==========
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_ibn152a', pretrained_path='/home/ma-user/work/Projects/ReIDNets_Checkpoints_TransReID/ResNet152_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/resnet152_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 0.370 (0.479)	Data 0.000 (0.022)	
Extract Features: [100/128]	Time 0.242 (0.375)	Data 0.000 (0.011)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.116682052612305
Clustering criterion: eps: 0.700
==> Statistics for epoch 0: 891 clusters
Epoch: [0][20/200]	Time 0.732 (1.192)	Data 0.000 (0.051)	Loss 2.350 (2.495)
Epoch: [0][40/200]	Time 0.747 (1.006)	Data 0.002 (0.064)	Loss 3.102 (2.681)
Epoch: [0][60/200]	Time 0.754 (0.944)	Data 0.001 (0.068)	Loss 2.169 (2.823)
Epoch: [0][80/200]	Time 0.739 (0.896)	Data 0.000 (0.051)	Loss 2.710 (2.696)
Epoch: [0][100/200]	Time 0.746 (0.884)	Data 0.001 (0.058)	Loss 2.027 (2.608)
Epoch: [0][120/200]	Time 0.744 (0.876)	Data 0.001 (0.061)	Loss 1.664 (2.514)
Epoch: [0][140/200]	Time 0.742 (0.870)	Data 0.001 (0.064)	Loss 1.736 (2.432)
Epoch: [0][160/200]	Time 0.740 (0.856)	Data 0.000 (0.056)	Loss 2.083 (2.380)
Epoch: [0][180/200]	Time 0.745 (0.853)	Data 0.001 (0.059)	Loss 1.557 (2.328)
Epoch: [0][200/200]	Time 0.743 (0.851)	Data 0.000 (0.062)	Loss 1.283 (2.282)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.244 (0.282)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.424 (0.274)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.6416654586792
==> Statistics for epoch 1: 965 clusters
Epoch: [1][20/200]	Time 0.730 (0.788)	Data 0.001 (0.049)	Loss 0.841 (0.661)
Epoch: [1][40/200]	Time 0.745 (0.803)	Data 0.001 (0.061)	Loss 1.889 (0.929)
Epoch: [1][60/200]	Time 0.741 (0.786)	Data 0.000 (0.041)	Loss 1.827 (1.220)
Epoch: [1][80/200]	Time 0.741 (0.795)	Data 0.001 (0.050)	Loss 1.341 (1.351)
Epoch: [1][100/200]	Time 0.734 (0.800)	Data 0.001 (0.054)	Loss 1.317 (1.394)
Epoch: [1][120/200]	Time 0.737 (0.791)	Data 0.000 (0.045)	Loss 1.512 (1.411)
Epoch: [1][140/200]	Time 0.744 (0.795)	Data 0.001 (0.050)	Loss 1.967 (1.428)
Epoch: [1][160/200]	Time 0.747 (0.800)	Data 0.001 (0.054)	Loss 1.359 (1.432)
Epoch: [1][180/200]	Time 0.825 (0.794)	Data 0.000 (0.048)	Loss 1.504 (1.432)
Epoch: [1][200/200]	Time 0.746 (0.797)	Data 0.001 (0.050)	Loss 1.272 (1.428)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.245 (0.285)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.248 (0.269)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.83113408088684
==> Statistics for epoch 2: 1003 clusters
Epoch: [2][20/200]	Time 0.734 (0.790)	Data 0.001 (0.054)	Loss 0.421 (0.466)
Epoch: [2][40/200]	Time 0.738 (0.807)	Data 0.001 (0.067)	Loss 1.480 (0.707)
Epoch: [2][60/200]	Time 0.736 (0.786)	Data 0.000 (0.045)	Loss 1.942 (1.022)
Epoch: [2][80/200]	Time 0.744 (0.796)	Data 0.001 (0.053)	Loss 1.634 (1.167)
Epoch: [2][100/200]	Time 0.742 (0.802)	Data 0.001 (0.058)	Loss 1.337 (1.253)
Epoch: [2][120/200]	Time 0.745 (0.793)	Data 0.000 (0.049)	Loss 2.117 (1.316)
Epoch: [2][140/200]	Time 0.743 (0.800)	Data 0.001 (0.055)	Loss 1.972 (1.347)
Epoch: [2][160/200]	Time 0.740 (0.803)	Data 0.001 (0.058)	Loss 1.296 (1.375)
Epoch: [2][180/200]	Time 0.736 (0.797)	Data 0.000 (0.051)	Loss 1.314 (1.395)
Epoch: [2][200/200]	Time 0.744 (0.801)	Data 0.001 (0.055)	Loss 1.615 (1.415)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.244 (0.286)	Data 0.000 (0.029)	
Extract Features: [100/128]	Time 0.248 (0.270)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.27294850349426
==> Statistics for epoch 3: 1018 clusters
Epoch: [3][20/200]	Time 0.738 (0.793)	Data 0.001 (0.049)	Loss 0.244 (0.389)
