==========
Args:Namespace(dataset='msmt17', batch_size=256, workers=4, height=256, width=128, num_instances=8, eps=0.7, eps_gap=0.02, k1=30, k2=6, arch='resnet_ibn50a', pretrained_path='/home/ma-user/work/Projects/ReIDNets_Checkpoints_TransReID/ResNet50_IBN.pth', features=0, dropout=0, momentum=0.2, drop_path_rate=0.3, hw_ratio=2, self_norm=True, conv_stem=False, lr=0.00035, weight_decay=0.0005, optimizer='SGD', epochs=50, iters=200, step_size=20, seed=1, print_freq=20, eval_step=50, temp=0.05, data_dir='/home/ma-user/work/Projects/ReIDNet_Finetune/CContrast/data', logs_dir='log/msmt17/resnet50_ibn_cion', pooling_type='gem', use_hard=True)
==========
==> Load unlabeled dataset
=> MSMT17 loaded
Dataset statistics:
  ----------------------------------------
  subset   | # ids | # images | # cameras
  ----------------------------------------
  train    |  1041 |    32621 |        15
  query    |  3060 |    11659 |        15
  gallery  |  3060 |    82161 |        15
  ----------------------------------------
pooling_type: gem
checkpoint loaded!
optimizer: SGD
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.380 (0.372)	Data 0.264 (0.077)	
Extract Features: [100/128]	Time 0.116 (0.276)	Data 0.000 (0.068)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.87052655220032
Clustering criterion: eps: 0.700
==> Statistics for epoch 0: 894 clusters
Epoch: [0][20/200]	Time 0.365 (0.786)	Data 0.001 (0.051)	Loss 2.761 (2.469)
Epoch: [0][40/200]	Time 0.362 (0.614)	Data 0.001 (0.065)	Loss 3.835 (2.702)
Epoch: [0][60/200]	Time 0.363 (0.558)	Data 0.001 (0.070)	Loss 2.850 (2.844)
Epoch: [0][80/200]	Time 0.365 (0.510)	Data 0.000 (0.053)	Loss 2.585 (2.770)
Epoch: [0][100/200]	Time 0.369 (0.498)	Data 0.001 (0.058)	Loss 2.727 (2.673)
Epoch: [0][120/200]	Time 0.366 (0.489)	Data 0.001 (0.061)	Loss 1.939 (2.596)
Epoch: [0][140/200]	Time 0.371 (0.483)	Data 0.001 (0.064)	Loss 1.931 (2.541)
Epoch: [0][160/200]	Time 0.367 (0.469)	Data 0.000 (0.056)	Loss 2.081 (2.482)
Epoch: [0][180/200]	Time 0.369 (0.467)	Data 0.001 (0.059)	Loss 1.887 (2.427)
Epoch: [0][200/200]	Time 0.363 (0.464)	Data 0.001 (0.060)	Loss 1.757 (2.394)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.213)	Data 0.000 (0.095)	
Extract Features: [100/128]	Time 0.121 (0.193)	Data 0.000 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.44686222076416
==> Statistics for epoch 1: 1070 clusters
Epoch: [1][20/200]	Time 0.360 (0.410)	Data 0.001 (0.046)	Loss 0.788 (0.552)
Epoch: [1][40/200]	Time 0.361 (0.429)	Data 0.001 (0.066)	Loss 1.852 (0.731)
Epoch: [1][60/200]	Time 0.364 (0.407)	Data 0.000 (0.044)	Loss 1.763 (1.137)
Epoch: [1][80/200]	Time 0.366 (0.415)	Data 0.001 (0.052)	Loss 2.167 (1.348)
Epoch: [1][100/200]	Time 2.039 (0.423)	Data 1.655 (0.058)	Loss 1.958 (1.449)
Epoch: [1][120/200]	Time 0.362 (0.413)	Data 0.001 (0.048)	Loss 2.041 (1.512)
Epoch: [1][140/200]	Time 0.368 (0.418)	Data 0.001 (0.053)	Loss 1.557 (1.563)
Epoch: [1][160/200]	Time 0.364 (0.413)	Data 0.000 (0.047)	Loss 1.945 (1.593)
Epoch: [1][180/200]	Time 0.367 (0.417)	Data 0.001 (0.051)	Loss 1.676 (1.605)
Epoch: [1][200/200]	Time 0.365 (0.419)	Data 0.001 (0.053)	Loss 1.552 (1.623)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.119 (0.217)	Data 0.000 (0.098)	
Extract Features: [100/128]	Time 0.119 (0.194)	Data 0.000 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.88249158859253
==> Statistics for epoch 2: 1033 clusters
Epoch: [2][20/200]	Time 0.363 (0.433)	Data 0.001 (0.063)	Loss 0.579 (0.457)
Epoch: [2][40/200]	Time 0.363 (0.439)	Data 0.001 (0.071)	Loss 1.861 (0.740)
Epoch: [2][60/200]	Time 0.470 (0.417)	Data 0.000 (0.048)	Loss 1.574 (1.128)
Epoch: [2][80/200]	Time 0.369 (0.425)	Data 0.001 (0.056)	Loss 2.030 (1.329)
Epoch: [2][100/200]	Time 0.368 (0.429)	Data 0.001 (0.060)	Loss 1.593 (1.432)
Epoch: [2][120/200]	Time 0.366 (0.418)	Data 0.000 (0.050)	Loss 1.542 (1.503)
Epoch: [2][140/200]	Time 0.366 (0.422)	Data 0.001 (0.054)	Loss 2.214 (1.559)
Epoch: [2][160/200]	Time 0.365 (0.415)	Data 0.000 (0.048)	Loss 1.839 (1.590)
Epoch: [2][180/200]	Time 0.368 (0.419)	Data 0.001 (0.052)	Loss 1.354 (1.615)
Epoch: [2][200/200]	Time 0.367 (0.423)	Data 0.001 (0.055)	Loss 1.495 (1.636)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.117 (0.210)	Data 0.000 (0.088)	
Extract Features: [100/128]	Time 0.123 (0.193)	Data 0.001 (0.071)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.5540018081665
==> Statistics for epoch 3: 1053 clusters
Epoch: [3][20/200]	Time 0.362 (0.418)	Data 0.001 (0.053)	Loss 0.329 (0.438)
Epoch: [3][40/200]	Time 0.360 (0.431)	Data 0.001 (0.066)	Loss 2.281 (0.651)
Epoch: [3][60/200]	Time 0.362 (0.411)	Data 0.000 (0.044)	Loss 2.037 (1.040)
Epoch: [3][80/200]	Time 0.363 (0.420)	Data 0.001 (0.053)	Loss 1.498 (1.233)
Epoch: [3][100/200]	Time 0.365 (0.425)	Data 0.000 (0.059)	Loss 1.654 (1.333)
Epoch: [3][120/200]	Time 0.496 (0.417)	Data 0.001 (0.049)	Loss 1.770 (1.406)
Epoch: [3][140/200]	Time 0.369 (0.421)	Data 0.001 (0.053)	Loss 1.874 (1.460)
Epoch: [3][160/200]	Time 0.365 (0.414)	Data 0.000 (0.047)	Loss 1.659 (1.494)
Epoch: [3][180/200]	Time 0.367 (0.419)	Data 0.001 (0.051)	Loss 1.808 (1.526)
Epoch: [3][200/200]	Time 0.370 (0.422)	Data 0.001 (0.054)	Loss 1.607 (1.540)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.192 (0.214)	Data 0.076 (0.097)	
Extract Features: [100/128]	Time 0.123 (0.194)	Data 0.000 (0.075)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.0604932308197
==> Statistics for epoch 4: 1057 clusters
Epoch: [4][20/200]	Time 0.360 (0.419)	Data 0.001 (0.056)	Loss 0.294 (0.429)
Epoch: [4][40/200]	Time 0.364 (0.441)	Data 0.000 (0.075)	Loss 2.137 (0.656)
Epoch: [4][60/200]	Time 0.371 (0.416)	Data 0.000 (0.050)	Loss 1.304 (1.023)
Epoch: [4][80/200]	Time 0.367 (0.425)	Data 0.001 (0.059)	Loss 1.828 (1.210)
Epoch: [4][100/200]	Time 2.214 (0.431)	Data 1.836 (0.065)	Loss 1.880 (1.318)
Epoch: [4][120/200]	Time 0.373 (0.422)	Data 0.001 (0.055)	Loss 1.689 (1.386)
Epoch: [4][140/200]	Time 0.366 (0.426)	Data 0.001 (0.059)	Loss 1.893 (1.450)
Epoch: [4][160/200]	Time 0.368 (0.418)	Data 0.000 (0.052)	Loss 1.338 (1.486)
Epoch: [4][180/200]	Time 0.366 (0.422)	Data 0.001 (0.055)	Loss 1.462 (1.523)
Epoch: [4][200/200]	Time 0.369 (0.425)	Data 0.001 (0.058)	Loss 2.062 (1.541)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.124 (0.217)	Data 0.001 (0.099)	
Extract Features: [100/128]	Time 0.118 (0.195)	Data 0.000 (0.075)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.24374580383301
==> Statistics for epoch 5: 1043 clusters
Epoch: [5][20/200]	Time 0.363 (0.423)	Data 0.001 (0.059)	Loss 0.284 (0.383)
Epoch: [5][40/200]	Time 0.362 (0.439)	Data 0.000 (0.075)	Loss 1.615 (0.622)
Epoch: [5][60/200]	Time 0.364 (0.413)	Data 0.000 (0.050)	Loss 1.621 (0.981)
