==========
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='resnet152', pretrained_path='/home/ma-user/work/Projects/ReIDNets_Checkpoints_TransReID/ResNet152.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/resnet152_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
optimizer: SGD
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.234 (0.441)	Data 0.000 (0.022)	
Extract Features: [100/128]	Time 0.227 (0.347)	Data 0.001 (0.011)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.066983222961426
Clustering criterion: eps: 0.700
==> Statistics for epoch 0: 925 clusters
Epoch: [0][20/200]	Time 0.695 (1.215)	Data 0.001 (0.053)	Loss 2.183 (2.530)
Epoch: [0][40/200]	Time 0.695 (1.003)	Data 0.001 (0.071)	Loss 3.529 (2.725)
Epoch: [0][60/200]	Time 0.694 (0.928)	Data 0.001 (0.073)	Loss 1.926 (2.836)
Epoch: [0][80/200]	Time 0.696 (0.872)	Data 0.000 (0.055)	Loss 2.184 (2.735)
Epoch: [0][100/200]	Time 0.695 (0.853)	Data 0.001 (0.060)	Loss 2.284 (2.627)
Epoch: [0][120/200]	Time 0.691 (0.840)	Data 0.001 (0.063)	Loss 1.804 (2.551)
Epoch: [0][140/200]	Time 0.694 (0.819)	Data 0.000 (0.054)	Loss 1.869 (2.479)
Epoch: [0][160/200]	Time 0.698 (0.814)	Data 0.001 (0.058)	Loss 2.183 (2.434)
Epoch: [0][180/200]	Time 0.824 (0.811)	Data 0.001 (0.060)	Loss 1.507 (2.395)
Epoch: [0][200/200]	Time 0.694 (0.809)	Data 0.001 (0.063)	Loss 1.629 (2.338)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.231 (0.260)	Data 0.001 (0.025)	
Extract Features: [100/128]	Time 0.228 (0.251)	Data 0.001 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.01284980773926
==> Statistics for epoch 1: 1001 clusters
Epoch: [1][20/200]	Time 0.690 (0.747)	Data 0.001 (0.047)	Loss 0.385 (0.529)
Epoch: [1][40/200]	Time 0.814 (0.765)	Data 0.001 (0.066)	Loss 1.739 (0.813)
Epoch: [1][60/200]	Time 0.694 (0.741)	Data 0.000 (0.044)	Loss 2.505 (1.193)
Epoch: [1][80/200]	Time 0.699 (0.752)	Data 0.001 (0.054)	Loss 2.290 (1.402)
Epoch: [1][100/200]	Time 0.694 (0.756)	Data 0.001 (0.059)	Loss 1.717 (1.498)
Epoch: [1][120/200]	Time 0.697 (0.746)	Data 0.000 (0.049)	Loss 1.666 (1.563)
Epoch: [1][140/200]	Time 0.840 (0.753)	Data 0.002 (0.054)	Loss 2.047 (1.610)
Epoch: [1][160/200]	Time 0.698 (0.757)	Data 0.001 (0.058)	Loss 1.388 (1.625)
Epoch: [1][180/200]	Time 0.697 (0.752)	Data 0.000 (0.051)	Loss 2.049 (1.654)
Epoch: [1][200/200]	Time 0.695 (0.756)	Data 0.001 (0.054)	Loss 1.370 (1.662)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.232 (0.259)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.228 (0.247)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.64435601234436
==> Statistics for epoch 2: 1004 clusters
Epoch: [2][20/200]	Time 0.690 (0.742)	Data 0.001 (0.050)	Loss 0.607 (0.559)
Epoch: [2][40/200]	Time 0.690 (0.762)	Data 0.001 (0.070)	Loss 1.838 (0.834)
Epoch: [2][60/200]	Time 0.693 (0.741)	Data 0.000 (0.047)	Loss 1.828 (1.180)
Epoch: [2][80/200]	Time 0.695 (0.751)	Data 0.001 (0.056)	Loss 1.335 (1.315)
Epoch: [2][100/200]	Time 0.697 (0.759)	Data 0.001 (0.063)	Loss 1.815 (1.400)
Epoch: [2][120/200]	Time 0.699 (0.748)	Data 0.000 (0.053)	Loss 1.467 (1.427)
Epoch: [2][140/200]	Time 0.697 (0.755)	Data 0.001 (0.057)	Loss 1.748 (1.461)
Epoch: [2][160/200]	Time 0.817 (0.760)	Data 0.001 (0.061)	Loss 1.530 (1.475)
Epoch: [2][180/200]	Time 0.694 (0.754)	Data 0.000 (0.054)	Loss 2.296 (1.498)
Epoch: [2][200/200]	Time 0.699 (0.757)	Data 0.001 (0.057)	Loss 1.541 (1.503)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.226 (0.263)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.231 (0.249)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.2339973449707
==> Statistics for epoch 3: 1036 clusters
Epoch: [3][20/200]	Time 0.695 (0.752)	Data 0.001 (0.049)	Loss 0.312 (0.454)
Epoch: [3][40/200]	Time 0.694 (0.766)	Data 0.001 (0.066)	Loss 2.278 (0.693)
Epoch: [3][60/200]	Time 0.694 (0.742)	Data 0.000 (0.045)	Loss 1.823 (1.062)
Epoch: [3][80/200]	Time 0.694 (0.755)	Data 0.001 (0.055)	Loss 1.822 (1.207)
Epoch: [3][100/200]	Time 0.697 (0.763)	Data 0.001 (0.062)	Loss 1.220 (1.302)
Epoch: [3][120/200]	Time 0.698 (0.754)	Data 0.001 (0.052)	Loss 1.922 (1.374)
Epoch: [3][140/200]	Time 0.702 (0.759)	Data 0.001 (0.057)	Loss 1.632 (1.438)
Epoch: [3][160/200]	Time 0.697 (0.753)	Data 0.000 (0.050)	Loss 1.874 (1.457)
Epoch: [3][180/200]	Time 0.694 (0.758)	Data 0.001 (0.055)	Loss 1.983 (1.477)
Epoch: [3][200/200]	Time 0.694 (0.762)	Data 0.000 (0.059)	Loss 1.800 (1.497)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.229 (0.261)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.226 (0.249)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.17947602272034
==> Statistics for epoch 4: 980 clusters
Epoch: [4][20/200]	Time 0.697 (0.749)	Data 0.001 (0.054)	Loss 0.470 (0.447)
Epoch: [4][40/200]	Time 0.840 (0.767)	Data 0.001 (0.070)	Loss 1.997 (0.744)
Epoch: [4][60/200]	Time 0.701 (0.745)	Data 0.000 (0.047)	Loss 1.483 (1.053)
Epoch: [4][80/200]	Time 0.696 (0.757)	Data 0.001 (0.056)	Loss 1.851 (1.192)
Epoch: [4][100/200]	Time 0.699 (0.764)	Data 0.001 (0.061)	Loss 1.274 (1.294)
Epoch: [4][120/200]	Time 0.698 (0.753)	Data 0.000 (0.051)	Loss 2.046 (1.362)
Epoch: [4][140/200]	Time 0.695 (0.759)	Data 0.001 (0.056)	Loss 1.947 (1.398)
Epoch: [4][160/200]	Time 0.692 (0.763)	Data 0.001 (0.060)	Loss 1.093 (1.432)
Epoch: [4][180/200]	Time 0.694 (0.757)	Data 0.000 (0.054)	Loss 1.652 (1.452)
Epoch: [4][200/200]	Time 0.692 (0.760)	Data 0.001 (0.056)	Loss 1.481 (1.460)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.228 (0.262)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.229 (0.248)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.57536435127258
==> Statistics for epoch 5: 1051 clusters
Epoch: [5][20/200]	Time 0.692 (0.754)	Data 0.001 (0.056)	Loss 0.683 (0.519)
Epoch: [5][40/200]	Time 0.694 (0.775)	Data 0.001 (0.075)	Loss 1.893 (0.742)
Epoch: [5][60/200]	Time 0.695 (0.753)	Data 0.000 (0.050)	Loss 1.269 (1.050)
Epoch: [5][80/200]	Time 0.695 (0.763)	Data 0.001 (0.060)	Loss 1.808 (1.203)
Epoch: [5][100/200]	Time 0.691 (0.769)	Data 0.001 (0.066)	Loss 2.048 (1.289)
Epoch: [5][120/200]	Time 0.695 (0.758)	Data 0.001 (0.055)	Loss 1.772 (1.341)
Epoch: [5][140/200]	Time 0.701 (0.762)	Data 0.001 (0.059)	Loss 1.496 (1.382)
Epoch: [5][160/200]	Time 0.696 (0.755)	Data 0.000 (0.052)	Loss 1.800 (1.410)
Epoch: [5][180/200]	Time 0.693 (0.759)	Data 0.001 (0.056)	Loss 1.519 (1.429)
Epoch: [5][200/200]	Time 0.698 (0.761)	Data 0.001 (0.059)	Loss 1.332 (1.441)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.228 (0.263)	Data 0.000 (0.029)	
Extract Features: [100/128]	Time 0.228 (0.249)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.51370310783386