Epoch: [3][40/200]	Time 0.736 (0.808)	Data 0.001 (0.063)	Loss 1.832 (0.698)
Epoch: [3][60/200]	Time 0.743 (0.789)	Data 0.000 (0.042)	Loss 1.431 (0.993)
Epoch: [3][80/200]	Time 0.739 (0.797)	Data 0.001 (0.050)	Loss 1.717 (1.162)
Epoch: [3][100/200]	Time 0.737 (0.801)	Data 0.001 (0.055)	Loss 1.993 (1.262)
Epoch: [3][120/200]	Time 0.743 (0.794)	Data 0.000 (0.046)	Loss 1.944 (1.318)
Epoch: [3][140/200]	Time 0.743 (0.800)	Data 0.001 (0.051)	Loss 1.055 (1.369)
Epoch: [3][160/200]	Time 0.743 (0.803)	Data 0.001 (0.054)	Loss 1.712 (1.389)
Epoch: [3][180/200]	Time 0.740 (0.798)	Data 0.000 (0.048)	Loss 1.286 (1.409)
Epoch: [3][200/200]	Time 0.740 (0.801)	Data 0.001 (0.050)	Loss 1.781 (1.421)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.244 (0.277)	Data 0.000 (0.023)	
Extract Features: [100/128]	Time 0.250 (0.266)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.078797340393066
==> Statistics for epoch 4: 1024 clusters
Epoch: [4][20/200]	Time 0.734 (0.797)	Data 0.001 (0.048)	Loss 0.594 (0.441)
Epoch: [4][40/200]	Time 0.740 (0.814)	Data 0.001 (0.067)	Loss 1.734 (0.659)
Epoch: [4][60/200]	Time 0.738 (0.792)	Data 0.000 (0.045)	Loss 1.918 (1.017)
Epoch: [4][80/200]	Time 0.745 (0.806)	Data 0.001 (0.057)	Loss 2.016 (1.171)
Epoch: [4][100/200]	Time 0.741 (0.813)	Data 0.001 (0.064)	Loss 1.991 (1.260)
Epoch: [4][120/200]	Time 0.746 (0.802)	Data 0.001 (0.053)	Loss 2.213 (1.328)
Epoch: [4][140/200]	Time 0.744 (0.806)	Data 0.001 (0.058)	Loss 1.300 (1.359)
Epoch: [4][160/200]	Time 0.738 (0.799)	Data 0.000 (0.051)	Loss 1.818 (1.386)
Epoch: [4][180/200]	Time 0.748 (0.803)	Data 0.001 (0.055)	Loss 1.068 (1.409)
Epoch: [4][200/200]	Time 0.739 (0.807)	Data 0.001 (0.059)	Loss 1.593 (1.421)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.246 (0.282)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.246 (0.269)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.56385636329651
==> Statistics for epoch 5: 977 clusters
Epoch: [5][20/200]	Time 0.849 (0.811)	Data 0.001 (0.061)	Loss 0.225 (0.341)
Epoch: [5][40/200]	Time 0.740 (0.821)	Data 0.001 (0.075)	Loss 1.128 (0.588)
Epoch: [5][60/200]	Time 0.737 (0.796)	Data 0.000 (0.050)	Loss 1.317 (0.921)
Epoch: [5][80/200]	Time 0.741 (0.809)	Data 0.001 (0.060)	Loss 1.404 (1.070)
Epoch: [5][100/200]	Time 0.736 (0.812)	Data 0.001 (0.065)	Loss 1.776 (1.184)
Epoch: [5][120/200]	Time 0.846 (0.802)	Data 0.000 (0.054)	Loss 1.730 (1.235)
Epoch: [5][140/200]	Time 0.746 (0.806)	Data 0.001 (0.059)	Loss 1.367 (1.269)
Epoch: [5][160/200]	Time 0.746 (0.811)	Data 0.001 (0.062)	Loss 1.899 (1.303)
Epoch: [5][180/200]	Time 0.739 (0.803)	Data 0.000 (0.055)	Loss 1.439 (1.314)
Epoch: [5][200/200]	Time 0.740 (0.806)	Data 0.001 (0.058)	Loss 0.979 (1.335)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.244 (0.286)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.247 (0.271)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.84079432487488
==> Statistics for epoch 6: 995 clusters
Epoch: [6][20/200]	Time 0.736 (0.807)	Data 0.001 (0.058)	Loss 0.370 (0.322)
Epoch: [6][40/200]	Time 0.743 (0.823)	Data 0.005 (0.074)	Loss 1.552 (0.575)
Epoch: [6][60/200]	Time 0.739 (0.798)	Data 0.000 (0.049)	Loss 1.436 (0.881)
Epoch: [6][80/200]	Time 0.739 (0.809)	Data 0.001 (0.060)	Loss 1.443 (1.042)
Epoch: [6][100/200]	Time 0.744 (0.815)	Data 0.001 (0.066)	Loss 1.194 (1.118)
Epoch: [6][120/200]	Time 0.740 (0.804)	Data 0.000 (0.055)	Loss 1.485 (1.192)
Epoch: [6][140/200]	Time 0.764 (0.810)	Data 0.001 (0.060)	Loss 1.821 (1.231)
Epoch: [6][160/200]	Time 0.739 (0.813)	Data 0.001 (0.064)	Loss 1.486 (1.252)
Epoch: [6][180/200]	Time 0.740 (0.807)	Data 0.000 (0.057)	Loss 1.106 (1.275)