Epoch: [5][80/200]	Time 0.366 (0.422)	Data 0.001 (0.058)	Loss 1.730 (1.183)
Epoch: [5][100/200]	Time 0.367 (0.427)	Data 0.002 (0.063)	Loss 1.946 (1.298)
Epoch: [5][120/200]	Time 0.367 (0.417)	Data 0.001 (0.052)	Loss 2.184 (1.380)
Epoch: [5][140/200]	Time 0.367 (0.423)	Data 0.001 (0.057)	Loss 1.666 (1.438)
Epoch: [5][160/200]	Time 0.366 (0.416)	Data 0.000 (0.050)	Loss 1.905 (1.467)
Epoch: [5][180/200]	Time 0.364 (0.420)	Data 0.001 (0.055)	Loss 1.898 (1.491)
Epoch: [5][200/200]	Time 0.373 (0.423)	Data 0.001 (0.057)	Loss 1.799 (1.521)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.117 (0.217)	Data 0.000 (0.096)	
Extract Features: [100/128]	Time 0.118 (0.194)	Data 0.000 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.57247066497803
==> Statistics for epoch 6: 1005 clusters
Epoch: [6][20/200]	Time 0.360 (0.418)	Data 0.000 (0.053)	Loss 0.433 (0.415)
Epoch: [6][40/200]	Time 0.363 (0.432)	Data 0.001 (0.067)	Loss 1.842 (0.683)
Epoch: [6][60/200]	Time 0.363 (0.409)	Data 0.000 (0.045)	Loss 1.756 (1.029)
Epoch: [6][80/200]	Time 0.365 (0.419)	Data 0.001 (0.054)	Loss 1.562 (1.208)
Epoch: [6][100/200]	Time 0.362 (0.425)	Data 0.001 (0.060)	Loss 1.662 (1.326)
Epoch: [6][120/200]	Time 0.363 (0.415)	Data 0.000 (0.050)	Loss 1.780 (1.386)
Epoch: [6][140/200]	Time 0.365 (0.419)	Data 0.001 (0.054)	Loss 1.911 (1.429)
Epoch: [6][160/200]	Time 0.367 (0.423)	Data 0.001 (0.058)	Loss 1.321 (1.462)
Epoch: [6][180/200]	Time 0.364 (0.417)	Data 0.000 (0.051)	Loss 2.049 (1.485)
Epoch: [6][200/200]	Time 0.363 (0.420)	Data 0.001 (0.054)	Loss 1.601 (1.518)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.298 (0.213)	Data 0.049 (0.093)	
Extract Features: [100/128]	Time 0.118 (0.191)	Data 0.000 (0.072)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.76935338973999
==> Statistics for epoch 7: 1014 clusters
Epoch: [7][20/200]	Time 0.365 (0.419)	Data 0.001 (0.053)	Loss 0.376 (0.394)
Epoch: [7][40/200]	Time 0.506 (0.441)	Data 0.001 (0.072)	Loss 1.397 (0.634)
Epoch: [7][60/200]	Time 0.363 (0.415)	Data 0.000 (0.048)	Loss 1.885 (1.020)
Epoch: [7][80/200]	Time 0.362 (0.424)	Data 0.001 (0.057)	Loss 1.655 (1.214)
Epoch: [7][100/200]	Time 0.365 (0.429)	Data 0.001 (0.063)	Loss 1.541 (1.323)
Epoch: [7][120/200]	Time 0.363 (0.418)	Data 0.000 (0.053)	Loss 2.225 (1.411)
Epoch: [7][140/200]	Time 0.364 (0.423)	Data 0.001 (0.057)	Loss 1.578 (1.446)
Epoch: [7][160/200]	Time 0.364 (0.427)	Data 0.001 (0.061)	Loss 1.906 (1.482)
Epoch: [7][180/200]	Time 0.366 (0.420)	Data 0.000 (0.054)	Loss 2.076 (1.509)
Epoch: [7][200/200]	Time 0.367 (0.424)	Data 0.001 (0.058)	Loss 1.822 (1.533)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.117 (0.208)	Data 0.001 (0.087)	
Extract Features: [100/128]	Time 0.124 (0.189)	Data 0.007 (0.067)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.26243209838867
==> Statistics for epoch 8: 1000 clusters
Epoch: [8][20/200]	Time 0.366 (0.419)	Data 0.001 (0.052)	Loss 0.318 (0.400)
Epoch: [8][40/200]	Time 0.364 (0.431)	Data 0.001 (0.065)	Loss 1.557 (0.681)
Epoch: [8][60/200]	Time 0.363 (0.411)	Data 0.000 (0.044)	Loss 1.419 (1.012)
Epoch: [8][80/200]	Time 0.365 (0.421)	Data 0.001 (0.054)	Loss 1.985 (1.187)
Epoch: [8][100/200]	Time 0.365 (0.427)	Data 0.001 (0.060)	Loss 1.313 (1.285)
Epoch: [8][120/200]	Time 0.367 (0.418)	Data 0.000 (0.050)	Loss 1.279 (1.352)
Epoch: [8][140/200]	Time 0.365 (0.423)	Data 0.001 (0.055)	Loss 1.281 (1.397)
Epoch: [8][160/200]	Time 0.368 (0.426)	Data 0.000 (0.058)	Loss 1.616 (1.439)
Epoch: [8][180/200]	Time 0.366 (0.419)	Data 0.000 (0.052)	Loss 1.689 (1.464)
Epoch: [8][200/200]	Time 0.366 (0.423)	Data 0.001 (0.056)	Loss 1.799 (1.496)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.216)	Data 0.000 (0.095)	
Extract Features: [100/128]	Time 0.120 (0.194)	Data 0.000 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.34680199623108
==> Statistics for epoch 9: 979 clusters
Epoch: [9][20/200]	Time 0.366 (0.426)	Data 0.001 (0.060)	Loss 0.240 (0.345)
Epoch: [9][40/200]	Time 0.364 (0.437)	Data 0.001 (0.071)	Loss 1.807 (0.666)
Epoch: [9][60/200]	Time 0.365 (0.413)	Data 0.000 (0.048)	Loss 1.642 (0.982)
Epoch: [9][80/200]	Time 0.366 (0.425)	Data 0.001 (0.058)	Loss 1.441 (1.156)
Epoch: [9][100/200]	Time 0.365 (0.430)	Data 0.001 (0.063)	Loss 1.422 (1.261)
Epoch: [9][120/200]	Time 0.365 (0.420)	Data 0.000 (0.053)	Loss 1.449 (1.316)
Epoch: [9][140/200]	Time 0.367 (0.426)	Data 0.001 (0.058)	Loss 1.744 (1.377)
Epoch: [9][160/200]	Time 0.369 (0.429)	Data 0.001 (0.061)	Loss 1.723 (1.417)
Epoch: [9][180/200]	Time 0.366 (0.422)	Data 0.000 (0.055)	Loss 1.960 (1.454)
Epoch: [9][200/200]	Time 0.363 (0.425)	Data 0.001 (0.057)	Loss 1.860 (1.474)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.117 (0.222)	Data 0.000 (0.102)	
Extract Features: [100/128]	Time 0.118 (0.198)	Data 0.000 (0.078)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.305065631866455
==> Statistics for epoch 10: 1028 clusters
Epoch: [10][20/200]	Time 0.364 (0.418)	Data 0.001 (0.054)	Loss 0.311 (0.405)
Epoch: [10][40/200]	Time 0.362 (0.431)	Data 0.001 (0.067)	Loss 1.741 (0.654)
Epoch: [10][60/200]	Time 0.361 (0.409)	Data 0.000 (0.045)	Loss 1.859 (1.008)
Epoch: [10][80/200]	Time 0.365 (0.419)	Data 0.001 (0.055)	Loss 1.494 (1.167)
Epoch: [10][100/200]	Time 0.366 (0.427)	Data 0.001 (0.060)	Loss 1.395 (1.264)
Epoch: [10][120/200]	Time 0.368 (0.417)	Data 0.001 (0.051)	Loss 1.691 (1.346)
Epoch: [10][140/200]	Time 0.366 (0.423)	Data 0.001 (0.057)	Loss 1.681 (1.388)
Epoch: [10][160/200]	Time 0.365 (0.416)	Data 0.000 (0.050)	Loss 1.832 (1.420)
Epoch: [10][180/200]	Time 0.371 (0.420)	Data 0.001 (0.054)	Loss 1.074 (1.441)
Epoch: [10][200/200]	Time 0.364 (0.424)	Data 0.001 (0.057)	Loss 1.859 (1.467)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.264 (0.217)	Data 0.000 (0.097)	
Extract Features: [100/128]	Time 0.118 (0.192)	Data 0.000 (0.072)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.896547079086304
==> Statistics for epoch 11: 1017 clusters
Epoch: [11][20/200]	Time 0.374 (0.423)	Data 0.001 (0.057)	Loss 0.208 (0.366)
Epoch: [11][40/200]	Time 0.364 (0.437)	Data 0.001 (0.072)	Loss 1.204 (0.645)
Epoch: [11][60/200]	Time 0.359 (0.416)	Data 0.000 (0.048)	Loss 1.328 (0.972)
Epoch: [11][80/200]	Time 0.367 (0.424)	Data 0.001 (0.058)	Loss 2.150 (1.163)
Epoch: [11][100/200]	Time 0.369 (0.430)	Data 0.001 (0.063)	Loss 1.637 (1.269)
Epoch: [11][120/200]	Time 0.364 (0.420)	Data 0.000 (0.052)	Loss 1.516 (1.350)
Epoch: [11][140/200]	Time 0.363 (0.424)	Data 0.001 (0.057)	Loss 2.157 (1.405)
Epoch: [11][160/200]	Time 0.366 (0.428)	Data 0.000 (0.060)	Loss 1.624 (1.434)
Epoch: [11][180/200]	Time 0.364 (0.421)	Data 0.000 (0.053)	Loss 1.819 (1.455)
Epoch: [11][200/200]	Time 0.364 (0.423)	Data 0.001 (0.056)	Loss 1.557 (1.480)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.119 (0.211)	Data 0.000 (0.093)	