==> Statistics for epoch 6: 1016 clusters
Epoch: [6][20/200]	Time 0.689 (0.757)	Data 0.001 (0.054)	Loss 0.510 (0.559)
Epoch: [6][40/200]	Time 0.692 (0.768)	Data 0.001 (0.068)	Loss 1.434 (0.754)
Epoch: [6][60/200]	Time 0.691 (0.747)	Data 0.000 (0.045)	Loss 1.617 (1.009)
Epoch: [6][80/200]	Time 0.694 (0.758)	Data 0.001 (0.056)	Loss 1.463 (1.127)
Epoch: [6][100/200]	Time 0.693 (0.765)	Data 0.001 (0.062)	Loss 1.528 (1.168)
Epoch: [6][120/200]	Time 0.693 (0.754)	Data 0.000 (0.052)	Loss 1.378 (1.215)
Epoch: [6][140/200]	Time 0.697 (0.758)	Data 0.001 (0.056)	Loss 1.684 (1.240)
Epoch: [6][160/200]	Time 0.693 (0.762)	Data 0.001 (0.060)	Loss 1.816 (1.261)
Epoch: [6][180/200]	Time 0.693 (0.755)	Data 0.000 (0.054)	Loss 1.305 (1.278)
Epoch: [6][200/200]	Time 0.693 (0.758)	Data 0.001 (0.057)	Loss 1.470 (1.293)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.234 (0.263)	Data 0.000 (0.031)	
Extract Features: [100/128]	Time 0.230 (0.249)	Data 0.000 (0.016)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.978790044784546
==> Statistics for epoch 7: 1055 clusters
Epoch: [7][20/200]	Time 0.687 (0.744)	Data 0.001 (0.050)	Loss 0.479 (0.361)
Epoch: [7][40/200]	Time 0.692 (0.763)	Data 0.001 (0.065)	Loss 0.938 (0.566)
Epoch: [7][60/200]	Time 0.687 (0.740)	Data 0.000 (0.044)	Loss 1.424 (0.888)
Epoch: [7][80/200]	Time 0.697 (0.752)	Data 0.001 (0.054)	Loss 1.594 (1.041)
Epoch: [7][100/200]	Time 0.704 (0.757)	Data 0.002 (0.059)	Loss 1.643 (1.134)
Epoch: [7][120/200]	Time 0.700 (0.747)	Data 0.001 (0.050)	Loss 1.979 (1.215)
Epoch: [7][140/200]	Time 0.699 (0.752)	Data 0.001 (0.054)	Loss 1.308 (1.243)
Epoch: [7][160/200]	Time 0.693 (0.746)	Data 0.000 (0.047)	Loss 1.623 (1.271)
Epoch: [7][180/200]	Time 0.697 (0.751)	Data 0.002 (0.051)	Loss 1.085 (1.287)
Epoch: [7][200/200]	Time 0.699 (0.755)	Data 0.001 (0.054)	Loss 1.138 (1.309)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.227 (0.259)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.237 (0.247)	Data 0.001 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.24347853660583
==> Statistics for epoch 8: 1034 clusters
Epoch: [8][20/200]	Time 0.699 (0.746)	Data 0.001 (0.049)	Loss 0.250 (0.345)
Epoch: [8][40/200]	Time 0.695 (0.759)	Data 0.001 (0.063)	Loss 1.536 (0.584)
Epoch: [8][60/200]	Time 0.694 (0.738)	Data 0.000 (0.042)	Loss 1.339 (0.871)
Epoch: [8][80/200]	Time 0.696 (0.753)	Data 0.001 (0.053)	Loss 1.274 (0.995)
Epoch: [8][100/200]	Time 0.702 (0.761)	Data 0.001 (0.059)	Loss 1.146 (1.094)
Epoch: [8][120/200]	Time 0.787 (0.751)	Data 0.001 (0.049)	Loss 1.466 (1.144)
Epoch: [8][140/200]	Time 0.695 (0.756)	Data 0.001 (0.054)	Loss 1.333 (1.176)
Epoch: [8][160/200]	Time 0.695 (0.750)	Data 0.000 (0.047)	Loss 1.425 (1.209)
Epoch: [8][180/200]	Time 0.697 (0.755)	Data 0.001 (0.051)	Loss 1.702 (1.227)
Epoch: [8][200/200]	Time 0.695 (0.757)	Data 0.001 (0.054)	Loss 0.820 (1.244)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.355 (0.262)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.380 (0.249)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.43061447143555
==> Statistics for epoch 9: 1021 clusters
Epoch: [9][20/200]	Time 0.692 (0.755)	Data 0.001 (0.053)	Loss 0.318 (0.306)
Epoch: [9][40/200]	Time 0.694 (0.771)	Data 0.001 (0.066)	Loss 1.649 (0.578)
Epoch: [9][60/200]	Time 0.697 (0.750)	Data 0.000 (0.044)	Loss 1.445 (0.835)
Epoch: [9][80/200]	Time 0.702 (0.761)	Data 0.001 (0.055)	Loss 1.185 (0.964)
Epoch: [9][100/200]	Time 0.693 (0.766)	Data 0.001 (0.059)	Loss 0.903 (1.066)
Epoch: [9][120/200]	Time 0.690 (0.756)	Data 0.000 (0.050)	Loss 1.661 (1.125)
Epoch: [9][140/200]	Time 0.696 (0.760)	Data 0.001 (0.054)	Loss 1.290 (1.159)
Epoch: [9][160/200]	Time 0.704 (0.763)	Data 0.001 (0.058)	Loss 1.381 (1.198)
Epoch: [9][180/200]	Time 0.693 (0.756)	Data 0.000 (0.052)	Loss 1.364 (1.220)
Epoch: [9][200/200]	Time 0.697 (0.759)	Data 0.001 (0.055)	Loss 1.385 (1.236)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.225 (0.262)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.230 (0.248)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.31537365913391
==> Statistics for epoch 10: 1042 clusters
Epoch: [10][20/200]	Time 0.689 (0.753)	Data 0.001 (0.057)	Loss 0.319 (0.309)
Epoch: [10][40/200]	Time 0.691 (0.769)	Data 0.001 (0.069)	Loss 1.261 (0.527)
Epoch: [10][60/200]	Time 0.692 (0.745)	Data 0.000 (0.046)	Loss 1.388 (0.828)
Epoch: [10][80/200]	Time 0.702 (0.754)	Data 0.001 (0.054)	Loss 1.075 (0.976)
Epoch: [10][100/200]	Time 0.692 (0.758)	Data 0.001 (0.058)	Loss 1.097 (1.071)
Epoch: [10][120/200]	Time 0.706 (0.749)	Data 0.001 (0.049)	Loss 1.482 (1.139)
Epoch: [10][140/200]	Time 0.702 (0.755)	Data 0.003 (0.055)	Loss 1.677 (1.179)
Epoch: [10][160/200]	Time 0.696 (0.748)	Data 0.000 (0.048)	Loss 1.771 (1.209)
Epoch: [10][180/200]	Time 0.701 (0.753)	Data 0.001 (0.053)	Loss 1.314 (1.238)
Epoch: [10][200/200]	Time 0.695 (0.757)	Data 0.001 (0.056)	Loss 1.359 (1.260)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.231 (0.265)	Data 0.000 (0.031)	
Extract Features: [100/128]	Time 0.230 (0.249)	Data 0.001 (0.016)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.95331954956055
==> Statistics for epoch 11: 1047 clusters
Epoch: [11][20/200]	Time 0.692 (0.747)	Data 0.001 (0.054)	Loss 0.317 (0.306)
Epoch: [11][40/200]	Time 0.697 (0.764)	Data 0.001 (0.071)	Loss 1.436 (0.519)
Epoch: [11][60/200]	Time 0.696 (0.741)	Data 0.000 (0.047)	Loss 1.031 (0.772)
Epoch: [11][80/200]	Time 0.794 (0.755)	Data 0.001 (0.058)	Loss 1.179 (0.942)
Epoch: [11][100/200]	Time 0.696 (0.762)	Data 0.001 (0.063)	Loss 1.394 (1.046)
Epoch: [11][120/200]	Time 0.696 (0.753)	Data 0.001 (0.053)	Loss 1.185 (1.102)
Epoch: [11][140/200]	Time 0.695 (0.759)	Data 0.001 (0.058)	Loss 1.178 (1.135)
Epoch: [11][160/200]	Time 0.696 (0.752)	Data 0.000 (0.051)	Loss 1.265 (1.179)
Epoch: [11][180/200]	Time 0.697 (0.755)	Data 0.001 (0.054)	Loss 1.231 (1.209)
Epoch: [11][200/200]	Time 0.841 (0.760)	Data 0.001 (0.057)	Loss 1.545 (1.224)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.229 (0.259)	Data 0.001 (0.026)	
Extract Features: [100/128]	Time 0.229 (0.247)	Data 0.001 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.02438139915466
==> Statistics for epoch 12: 1055 clusters
Epoch: [12][20/200]	Time 0.688 (0.756)	Data 0.001 (0.057)	Loss 0.194 (0.294)
Epoch: [12][40/200]	Time 0.704 (0.773)	Data 0.001 (0.069)	Loss 1.723 (0.499)
Epoch: [12][60/200]	Time 0.692 (0.750)	Data 0.000 (0.047)	Loss 1.296 (0.768)
Epoch: [12][80/200]	Time 0.701 (0.760)	Data 0.005 (0.056)	Loss 1.328 (0.904)
Epoch: [12][100/200]	Time 0.695 (0.766)	Data 0.001 (0.062)	Loss 1.285 (0.989)