Epoch: [6][200/200]	Time 0.757 (0.810)	Data 0.001 (0.060)	Loss 1.830 (1.303)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.246 (0.284)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.400 (0.271)	Data 0.001 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.18966627120972
==> Statistics for epoch 7: 932 clusters
Epoch: [7][20/200]	Time 0.736 (0.799)	Data 0.001 (0.053)	Loss 0.430 (0.400)
Epoch: [7][40/200]	Time 0.740 (0.812)	Data 0.001 (0.069)	Loss 0.961 (0.651)
Epoch: [7][60/200]	Time 0.747 (0.821)	Data 0.001 (0.076)	Loss 0.977 (0.910)
Epoch: [7][80/200]	Time 0.734 (0.802)	Data 0.000 (0.057)	Loss 1.135 (0.982)
Epoch: [7][100/200]	Time 0.748 (0.810)	Data 0.003 (0.063)	Loss 1.300 (1.058)
Epoch: [7][120/200]	Time 0.739 (0.814)	Data 0.001 (0.067)	Loss 1.416 (1.095)
Epoch: [7][140/200]	Time 0.741 (0.805)	Data 0.000 (0.058)	Loss 1.112 (1.118)
Epoch: [7][160/200]	Time 0.740 (0.809)	Data 0.001 (0.061)	Loss 1.694 (1.134)
Epoch: [7][180/200]	Time 0.740 (0.812)	Data 0.001 (0.064)	Loss 1.288 (1.156)
Epoch: [7][200/200]	Time 0.844 (0.806)	Data 0.000 (0.058)	Loss 1.211 (1.170)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.245 (0.280)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.245 (0.266)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.98474931716919
==> Statistics for epoch 8: 997 clusters
Epoch: [8][20/200]	Time 0.737 (0.793)	Data 0.001 (0.049)	Loss 0.231 (0.292)
Epoch: [8][40/200]	Time 0.736 (0.810)	Data 0.001 (0.065)	Loss 1.071 (0.523)
Epoch: [8][60/200]	Time 0.734 (0.789)	Data 0.000 (0.044)	Loss 1.445 (0.799)
Epoch: [8][80/200]	Time 0.740 (0.799)	Data 0.001 (0.051)	Loss 1.201 (0.920)
Epoch: [8][100/200]	Time 0.741 (0.805)	Data 0.001 (0.056)	Loss 1.599 (1.005)
Epoch: [8][120/200]	Time 0.740 (0.795)	Data 0.000 (0.047)	Loss 1.098 (1.061)
Epoch: [8][140/200]	Time 0.741 (0.799)	Data 0.001 (0.051)	Loss 1.227 (1.095)
Epoch: [8][160/200]	Time 0.753 (0.803)	Data 0.001 (0.056)	Loss 1.429 (1.126)
Epoch: [8][180/200]	Time 0.744 (0.798)	Data 0.000 (0.050)	Loss 1.441 (1.144)
Epoch: [8][200/200]	Time 0.741 (0.801)	Data 0.001 (0.053)	Loss 1.051 (1.159)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.252 (0.279)	Data 0.000 (0.024)	
Extract Features: [100/128]	Time 0.245 (0.267)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.56402611732483
==> Statistics for epoch 9: 974 clusters
Epoch: [9][20/200]	Time 0.736 (0.804)	Data 0.001 (0.049)	Loss 0.451 (0.289)
Epoch: [9][40/200]	Time 0.869 (0.820)	Data 0.001 (0.069)	Loss 1.222 (0.526)
Epoch: [9][60/200]	Time 0.740 (0.796)	Data 0.000 (0.046)	Loss 1.869 (0.785)
Epoch: [9][80/200]	Time 0.741 (0.805)	Data 0.001 (0.056)	Loss 1.146 (0.911)
Epoch: [9][100/200]	Time 0.740 (0.813)	Data 0.001 (0.063)	Loss 1.330 (0.967)
Epoch: [9][120/200]	Time 0.737 (0.802)	Data 0.000 (0.053)	Loss 1.175 (1.022)
Epoch: [9][140/200]	Time 0.740 (0.806)	Data 0.001 (0.057)	Loss 0.902 (1.063)
Epoch: [9][160/200]	Time 0.736 (0.808)	Data 0.001 (0.060)	Loss 1.521 (1.090)
Epoch: [9][180/200]	Time 0.740 (0.801)	Data 0.000 (0.053)	Loss 1.431 (1.107)
Epoch: [9][200/200]	Time 0.751 (0.805)	Data 0.001 (0.057)	Loss 1.056 (1.114)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.244 (0.282)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.247 (0.268)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.04329490661621
==> Statistics for epoch 10: 1030 clusters
Epoch: [10][20/200]	Time 0.737 (0.797)	Data 0.001 (0.052)	Loss 0.198 (0.261)
Epoch: [10][40/200]	Time 0.744 (0.814)	Data 0.001 (0.070)	Loss 1.578 (0.477)
Epoch: [10][60/200]	Time 0.738 (0.793)	Data 0.000 (0.047)	Loss 1.351 (0.763)
Epoch: [10][80/200]	Time 0.739 (0.801)	Data 0.000 (0.054)	Loss 1.553 (0.900)