Extract Features: [100/128]	Time 0.119 (0.192)	Data 0.001 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.71206831932068
==> Statistics for epoch 12: 1021 clusters
Epoch: [12][20/200]	Time 0.363 (0.421)	Data 0.001 (0.056)	Loss 0.335 (0.352)
Epoch: [12][40/200]	Time 0.364 (0.440)	Data 0.001 (0.072)	Loss 1.775 (0.644)
Epoch: [12][60/200]	Time 0.367 (0.415)	Data 0.000 (0.048)	Loss 1.719 (0.964)
Epoch: [12][80/200]	Time 0.365 (0.423)	Data 0.001 (0.056)	Loss 1.838 (1.130)
Epoch: [12][100/200]	Time 0.367 (0.427)	Data 0.001 (0.060)	Loss 2.019 (1.237)
Epoch: [12][120/200]	Time 0.361 (0.417)	Data 0.000 (0.050)	Loss 2.295 (1.303)
Epoch: [12][140/200]	Time 0.366 (0.422)	Data 0.001 (0.055)	Loss 1.735 (1.357)
Epoch: [12][160/200]	Time 0.368 (0.426)	Data 0.001 (0.058)	Loss 1.505 (1.392)
Epoch: [12][180/200]	Time 0.370 (0.420)	Data 0.000 (0.052)	Loss 1.605 (1.427)
Epoch: [12][200/200]	Time 0.365 (0.423)	Data 0.001 (0.055)	Loss 1.892 (1.462)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.420 (0.217)	Data 0.304 (0.097)	
Extract Features: [100/128]	Time 0.119 (0.195)	Data 0.000 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.69394898414612
==> Statistics for epoch 13: 1043 clusters
Epoch: [13][20/200]	Time 0.364 (0.416)	Data 0.001 (0.051)	Loss 0.240 (0.357)
Epoch: [13][40/200]	Time 0.366 (0.437)	Data 0.001 (0.068)	Loss 1.757 (0.611)
Epoch: [13][60/200]	Time 0.363 (0.413)	Data 0.000 (0.046)	Loss 1.585 (0.971)
Epoch: [13][80/200]	Time 0.364 (0.424)	Data 0.001 (0.057)	Loss 2.082 (1.149)
Epoch: [13][100/200]	Time 0.370 (0.431)	Data 0.001 (0.064)	Loss 1.808 (1.271)
Epoch: [13][120/200]	Time 0.367 (0.420)	Data 0.001 (0.053)	Loss 1.514 (1.348)
Epoch: [13][140/200]	Time 0.363 (0.425)	Data 0.001 (0.059)	Loss 1.657 (1.394)
Epoch: [13][160/200]	Time 0.365 (0.418)	Data 0.000 (0.051)	Loss 1.689 (1.423)
Epoch: [13][180/200]	Time 0.363 (0.422)	Data 0.000 (0.056)	Loss 1.394 (1.447)
Epoch: [13][200/200]	Time 0.369 (0.425)	Data 0.001 (0.059)	Loss 1.493 (1.463)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.116 (0.214)	Data 0.000 (0.093)	
Extract Features: [100/128]	Time 0.120 (0.193)	Data 0.000 (0.072)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.56226325035095
==> Statistics for epoch 14: 1032 clusters
Epoch: [14][20/200]	Time 0.363 (0.421)	Data 0.001 (0.054)	Loss 0.326 (0.326)
Epoch: [14][40/200]	Time 0.365 (0.435)	Data 0.001 (0.069)	Loss 1.645 (0.575)
Epoch: [14][60/200]	Time 0.363 (0.412)	Data 0.000 (0.046)	Loss 1.716 (0.904)
Epoch: [14][80/200]	Time 0.368 (0.422)	Data 0.001 (0.056)	Loss 1.403 (1.093)
Epoch: [14][100/200]	Time 0.366 (0.427)	Data 0.001 (0.061)	Loss 1.746 (1.220)
Epoch: [14][120/200]	Time 0.365 (0.417)	Data 0.001 (0.051)	Loss 1.649 (1.289)
Epoch: [14][140/200]	Time 0.366 (0.422)	Data 0.001 (0.055)	Loss 1.766 (1.340)
Epoch: [14][160/200]	Time 0.376 (0.416)	Data 0.000 (0.048)	Loss 1.456 (1.392)
Epoch: [14][180/200]	Time 0.373 (0.420)	Data 0.001 (0.053)	Loss 2.223 (1.419)
Epoch: [14][200/200]	Time 0.367 (0.423)	Data 0.001 (0.056)	Loss 1.352 (1.437)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.119 (0.208)	Data 0.000 (0.087)	
Extract Features: [100/128]	Time 0.119 (0.189)	Data 0.000 (0.068)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.079087257385254
==> Statistics for epoch 15: 1044 clusters
Epoch: [15][20/200]	Time 0.365 (0.417)	Data 0.000 (0.050)	Loss 0.225 (0.350)
Epoch: [15][40/200]	Time 0.365 (0.433)	Data 0.001 (0.067)	Loss 1.007 (0.550)
Epoch: [15][60/200]	Time 0.361 (0.410)	Data 0.000 (0.045)	Loss 1.386 (0.895)
Epoch: [15][80/200]	Time 0.365 (0.420)	Data 0.001 (0.055)	Loss 1.346 (1.079)
Epoch: [15][100/200]	Time 0.373 (0.426)	Data 0.001 (0.060)	Loss 1.495 (1.182)
Epoch: [15][120/200]	Time 0.365 (0.416)	Data 0.001 (0.050)	Loss 1.886 (1.267)
Epoch: [15][140/200]	Time 0.367 (0.421)	Data 0.001 (0.054)	Loss 1.787 (1.323)
Epoch: [15][160/200]	Time 0.365 (0.414)	Data 0.000 (0.047)	Loss 1.360 (1.355)
Epoch: [15][180/200]	Time 0.369 (0.419)	Data 0.001 (0.051)	Loss 1.685 (1.383)
Epoch: [15][200/200]	Time 0.365 (0.422)	Data 0.001 (0.054)	Loss 1.448 (1.407)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.212)	Data 0.000 (0.092)	
Extract Features: [100/128]	Time 0.119 (0.192)	Data 0.000 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.91668438911438
==> Statistics for epoch 16: 1043 clusters
Epoch: [16][20/200]	Time 0.364 (0.416)	Data 0.001 (0.050)	Loss 0.167 (0.374)
Epoch: [16][40/200]	Time 0.365 (0.434)	Data 0.001 (0.068)	Loss 1.389 (0.575)
Epoch: [16][60/200]	Time 0.365 (0.411)	Data 0.000 (0.046)	Loss 1.499 (0.940)
Epoch: [16][80/200]	Time 0.364 (0.421)	Data 0.001 (0.056)	Loss 2.143 (1.084)
Epoch: [16][100/200]	Time 0.366 (0.427)	Data 0.001 (0.061)	Loss 2.020 (1.191)
Epoch: [16][120/200]	Time 0.367 (0.417)	Data 0.001 (0.051)	Loss 1.454 (1.242)
Epoch: [16][140/200]	Time 0.366 (0.422)	Data 0.001 (0.056)	Loss 1.865 (1.301)
Epoch: [16][160/200]	Time 0.368 (0.415)	Data 0.001 (0.049)	Loss 1.169 (1.335)
Epoch: [16][180/200]	Time 0.368 (0.419)	Data 0.001 (0.053)	Loss 1.510 (1.364)
Epoch: [16][200/200]	Time 0.368 (0.423)	Data 0.001 (0.056)	Loss 1.818 (1.385)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.296 (0.213)	Data 0.181 (0.092)	
Extract Features: [100/128]	Time 0.118 (0.193)	Data 0.000 (0.072)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.82760453224182
==> Statistics for epoch 17: 1006 clusters
Epoch: [17][20/200]	Time 0.360 (0.425)	Data 0.000 (0.053)	Loss 0.192 (0.326)
Epoch: [17][40/200]	Time 0.376 (0.437)	Data 0.001 (0.069)	Loss 2.063 (0.589)
Epoch: [17][60/200]	Time 0.362 (0.413)	Data 0.000 (0.046)	Loss 1.507 (0.906)
Epoch: [17][80/200]	Time 0.362 (0.423)	Data 0.001 (0.055)	Loss 1.433 (1.059)
Epoch: [17][100/200]	Time 0.363 (0.427)	Data 0.001 (0.060)	Loss 1.250 (1.158)
Epoch: [17][120/200]	Time 0.362 (0.416)	Data 0.000 (0.050)	Loss 1.261 (1.221)
Epoch: [17][140/200]	Time 0.368 (0.422)	Data 0.000 (0.054)	Loss 1.338 (1.270)
Epoch: [17][160/200]	Time 0.363 (0.425)	Data 0.000 (0.058)	Loss 1.586 (1.305)
Epoch: [17][180/200]	Time 0.364 (0.418)	Data 0.000 (0.051)	Loss 1.671 (1.328)
Epoch: [17][200/200]	Time 0.363 (0.422)	Data 0.001 (0.055)	Loss 1.597 (1.349)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.120 (0.208)	Data 0.000 (0.090)	
Extract Features: [100/128]	Time 0.117 (0.194)	Data 0.000 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.36252474784851
==> Statistics for epoch 18: 1037 clusters
Epoch: [18][20/200]	Time 0.361 (0.419)	Data 0.001 (0.054)	Loss 0.342 (0.314)
Epoch: [18][40/200]	Time 0.365 (0.433)	Data 0.001 (0.070)	Loss 1.592 (0.558)
Epoch: [18][60/200]	Time 0.362 (0.412)	Data 0.000 (0.047)	Loss 1.620 (0.875)
Epoch: [18][80/200]	Time 0.364 (0.421)	Data 0.001 (0.056)	Loss 1.468 (1.062)
Epoch: [18][100/200]	Time 0.504 (0.427)	Data 0.001 (0.060)	Loss 1.855 (1.152)