Epoch: [12][120/200]	Time 0.704 (0.756)	Data 0.001 (0.052)	Loss 1.655 (1.048)
Epoch: [12][140/200]	Time 0.697 (0.760)	Data 0.001 (0.057)	Loss 1.503 (1.087)
Epoch: [12][160/200]	Time 0.694 (0.753)	Data 0.000 (0.050)	Loss 1.607 (1.115)
Epoch: [12][180/200]	Time 0.695 (0.756)	Data 0.001 (0.054)	Loss 1.282 (1.136)
Epoch: [12][200/200]	Time 0.694 (0.759)	Data 0.001 (0.057)	Loss 1.426 (1.163)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.228 (0.260)	Data 0.000 (0.025)	
Extract Features: [100/128]	Time 0.233 (0.248)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.151293992996216
==> Statistics for epoch 13: 1043 clusters
Epoch: [13][20/200]	Time 0.696 (0.751)	Data 0.001 (0.057)	Loss 0.215 (0.307)
Epoch: [13][40/200]	Time 0.699 (0.765)	Data 0.001 (0.068)	Loss 2.007 (0.543)
Epoch: [13][60/200]	Time 0.692 (0.742)	Data 0.000 (0.045)	Loss 1.137 (0.825)
Epoch: [13][80/200]	Time 0.697 (0.755)	Data 0.001 (0.056)	Loss 1.236 (0.952)
Epoch: [13][100/200]	Time 0.695 (0.759)	Data 0.001 (0.061)	Loss 1.224 (1.060)
Epoch: [13][120/200]	Time 0.693 (0.749)	Data 0.001 (0.051)	Loss 1.276 (1.121)
Epoch: [13][140/200]	Time 0.698 (0.753)	Data 0.001 (0.054)	Loss 1.284 (1.162)
Epoch: [13][160/200]	Time 0.691 (0.745)	Data 0.000 (0.048)	Loss 1.967 (1.201)
Epoch: [13][180/200]	Time 0.703 (0.749)	Data 0.001 (0.051)	Loss 1.592 (1.236)
Epoch: [13][200/200]	Time 0.700 (0.753)	Data 0.001 (0.054)	Loss 1.199 (1.251)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.229 (0.260)	Data 0.001 (0.026)	
Extract Features: [100/128]	Time 0.235 (0.248)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.05530381202698
==> Statistics for epoch 14: 1056 clusters
Epoch: [14][20/200]	Time 0.695 (0.749)	Data 0.001 (0.057)	Loss 0.223 (0.316)
Epoch: [14][40/200]	Time 0.692 (0.766)	Data 0.001 (0.073)	Loss 1.526 (0.500)
Epoch: [14][60/200]	Time 0.694 (0.744)	Data 0.000 (0.049)	Loss 1.336 (0.792)
Epoch: [14][80/200]	Time 0.693 (0.756)	Data 0.001 (0.059)	Loss 1.158 (0.909)
Epoch: [14][100/200]	Time 2.571 (0.765)	Data 1.818 (0.066)	Loss 1.323 (1.006)
Epoch: [14][120/200]	Time 0.700 (0.756)	Data 0.001 (0.055)	Loss 1.216 (1.057)
Epoch: [14][140/200]	Time 0.699 (0.762)	Data 0.001 (0.059)	Loss 1.164 (1.101)
Epoch: [14][160/200]	Time 0.692 (0.754)	Data 0.000 (0.052)	Loss 0.946 (1.122)
Epoch: [14][180/200]	Time 0.697 (0.759)	Data 0.001 (0.056)	Loss 1.913 (1.151)
Epoch: [14][200/200]	Time 0.703 (0.762)	Data 0.001 (0.059)	Loss 1.212 (1.162)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.228 (0.268)	Data 0.000 (0.029)	
Extract Features: [100/128]	Time 0.364 (0.252)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.06281065940857
==> Statistics for epoch 15: 1067 clusters
Epoch: [15][20/200]	Time 0.692 (0.755)	Data 0.001 (0.050)	Loss 0.355 (0.258)
Epoch: [15][40/200]	Time 0.693 (0.774)	Data 0.001 (0.069)	Loss 1.418 (0.442)
Epoch: [15][60/200]	Time 0.693 (0.751)	Data 0.000 (0.046)	Loss 1.290 (0.734)
Epoch: [15][80/200]	Time 0.842 (0.763)	Data 0.001 (0.056)	Loss 0.850 (0.871)
Epoch: [15][100/200]	Time 2.448 (0.767)	Data 1.563 (0.061)	Loss 1.189 (0.956)
Epoch: [15][120/200]	Time 0.694 (0.755)	Data 0.001 (0.051)	Loss 0.919 (1.012)
Epoch: [15][140/200]	Time 0.697 (0.760)	Data 0.001 (0.056)	Loss 1.144 (1.057)
Epoch: [15][160/200]	Time 0.695 (0.752)	Data 0.000 (0.049)	Loss 1.848 (1.084)
Epoch: [15][180/200]	Time 0.703 (0.756)	Data 0.002 (0.053)	Loss 1.659 (1.107)
Epoch: [15][200/200]	Time 0.694 (0.758)	Data 0.001 (0.056)	Loss 1.539 (1.127)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.240 (0.260)	Data 0.001 (0.028)	
Extract Features: [100/128]	Time 0.229 (0.249)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.80333709716797
==> Statistics for epoch 16: 1028 clusters
Epoch: [16][20/200]	Time 0.696 (0.754)	Data 0.001 (0.055)	Loss 0.182 (0.275)
Epoch: [16][40/200]	Time 0.700 (0.767)	Data 0.001 (0.068)	Loss 1.048 (0.443)
Epoch: [16][60/200]	Time 0.692 (0.744)	Data 0.000 (0.045)	Loss 0.895 (0.695)
Epoch: [16][80/200]	Time 0.695 (0.757)	Data 0.001 (0.058)	Loss 1.410 (0.831)
Epoch: [16][100/200]	Time 0.694 (0.762)	Data 0.001 (0.062)	Loss 1.349 (0.918)
Epoch: [16][120/200]	Time 0.699 (0.751)	Data 0.002 (0.052)	Loss 1.736 (0.980)
Epoch: [16][140/200]	Time 0.696 (0.757)	Data 0.001 (0.058)	Loss 1.169 (1.012)
Epoch: [16][160/200]	Time 0.701 (0.750)	Data 0.000 (0.051)	Loss 0.836 (1.034)
Epoch: [16][180/200]	Time 0.698 (0.753)	Data 0.001 (0.054)	Loss 1.223 (1.048)
Epoch: [16][200/200]	Time 0.706 (0.756)	Data 0.001 (0.057)	Loss 1.197 (1.060)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.229 (0.264)	Data 0.000 (0.031)	
Extract Features: [100/128]	Time 0.233 (0.249)	Data 0.000 (0.016)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.90330982208252
==> Statistics for epoch 17: 999 clusters
Epoch: [17][20/200]	Time 0.690 (0.746)	Data 0.001 (0.054)	Loss 0.355 (0.424)
Epoch: [17][40/200]	Time 0.693 (0.760)	Data 0.001 (0.065)	Loss 1.484 (0.612)
Epoch: [17][60/200]	Time 0.691 (0.740)	Data 0.000 (0.043)	Loss 0.759 (0.824)
Epoch: [17][80/200]	Time 0.696 (0.749)	Data 0.001 (0.052)	Loss 1.414 (0.924)
Epoch: [17][100/200]	Time 0.698 (0.759)	Data 0.001 (0.061)	Loss 1.679 (0.972)
Epoch: [17][120/200]	Time 0.696 (0.749)	Data 0.000 (0.051)	Loss 1.394 (1.008)
Epoch: [17][140/200]	Time 0.698 (0.754)	Data 0.001 (0.056)	Loss 0.883 (1.023)
Epoch: [17][160/200]	Time 0.696 (0.757)	Data 0.001 (0.059)	Loss 1.548 (1.040)
Epoch: [17][180/200]	Time 0.694 (0.750)	Data 0.000 (0.052)	Loss 1.683 (1.054)
Epoch: [17][200/200]	Time 0.699 (0.754)	Data 0.001 (0.055)	Loss 1.075 (1.058)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.230 (0.266)	Data 0.001 (0.029)	
Extract Features: [100/128]	Time 0.230 (0.251)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.68489599227905
==> Statistics for epoch 18: 1059 clusters
Epoch: [18][20/200]	Time 0.689 (0.747)	Data 0.001 (0.051)	Loss 0.473 (0.279)
Epoch: [18][40/200]	Time 0.693 (0.763)	Data 0.001 (0.068)	Loss 1.462 (0.448)
Epoch: [18][60/200]	Time 0.695 (0.743)	Data 0.000 (0.046)	Loss 0.908 (0.719)
Epoch: [18][80/200]	Time 0.700 (0.756)	Data 0.001 (0.058)	Loss 1.167 (0.837)
Epoch: [18][100/200]	Time 2.475 (0.762)	Data 1.742 (0.064)	Loss 1.503 (0.921)
Epoch: [18][120/200]	Time 0.695 (0.753)	Data 0.001 (0.054)	Loss 1.606 (0.979)
Epoch: [18][140/200]	Time 0.689 (0.757)	Data 0.001 (0.057)	Loss 1.535 (1.021)
Epoch: [18][160/200]	Time 0.696 (0.750)	Data 0.000 (0.050)	Loss 1.308 (1.044)
Epoch: [18][180/200]	Time 0.695 (0.754)	Data 0.001 (0.053)	Loss 1.039 (1.072)