Epoch: [10][100/200]	Time 0.736 (0.805)	Data 0.001 (0.058)	Loss 0.997 (0.984)
Epoch: [10][120/200]	Time 0.738 (0.795)	Data 0.001 (0.049)	Loss 1.658 (1.046)
Epoch: [10][140/200]	Time 0.738 (0.800)	Data 0.001 (0.053)	Loss 1.179 (1.086)
Epoch: [10][160/200]	Time 0.733 (0.793)	Data 0.000 (0.047)	Loss 1.396 (1.114)
Epoch: [10][180/200]	Time 0.745 (0.797)	Data 0.001 (0.050)	Loss 1.336 (1.134)
Epoch: [10][200/200]	Time 0.743 (0.801)	Data 0.001 (0.053)	Loss 1.744 (1.155)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.243 (0.285)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.248 (0.271)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.112207889556885
==> Statistics for epoch 11: 995 clusters
Epoch: [11][20/200]	Time 0.737 (0.802)	Data 0.001 (0.053)	Loss 0.170 (0.244)
Epoch: [11][40/200]	Time 0.738 (0.817)	Data 0.001 (0.068)	Loss 0.900 (0.441)
Epoch: [11][60/200]	Time 0.739 (0.795)	Data 0.000 (0.046)	Loss 1.151 (0.742)
Epoch: [11][80/200]	Time 0.738 (0.806)	Data 0.001 (0.054)	Loss 1.081 (0.868)
Epoch: [11][100/200]	Time 0.740 (0.809)	Data 0.001 (0.060)	Loss 1.101 (0.954)
Epoch: [11][120/200]	Time 0.740 (0.799)	Data 0.000 (0.050)	Loss 1.597 (1.019)
Epoch: [11][140/200]	Time 0.843 (0.804)	Data 0.001 (0.055)	Loss 1.893 (1.046)
Epoch: [11][160/200]	Time 0.741 (0.808)	Data 0.001 (0.059)	Loss 1.763 (1.086)
Epoch: [11][180/200]	Time 0.740 (0.801)	Data 0.000 (0.053)	Loss 1.650 (1.107)
Epoch: [11][200/200]	Time 0.738 (0.803)	Data 0.001 (0.055)	Loss 1.298 (1.117)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.243 (0.278)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.246 (0.266)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.446197271347046
==> Statistics for epoch 12: 1019 clusters
Epoch: [12][20/200]	Time 0.859 (0.806)	Data 0.001 (0.053)	Loss 0.320 (0.270)
Epoch: [12][40/200]	Time 0.741 (0.822)	Data 0.001 (0.072)	Loss 1.273 (0.464)
Epoch: [12][60/200]	Time 0.741 (0.795)	Data 0.000 (0.048)	Loss 1.150 (0.718)
Epoch: [12][80/200]	Time 0.738 (0.804)	Data 0.001 (0.057)	Loss 2.266 (0.852)
Epoch: [12][100/200]	Time 0.743 (0.811)	Data 0.001 (0.063)	Loss 1.376 (0.914)
Epoch: [12][120/200]	Time 0.740 (0.800)	Data 0.000 (0.053)	Loss 1.118 (0.960)
Epoch: [12][140/200]	Time 0.743 (0.805)	Data 0.001 (0.057)	Loss 1.147 (0.992)
Epoch: [12][160/200]	Time 0.738 (0.807)	Data 0.001 (0.060)	Loss 1.424 (1.029)
Epoch: [12][180/200]	Time 0.741 (0.802)	Data 0.000 (0.054)	Loss 1.153 (1.052)
Epoch: [12][200/200]	Time 0.748 (0.804)	Data 0.001 (0.056)	Loss 0.881 (1.069)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.245 (0.285)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.243 (0.270)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.91382884979248
==> Statistics for epoch 13: 1037 clusters
Epoch: [13][20/200]	Time 0.735 (0.788)	Data 0.001 (0.052)	Loss 0.217 (0.268)
Epoch: [13][40/200]	Time 0.737 (0.803)	Data 0.001 (0.062)	Loss 1.334 (0.461)
Epoch: [13][60/200]	Time 0.737 (0.783)	Data 0.000 (0.041)	Loss 1.543 (0.746)
Epoch: [13][80/200]	Time 0.754 (0.793)	Data 0.001 (0.050)	Loss 1.209 (0.875)
Epoch: [13][100/200]	Time 0.737 (0.801)	Data 0.001 (0.056)	Loss 1.167 (0.932)
Epoch: [13][120/200]	Time 0.737 (0.791)	Data 0.001 (0.047)	Loss 1.182 (0.986)
Epoch: [13][140/200]	Time 0.739 (0.796)	Data 0.001 (0.051)	Loss 1.319 (1.020)
Epoch: [13][160/200]	Time 0.738 (0.789)	Data 0.000 (0.045)	Loss 1.164 (1.049)
Epoch: [13][180/200]	Time 0.738 (0.794)	Data 0.001 (0.049)	Loss 1.192 (1.066)
Epoch: [13][200/200]	Time 0.736 (0.796)	Data 0.001 (0.051)	Loss 1.010 (1.090)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.246 (0.276)	Data 0.000 (0.025)	