Epoch: [18][120/200]	Time 0.363 (0.417)	Data 0.001 (0.051)	Loss 1.718 (1.233)
Epoch: [18][140/200]	Time 0.364 (0.422)	Data 0.000 (0.056)	Loss 1.346 (1.268)
Epoch: [18][160/200]	Time 0.364 (0.415)	Data 0.000 (0.049)	Loss 1.607 (1.299)
Epoch: [18][180/200]	Time 0.376 (0.419)	Data 0.001 (0.053)	Loss 1.261 (1.332)
Epoch: [18][200/200]	Time 0.370 (0.423)	Data 0.001 (0.056)	Loss 1.811 (1.353)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.120 (0.214)	Data 0.000 (0.093)	
Extract Features: [100/128]	Time 0.117 (0.193)	Data 0.000 (0.072)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.86946773529053
==> Statistics for epoch 19: 1031 clusters
Epoch: [19][20/200]	Time 0.365 (0.416)	Data 0.001 (0.050)	Loss 0.492 (0.368)
Epoch: [19][40/200]	Time 0.364 (0.436)	Data 0.001 (0.070)	Loss 1.517 (0.604)
Epoch: [19][60/200]	Time 0.358 (0.411)	Data 0.000 (0.047)	Loss 1.510 (0.882)
Epoch: [19][80/200]	Time 0.370 (0.420)	Data 0.001 (0.055)	Loss 1.583 (1.014)
Epoch: [19][100/200]	Time 0.368 (0.424)	Data 0.001 (0.060)	Loss 1.288 (1.106)
Epoch: [19][120/200]	Time 0.375 (0.415)	Data 0.001 (0.050)	Loss 1.756 (1.165)
Epoch: [19][140/200]	Time 0.365 (0.419)	Data 0.001 (0.054)	Loss 1.380 (1.199)
Epoch: [19][160/200]	Time 0.365 (0.412)	Data 0.000 (0.047)	Loss 1.600 (1.240)
Epoch: [19][180/200]	Time 0.367 (0.417)	Data 0.001 (0.051)	Loss 1.388 (1.261)
Epoch: [19][200/200]	Time 0.365 (0.420)	Data 0.001 (0.054)	Loss 1.332 (1.277)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.124 (0.210)	Data 0.007 (0.089)	
Extract Features: [100/128]	Time 0.118 (0.191)	Data 0.000 (0.070)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.90254783630371
==> Statistics for epoch 20: 1050 clusters
Epoch: [20][20/200]	Time 0.364 (0.422)	Data 0.001 (0.056)	Loss 0.235 (0.311)
Epoch: [20][40/200]	Time 0.368 (0.439)	Data 0.001 (0.073)	Loss 1.454 (0.522)
Epoch: [20][60/200]	Time 0.364 (0.414)	Data 0.000 (0.049)	Loss 1.277 (0.826)
Epoch: [20][80/200]	Time 0.362 (0.423)	Data 0.001 (0.059)	Loss 1.384 (0.988)
Epoch: [20][100/200]	Time 0.367 (0.429)	Data 0.001 (0.064)	Loss 1.540 (1.073)
Epoch: [20][120/200]	Time 0.365 (0.419)	Data 0.001 (0.053)	Loss 1.491 (1.124)
Epoch: [20][140/200]	Time 0.364 (0.424)	Data 0.001 (0.059)	Loss 1.453 (1.168)
Epoch: [20][160/200]	Time 0.369 (0.418)	Data 0.000 (0.051)	Loss 1.476 (1.202)
Epoch: [20][180/200]	Time 0.366 (0.422)	Data 0.001 (0.055)	Loss 1.318 (1.234)
Epoch: [20][200/200]	Time 0.368 (0.425)	Data 0.001 (0.058)	Loss 1.509 (1.240)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.208)	Data 0.000 (0.089)	
Extract Features: [100/128]	Time 0.119 (0.195)	Data 0.000 (0.075)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.827958822250366
==> Statistics for epoch 21: 1065 clusters
Epoch: [21][20/200]	Time 0.362 (0.417)	Data 0.001 (0.051)	Loss 0.291 (0.251)
Epoch: [21][40/200]	Time 0.364 (0.433)	Data 0.001 (0.068)	Loss 1.409 (0.463)
Epoch: [21][60/200]	Time 0.365 (0.411)	Data 0.000 (0.046)	Loss 1.653 (0.813)
Epoch: [21][80/200]	Time 0.365 (0.421)	Data 0.001 (0.055)	Loss 1.306 (0.967)
Epoch: [21][100/200]	Time 1.955 (0.425)	Data 1.565 (0.060)	Loss 2.044 (1.076)
Epoch: [21][120/200]	Time 0.363 (0.415)	Data 0.001 (0.050)	Loss 1.457 (1.151)
Epoch: [21][140/200]	Time 0.366 (0.420)	Data 0.001 (0.055)	Loss 1.790 (1.212)
Epoch: [21][160/200]	Time 0.364 (0.413)	Data 0.000 (0.048)	Loss 1.406 (1.247)
Epoch: [21][180/200]	Time 0.367 (0.418)	Data 0.001 (0.052)	Loss 1.681 (1.274)
Epoch: [21][200/200]	Time 0.365 (0.421)	Data 0.001 (0.056)	Loss 1.627 (1.298)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.115 (0.214)	Data 0.000 (0.094)	
Extract Features: [100/128]	Time 0.120 (0.194)	Data 0.001 (0.072)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.502228021621704
==> Statistics for epoch 22: 1050 clusters
Epoch: [22][20/200]	Time 0.363 (0.416)	Data 0.001 (0.052)	Loss 0.296 (0.277)
Epoch: [22][40/200]	Time 0.363 (0.430)	Data 0.001 (0.067)	Loss 1.187 (0.524)
Epoch: [22][60/200]	Time 0.359 (0.409)	Data 0.000 (0.045)	Loss 1.294 (0.803)
Epoch: [22][80/200]	Time 0.363 (0.417)	Data 0.001 (0.052)	Loss 1.470 (0.959)
Epoch: [22][100/200]	Time 0.362 (0.423)	Data 0.001 (0.059)	Loss 1.111 (1.056)
Epoch: [22][120/200]	Time 0.366 (0.414)	Data 0.001 (0.049)	Loss 1.751 (1.128)
Epoch: [22][140/200]	Time 0.367 (0.419)	Data 0.001 (0.054)	Loss 1.566 (1.174)
Epoch: [22][160/200]	Time 0.364 (0.412)	Data 0.000 (0.047)	Loss 1.729 (1.216)
Epoch: [22][180/200]	Time 0.367 (0.416)	Data 0.001 (0.051)	Loss 1.385 (1.244)
Epoch: [22][200/200]	Time 0.368 (0.420)	Data 0.001 (0.055)	Loss 1.170 (1.267)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.119 (0.215)	Data 0.000 (0.094)	
Extract Features: [100/128]	Time 0.118 (0.199)	Data 0.000 (0.078)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.95039701461792
==> Statistics for epoch 23: 1070 clusters
Epoch: [23][20/200]	Time 0.364 (0.422)	Data 0.001 (0.058)	Loss 0.210 (0.294)
Epoch: [23][40/200]	Time 0.361 (0.435)	Data 0.001 (0.069)	Loss 1.366 (0.484)
Epoch: [23][60/200]	Time 0.369 (0.411)	Data 0.000 (0.046)	Loss 1.298 (0.812)
Epoch: [23][80/200]	Time 0.363 (0.419)	Data 0.001 (0.055)	Loss 2.024 (0.981)
Epoch: [23][100/200]	Time 2.060 (0.425)	Data 1.675 (0.061)	Loss 1.349 (1.083)
Epoch: [23][120/200]	Time 0.364 (0.415)	Data 0.001 (0.051)	Loss 1.685 (1.151)
Epoch: [23][140/200]	Time 0.364 (0.420)	Data 0.001 (0.055)	Loss 1.130 (1.207)
Epoch: [23][160/200]	Time 0.364 (0.413)	Data 0.000 (0.048)	Loss 1.805 (1.250)
Epoch: [23][180/200]	Time 0.361 (0.417)	Data 0.001 (0.052)	Loss 1.389 (1.288)
Epoch: [23][200/200]	Time 0.364 (0.421)	Data 0.001 (0.056)	Loss 1.661 (1.302)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.290 (0.210)	Data 0.173 (0.090)	
Extract Features: [100/128]	Time 0.121 (0.191)	Data 0.000 (0.071)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.126683950424194
==> Statistics for epoch 24: 1061 clusters
Epoch: [24][20/200]	Time 0.364 (0.420)	Data 0.001 (0.057)	Loss 0.270 (0.275)
Epoch: [24][40/200]	Time 0.362 (0.432)	Data 0.001 (0.069)	Loss 1.604 (0.482)
Epoch: [24][60/200]	Time 0.367 (0.410)	Data 0.000 (0.046)	Loss 1.689 (0.815)
Epoch: [24][80/200]	Time 0.365 (0.420)	Data 0.001 (0.054)	Loss 1.354 (0.976)
Epoch: [24][100/200]	Time 2.245 (0.428)	Data 1.872 (0.062)	Loss 1.548 (1.067)
Epoch: [24][120/200]	Time 0.372 (0.418)	Data 0.001 (0.052)	Loss 1.229 (1.138)
Epoch: [24][140/200]	Time 0.368 (0.422)	Data 0.001 (0.056)	Loss 1.253 (1.201)
Epoch: [24][160/200]	Time 0.360 (0.416)	Data 0.000 (0.049)	Loss 1.615 (1.228)
Epoch: [24][180/200]	Time 0.367 (0.419)	Data 0.001 (0.053)	Loss 1.560 (1.258)
Epoch: [24][200/200]	Time 0.364 (0.422)	Data 0.001 (0.055)	Loss 2.069 (1.281)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.119 (0.214)	Data 0.000 (0.093)	