Epoch: [18][200/200]	Time 0.712 (0.756)	Data 0.001 (0.056)	Loss 1.003 (1.086)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.228 (0.264)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.369 (0.249)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.80461549758911
==> Statistics for epoch 19: 1058 clusters
Epoch: [19][20/200]	Time 0.694 (0.754)	Data 0.001 (0.054)	Loss 0.294 (0.264)
Epoch: [19][40/200]	Time 0.688 (0.767)	Data 0.001 (0.070)	Loss 1.118 (0.414)
Epoch: [19][60/200]	Time 0.693 (0.745)	Data 0.000 (0.047)	Loss 1.314 (0.681)
Epoch: [19][80/200]	Time 0.695 (0.758)	Data 0.001 (0.057)	Loss 0.914 (0.831)
Epoch: [19][100/200]	Time 2.303 (0.763)	Data 1.580 (0.061)	Loss 0.751 (0.904)
Epoch: [19][120/200]	Time 0.697 (0.753)	Data 0.001 (0.051)	Loss 0.990 (0.952)
Epoch: [19][140/200]	Time 0.694 (0.758)	Data 0.001 (0.056)	Loss 1.512 (0.997)
Epoch: [19][160/200]	Time 0.695 (0.751)	Data 0.000 (0.049)	Loss 1.307 (1.020)
Epoch: [19][180/200]	Time 0.703 (0.755)	Data 0.001 (0.054)	Loss 1.662 (1.040)
Epoch: [19][200/200]	Time 0.697 (0.758)	Data 0.001 (0.057)	Loss 0.942 (1.063)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.227 (0.258)	Data 0.001 (0.025)	
Extract Features: [100/128]	Time 0.237 (0.246)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.15568423271179
==> Statistics for epoch 20: 1087 clusters
Epoch: [20][20/200]	Time 0.695 (0.754)	Data 0.001 (0.055)	Loss 0.193 (0.239)
Epoch: [20][40/200]	Time 0.697 (0.773)	Data 0.001 (0.072)	Loss 0.817 (0.370)
Epoch: [20][60/200]	Time 0.694 (0.747)	Data 0.000 (0.049)	Loss 1.310 (0.655)
Epoch: [20][80/200]	Time 0.695 (0.760)	Data 0.001 (0.060)	Loss 1.100 (0.776)
Epoch: [20][100/200]	Time 2.447 (0.764)	Data 1.690 (0.065)	Loss 1.023 (0.855)
Epoch: [20][120/200]	Time 0.694 (0.753)	Data 0.001 (0.054)	Loss 1.019 (0.915)
Epoch: [20][140/200]	Time 0.694 (0.757)	Data 0.001 (0.059)	Loss 1.264 (0.953)
Epoch: [20][160/200]	Time 0.697 (0.749)	Data 0.000 (0.051)	Loss 1.301 (0.982)
Epoch: [20][180/200]	Time 0.695 (0.753)	Data 0.001 (0.055)	Loss 1.242 (0.997)
Epoch: [20][200/200]	Time 0.700 (0.758)	Data 0.001 (0.058)	Loss 1.491 (1.023)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.231 (0.259)	Data 0.000 (0.025)	
Extract Features: [100/128]	Time 0.229 (0.249)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.90069913864136
==> Statistics for epoch 21: 1083 clusters
Epoch: [21][20/200]	Time 0.692 (0.765)	Data 0.001 (0.057)	Loss 0.161 (0.214)
Epoch: [21][40/200]	Time 0.692 (0.778)	Data 0.001 (0.072)	Loss 1.365 (0.393)
Epoch: [21][60/200]	Time 0.698 (0.755)	Data 0.000 (0.048)	Loss 0.948 (0.646)
Epoch: [21][80/200]	Time 0.696 (0.764)	Data 0.001 (0.058)	Loss 0.988 (0.766)
Epoch: [21][100/200]	Time 2.510 (0.771)	Data 1.777 (0.064)	Loss 0.986 (0.838)
Epoch: [21][120/200]	Time 0.693 (0.759)	Data 0.001 (0.054)	Loss 0.753 (0.902)
Epoch: [21][140/200]	Time 0.696 (0.764)	Data 0.001 (0.059)	Loss 1.241 (0.944)
Epoch: [21][160/200]	Time 0.696 (0.756)	Data 0.000 (0.052)	Loss 1.331 (0.972)
Epoch: [21][180/200]	Time 0.697 (0.760)	Data 0.001 (0.056)	Loss 1.158 (0.988)
Epoch: [21][200/200]	Time 0.706 (0.763)	Data 0.001 (0.059)	Loss 1.102 (1.006)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.229 (0.262)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.228 (0.249)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.91547775268555
==> Statistics for epoch 22: 1096 clusters
Epoch: [22][20/200]	Time 0.693 (0.757)	Data 0.001 (0.056)	Loss 0.171 (0.201)
Epoch: [22][40/200]	Time 0.696 (0.768)	Data 0.001 (0.069)	Loss 1.188 (0.342)
Epoch: [22][60/200]	Time 0.700 (0.744)	Data 0.001 (0.046)	Loss 1.192 (0.624)
Epoch: [22][80/200]	Time 0.709 (0.753)	Data 0.001 (0.055)	Loss 1.273 (0.747)
Epoch: [22][100/200]	Time 0.689 (0.742)	Data 0.000 (0.044)	Loss 1.474 (0.836)
Epoch: [22][120/200]	Time 0.696 (0.750)	Data 0.001 (0.052)	Loss 1.270 (0.896)
Epoch: [22][140/200]	Time 0.696 (0.755)	Data 0.001 (0.057)	Loss 0.991 (0.936)
Epoch: [22][160/200]	Time 0.694 (0.748)	Data 0.001 (0.050)	Loss 1.147 (0.966)
Epoch: [22][180/200]	Time 0.699 (0.752)	Data 0.001 (0.053)	Loss 1.559 (0.980)
Epoch: [22][200/200]	Time 0.697 (0.747)	Data 0.000 (0.048)	Loss 0.834 (0.997)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.229 (0.265)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.224 (0.250)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.82380986213684
==> Statistics for epoch 23: 1098 clusters
Epoch: [23][20/200]	Time 0.690 (0.753)	Data 0.001 (0.055)	Loss 0.223 (0.216)
Epoch: [23][40/200]	Time 0.698 (0.767)	Data 0.001 (0.071)	Loss 1.154 (0.333)
Epoch: [23][60/200]	Time 0.694 (0.743)	Data 0.001 (0.048)	Loss 1.126 (0.611)
Epoch: [23][80/200]	Time 0.696 (0.756)	Data 0.001 (0.058)	Loss 1.337 (0.745)
Epoch: [23][100/200]	Time 0.695 (0.747)	Data 0.000 (0.047)	Loss 1.237 (0.839)
Epoch: [23][120/200]	Time 0.695 (0.755)	Data 0.001 (0.053)	Loss 1.126 (0.888)
Epoch: [23][140/200]	Time 0.696 (0.759)	Data 0.001 (0.056)	Loss 0.713 (0.927)
Epoch: [23][160/200]	Time 0.709 (0.754)	Data 0.001 (0.049)	Loss 1.015 (0.959)
Epoch: [23][180/200]	Time 0.696 (0.759)	Data 0.001 (0.054)	Loss 1.341 (0.989)
Epoch: [23][200/200]	Time 0.692 (0.753)	Data 0.000 (0.048)	Loss 1.150 (1.011)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.228 (0.264)	Data 0.000 (0.030)	
Extract Features: [100/128]	Time 0.236 (0.250)	Data 0.001 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.2520387172699
==> Statistics for epoch 24: 1098 clusters
Epoch: [24][20/200]	Time 0.802 (0.761)	Data 0.001 (0.056)	Loss 0.342 (0.199)
Epoch: [24][40/200]	Time 0.693 (0.773)	Data 0.001 (0.071)	Loss 1.194 (0.321)
Epoch: [24][60/200]	Time 0.692 (0.750)	Data 0.001 (0.048)	Loss 0.881 (0.582)
Epoch: [24][80/200]	Time 0.697 (0.759)	Data 0.001 (0.056)	Loss 1.332 (0.729)
Epoch: [24][100/200]	Time 0.695 (0.748)	Data 0.000 (0.045)	Loss 0.654 (0.806)
Epoch: [24][120/200]	Time 0.694 (0.754)	Data 0.001 (0.051)	Loss 0.945 (0.868)
Epoch: [24][140/200]	Time 0.698 (0.761)	Data 0.001 (0.057)	Loss 1.059 (0.915)
Epoch: [24][160/200]	Time 0.699 (0.753)	Data 0.001 (0.050)	Loss 0.983 (0.941)
Epoch: [24][180/200]	Time 0.697 (0.757)	Data 0.001 (0.054)	Loss 0.757 (0.965)
Epoch: [24][200/200]	Time 0.694 (0.752)	Data 0.000 (0.049)	Loss 1.482 (0.991)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.228 (0.261)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.226 (0.248)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.095515727996826
==> Statistics for epoch 25: 1099 clusters
Epoch: [25][20/200]	Time 0.694 (0.755)	Data 0.001 (0.056)	Loss 0.192 (0.198)
Epoch: [25][40/200]	Time 0.693 (0.774)	Data 0.001 (0.071)	Loss 0.993 (0.336)
Epoch: [25][60/200]	Time 0.694 (0.749)	Data 0.001 (0.048)	Loss 1.557 (0.609)