Extract Features: [100/128]	Time 0.246 (0.265)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.93141841888428
==> Statistics for epoch 14: 1017 clusters
Epoch: [14][20/200]	Time 0.736 (0.801)	Data 0.001 (0.051)	Loss 0.089 (0.207)
Epoch: [14][40/200]	Time 0.732 (0.816)	Data 0.001 (0.068)	Loss 1.258 (0.393)
Epoch: [14][60/200]	Time 0.735 (0.793)	Data 0.000 (0.046)	Loss 1.147 (0.643)
Epoch: [14][80/200]	Time 0.743 (0.805)	Data 0.001 (0.056)	Loss 0.879 (0.755)
Epoch: [14][100/200]	Time 0.750 (0.812)	Data 0.001 (0.063)	Loss 0.769 (0.822)
Epoch: [14][120/200]	Time 0.743 (0.803)	Data 0.000 (0.052)	Loss 0.964 (0.870)
Epoch: [14][140/200]	Time 0.748 (0.808)	Data 0.001 (0.057)	Loss 1.025 (0.905)
Epoch: [14][160/200]	Time 0.747 (0.811)	Data 0.001 (0.060)	Loss 1.140 (0.929)
Epoch: [14][180/200]	Time 0.736 (0.804)	Data 0.000 (0.054)	Loss 1.432 (0.954)
Epoch: [14][200/200]	Time 0.746 (0.807)	Data 0.001 (0.056)	Loss 0.934 (0.967)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.243 (0.279)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.245 (0.267)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.19676876068115
==> Statistics for epoch 15: 1029 clusters
Epoch: [15][20/200]	Time 0.738 (0.797)	Data 0.001 (0.052)	Loss 0.187 (0.235)
Epoch: [15][40/200]	Time 0.739 (0.804)	Data 0.001 (0.062)	Loss 0.943 (0.416)
Epoch: [15][60/200]	Time 0.739 (0.786)	Data 0.000 (0.042)	Loss 1.263 (0.673)
Epoch: [15][80/200]	Time 0.739 (0.797)	Data 0.001 (0.053)	Loss 1.344 (0.796)
Epoch: [15][100/200]	Time 0.745 (0.803)	Data 0.001 (0.059)	Loss 1.224 (0.857)
Epoch: [15][120/200]	Time 0.753 (0.794)	Data 0.001 (0.049)	Loss 1.644 (0.913)
Epoch: [15][140/200]	Time 0.742 (0.799)	Data 0.001 (0.053)	Loss 1.051 (0.948)
Epoch: [15][160/200]	Time 0.742 (0.793)	Data 0.000 (0.047)	Loss 1.153 (0.968)
Epoch: [15][180/200]	Time 0.742 (0.797)	Data 0.001 (0.050)	Loss 0.889 (0.981)
Epoch: [15][200/200]	Time 0.746 (0.799)	Data 0.001 (0.052)	Loss 1.468 (1.005)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.249 (0.277)	Data 0.001 (0.026)	
Extract Features: [100/128]	Time 0.243 (0.264)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.317975997924805
==> Statistics for epoch 16: 1042 clusters
Epoch: [16][20/200]	Time 0.837 (0.799)	Data 0.001 (0.052)	Loss 0.302 (0.254)
Epoch: [16][40/200]	Time 0.739 (0.807)	Data 0.001 (0.062)	Loss 0.787 (0.393)
Epoch: [16][60/200]	Time 0.733 (0.784)	Data 0.000 (0.042)	Loss 1.286 (0.659)
Epoch: [16][80/200]	Time 0.740 (0.795)	Data 0.001 (0.051)	Loss 1.440 (0.788)
Epoch: [16][100/200]	Time 0.735 (0.801)	Data 0.001 (0.056)	Loss 0.725 (0.845)
Epoch: [16][120/200]	Time 0.749 (0.792)	Data 0.001 (0.047)	Loss 1.438 (0.889)
Epoch: [16][140/200]	Time 0.739 (0.796)	Data 0.001 (0.051)	Loss 1.200 (0.932)
Epoch: [16][160/200]	Time 0.733 (0.790)	Data 0.000 (0.045)	Loss 1.137 (0.963)
Epoch: [16][180/200]	Time 0.735 (0.795)	Data 0.001 (0.049)	Loss 0.929 (0.988)
Epoch: [16][200/200]	Time 0.739 (0.797)	Data 0.001 (0.052)	Loss 1.128 (1.002)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.246 (0.276)	Data 0.000 (0.023)	
Extract Features: [100/128]	Time 0.254 (0.266)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.36913275718689
==> Statistics for epoch 17: 1048 clusters
Epoch: [17][20/200]	Time 0.738 (0.795)	Data 0.001 (0.047)	Loss 0.323 (0.244)
Epoch: [17][40/200]	Time 0.746 (0.807)	Data 0.001 (0.060)	Loss 1.224 (0.396)
Epoch: [17][60/200]	Time 0.732 (0.787)	Data 0.000 (0.040)	Loss 0.691 (0.627)
Epoch: [17][80/200]	Time 0.739 (0.795)	Data 0.001 (0.048)	Loss 1.146 (0.747)
Epoch: [17][100/200]	Time 0.744 (0.800)	Data 0.001 (0.054)	Loss 1.236 (0.834)
Epoch: [17][120/200]	Time 0.738 (0.791)	Data 0.001 (0.045)	Loss 1.006 (0.887)