Extract Features: [100/128]	Time 0.118 (0.192)	Data 0.000 (0.072)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.604779958724976
==> Statistics for epoch 25: 1076 clusters
Epoch: [25][20/200]	Time 0.361 (0.421)	Data 0.001 (0.056)	Loss 0.346 (0.290)
Epoch: [25][40/200]	Time 0.362 (0.432)	Data 0.001 (0.068)	Loss 1.432 (0.452)
Epoch: [25][60/200]	Time 0.362 (0.411)	Data 0.000 (0.045)	Loss 1.481 (0.790)
Epoch: [25][80/200]	Time 0.363 (0.420)	Data 0.001 (0.054)	Loss 1.555 (0.978)
Epoch: [25][100/200]	Time 1.941 (0.424)	Data 1.557 (0.059)	Loss 1.721 (1.090)
Epoch: [25][120/200]	Time 0.373 (0.415)	Data 0.001 (0.049)	Loss 1.248 (1.162)
Epoch: [25][140/200]	Time 0.374 (0.420)	Data 0.001 (0.054)	Loss 1.756 (1.218)
Epoch: [25][160/200]	Time 0.359 (0.413)	Data 0.000 (0.047)	Loss 1.794 (1.255)
Epoch: [25][180/200]	Time 0.487 (0.418)	Data 0.000 (0.051)	Loss 1.390 (1.289)
Epoch: [25][200/200]	Time 0.366 (0.421)	Data 0.000 (0.054)	Loss 1.560 (1.310)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.220)	Data 0.000 (0.101)	
Extract Features: [100/128]	Time 0.118 (0.196)	Data 0.000 (0.075)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.708149671554565
==> Statistics for epoch 26: 1073 clusters
Epoch: [26][20/200]	Time 0.362 (0.423)	Data 0.001 (0.059)	Loss 0.162 (0.287)
Epoch: [26][40/200]	Time 0.363 (0.438)	Data 0.001 (0.074)	Loss 1.377 (0.471)
Epoch: [26][60/200]	Time 0.365 (0.416)	Data 0.000 (0.050)	Loss 1.461 (0.809)
Epoch: [26][80/200]	Time 0.363 (0.425)	Data 0.001 (0.059)	Loss 1.426 (0.981)
Epoch: [26][100/200]	Time 2.165 (0.431)	Data 1.771 (0.065)	Loss 1.361 (1.097)
Epoch: [26][120/200]	Time 0.363 (0.421)	Data 0.001 (0.055)	Loss 1.825 (1.154)
Epoch: [26][140/200]	Time 0.366 (0.426)	Data 0.001 (0.060)	Loss 1.441 (1.216)
Epoch: [26][160/200]	Time 0.364 (0.419)	Data 0.000 (0.052)	Loss 1.720 (1.250)
Epoch: [26][180/200]	Time 0.369 (0.423)	Data 0.004 (0.056)	Loss 1.735 (1.278)
Epoch: [26][200/200]	Time 0.363 (0.426)	Data 0.001 (0.060)	Loss 1.268 (1.294)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.121 (0.213)	Data 0.000 (0.092)	
Extract Features: [100/128]	Time 0.119 (0.193)	Data 0.000 (0.072)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.71374201774597
==> Statistics for epoch 27: 1072 clusters
Epoch: [27][20/200]	Time 0.363 (0.419)	Data 0.001 (0.054)	Loss 0.165 (0.245)
Epoch: [27][40/200]	Time 0.361 (0.433)	Data 0.001 (0.069)	Loss 1.213 (0.442)
Epoch: [27][60/200]	Time 0.363 (0.413)	Data 0.000 (0.046)	Loss 1.429 (0.761)
Epoch: [27][80/200]	Time 0.364 (0.421)	Data 0.001 (0.055)	Loss 1.840 (0.950)
Epoch: [27][100/200]	Time 2.222 (0.428)	Data 1.842 (0.062)	Loss 1.326 (1.041)
Epoch: [27][120/200]	Time 0.361 (0.418)	Data 0.001 (0.052)	Loss 2.125 (1.118)
Epoch: [27][140/200]	Time 0.365 (0.423)	Data 0.001 (0.058)	Loss 1.564 (1.181)
Epoch: [27][160/200]	Time 0.364 (0.416)	Data 0.000 (0.051)	Loss 1.521 (1.221)
Epoch: [27][180/200]	Time 0.362 (0.421)	Data 0.001 (0.055)	Loss 1.116 (1.248)
Epoch: [27][200/200]	Time 0.368 (0.424)	Data 0.001 (0.058)	Loss 1.703 (1.278)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.119 (0.205)	Data 0.000 (0.083)	
Extract Features: [100/128]	Time 0.117 (0.188)	Data 0.000 (0.065)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.08022809028625
==> Statistics for epoch 28: 1063 clusters
Epoch: [28][20/200]	Time 0.371 (0.425)	Data 0.002 (0.057)	Loss 0.248 (0.255)
Epoch: [28][40/200]	Time 0.365 (0.440)	Data 0.001 (0.072)	Loss 1.429 (0.452)
Epoch: [28][60/200]	Time 0.365 (0.416)	Data 0.000 (0.049)	Loss 1.676 (0.799)
Epoch: [28][80/200]	Time 0.373 (0.423)	Data 0.001 (0.056)	Loss 1.523 (0.959)
Epoch: [28][100/200]	Time 2.039 (0.428)	Data 1.652 (0.061)	Loss 1.468 (1.071)
Epoch: [28][120/200]	Time 0.492 (0.419)	Data 0.001 (0.051)	Loss 1.281 (1.139)
Epoch: [28][140/200]	Time 0.364 (0.424)	Data 0.001 (0.055)	Loss 1.903 (1.191)
Epoch: [28][160/200]	Time 0.364 (0.417)	Data 0.000 (0.049)	Loss 2.145 (1.219)
Epoch: [28][180/200]	Time 0.368 (0.420)	Data 0.001 (0.052)	Loss 1.328 (1.254)
Epoch: [28][200/200]	Time 0.365 (0.423)	Data 0.001 (0.055)	Loss 1.916 (1.276)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.120 (0.216)	Data 0.000 (0.096)	
Extract Features: [100/128]	Time 0.117 (0.194)	Data 0.000 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.31722116470337
==> Statistics for epoch 29: 1078 clusters
Epoch: [29][20/200]	Time 0.364 (0.414)	Data 0.001 (0.049)	Loss 0.207 (0.288)
Epoch: [29][40/200]	Time 0.367 (0.433)	Data 0.001 (0.068)	Loss 1.430 (0.473)
Epoch: [29][60/200]	Time 0.366 (0.411)	Data 0.000 (0.046)	Loss 1.561 (0.807)
Epoch: [29][80/200]	Time 0.367 (0.423)	Data 0.001 (0.056)	Loss 1.248 (0.981)
Epoch: [29][100/200]	Time 2.095 (0.429)	Data 1.715 (0.062)	Loss 1.719 (1.081)
Epoch: [29][120/200]	Time 0.369 (0.419)	Data 0.001 (0.052)	Loss 1.087 (1.150)
Epoch: [29][140/200]	Time 0.370 (0.423)	Data 0.001 (0.056)	Loss 1.344 (1.189)
Epoch: [29][160/200]	Time 0.365 (0.417)	Data 0.000 (0.050)	Loss 1.417 (1.227)
Epoch: [29][180/200]	Time 0.362 (0.421)	Data 0.001 (0.053)	Loss 1.310 (1.265)
Epoch: [29][200/200]	Time 0.365 (0.423)	Data 0.001 (0.056)	Loss 1.372 (1.291)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.125 (0.212)	Data 0.010 (0.091)	
Extract Features: [100/128]	Time 0.119 (0.193)	Data 0.000 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.93139100074768
==> Statistics for epoch 30: 1067 clusters
Epoch: [30][20/200]	Time 0.365 (0.422)	Data 0.001 (0.056)	Loss 0.146 (0.262)
Epoch: [30][40/200]	Time 0.361 (0.433)	Data 0.001 (0.068)	Loss 1.207 (0.444)
Epoch: [30][60/200]	Time 0.361 (0.410)	Data 0.000 (0.045)	Loss 1.256 (0.785)
Epoch: [30][80/200]	Time 0.366 (0.420)	Data 0.001 (0.055)	Loss 1.326 (0.957)
Epoch: [30][100/200]	Time 1.987 (0.426)	Data 1.601 (0.060)	Loss 1.322 (1.066)
Epoch: [30][120/200]	Time 0.366 (0.416)	Data 0.001 (0.050)	Loss 1.695 (1.140)
Epoch: [30][140/200]	Time 0.367 (0.422)	Data 0.000 (0.055)	Loss 1.369 (1.189)
Epoch: [30][160/200]	Time 0.365 (0.415)	Data 0.000 (0.048)	Loss 1.555 (1.222)
Epoch: [30][180/200]	Time 0.368 (0.419)	Data 0.001 (0.051)	Loss 1.581 (1.262)
Epoch: [30][200/200]	Time 0.367 (0.422)	Data 0.001 (0.055)	Loss 1.211 (1.283)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.243 (0.211)	Data 0.126 (0.090)	
Extract Features: [100/128]	Time 0.118 (0.193)	Data 0.000 (0.072)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.51624393463135
==> Statistics for epoch 31: 1075 clusters
Epoch: [31][20/200]	Time 0.363 (0.420)	Data 0.001 (0.055)	Loss 0.247 (0.309)
Epoch: [31][40/200]	Time 0.361 (0.432)	Data 0.001 (0.066)	Loss 1.643 (0.465)
Epoch: [31][60/200]	Time 0.360 (0.412)	Data 0.000 (0.045)	Loss 1.498 (0.792)
Epoch: [31][80/200]	Time 0.365 (0.420)	Data 0.001 (0.053)	Loss 1.228 (0.955)
Epoch: [31][100/200]	Time 1.964 (0.425)	Data 1.553 (0.058)	Loss 1.464 (1.058)