Epoch: [25][80/200]	Time 0.690 (0.759)	Data 0.001 (0.059)	Loss 1.100 (0.728)
Epoch: [25][100/200]	Time 0.695 (0.748)	Data 0.000 (0.047)	Loss 1.096 (0.819)
Epoch: [25][120/200]	Time 0.693 (0.755)	Data 0.001 (0.054)	Loss 1.239 (0.902)
Epoch: [25][140/200]	Time 0.689 (0.760)	Data 0.001 (0.059)	Loss 1.175 (0.933)
Epoch: [25][160/200]	Time 0.693 (0.751)	Data 0.001 (0.052)	Loss 1.182 (0.965)
Epoch: [25][180/200]	Time 0.693 (0.756)	Data 0.001 (0.056)	Loss 1.422 (0.989)
Epoch: [25][200/200]	Time 0.693 (0.750)	Data 0.000 (0.050)	Loss 0.778 (1.012)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.224 (0.260)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.231 (0.247)	Data 0.001 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.739065408706665
==> Statistics for epoch 26: 1086 clusters
Epoch: [26][20/200]	Time 0.694 (0.755)	Data 0.001 (0.054)	Loss 0.323 (0.216)
Epoch: [26][40/200]	Time 0.689 (0.768)	Data 0.001 (0.072)	Loss 1.045 (0.372)
Epoch: [26][60/200]	Time 0.692 (0.746)	Data 0.000 (0.048)	Loss 1.036 (0.604)
Epoch: [26][80/200]	Time 0.697 (0.756)	Data 0.001 (0.059)	Loss 0.743 (0.717)
Epoch: [26][100/200]	Time 2.455 (0.761)	Data 1.726 (0.064)	Loss 1.624 (0.819)
Epoch: [26][120/200]	Time 0.696 (0.751)	Data 0.001 (0.054)	Loss 1.287 (0.869)
Epoch: [26][140/200]	Time 0.707 (0.756)	Data 0.001 (0.058)	Loss 1.541 (0.911)
Epoch: [26][160/200]	Time 0.696 (0.751)	Data 0.000 (0.051)	Loss 1.048 (0.939)
Epoch: [26][180/200]	Time 0.812 (0.756)	Data 0.001 (0.055)	Loss 1.218 (0.963)
Epoch: [26][200/200]	Time 0.696 (0.761)	Data 0.001 (0.060)	Loss 1.629 (0.982)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.231 (0.261)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.228 (0.249)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.97489380836487
==> Statistics for epoch 27: 1107 clusters
Epoch: [27][20/200]	Time 0.687 (0.743)	Data 0.001 (0.052)	Loss 0.307 (0.193)
Epoch: [27][40/200]	Time 0.694 (0.762)	Data 0.001 (0.071)	Loss 1.193 (0.313)
Epoch: [27][60/200]	Time 0.695 (0.743)	Data 0.001 (0.048)	Loss 1.040 (0.562)
Epoch: [27][80/200]	Time 0.698 (0.753)	Data 0.001 (0.054)	Loss 1.070 (0.691)
Epoch: [27][100/200]	Time 0.696 (0.744)	Data 0.000 (0.044)	Loss 1.384 (0.794)
Epoch: [27][120/200]	Time 0.798 (0.751)	Data 0.001 (0.049)	Loss 1.156 (0.880)
Epoch: [27][140/200]	Time 0.701 (0.757)	Data 0.002 (0.055)	Loss 1.622 (0.927)
Epoch: [27][160/200]	Time 0.698 (0.751)	Data 0.001 (0.048)	Loss 0.881 (0.948)
Epoch: [27][180/200]	Time 0.695 (0.755)	Data 0.001 (0.052)	Loss 0.800 (0.965)
Epoch: [27][200/200]	Time 0.694 (0.750)	Data 0.000 (0.047)	Loss 1.393 (0.985)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.233 (0.265)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.375 (0.252)	Data 0.001 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.07979989051819
==> Statistics for epoch 28: 1099 clusters
Epoch: [28][20/200]	Time 0.688 (0.753)	Data 0.001 (0.049)	Loss 0.142 (0.195)
Epoch: [28][40/200]	Time 0.691 (0.771)	Data 0.001 (0.069)	Loss 1.226 (0.335)
Epoch: [28][60/200]	Time 0.806 (0.751)	Data 0.001 (0.047)	Loss 1.272 (0.590)
Epoch: [28][80/200]	Time 0.693 (0.759)	Data 0.001 (0.057)	Loss 1.321 (0.730)
Epoch: [28][100/200]	Time 0.691 (0.748)	Data 0.000 (0.046)	Loss 1.176 (0.802)
Epoch: [28][120/200]	Time 0.694 (0.756)	Data 0.001 (0.053)	Loss 1.335 (0.861)
Epoch: [28][140/200]	Time 0.698 (0.760)	Data 0.001 (0.058)	Loss 1.082 (0.896)
Epoch: [28][160/200]	Time 0.698 (0.752)	Data 0.001 (0.051)	Loss 1.290 (0.938)
Epoch: [28][180/200]	Time 0.697 (0.756)	Data 0.001 (0.055)	Loss 0.981 (0.967)
Epoch: [28][200/200]	Time 0.699 (0.752)	Data 0.000 (0.050)	Loss 1.462 (0.984)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.238 (0.264)	Data 0.001 (0.028)	
Extract Features: [100/128]	Time 0.229 (0.251)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.198933124542236
==> Statistics for epoch 29: 1097 clusters
Epoch: [29][20/200]	Time 0.694 (0.756)	Data 0.001 (0.056)	Loss 0.193 (0.203)
Epoch: [29][40/200]	Time 0.696 (0.765)	Data 0.001 (0.067)	Loss 1.075 (0.330)
Epoch: [29][60/200]	Time 0.701 (0.742)	Data 0.001 (0.045)	Loss 1.210 (0.580)
Epoch: [29][80/200]	Time 0.700 (0.754)	Data 0.001 (0.057)	Loss 1.230 (0.707)
Epoch: [29][100/200]	Time 0.693 (0.743)	Data 0.000 (0.046)	Loss 1.323 (0.800)
Epoch: [29][120/200]	Time 0.699 (0.750)	Data 0.001 (0.052)	Loss 0.855 (0.869)
Epoch: [29][140/200]	Time 0.697 (0.755)	Data 0.002 (0.057)	Loss 0.941 (0.908)
Epoch: [29][160/200]	Time 0.695 (0.750)	Data 0.001 (0.050)	Loss 1.467 (0.942)
Epoch: [29][180/200]	Time 0.696 (0.755)	Data 0.001 (0.055)	Loss 1.248 (0.971)
Epoch: [29][200/200]	Time 0.697 (0.749)	Data 0.000 (0.049)	Loss 1.147 (0.993)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.229 (0.259)	Data 0.000 (0.025)	
Extract Features: [100/128]	Time 0.231 (0.249)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.147149324417114
==> Statistics for epoch 30: 1099 clusters
Epoch: [30][20/200]	Time 0.692 (0.754)	Data 0.001 (0.049)	Loss 0.196 (0.216)
Epoch: [30][40/200]	Time 0.694 (0.774)	Data 0.001 (0.069)	Loss 1.347 (0.334)
Epoch: [30][60/200]	Time 0.701 (0.749)	Data 0.001 (0.046)	Loss 1.354 (0.612)
Epoch: [30][80/200]	Time 0.697 (0.762)	Data 0.001 (0.057)	Loss 1.090 (0.741)
Epoch: [30][100/200]	Time 0.691 (0.750)	Data 0.000 (0.046)	Loss 0.977 (0.807)
Epoch: [30][120/200]	Time 0.695 (0.757)	Data 0.001 (0.053)	Loss 1.136 (0.862)
Epoch: [30][140/200]	Time 0.696 (0.763)	Data 0.001 (0.058)	Loss 1.317 (0.901)
Epoch: [30][160/200]	Time 0.698 (0.755)	Data 0.001 (0.051)	Loss 0.973 (0.931)
Epoch: [30][180/200]	Time 0.697 (0.758)	Data 0.001 (0.055)	Loss 0.904 (0.951)
Epoch: [30][200/200]	Time 0.694 (0.752)	Data 0.000 (0.049)	Loss 1.356 (0.976)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.232 (0.263)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.229 (0.249)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.895137548446655
==> Statistics for epoch 31: 1094 clusters
Epoch: [31][20/200]	Time 0.687 (0.753)	Data 0.001 (0.054)	Loss 0.191 (0.227)
Epoch: [31][40/200]	Time 0.692 (0.764)	Data 0.001 (0.069)	Loss 0.965 (0.334)
Epoch: [31][60/200]	Time 0.693 (0.742)	Data 0.001 (0.046)	Loss 1.300 (0.611)
Epoch: [31][80/200]	Time 0.694 (0.751)	Data 0.001 (0.054)	Loss 1.059 (0.732)
Epoch: [31][100/200]	Time 0.698 (0.740)	Data 0.000 (0.043)	Loss 1.318 (0.802)
Epoch: [31][120/200]	Time 0.696 (0.749)	Data 0.001 (0.051)	Loss 1.388 (0.869)
Epoch: [31][140/200]	Time 0.697 (0.754)	Data 0.001 (0.054)	Loss 1.592 (0.916)
Epoch: [31][160/200]	Time 0.703 (0.749)	Data 0.001 (0.048)	Loss 0.850 (0.946)
Epoch: [31][180/200]	Time 0.696 (0.755)	Data 0.001 (0.053)	Loss 1.084 (0.967)