Epoch: [17][140/200]	Time 0.742 (0.795)	Data 0.001 (0.049)	Loss 1.334 (0.919)
Epoch: [17][160/200]	Time 0.737 (0.789)	Data 0.000 (0.043)	Loss 0.842 (0.943)
Epoch: [17][180/200]	Time 0.875 (0.792)	Data 0.001 (0.046)	Loss 0.963 (0.963)
Epoch: [17][200/200]	Time 0.747 (0.795)	Data 0.001 (0.050)	Loss 1.120 (0.975)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.372 (0.287)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.246 (0.269)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.168437004089355
==> Statistics for epoch 18: 1058 clusters
Epoch: [18][20/200]	Time 0.733 (0.790)	Data 0.001 (0.049)	Loss 0.179 (0.222)
Epoch: [18][40/200]	Time 0.732 (0.805)	Data 0.001 (0.065)	Loss 0.713 (0.351)
Epoch: [18][60/200]	Time 0.740 (0.785)	Data 0.000 (0.044)	Loss 1.361 (0.610)
Epoch: [18][80/200]	Time 0.736 (0.797)	Data 0.001 (0.053)	Loss 0.992 (0.732)
Epoch: [18][100/200]	Time 2.318 (0.801)	Data 1.489 (0.058)	Loss 1.189 (0.819)
Epoch: [18][120/200]	Time 0.737 (0.790)	Data 0.001 (0.048)	Loss 1.045 (0.872)
Epoch: [18][140/200]	Time 0.741 (0.795)	Data 0.001 (0.052)	Loss 0.861 (0.903)
Epoch: [18][160/200]	Time 0.734 (0.788)	Data 0.000 (0.045)	Loss 1.276 (0.937)
Epoch: [18][180/200]	Time 0.738 (0.792)	Data 0.001 (0.049)	Loss 0.776 (0.955)
Epoch: [18][200/200]	Time 0.763 (0.796)	Data 0.001 (0.052)	Loss 1.321 (0.969)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.243 (0.277)	Data 0.000 (0.024)	
Extract Features: [100/128]	Time 0.249 (0.266)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.319491386413574
==> Statistics for epoch 19: 1049 clusters
Epoch: [19][20/200]	Time 0.735 (0.793)	Data 0.001 (0.049)	Loss 0.249 (0.219)
Epoch: [19][40/200]	Time 0.737 (0.803)	Data 0.001 (0.060)	Loss 1.294 (0.375)
Epoch: [19][60/200]	Time 0.736 (0.784)	Data 0.000 (0.041)	Loss 1.016 (0.597)
Epoch: [19][80/200]	Time 0.737 (0.796)	Data 0.001 (0.051)	Loss 0.855 (0.722)
Epoch: [19][100/200]	Time 0.739 (0.803)	Data 0.002 (0.057)	Loss 0.899 (0.788)
Epoch: [19][120/200]	Time 0.738 (0.794)	Data 0.001 (0.048)	Loss 0.980 (0.834)
Epoch: [19][140/200]	Time 0.740 (0.799)	Data 0.001 (0.053)	Loss 1.075 (0.867)
Epoch: [19][160/200]	Time 0.736 (0.792)	Data 0.000 (0.047)	Loss 1.051 (0.900)
Epoch: [19][180/200]	Time 0.740 (0.796)	Data 0.001 (0.050)	Loss 1.287 (0.918)
Epoch: [19][200/200]	Time 0.770 (0.800)	Data 0.001 (0.053)	Loss 0.786 (0.935)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.246 (0.282)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.243 (0.267)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.97195100784302
==> Statistics for epoch 20: 1036 clusters
Epoch: [20][20/200]	Time 0.730 (0.790)	Data 0.001 (0.052)	Loss 0.225 (0.201)
Epoch: [20][40/200]	Time 0.738 (0.802)	Data 0.001 (0.064)	Loss 1.170 (0.375)
Epoch: [20][60/200]	Time 0.733 (0.782)	Data 0.000 (0.043)	Loss 0.859 (0.579)
Epoch: [20][80/200]	Time 0.905 (0.795)	Data 0.001 (0.052)	Loss 1.129 (0.716)
Epoch: [20][100/200]	Time 0.741 (0.803)	Data 0.002 (0.058)	Loss 1.102 (0.787)
Epoch: [20][120/200]	Time 0.749 (0.794)	Data 0.001 (0.049)	Loss 1.069 (0.832)
Epoch: [20][140/200]	Time 0.738 (0.800)	Data 0.001 (0.054)	Loss 1.042 (0.856)
Epoch: [20][160/200]	Time 0.736 (0.793)	Data 0.000 (0.047)	Loss 0.940 (0.873)
Epoch: [20][180/200]	Time 0.834 (0.797)	Data 0.001 (0.051)	Loss 0.842 (0.890)
Epoch: [20][200/200]	Time 0.735 (0.799)	Data 0.001 (0.053)	Loss 0.689 (0.900)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.245 (0.276)	Data 0.000 (0.024)	
Extract Features: [100/128]	Time 0.253 (0.264)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.40424060821533
==> Statistics for epoch 21: 1076 clusters
Epoch: [21][20/200]	Time 0.739 (0.799)	Data 0.001 (0.053)	Loss 0.181 (0.204)