Epoch: [31][120/200]	Time 0.366 (0.416)	Data 0.001 (0.049)	Loss 1.435 (1.132)
Epoch: [31][140/200]	Time 0.369 (0.421)	Data 0.001 (0.054)	Loss 1.707 (1.189)
Epoch: [31][160/200]	Time 0.364 (0.414)	Data 0.000 (0.047)	Loss 1.359 (1.231)
Epoch: [31][180/200]	Time 0.366 (0.418)	Data 0.001 (0.051)	Loss 1.320 (1.257)
Epoch: [31][200/200]	Time 0.370 (0.421)	Data 0.001 (0.054)	Loss 1.173 (1.285)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.219)	Data 0.000 (0.099)	
Extract Features: [100/128]	Time 0.118 (0.198)	Data 0.000 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.03394818305969
==> Statistics for epoch 32: 1066 clusters
Epoch: [32][20/200]	Time 0.367 (0.424)	Data 0.001 (0.060)	Loss 0.257 (0.281)
Epoch: [32][40/200]	Time 0.363 (0.434)	Data 0.001 (0.070)	Loss 1.655 (0.468)
Epoch: [32][60/200]	Time 0.367 (0.413)	Data 0.000 (0.047)	Loss 1.458 (0.764)
Epoch: [32][80/200]	Time 0.365 (0.422)	Data 0.001 (0.056)	Loss 1.382 (0.944)
Epoch: [32][100/200]	Time 1.947 (0.426)	Data 1.558 (0.060)	Loss 1.924 (1.043)
Epoch: [32][120/200]	Time 0.364 (0.416)	Data 0.001 (0.050)	Loss 1.424 (1.121)
Epoch: [32][140/200]	Time 0.363 (0.421)	Data 0.001 (0.055)	Loss 1.493 (1.185)
Epoch: [32][160/200]	Time 0.364 (0.414)	Data 0.000 (0.048)	Loss 1.181 (1.218)
Epoch: [32][180/200]	Time 0.366 (0.417)	Data 0.001 (0.051)	Loss 1.169 (1.248)
Epoch: [32][200/200]	Time 0.363 (0.420)	Data 0.001 (0.054)	Loss 1.569 (1.265)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.313 (0.212)	Data 0.195 (0.092)	
Extract Features: [100/128]	Time 0.118 (0.197)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.781094551086426
==> Statistics for epoch 33: 1059 clusters
Epoch: [33][20/200]	Time 0.360 (0.422)	Data 0.001 (0.057)	Loss 0.201 (0.279)
Epoch: [33][40/200]	Time 0.363 (0.432)	Data 0.001 (0.068)	Loss 1.442 (0.443)
Epoch: [33][60/200]	Time 0.364 (0.410)	Data 0.000 (0.045)	Loss 1.674 (0.788)
Epoch: [33][80/200]	Time 0.364 (0.420)	Data 0.001 (0.055)	Loss 1.215 (0.939)
Epoch: [33][100/200]	Time 2.229 (0.428)	Data 1.848 (0.063)	Loss 1.663 (1.060)
Epoch: [33][120/200]	Time 0.366 (0.417)	Data 0.001 (0.053)	Loss 1.119 (1.127)
Epoch: [33][140/200]	Time 0.362 (0.424)	Data 0.001 (0.058)	Loss 1.903 (1.179)
Epoch: [33][160/200]	Time 0.365 (0.417)	Data 0.000 (0.051)	Loss 1.471 (1.211)
Epoch: [33][180/200]	Time 0.367 (0.420)	Data 0.001 (0.054)	Loss 1.656 (1.243)
Epoch: [33][200/200]	Time 0.366 (0.424)	Data 0.001 (0.058)	Loss 1.565 (1.269)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.209)	Data 0.000 (0.087)	
Extract Features: [100/128]	Time 0.118 (0.190)	Data 0.000 (0.069)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.75967812538147
==> Statistics for epoch 34: 1070 clusters
Epoch: [34][20/200]	Time 0.364 (0.421)	Data 0.001 (0.055)	Loss 0.268 (0.267)
Epoch: [34][40/200]	Time 0.369 (0.439)	Data 0.001 (0.073)	Loss 1.365 (0.450)
Epoch: [34][60/200]	Time 0.364 (0.414)	Data 0.000 (0.049)	Loss 1.181 (0.762)
Epoch: [34][80/200]	Time 0.363 (0.424)	Data 0.001 (0.059)	Loss 1.582 (0.908)
Epoch: [34][100/200]	Time 2.122 (0.430)	Data 1.716 (0.064)	Loss 1.546 (1.013)
Epoch: [34][120/200]	Time 0.366 (0.420)	Data 0.001 (0.054)	Loss 1.655 (1.091)
Epoch: [34][140/200]	Time 0.368 (0.424)	Data 0.000 (0.058)	Loss 1.216 (1.140)
Epoch: [34][160/200]	Time 0.367 (0.417)	Data 0.000 (0.051)	Loss 1.702 (1.177)
Epoch: [34][180/200]	Time 0.365 (0.421)	Data 0.001 (0.054)	Loss 1.559 (1.205)
Epoch: [34][200/200]	Time 0.373 (0.424)	Data 0.001 (0.056)	Loss 1.362 (1.227)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.119 (0.214)	Data 0.000 (0.095)	
Extract Features: [100/128]	Time 0.122 (0.193)	Data 0.000 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.80276298522949
==> Statistics for epoch 35: 1068 clusters
Epoch: [35][20/200]	Time 0.371 (0.423)	Data 0.001 (0.051)	Loss 0.339 (0.293)
Epoch: [35][40/200]	Time 0.370 (0.441)	Data 0.001 (0.071)	Loss 1.706 (0.487)
Epoch: [35][60/200]	Time 0.366 (0.416)	Data 0.000 (0.048)	Loss 1.229 (0.810)
Epoch: [35][80/200]	Time 0.362 (0.425)	Data 0.001 (0.057)	Loss 1.272 (0.974)
Epoch: [35][100/200]	Time 1.946 (0.429)	Data 1.558 (0.061)	Loss 1.650 (1.071)
Epoch: [35][120/200]	Time 0.363 (0.420)	Data 0.001 (0.051)	Loss 1.430 (1.144)
Epoch: [35][140/200]	Time 0.365 (0.424)	Data 0.001 (0.056)	Loss 0.991 (1.202)
Epoch: [35][160/200]	Time 0.366 (0.417)	Data 0.000 (0.049)	Loss 1.268 (1.232)
Epoch: [35][180/200]	Time 0.365 (0.421)	Data 0.001 (0.053)	Loss 1.596 (1.253)
Epoch: [35][200/200]	Time 0.366 (0.424)	Data 0.001 (0.056)	Loss 1.281 (1.277)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.117 (0.211)	Data 0.000 (0.090)	
Extract Features: [100/128]	Time 0.119 (0.196)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.776198625564575
==> Statistics for epoch 36: 1063 clusters
Epoch: [36][20/200]	Time 0.364 (0.421)	Data 0.001 (0.054)	Loss 0.312 (0.279)
Epoch: [36][40/200]	Time 0.368 (0.433)	Data 0.001 (0.066)	Loss 2.077 (0.476)
Epoch: [36][60/200]	Time 0.478 (0.413)	Data 0.000 (0.044)	Loss 1.111 (0.785)
Epoch: [36][80/200]	Time 0.367 (0.422)	Data 0.001 (0.054)	Loss 1.550 (0.963)
Epoch: [36][100/200]	Time 2.016 (0.427)	Data 1.609 (0.059)	Loss 1.490 (1.064)
Epoch: [36][120/200]	Time 0.366 (0.417)	Data 0.001 (0.049)	Loss 1.416 (1.138)
Epoch: [36][140/200]	Time 0.368 (0.422)	Data 0.001 (0.055)	Loss 1.272 (1.196)
Epoch: [36][160/200]	Time 0.365 (0.415)	Data 0.000 (0.048)	Loss 1.335 (1.226)
Epoch: [36][180/200]	Time 0.364 (0.420)	Data 0.001 (0.052)	Loss 1.712 (1.257)
Epoch: [36][200/200]	Time 0.365 (0.422)	Data 0.001 (0.055)	Loss 1.602 (1.279)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.222 (0.210)	Data 0.103 (0.089)	
Extract Features: [100/128]	Time 0.117 (0.193)	Data 0.000 (0.072)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.065367698669434
==> Statistics for epoch 37: 1060 clusters
Epoch: [37][20/200]	Time 0.367 (0.426)	Data 0.001 (0.061)	Loss 0.279 (0.284)
Epoch: [37][40/200]	Time 0.367 (0.440)	Data 0.001 (0.071)	Loss 1.362 (0.472)
Epoch: [37][60/200]	Time 0.366 (0.415)	Data 0.000 (0.047)	Loss 1.485 (0.791)
Epoch: [37][80/200]	Time 0.365 (0.423)	Data 0.001 (0.056)	Loss 1.575 (0.944)
Epoch: [37][100/200]	Time 1.979 (0.428)	Data 1.587 (0.061)	Loss 1.239 (1.040)
Epoch: [37][120/200]	Time 0.362 (0.418)	Data 0.001 (0.051)	Loss 1.433 (1.115)
Epoch: [37][140/200]	Time 0.364 (0.423)	Data 0.001 (0.056)	Loss 1.371 (1.166)
Epoch: [37][160/200]	Time 0.363 (0.416)	Data 0.000 (0.049)	Loss 1.295 (1.207)
Epoch: [37][180/200]	Time 0.371 (0.420)	Data 0.001 (0.053)	Loss 1.423 (1.233)
Epoch: [37][200/200]	Time 0.376 (0.423)	Data 0.001 (0.056)	Loss 1.679 (1.269)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.244 (0.211)	Data 0.126 (0.091)	
Extract Features: [100/128]	Time 0.120 (0.194)	Data 0.000 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.90842151641846