Epoch: [31][200/200]	Time 0.697 (0.750)	Data 0.000 (0.047)	Loss 1.012 (0.991)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.230 (0.260)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.230 (0.248)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.841575145721436
==> Statistics for epoch 32: 1107 clusters
Epoch: [32][20/200]	Time 0.690 (0.742)	Data 0.001 (0.051)	Loss 0.154 (0.203)
Epoch: [32][40/200]	Time 0.815 (0.762)	Data 0.001 (0.067)	Loss 1.190 (0.334)
Epoch: [32][60/200]	Time 0.696 (0.739)	Data 0.001 (0.045)	Loss 1.119 (0.590)
Epoch: [32][80/200]	Time 0.696 (0.750)	Data 0.001 (0.056)	Loss 1.237 (0.737)
Epoch: [32][100/200]	Time 0.694 (0.742)	Data 0.000 (0.045)	Loss 1.086 (0.826)
Epoch: [32][120/200]	Time 0.699 (0.749)	Data 0.001 (0.051)	Loss 1.116 (0.885)
Epoch: [32][140/200]	Time 0.698 (0.756)	Data 0.001 (0.057)	Loss 1.117 (0.922)
Epoch: [32][160/200]	Time 0.703 (0.749)	Data 0.001 (0.050)	Loss 1.255 (0.957)
Epoch: [32][180/200]	Time 0.701 (0.755)	Data 0.001 (0.055)	Loss 1.229 (0.976)
Epoch: [32][200/200]	Time 0.809 (0.750)	Data 0.000 (0.049)	Loss 1.182 (1.000)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.226 (0.259)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.229 (0.247)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.944682598114014
==> Statistics for epoch 33: 1094 clusters
Epoch: [33][20/200]	Time 0.691 (0.739)	Data 0.001 (0.048)	Loss 0.197 (0.194)
Epoch: [33][40/200]	Time 0.839 (0.766)	Data 0.001 (0.069)	Loss 1.158 (0.340)
Epoch: [33][60/200]	Time 0.697 (0.745)	Data 0.001 (0.047)	Loss 1.102 (0.613)
Epoch: [33][80/200]	Time 0.694 (0.758)	Data 0.001 (0.057)	Loss 1.024 (0.739)
Epoch: [33][100/200]	Time 0.693 (0.747)	Data 0.000 (0.046)	Loss 0.997 (0.819)
Epoch: [33][120/200]	Time 0.789 (0.755)	Data 0.001 (0.052)	Loss 1.308 (0.861)
Epoch: [33][140/200]	Time 0.699 (0.760)	Data 0.001 (0.057)	Loss 1.086 (0.904)
Epoch: [33][160/200]	Time 0.696 (0.752)	Data 0.001 (0.050)	Loss 1.134 (0.928)
Epoch: [33][180/200]	Time 0.697 (0.756)	Data 0.001 (0.054)	Loss 1.352 (0.952)
Epoch: [33][200/200]	Time 0.693 (0.751)	Data 0.000 (0.049)	Loss 0.897 (0.965)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.228 (0.264)	Data 0.000 (0.029)	
Extract Features: [100/128]	Time 0.234 (0.250)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.05115294456482
==> Statistics for epoch 34: 1090 clusters
Epoch: [34][20/200]	Time 0.687 (0.749)	Data 0.001 (0.051)	Loss 0.234 (0.199)
Epoch: [34][40/200]	Time 0.692 (0.764)	Data 0.001 (0.063)	Loss 1.185 (0.337)
Epoch: [34][60/200]	Time 0.699 (0.743)	Data 0.001 (0.042)	Loss 1.589 (0.606)
Epoch: [34][80/200]	Time 0.697 (0.753)	Data 0.001 (0.052)	Loss 1.114 (0.760)
Epoch: [34][100/200]	Time 0.694 (0.743)	Data 0.000 (0.041)	Loss 0.828 (0.829)
Epoch: [34][120/200]	Time 0.697 (0.750)	Data 0.001 (0.048)	Loss 1.166 (0.882)
Epoch: [34][140/200]	Time 0.700 (0.756)	Data 0.001 (0.055)	Loss 1.186 (0.927)
Epoch: [34][160/200]	Time 0.698 (0.750)	Data 0.001 (0.048)	Loss 1.306 (0.962)
Epoch: [34][180/200]	Time 0.695 (0.753)	Data 0.001 (0.052)	Loss 0.809 (0.980)
Epoch: [34][200/200]	Time 0.693 (0.748)	Data 0.000 (0.047)	Loss 1.255 (0.998)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.230 (0.260)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.227 (0.248)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.90213584899902
==> Statistics for epoch 35: 1088 clusters
Epoch: [35][20/200]	Time 0.694 (0.755)	Data 0.001 (0.057)	Loss 0.170 (0.184)
Epoch: [35][40/200]	Time 0.693 (0.766)	Data 0.001 (0.069)	Loss 1.427 (0.314)
Epoch: [35][60/200]	Time 0.788 (0.745)	Data 0.001 (0.046)	Loss 1.183 (0.556)
Epoch: [35][80/200]	Time 0.697 (0.755)	Data 0.001 (0.056)	Loss 1.368 (0.705)
Epoch: [35][100/200]	Time 0.703 (0.745)	Data 0.000 (0.045)	Loss 1.026 (0.780)
Epoch: [35][120/200]	Time 0.704 (0.751)	Data 0.001 (0.051)	Loss 1.303 (0.838)
Epoch: [35][140/200]	Time 0.693 (0.756)	Data 0.001 (0.055)	Loss 1.286 (0.881)
Epoch: [35][160/200]	Time 0.699 (0.749)	Data 0.001 (0.049)	Loss 0.873 (0.916)
Epoch: [35][180/200]	Time 0.701 (0.753)	Data 0.001 (0.053)	Loss 1.842 (0.942)
Epoch: [35][200/200]	Time 0.700 (0.748)	Data 0.000 (0.048)	Loss 1.315 (0.968)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.227 (0.263)	Data 0.001 (0.028)	
Extract Features: [100/128]	Time 0.236 (0.250)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.102782011032104
==> Statistics for epoch 36: 1096 clusters
Epoch: [36][20/200]	Time 0.695 (0.756)	Data 0.001 (0.053)	Loss 0.175 (0.214)
Epoch: [36][40/200]	Time 0.693 (0.768)	Data 0.001 (0.070)	Loss 1.259 (0.347)
Epoch: [36][60/200]	Time 0.695 (0.745)	Data 0.001 (0.047)	Loss 0.991 (0.590)
Epoch: [36][80/200]	Time 0.695 (0.756)	Data 0.001 (0.058)	Loss 1.474 (0.727)
Epoch: [36][100/200]	Time 0.693 (0.744)	Data 0.000 (0.047)	Loss 0.991 (0.794)
Epoch: [36][120/200]	Time 0.696 (0.753)	Data 0.001 (0.054)	Loss 1.051 (0.847)
Epoch: [36][140/200]	Time 0.698 (0.759)	Data 0.001 (0.059)	Loss 1.361 (0.892)
Epoch: [36][160/200]	Time 0.698 (0.752)	Data 0.001 (0.051)	Loss 0.963 (0.919)
Epoch: [36][180/200]	Time 0.702 (0.757)	Data 0.001 (0.055)	Loss 0.938 (0.944)
Epoch: [36][200/200]	Time 0.827 (0.753)	Data 0.000 (0.050)	Loss 1.028 (0.971)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.228 (0.260)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.235 (0.249)	Data 0.001 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.21446418762207
==> Statistics for epoch 37: 1096 clusters
Epoch: [37][20/200]	Time 0.690 (0.764)	Data 0.001 (0.055)	Loss 0.109 (0.194)
Epoch: [37][40/200]	Time 0.693 (0.777)	Data 0.001 (0.068)	Loss 0.984 (0.314)
Epoch: [37][60/200]	Time 0.697 (0.750)	Data 0.001 (0.046)	Loss 1.101 (0.573)
Epoch: [37][80/200]	Time 0.695 (0.757)	Data 0.001 (0.054)	Loss 0.929 (0.707)
Epoch: [37][100/200]	Time 0.700 (0.748)	Data 0.000 (0.043)	Loss 1.185 (0.788)
Epoch: [37][120/200]	Time 0.697 (0.757)	Data 0.001 (0.050)	Loss 1.396 (0.843)
Epoch: [37][140/200]	Time 0.700 (0.763)	Data 0.001 (0.055)	Loss 1.102 (0.886)
Epoch: [37][160/200]	Time 0.701 (0.755)	Data 0.001 (0.048)	Loss 1.270 (0.922)
Epoch: [37][180/200]	Time 0.695 (0.761)	Data 0.001 (0.053)	Loss 1.211 (0.939)
Epoch: [37][200/200]	Time 0.698 (0.755)	Data 0.000 (0.048)	Loss 1.172 (0.962)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.233 (0.267)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.229 (0.252)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.27534556388855
==> Statistics for epoch 38: 1093 clusters
Epoch: [38][20/200]	Time 0.694 (0.745)	Data 0.001 (0.052)	Loss 0.170 (0.201)