Epoch: [21][40/200]	Time 0.737 (0.818)	Data 0.001 (0.070)	Loss 0.815 (0.320)
Epoch: [21][60/200]	Time 0.788 (0.795)	Data 0.000 (0.047)	Loss 0.970 (0.548)
Epoch: [21][80/200]	Time 0.743 (0.804)	Data 0.001 (0.056)	Loss 1.135 (0.665)
Epoch: [21][100/200]	Time 2.355 (0.809)	Data 1.570 (0.060)	Loss 1.360 (0.756)
Epoch: [21][120/200]	Time 0.743 (0.800)	Data 0.001 (0.051)	Loss 1.215 (0.798)
Epoch: [21][140/200]	Time 0.749 (0.803)	Data 0.004 (0.054)	Loss 1.242 (0.842)
Epoch: [21][160/200]	Time 0.741 (0.797)	Data 0.000 (0.047)	Loss 0.973 (0.863)
Epoch: [21][180/200]	Time 0.743 (0.800)	Data 0.001 (0.051)	Loss 0.984 (0.882)
Epoch: [21][200/200]	Time 0.745 (0.804)	Data 0.001 (0.055)	Loss 0.888 (0.896)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.252 (0.281)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.245 (0.268)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.310736417770386
==> Statistics for epoch 22: 1081 clusters
Epoch: [22][20/200]	Time 0.739 (0.795)	Data 0.001 (0.050)	Loss 0.295 (0.192)
Epoch: [22][40/200]	Time 0.739 (0.815)	Data 0.001 (0.069)	Loss 1.082 (0.328)
Epoch: [22][60/200]	Time 0.742 (0.790)	Data 0.000 (0.046)	Loss 0.962 (0.550)
Epoch: [22][80/200]	Time 0.742 (0.800)	Data 0.001 (0.054)	Loss 0.666 (0.650)
Epoch: [22][100/200]	Time 2.340 (0.805)	Data 1.508 (0.059)	Loss 1.079 (0.737)
Epoch: [22][120/200]	Time 0.738 (0.794)	Data 0.001 (0.049)	Loss 1.004 (0.786)
Epoch: [22][140/200]	Time 0.735 (0.798)	Data 0.001 (0.053)	Loss 1.198 (0.828)
Epoch: [22][160/200]	Time 0.818 (0.791)	Data 0.000 (0.046)	Loss 1.110 (0.864)
Epoch: [22][180/200]	Time 0.747 (0.795)	Data 0.001 (0.050)	Loss 1.130 (0.887)
Epoch: [22][200/200]	Time 0.748 (0.798)	Data 0.001 (0.053)	Loss 1.123 (0.905)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.248 (0.279)	Data 0.000 (0.025)	
Extract Features: [100/128]	Time 0.246 (0.267)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.715888261795044
==> Statistics for epoch 23: 1071 clusters
Epoch: [23][20/200]	Time 0.745 (0.802)	Data 0.001 (0.049)	Loss 0.212 (0.190)
Epoch: [23][40/200]	Time 0.737 (0.811)	Data 0.001 (0.062)	Loss 1.030 (0.312)
Epoch: [23][60/200]	Time 0.752 (0.791)	Data 0.000 (0.042)	Loss 1.000 (0.548)
Epoch: [23][80/200]	Time 0.745 (0.800)	Data 0.002 (0.050)	Loss 1.206 (0.674)
Epoch: [23][100/200]	Time 2.252 (0.803)	Data 1.473 (0.055)	Loss 1.104 (0.743)
Epoch: [23][120/200]	Time 0.742 (0.794)	Data 0.001 (0.046)	Loss 1.001 (0.786)
Epoch: [23][140/200]	Time 0.736 (0.799)	Data 0.001 (0.051)	Loss 1.088 (0.822)
Epoch: [23][160/200]	Time 0.732 (0.792)	Data 0.000 (0.044)	Loss 1.063 (0.854)
Epoch: [23][180/200]	Time 0.738 (0.796)	Data 0.001 (0.048)	Loss 1.085 (0.871)
Epoch: [23][200/200]	Time 0.748 (0.798)	Data 0.001 (0.050)	Loss 1.120 (0.891)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.243 (0.280)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.244 (0.265)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.424335956573486
==> Statistics for epoch 24: 1062 clusters
Epoch: [24][20/200]	Time 0.736 (0.796)	Data 0.001 (0.054)	Loss 0.205 (0.200)
Epoch: [24][40/200]	Time 0.741 (0.813)	Data 0.001 (0.070)	Loss 0.868 (0.342)
Epoch: [24][60/200]	Time 0.741 (0.791)	Data 0.000 (0.047)	Loss 1.117 (0.571)
Epoch: [24][80/200]	Time 0.738 (0.803)	Data 0.001 (0.056)	Loss 1.000 (0.683)
Epoch: [24][100/200]	Time 2.529 (0.809)	Data 1.770 (0.063)	Loss 1.216 (0.751)
Epoch: [24][120/200]	Time 0.745 (0.799)	Data 0.001 (0.053)	Loss 0.938 (0.802)
Epoch: [24][140/200]	Time 0.741 (0.804)	Data 0.001 (0.057)	Loss 1.422 (0.841)
Epoch: [24][160/200]	Time 0.739 (0.797)	Data 0.000 (0.050)	Loss 1.352 (0.864)