==> Statistics for epoch 38: 1067 clusters
Epoch: [38][20/200]	Time 0.363 (0.423)	Data 0.001 (0.058)	Loss 0.244 (0.276)
Epoch: [38][40/200]	Time 0.362 (0.441)	Data 0.001 (0.072)	Loss 1.193 (0.438)
Epoch: [38][60/200]	Time 0.363 (0.415)	Data 0.000 (0.048)	Loss 1.116 (0.759)
Epoch: [38][80/200]	Time 0.368 (0.424)	Data 0.001 (0.058)	Loss 1.605 (0.922)
Epoch: [38][100/200]	Time 2.184 (0.430)	Data 1.797 (0.064)	Loss 1.279 (1.015)
Epoch: [38][120/200]	Time 0.358 (0.419)	Data 0.001 (0.054)	Loss 1.294 (1.087)
Epoch: [38][140/200]	Time 0.365 (0.425)	Data 0.001 (0.060)	Loss 1.455 (1.148)
Epoch: [38][160/200]	Time 0.370 (0.417)	Data 0.001 (0.052)	Loss 1.783 (1.185)
Epoch: [38][180/200]	Time 0.368 (0.421)	Data 0.001 (0.056)	Loss 1.557 (1.213)
Epoch: [38][200/200]	Time 0.363 (0.424)	Data 0.001 (0.059)	Loss 1.724 (1.240)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.117 (0.214)	Data 0.000 (0.093)	
Extract Features: [100/128]	Time 0.124 (0.195)	Data 0.000 (0.073)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.71517324447632
==> Statistics for epoch 39: 1074 clusters
Epoch: [39][20/200]	Time 0.362 (0.421)	Data 0.001 (0.057)	Loss 0.143 (0.267)
Epoch: [39][40/200]	Time 0.364 (0.436)	Data 0.001 (0.069)	Loss 1.215 (0.439)
Epoch: [39][60/200]	Time 0.363 (0.412)	Data 0.000 (0.046)	Loss 1.668 (0.756)
Epoch: [39][80/200]	Time 0.364 (0.424)	Data 0.001 (0.058)	Loss 1.826 (0.918)
Epoch: [39][100/200]	Time 2.168 (0.430)	Data 1.772 (0.064)	Loss 1.239 (1.009)
Epoch: [39][120/200]	Time 0.368 (0.420)	Data 0.001 (0.053)	Loss 1.532 (1.084)
Epoch: [39][140/200]	Time 0.370 (0.425)	Data 0.001 (0.058)	Loss 0.959 (1.124)
Epoch: [39][160/200]	Time 0.363 (0.417)	Data 0.000 (0.051)	Loss 1.413 (1.163)
Epoch: [39][180/200]	Time 0.363 (0.421)	Data 0.001 (0.055)	Loss 1.923 (1.194)
Epoch: [39][200/200]	Time 0.364 (0.425)	Data 0.001 (0.058)	Loss 1.252 (1.219)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.210)	Data 0.000 (0.089)	
Extract Features: [100/128]	Time 0.118 (0.191)	Data 0.000 (0.070)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.21483898162842
==> Statistics for epoch 40: 1087 clusters
Epoch: [40][20/200]	Time 0.359 (0.421)	Data 0.001 (0.056)	Loss 0.202 (0.277)
Epoch: [40][40/200]	Time 0.363 (0.439)	Data 0.001 (0.071)	Loss 1.490 (0.492)
Epoch: [40][60/200]	Time 0.371 (0.415)	Data 0.000 (0.047)	Loss 1.117 (0.792)
Epoch: [40][80/200]	Time 0.364 (0.423)	Data 0.001 (0.056)	Loss 1.222 (0.953)
Epoch: [40][100/200]	Time 2.035 (0.428)	Data 1.643 (0.061)	Loss 1.467 (1.060)
Epoch: [40][120/200]	Time 0.362 (0.418)	Data 0.000 (0.051)	Loss 1.107 (1.130)
Epoch: [40][140/200]	Time 0.373 (0.423)	Data 0.001 (0.057)	Loss 1.098 (1.173)
Epoch: [40][160/200]	Time 0.363 (0.416)	Data 0.000 (0.050)	Loss 1.623 (1.216)
Epoch: [40][180/200]	Time 0.365 (0.420)	Data 0.001 (0.054)	Loss 1.502 (1.240)
Epoch: [40][200/200]	Time 0.365 (0.424)	Data 0.000 (0.058)	Loss 1.282 (1.267)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.215)	Data 0.000 (0.094)	
Extract Features: [100/128]	Time 0.125 (0.196)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.81953763961792
==> Statistics for epoch 41: 1077 clusters
Epoch: [41][20/200]	Time 0.361 (0.419)	Data 0.001 (0.055)	Loss 0.362 (0.260)
Epoch: [41][40/200]	Time 0.362 (0.430)	Data 0.000 (0.066)	Loss 1.210 (0.457)
Epoch: [41][60/200]	Time 0.362 (0.408)	Data 0.000 (0.044)	Loss 1.360 (0.774)
Epoch: [41][80/200]	Time 0.362 (0.418)	Data 0.001 (0.054)	Loss 1.132 (0.937)
Epoch: [41][100/200]	Time 2.033 (0.425)	Data 1.646 (0.060)	Loss 1.151 (1.030)
Epoch: [41][120/200]	Time 0.362 (0.415)	Data 0.000 (0.050)	Loss 1.369 (1.094)
Epoch: [41][140/200]	Time 0.362 (0.419)	Data 0.001 (0.054)	Loss 1.760 (1.149)
Epoch: [41][160/200]	Time 0.361 (0.412)	Data 0.000 (0.048)	Loss 1.147 (1.187)
Epoch: [41][180/200]	Time 0.362 (0.416)	Data 0.000 (0.051)	Loss 1.413 (1.220)
Epoch: [41][200/200]	Time 0.360 (0.420)	Data 0.001 (0.054)	Loss 1.423 (1.245)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.207)	Data 0.000 (0.086)	
Extract Features: [100/128]	Time 0.118 (0.190)	Data 0.000 (0.070)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.0703604221344
==> Statistics for epoch 42: 1080 clusters
Epoch: [42][20/200]	Time 0.362 (0.413)	Data 0.001 (0.049)	Loss 0.265 (0.245)
Epoch: [42][40/200]	Time 0.361 (0.426)	Data 0.001 (0.063)	Loss 1.265 (0.476)
Epoch: [42][60/200]	Time 0.363 (0.407)	Data 0.000 (0.042)	Loss 1.691 (0.777)
Epoch: [42][80/200]	Time 0.366 (0.420)	Data 0.001 (0.055)	Loss 1.624 (0.936)
Epoch: [42][100/200]	Time 2.227 (0.429)	Data 1.855 (0.063)	Loss 2.039 (1.032)
Epoch: [42][120/200]	Time 0.360 (0.418)	Data 0.001 (0.052)	Loss 1.580 (1.093)
Epoch: [42][140/200]	Time 0.363 (0.423)	Data 0.001 (0.057)	Loss 1.601 (1.155)
Epoch: [42][160/200]	Time 0.362 (0.415)	Data 0.000 (0.050)	Loss 1.262 (1.193)
Epoch: [42][180/200]	Time 0.368 (0.421)	Data 0.001 (0.055)	Loss 1.704 (1.222)
Epoch: [42][200/200]	Time 0.366 (0.424)	Data 0.001 (0.058)	Loss 1.690 (1.249)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.213)	Data 0.000 (0.092)	
Extract Features: [100/128]	Time 0.118 (0.191)	Data 0.000 (0.071)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.614001512527466
==> Statistics for epoch 43: 1075 clusters
Epoch: [43][20/200]	Time 0.363 (0.420)	Data 0.001 (0.056)	Loss 0.188 (0.287)
Epoch: [43][40/200]	Time 0.364 (0.433)	Data 0.001 (0.069)	Loss 1.606 (0.461)
Epoch: [43][60/200]	Time 0.364 (0.411)	Data 0.000 (0.047)	Loss 1.682 (0.760)
Epoch: [43][80/200]	Time 0.365 (0.420)	Data 0.001 (0.055)	Loss 1.144 (0.927)
Epoch: [43][100/200]	Time 2.034 (0.426)	Data 1.651 (0.060)	Loss 1.858 (1.025)
Epoch: [43][120/200]	Time 0.366 (0.416)	Data 0.001 (0.050)	Loss 1.451 (1.100)
Epoch: [43][140/200]	Time 0.371 (0.422)	Data 0.001 (0.055)	Loss 1.818 (1.153)
Epoch: [43][160/200]	Time 0.363 (0.415)	Data 0.000 (0.049)	Loss 1.781 (1.191)
Epoch: [43][180/200]	Time 0.367 (0.419)	Data 0.001 (0.053)	Loss 1.809 (1.223)
Epoch: [43][200/200]	Time 0.367 (0.422)	Data 0.001 (0.056)	Loss 1.369 (1.246)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.202 (0.215)	Data 0.087 (0.096)	
Extract Features: [100/128]	Time 0.119 (0.198)	Data 0.000 (0.077)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.87165880203247
==> Statistics for epoch 44: 1081 clusters
Epoch: [44][20/200]	Time 0.359 (0.432)	Data 0.001 (0.060)	Loss 0.167 (0.258)
Epoch: [44][40/200]	Time 0.363 (0.442)	Data 0.001 (0.074)	Loss 1.396 (0.469)
Epoch: [44][60/200]	Time 0.365 (0.416)	Data 0.000 (0.050)	Loss 1.413 (0.793)
Epoch: [44][80/200]	Time 0.365 (0.423)	Data 0.000 (0.057)	Loss 1.149 (0.948)
Epoch: [44][100/200]	Time 2.082 (0.428)	Data 1.704 (0.063)	Loss 1.214 (1.051)
Epoch: [44][120/200]	Time 0.363 (0.418)	Data 0.001 (0.052)	Loss 1.455 (1.115)