Epoch: [38][40/200]	Time 0.695 (0.766)	Data 0.001 (0.069)	Loss 0.951 (0.318)
Epoch: [38][60/200]	Time 0.694 (0.747)	Data 0.001 (0.046)	Loss 0.860 (0.576)
Epoch: [38][80/200]	Time 0.695 (0.761)	Data 0.001 (0.058)	Loss 1.498 (0.722)
Epoch: [38][100/200]	Time 0.697 (0.750)	Data 0.000 (0.046)	Loss 1.409 (0.788)
Epoch: [38][120/200]	Time 0.701 (0.758)	Data 0.002 (0.053)	Loss 1.299 (0.846)
Epoch: [38][140/200]	Time 0.693 (0.763)	Data 0.001 (0.058)	Loss 0.895 (0.885)
Epoch: [38][160/200]	Time 0.701 (0.756)	Data 0.001 (0.051)	Loss 1.013 (0.905)
Epoch: [38][180/200]	Time 0.703 (0.761)	Data 0.001 (0.054)	Loss 0.880 (0.935)
Epoch: [38][200/200]	Time 0.693 (0.755)	Data 0.000 (0.049)	Loss 1.285 (0.951)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.231 (0.264)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.231 (0.251)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.91041874885559
==> Statistics for epoch 39: 1095 clusters
Epoch: [39][20/200]	Time 0.689 (0.753)	Data 0.001 (0.051)	Loss 0.224 (0.194)
Epoch: [39][40/200]	Time 0.691 (0.773)	Data 0.001 (0.069)	Loss 1.288 (0.327)
Epoch: [39][60/200]	Time 0.695 (0.750)	Data 0.001 (0.046)	Loss 1.101 (0.577)
Epoch: [39][80/200]	Time 0.707 (0.760)	Data 0.001 (0.056)	Loss 1.022 (0.703)
Epoch: [39][100/200]	Time 0.697 (0.749)	Data 0.000 (0.045)	Loss 1.169 (0.780)
Epoch: [39][120/200]	Time 0.692 (0.756)	Data 0.001 (0.052)	Loss 1.124 (0.844)
Epoch: [39][140/200]	Time 0.710 (0.761)	Data 0.001 (0.056)	Loss 1.023 (0.874)
Epoch: [39][160/200]	Time 0.697 (0.754)	Data 0.001 (0.049)	Loss 1.152 (0.903)
Epoch: [39][180/200]	Time 0.693 (0.758)	Data 0.001 (0.054)	Loss 0.964 (0.931)
Epoch: [39][200/200]	Time 0.698 (0.752)	Data 0.000 (0.048)	Loss 1.042 (0.953)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.228 (0.262)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.227 (0.248)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.62936353683472
==> Statistics for epoch 40: 1094 clusters
Epoch: [40][20/200]	Time 0.691 (0.753)	Data 0.001 (0.054)	Loss 0.185 (0.212)
Epoch: [40][40/200]	Time 0.691 (0.775)	Data 0.001 (0.073)	Loss 1.090 (0.316)
Epoch: [40][60/200]	Time 0.693 (0.749)	Data 0.001 (0.049)	Loss 1.093 (0.591)
Epoch: [40][80/200]	Time 0.693 (0.762)	Data 0.001 (0.060)	Loss 1.146 (0.731)
Epoch: [40][100/200]	Time 0.700 (0.751)	Data 0.000 (0.048)	Loss 0.743 (0.796)
Epoch: [40][120/200]	Time 0.695 (0.757)	Data 0.001 (0.053)	Loss 1.330 (0.859)
Epoch: [40][140/200]	Time 0.694 (0.762)	Data 0.001 (0.058)	Loss 0.909 (0.899)
Epoch: [40][160/200]	Time 0.700 (0.755)	Data 0.001 (0.051)	Loss 0.948 (0.933)
Epoch: [40][180/200]	Time 0.695 (0.759)	Data 0.001 (0.055)	Loss 0.932 (0.954)
Epoch: [40][200/200]	Time 0.696 (0.753)	Data 0.000 (0.050)	Loss 0.952 (0.978)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.232 (0.263)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.232 (0.250)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.32293200492859
==> Statistics for epoch 41: 1098 clusters
Epoch: [41][20/200]	Time 0.696 (0.754)	Data 0.001 (0.052)	Loss 0.276 (0.192)
Epoch: [41][40/200]	Time 0.693 (0.766)	Data 0.001 (0.068)	Loss 0.923 (0.311)
Epoch: [41][60/200]	Time 0.707 (0.746)	Data 0.001 (0.046)	Loss 1.137 (0.571)
Epoch: [41][80/200]	Time 0.694 (0.756)	Data 0.001 (0.057)	Loss 1.193 (0.696)
Epoch: [41][100/200]	Time 0.694 (0.746)	Data 0.000 (0.045)	Loss 1.030 (0.778)
Epoch: [41][120/200]	Time 0.695 (0.752)	Data 0.001 (0.052)	Loss 0.779 (0.831)
Epoch: [41][140/200]	Time 0.700 (0.757)	Data 0.001 (0.058)	Loss 0.993 (0.885)
Epoch: [41][160/200]	Time 0.699 (0.751)	Data 0.001 (0.051)	Loss 1.340 (0.916)
Epoch: [41][180/200]	Time 0.700 (0.755)	Data 0.001 (0.054)	Loss 0.897 (0.936)
Epoch: [41][200/200]	Time 0.697 (0.750)	Data 0.000 (0.049)	Loss 1.059 (0.958)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.228 (0.265)	Data 0.001 (0.026)	
Extract Features: [100/128]	Time 0.229 (0.250)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.698734521865845
==> Statistics for epoch 42: 1092 clusters
Epoch: [42][20/200]	Time 0.695 (0.746)	Data 0.001 (0.051)	Loss 0.102 (0.190)
Epoch: [42][40/200]	Time 0.689 (0.759)	Data 0.001 (0.066)	Loss 1.641 (0.327)
Epoch: [42][60/200]	Time 0.691 (0.737)	Data 0.001 (0.044)	Loss 0.991 (0.583)
Epoch: [42][80/200]	Time 0.695 (0.748)	Data 0.001 (0.055)	Loss 1.153 (0.719)
Epoch: [42][100/200]	Time 0.692 (0.740)	Data 0.000 (0.044)	Loss 1.420 (0.794)
Epoch: [42][120/200]	Time 0.695 (0.748)	Data 0.001 (0.051)	Loss 1.004 (0.853)
Epoch: [42][140/200]	Time 0.697 (0.753)	Data 0.002 (0.055)	Loss 1.367 (0.891)
Epoch: [42][160/200]	Time 0.808 (0.748)	Data 0.001 (0.048)	Loss 1.070 (0.920)
Epoch: [42][180/200]	Time 0.695 (0.752)	Data 0.001 (0.052)	Loss 1.244 (0.940)
Epoch: [42][200/200]	Time 0.696 (0.747)	Data 0.000 (0.046)	Loss 1.256 (0.956)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.230 (0.260)	Data 0.000 (0.025)	
Extract Features: [100/128]	Time 0.227 (0.250)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.96769881248474
==> Statistics for epoch 43: 1093 clusters
Epoch: [43][20/200]	Time 0.696 (0.749)	Data 0.001 (0.057)	Loss 0.153 (0.179)
Epoch: [43][40/200]	Time 0.704 (0.762)	Data 0.001 (0.066)	Loss 1.107 (0.303)
Epoch: [43][60/200]	Time 0.694 (0.744)	Data 0.001 (0.045)	Loss 1.258 (0.572)
Epoch: [43][80/200]	Time 0.698 (0.755)	Data 0.001 (0.055)	Loss 1.123 (0.714)
Epoch: [43][100/200]	Time 0.701 (0.747)	Data 0.000 (0.044)	Loss 0.897 (0.775)
Epoch: [43][120/200]	Time 0.703 (0.755)	Data 0.001 (0.051)	Loss 0.955 (0.828)
Epoch: [43][140/200]	Time 0.701 (0.761)	Data 0.001 (0.055)	Loss 0.962 (0.868)
Epoch: [43][160/200]	Time 0.699 (0.754)	Data 0.001 (0.049)	Loss 1.371 (0.905)
Epoch: [43][180/200]	Time 0.700 (0.758)	Data 0.001 (0.053)	Loss 1.126 (0.922)
Epoch: [43][200/200]	Time 0.795 (0.753)	Data 0.000 (0.047)	Loss 1.255 (0.946)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.232 (0.263)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.229 (0.250)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.90437126159668
==> Statistics for epoch 44: 1101 clusters
Epoch: [44][20/200]	Time 0.694 (0.756)	Data 0.001 (0.056)	Loss 0.257 (0.197)
Epoch: [44][40/200]	Time 0.691 (0.772)	Data 0.001 (0.070)	Loss 1.059 (0.308)
Epoch: [44][60/200]	Time 0.693 (0.749)	Data 0.001 (0.047)	Loss 0.830 (0.564)
Epoch: [44][80/200]	Time 0.694 (0.758)	Data 0.001 (0.056)	Loss 1.306 (0.692)
Epoch: [44][100/200]	Time 0.693 (0.747)	Data 0.000 (0.045)	Loss 1.095 (0.771)
Epoch: [44][120/200]	Time 0.697 (0.753)	Data 0.001 (0.052)	Loss 1.006 (0.831)
Epoch: [44][140/200]	Time 0.699 (0.758)	Data 0.001 (0.056)	Loss 1.093 (0.878)
