Epoch[317](95280/301): Loss 0.1259	LR: 2.413e-02	Score 95.620	Data time: 2.2096, Total iter time: 5.5728
thomas 04/12 11:54:12 ===> Epoch[317](95320/301): Loss 0.1654	LR: 2.409e-02	Score 94.510	Data time: 2.3292, Total iter time: 5.8637
thomas 04/12 11:57:54 ===> Epoch[317](95360/301): Loss 0.1428	LR: 2.406e-02	Score 95.158	Data time: 2.1981, Total iter time: 5.4570
thomas 04/12 12:01:24 ===> Epoch[317](95400/301): Loss 0.1370	LR: 2.402e-02	Score 95.370	Data time: 2.0706, Total iter time: 5.1978
thomas 04/12 12:04:59 ===> Epoch[318](95440/301): Loss 0.1340	LR: 2.399e-02	Score 95.438	Data time: 2.0639, Total iter time: 5.2779
thomas 04/12 12:08:46 ===> Epoch[318](95480/301): Loss 0.1505	LR: 2.395e-02	Score 94.898	Data time: 2.1872, Total iter time: 5.6098
thomas 04/12 12:12:04 ===> Epoch[318](95520/301): Loss 0.1408	LR: 2.392e-02	Score 95.212	Data time: 1.9299, Total iter time: 4.8951
thomas 04/12 12:15:32 ===> Epoch[318](95560/301): Loss 0.1450	LR: 2.388e-02	Score 94.943	Data time: 2.0057, Total iter time: 5.1382
thomas 04/12 12:19:17 ===> Epoch[318](95600/301): Loss 0.1374	LR: 2.385e-02	Score 95.400	Data time: 2.1784, Total iter time: 5.5522
thomas 04/12 12:22:55 ===> Epoch[318](95640/301): Loss 0.1502	LR: 2.381e-02	Score 95.027	Data time: 2.0950, Total iter time: 5.3785
```