Epoch: [44][140/200]	Time 0.368 (0.422)	Data 0.001 (0.056)	Loss 1.279 (1.163)
Epoch: [44][160/200]	Time 0.366 (0.415)	Data 0.000 (0.049)	Loss 1.765 (1.199)
Epoch: [44][180/200]	Time 0.367 (0.419)	Data 0.001 (0.054)	Loss 1.662 (1.223)
Epoch: [44][200/200]	Time 0.363 (0.423)	Data 0.001 (0.058)	Loss 1.597 (1.241)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.118 (0.209)	Data 0.000 (0.088)	
Extract Features: [100/128]	Time 0.119 (0.191)	Data 0.000 (0.069)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.28661489486694
==> Statistics for epoch 45: 1078 clusters
Epoch: [45][20/200]	Time 0.365 (0.429)	Data 0.001 (0.055)	Loss 0.174 (0.254)
Epoch: [45][40/200]	Time 0.366 (0.440)	Data 0.001 (0.071)	Loss 1.515 (0.457)
Epoch: [45][60/200]	Time 0.364 (0.415)	Data 0.000 (0.048)	Loss 1.780 (0.798)
Epoch: [45][80/200]	Time 0.367 (0.425)	Data 0.001 (0.058)	Loss 1.492 (0.942)
Epoch: [45][100/200]	Time 2.110 (0.432)	Data 1.721 (0.064)	Loss 1.492 (1.051)
Epoch: [45][120/200]	Time 0.363 (0.420)	Data 0.001 (0.053)	Loss 1.601 (1.128)
Epoch: [45][140/200]	Time 0.366 (0.426)	Data 0.001 (0.059)	Loss 1.229 (1.169)
Epoch: [45][160/200]	Time 0.363 (0.419)	Data 0.000 (0.051)	Loss 1.767 (1.207)
Epoch: [45][180/200]	Time 0.364 (0.422)	Data 0.001 (0.055)	Loss 1.490 (1.238)
Epoch: [45][200/200]	Time 0.367 (0.425)	Data 0.000 (0.058)	Loss 1.291 (1.261)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.119 (0.214)	Data 0.000 (0.095)	
Extract Features: [100/128]	Time 0.119 (0.194)	Data 0.000 (0.074)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.57830452919006
==> Statistics for epoch 46: 1077 clusters
Epoch: [46][20/200]	Time 0.363 (0.423)	Data 0.001 (0.053)	Loss 0.295 (0.246)
Epoch: [46][40/200]	Time 0.365 (0.432)	Data 0.001 (0.065)	Loss 1.288 (0.467)
Epoch: [46][60/200]	Time 0.364 (0.410)	Data 0.000 (0.044)	Loss 1.689 (0.783)
Epoch: [46][80/200]	Time 0.367 (0.418)	Data 0.001 (0.052)	Loss 1.608 (0.943)
Epoch: [46][100/200]	Time 2.025 (0.424)	Data 1.652 (0.058)	Loss 1.029 (1.030)
Epoch: [46][120/200]	Time 0.364 (0.414)	Data 0.001 (0.049)	Loss 1.430 (1.102)
Epoch: [46][140/200]	Time 0.367 (0.419)	Data 0.001 (0.053)	Loss 1.613 (1.154)
Epoch: [46][160/200]	Time 0.363 (0.412)	Data 0.000 (0.047)	Loss 1.664 (1.190)
Epoch: [46][180/200]	Time 0.368 (0.416)	Data 0.001 (0.051)	Loss 1.482 (1.226)
Epoch: [46][200/200]	Time 0.478 (0.420)	Data 0.001 (0.054)	Loss 1.358 (1.239)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.183 (0.208)	Data 0.063 (0.090)	
Extract Features: [100/128]	Time 0.118 (0.189)	Data 0.000 (0.069)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.09092903137207
==> Statistics for epoch 47: 1082 clusters
Epoch: [47][20/200]	Time 0.363 (0.424)	Data 0.001 (0.058)	Loss 0.178 (0.263)
Epoch: [47][40/200]	Time 0.366 (0.438)	Data 0.001 (0.074)	Loss 1.385 (0.464)
Epoch: [47][60/200]	Time 0.363 (0.416)	Data 0.000 (0.049)	Loss 1.552 (0.778)
Epoch: [47][80/200]	Time 0.365 (0.425)	Data 0.001 (0.058)	Loss 1.073 (0.943)
Epoch: [47][100/200]	Time 2.131 (0.430)	Data 1.744 (0.064)	Loss 1.676 (1.051)
Epoch: [47][120/200]	Time 0.374 (0.421)	Data 0.001 (0.054)	Loss 1.400 (1.121)
Epoch: [47][140/200]	Time 0.366 (0.425)	Data 0.001 (0.058)	Loss 1.411 (1.174)
Epoch: [47][160/200]	Time 0.365 (0.418)	Data 0.000 (0.051)	Loss 1.552 (1.213)
Epoch: [47][180/200]	Time 0.363 (0.422)	Data 0.001 (0.055)	Loss 1.050 (1.234)
Epoch: [47][200/200]	Time 0.364 (0.425)	Data 0.001 (0.058)	Loss 1.030 (1.262)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.117 (0.211)	Data 0.000 (0.089)	
Extract Features: [100/128]	Time 0.121 (0.190)	Data 0.000 (0.070)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.217966079711914
==> Statistics for epoch 48: 1067 clusters
Epoch: [48][20/200]	Time 0.363 (0.425)	Data 0.001 (0.057)	Loss 0.180 (0.271)
Epoch: [48][40/200]	Time 0.365 (0.434)	Data 0.001 (0.069)	Loss 1.548 (0.452)
Epoch: [48][60/200]	Time 0.365 (0.411)	Data 0.000 (0.047)	Loss 1.198 (0.769)
Epoch: [48][80/200]	Time 0.363 (0.422)	Data 0.001 (0.056)	Loss 1.677 (0.946)
Epoch: [48][100/200]	Time 2.006 (0.426)	Data 1.621 (0.061)	Loss 1.687 (1.053)
Epoch: [48][120/200]	Time 0.371 (0.416)	Data 0.001 (0.051)	Loss 1.547 (1.126)
Epoch: [48][140/200]	Time 0.363 (0.420)	Data 0.001 (0.056)	Loss 1.230 (1.172)
Epoch: [48][160/200]	Time 0.363 (0.413)	Data 0.000 (0.049)	Loss 1.510 (1.204)
Epoch: [48][180/200]	Time 0.364 (0.417)	Data 0.001 (0.052)	Loss 1.394 (1.229)
Epoch: [48][200/200]	Time 0.367 (0.420)	Data 0.001 (0.055)	Loss 1.381 (1.253)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.119 (0.218)	Data 0.000 (0.098)	
Extract Features: [100/128]	Time 0.118 (0.197)	Data 0.000 (0.076)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.05921792984009
==> Statistics for epoch 49: 1078 clusters
Epoch: [49][20/200]	Time 0.362 (0.424)	Data 0.001 (0.058)	Loss 0.201 (0.260)
Epoch: [49][40/200]	Time 0.363 (0.438)	Data 0.001 (0.070)	Loss 1.494 (0.441)
Epoch: [49][60/200]	Time 0.363 (0.413)	Data 0.000 (0.047)	Loss 1.165 (0.770)
Epoch: [49][80/200]	Time 0.361 (0.421)	Data 0.000 (0.055)	Loss 1.009 (0.932)
Epoch: [49][100/200]	Time 2.080 (0.426)	Data 1.694 (0.061)	Loss 1.843 (1.043)
Epoch: [49][120/200]	Time 0.365 (0.416)	Data 0.001 (0.051)	Loss 1.934 (1.105)
Epoch: [49][140/200]	Time 0.376 (0.421)	Data 0.001 (0.056)	Loss 1.752 (1.159)
Epoch: [49][160/200]	Time 0.366 (0.414)	Data 0.000 (0.049)	Loss 1.183 (1.198)
Epoch: [49][180/200]	Time 0.364 (0.419)	Data 0.001 (0.054)	Loss 1.493 (1.219)
Epoch: [49][200/200]	Time 0.363 (0.422)	Data 0.001 (0.057)	Loss 1.896 (1.243)
Extract Features: [50/367]	Time 0.337 (0.217)	Data 0.219 (0.097)	
Extract Features: [100/367]	Time 0.119 (0.198)	Data 0.000 (0.078)	
Extract Features: [150/367]	Time 0.347 (0.195)	Data 0.229 (0.074)	
Extract Features: [200/367]	Time 0.120 (0.191)	Data 0.000 (0.070)	
Extract Features: [250/367]	Time 0.450 (0.189)	Data 0.334 (0.068)	
Extract Features: [300/367]	Time 0.119 (0.187)	Data 0.000 (0.067)	
Extract Features: [350/367]	Time 0.351 (0.187)	Data 0.234 (0.066)	
Mean AP: 59.4%

 * Finished epoch  49  model mAP: 59.4%  best: 59.4% *

==> Test with the best model:
=> Loaded checkpoint 'log/msmt17/resnet50_ibn_cion/model_best.pth.tar'
Extract Features: [50/367]	Time 0.263 (0.215)	Data 0.146 (0.096)	
Extract Features: [100/367]	Time 0.118 (0.199)	Data 0.000 (0.079)	
Extract Features: [150/367]	Time 0.278 (0.194)	Data 0.155 (0.074)	
Extract Features: [200/367]	Time 0.118 (0.190)	Data 0.000 (0.070)	
Extract Features: [250/367]	Time 0.357 (0.189)	Data 0.242 (0.068)	
Extract Features: [300/367]	Time 0.119 (0.187)	Data 0.000 (0.067)	
Extract Features: [350/367]	Time 0.334 (0.187)	Data 0.218 (0.066)	
Mean AP: 59.4%
CMC Scores:
  top-1          82.4%
  top-5          89.9%
  top-10         92.2%
Total running time:  2:41:22.378970