Epoch: [44][160/200]	Time 0.701 (0.751)	Data 0.002 (0.049)	Loss 0.683 (0.916)
Epoch: [44][180/200]	Time 0.715 (0.755)	Data 0.001 (0.054)	Loss 1.199 (0.947)
Epoch: [44][200/200]	Time 0.692 (0.749)	Data 0.000 (0.049)	Loss 1.376 (0.968)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.374 (0.263)	Data 0.001 (0.026)	
Extract Features: [100/128]	Time 0.231 (0.247)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.99321794509888
==> Statistics for epoch 45: 1106 clusters
Epoch: [45][20/200]	Time 0.793 (0.754)	Data 0.001 (0.052)	Loss 0.257 (0.215)
Epoch: [45][40/200]	Time 0.699 (0.767)	Data 0.001 (0.068)	Loss 1.232 (0.343)
Epoch: [45][60/200]	Time 0.692 (0.744)	Data 0.001 (0.045)	Loss 1.248 (0.574)
Epoch: [45][80/200]	Time 0.853 (0.754)	Data 0.001 (0.055)	Loss 0.945 (0.737)
Epoch: [45][100/200]	Time 0.690 (0.742)	Data 0.000 (0.044)	Loss 0.900 (0.806)
Epoch: [45][120/200]	Time 0.695 (0.750)	Data 0.002 (0.051)	Loss 1.111 (0.864)
Epoch: [45][140/200]	Time 0.693 (0.755)	Data 0.001 (0.056)	Loss 0.720 (0.901)
Epoch: [45][160/200]	Time 0.693 (0.748)	Data 0.001 (0.049)	Loss 1.091 (0.935)
Epoch: [45][180/200]	Time 0.700 (0.751)	Data 0.001 (0.053)	Loss 0.879 (0.956)
Epoch: [45][200/200]	Time 0.697 (0.746)	Data 0.000 (0.048)	Loss 1.003 (0.975)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.228 (0.263)	Data 0.001 (0.027)	
Extract Features: [100/128]	Time 0.241 (0.250)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.00205135345459
==> Statistics for epoch 46: 1100 clusters
Epoch: [46][20/200]	Time 0.690 (0.756)	Data 0.001 (0.058)	Loss 0.272 (0.183)
Epoch: [46][40/200]	Time 0.693 (0.766)	Data 0.001 (0.069)	Loss 1.251 (0.292)
Epoch: [46][60/200]	Time 0.696 (0.744)	Data 0.001 (0.047)	Loss 1.042 (0.562)
Epoch: [46][80/200]	Time 0.712 (0.751)	Data 0.001 (0.054)	Loss 1.193 (0.689)
Epoch: [46][100/200]	Time 0.694 (0.740)	Data 0.000 (0.043)	Loss 1.372 (0.773)
Epoch: [46][120/200]	Time 0.696 (0.750)	Data 0.001 (0.050)	Loss 0.720 (0.843)
Epoch: [46][140/200]	Time 0.700 (0.753)	Data 0.001 (0.054)	Loss 1.121 (0.877)
Epoch: [46][160/200]	Time 0.696 (0.746)	Data 0.001 (0.047)	Loss 1.186 (0.911)
Epoch: [46][180/200]	Time 0.696 (0.752)	Data 0.001 (0.052)	Loss 0.730 (0.928)
Epoch: [46][200/200]	Time 0.698 (0.748)	Data 0.000 (0.047)	Loss 1.618 (0.950)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.234 (0.268)	Data 0.001 (0.031)	
Extract Features: [100/128]	Time 0.233 (0.253)	Data 0.000 (0.016)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.94428896903992
==> Statistics for epoch 47: 1100 clusters
Epoch: [47][20/200]	Time 0.689 (0.749)	Data 0.001 (0.056)	Loss 0.093 (0.193)
Epoch: [47][40/200]	Time 0.691 (0.762)	Data 0.001 (0.069)	Loss 0.894 (0.303)
Epoch: [47][60/200]	Time 0.693 (0.739)	Data 0.001 (0.046)	Loss 1.035 (0.560)
Epoch: [47][80/200]	Time 0.693 (0.750)	Data 0.001 (0.054)	Loss 0.692 (0.714)
Epoch: [47][100/200]	Time 0.695 (0.742)	Data 0.000 (0.043)	Loss 1.145 (0.797)
Epoch: [47][120/200]	Time 0.698 (0.749)	Data 0.001 (0.049)	Loss 1.045 (0.848)
Epoch: [47][140/200]	Time 0.701 (0.757)	Data 0.002 (0.055)	Loss 0.932 (0.892)
Epoch: [47][160/200]	Time 0.698 (0.751)	Data 0.001 (0.049)	Loss 1.282 (0.911)
Epoch: [47][180/200]	Time 0.695 (0.756)	Data 0.001 (0.052)	Loss 0.762 (0.937)
Epoch: [47][200/200]	Time 0.696 (0.751)	Data 0.000 (0.047)	Loss 0.884 (0.957)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.233 (0.264)	Data 0.001 (0.029)	
Extract Features: [100/128]	Time 0.230 (0.250)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.19491958618164
==> Statistics for epoch 48: 1096 clusters
Epoch: [48][20/200]	Time 0.696 (0.751)	Data 0.001 (0.049)	Loss 0.178 (0.213)
Epoch: [48][40/200]	Time 0.692 (0.767)	Data 0.001 (0.068)	Loss 0.793 (0.318)
Epoch: [48][60/200]	Time 0.696 (0.744)	Data 0.001 (0.046)	Loss 1.004 (0.573)
Epoch: [48][80/200]	Time 0.705 (0.756)	Data 0.001 (0.057)	Loss 1.404 (0.704)
Epoch: [48][100/200]	Time 0.697 (0.747)	Data 0.000 (0.046)	Loss 1.037 (0.780)
Epoch: [48][120/200]	Time 0.698 (0.756)	Data 0.001 (0.053)	Loss 1.116 (0.854)
Epoch: [48][140/200]	Time 0.699 (0.761)	Data 0.001 (0.058)	Loss 0.933 (0.892)
Epoch: [48][160/200]	Time 0.704 (0.755)	Data 0.001 (0.051)	Loss 1.406 (0.917)
Epoch: [48][180/200]	Time 0.701 (0.760)	Data 0.001 (0.055)	Loss 0.710 (0.932)
Epoch: [48][200/200]	Time 0.698 (0.754)	Data 0.000 (0.050)	Loss 0.648 (0.946)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.341 (0.264)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.229 (0.250)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.02144193649292
==> Statistics for epoch 49: 1099 clusters
Epoch: [49][20/200]	Time 0.697 (0.762)	Data 0.001 (0.053)	Loss 0.247 (0.197)
Epoch: [49][40/200]	Time 0.692 (0.774)	Data 0.001 (0.068)	Loss 0.968 (0.298)
Epoch: [49][60/200]	Time 0.693 (0.750)	Data 0.001 (0.045)	Loss 1.107 (0.579)
Epoch: [49][80/200]	Time 0.698 (0.759)	Data 0.001 (0.055)	Loss 1.553 (0.702)
Epoch: [49][100/200]	Time 0.693 (0.747)	Data 0.000 (0.044)	Loss 0.936 (0.770)
Epoch: [49][120/200]	Time 0.696 (0.752)	Data 0.001 (0.050)	Loss 1.278 (0.826)
Epoch: [49][140/200]	Time 0.694 (0.757)	Data 0.001 (0.055)	Loss 0.975 (0.872)
Epoch: [49][160/200]	Time 0.694 (0.750)	Data 0.001 (0.048)	Loss 1.373 (0.899)
Epoch: [49][180/200]	Time 0.693 (0.753)	Data 0.001 (0.052)	Loss 1.065 (0.918)
Epoch: [49][200/200]	Time 0.691 (0.747)	Data 0.000 (0.047)	Loss 1.227 (0.940)
Extract Features: [50/367]	Time 0.227 (0.264)	Data 0.000 (0.028)	
Extract Features: [100/367]	Time 0.233 (0.249)	Data 0.000 (0.014)	
Extract Features: [150/367]	Time 0.233 (0.243)	Data 0.000 (0.010)	
Extract Features: [200/367]	Time 0.226 (0.243)	Data 0.000 (0.007)	
Extract Features: [250/367]	Time 0.227 (0.243)	Data 0.000 (0.006)	
Extract Features: [300/367]	Time 0.235 (0.244)	Data 0.000 (0.005)	
Extract Features: [350/367]	Time 0.227 (0.244)	Data 0.000 (0.005)	
Mean AP: 68.8%

 * Finished epoch  49  model mAP: 68.8%  best: 68.8% *

==> Test with the best model:
=> Loaded checkpoint 'log/msmt17/resnet152_cion/model_best.pth.tar'
Extract Features: [50/367]	Time 0.228 (0.260)	Data 0.000 (0.028)	
Extract Features: [100/367]	Time 0.226 (0.245)	Data 0.000 (0.014)	
Extract Features: [150/367]	Time 0.226 (0.241)	Data 0.000 (0.010)	
Extract Features: [200/367]	Time 0.353 (0.239)	Data 0.000 (0.007)	
Extract Features: [250/367]	Time 0.225 (0.237)	Data 0.000 (0.006)	
Extract Features: [300/367]	Time 0.227 (0.236)	Data 0.000 (0.005)	
Extract Features: [350/367]	Time 0.227 (0.235)	Data 0.000 (0.004)	
Mean AP: 68.8%
CMC Scores:
  top-1          87.6%
  top-5          93.1%
  top-10         94.5%
Total running time:  3:43:22.783899