Epoch: [24][180/200]	Time 0.736 (0.801)	Data 0.001 (0.054)	Loss 1.187 (0.884)
Epoch: [24][200/200]	Time 0.756 (0.802)	Data 0.001 (0.056)	Loss 1.463 (0.906)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.245 (0.276)	Data 0.000 (0.023)	
Extract Features: [100/128]	Time 0.244 (0.264)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.2529718875885
==> Statistics for epoch 25: 1068 clusters
Epoch: [25][20/200]	Time 0.868 (0.796)	Data 0.001 (0.051)	Loss 0.174 (0.182)
Epoch: [25][40/200]	Time 0.738 (0.812)	Data 0.001 (0.069)	Loss 1.003 (0.320)
Epoch: [25][60/200]	Time 0.742 (0.790)	Data 0.000 (0.047)	Loss 1.232 (0.571)
Epoch: [25][80/200]	Time 0.735 (0.797)	Data 0.001 (0.054)	Loss 0.862 (0.695)
Epoch: [25][100/200]	Time 2.258 (0.801)	Data 1.467 (0.058)	Loss 1.189 (0.757)
Epoch: [25][120/200]	Time 0.736 (0.793)	Data 0.001 (0.049)	Loss 0.758 (0.809)
Epoch: [25][140/200]	Time 0.746 (0.797)	Data 0.001 (0.053)	Loss 0.977 (0.834)
Epoch: [25][160/200]	Time 0.751 (0.791)	Data 0.000 (0.046)	Loss 1.248 (0.860)
Epoch: [25][180/200]	Time 0.737 (0.794)	Data 0.001 (0.050)	Loss 1.361 (0.883)
Epoch: [25][200/200]	Time 0.742 (0.796)	Data 0.001 (0.052)	Loss 1.124 (0.897)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.251 (0.276)	Data 0.000 (0.023)	
Extract Features: [100/128]	Time 0.242 (0.264)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.109214782714844
==> Statistics for epoch 26: 1071 clusters
Epoch: [26][20/200]	Time 0.731 (0.796)	Data 0.001 (0.055)	Loss 0.350 (0.192)
Epoch: [26][40/200]	Time 0.735 (0.810)	Data 0.001 (0.068)	Loss 0.886 (0.329)
Epoch: [26][60/200]	Time 0.743 (0.787)	Data 0.000 (0.046)	Loss 0.876 (0.542)
Epoch: [26][80/200]	Time 0.746 (0.797)	Data 0.001 (0.054)	Loss 1.132 (0.675)
Epoch: [26][100/200]	Time 2.447 (0.803)	Data 1.661 (0.060)	Loss 1.075 (0.736)
Epoch: [26][120/200]	Time 0.736 (0.794)	Data 0.001 (0.050)	Loss 0.997 (0.789)
Epoch: [26][140/200]	Time 0.738 (0.799)	Data 0.001 (0.055)	Loss 0.928 (0.827)
Epoch: [26][160/200]	Time 0.738 (0.792)	Data 0.000 (0.048)	Loss 0.550 (0.847)
Epoch: [26][180/200]	Time 0.743 (0.795)	Data 0.001 (0.052)	Loss 1.325 (0.870)
Epoch: [26][200/200]	Time 0.867 (0.798)	Data 0.001 (0.054)	Loss 1.160 (0.881)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.247 (0.275)	Data 0.000 (0.023)	
Extract Features: [100/128]	Time 0.245 (0.264)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.97429156303406
==> Statistics for epoch 27: 1071 clusters
Epoch: [27][20/200]	Time 0.741 (0.799)	Data 0.001 (0.054)	Loss 0.129 (0.194)
Epoch: [27][40/200]	Time 0.740 (0.811)	Data 0.001 (0.068)	Loss 0.834 (0.318)
Epoch: [27][60/200]	Time 0.741 (0.790)	Data 0.000 (0.046)	Loss 1.444 (0.555)
Epoch: [27][80/200]	Time 0.740 (0.800)	Data 0.001 (0.054)	Loss 0.983 (0.670)
Epoch: [27][100/200]	Time 2.334 (0.804)	Data 1.541 (0.059)	Loss 1.330 (0.741)
Epoch: [27][120/200]	Time 0.740 (0.795)	Data 0.001 (0.049)	Loss 1.170 (0.802)
Epoch: [27][140/200]	Time 0.740 (0.799)	Data 0.001 (0.054)	Loss 0.791 (0.825)
Epoch: [27][160/200]	Time 0.742 (0.793)	Data 0.000 (0.047)	Loss 0.579 (0.845)
Epoch: [27][180/200]	Time 0.741 (0.798)	Data 0.001 (0.051)	Loss 1.237 (0.867)
Epoch: [27][200/200]	Time 0.741 (0.801)	Data 0.001 (0.054)	Loss 1.325 (0.883)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.250 (0.279)	Data 0.001 (0.026)	
Extract Features: [100/128]	Time 0.243 (0.266)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.7573459148407
==> Statistics for epoch 28: 1075 clusters
Epoch: [28][20/200]	Time 0.738 (0.797)	Data 0.001 (0.056)	Loss 0.122 (0.157)
Epoch: [28][40/200]	Time 0.738 (0.808)	Data 0.001 (0.065)	Loss 0.982 (0.288)
Epoch: [28][60/200]	Time 0.736 (0.791)	Data 0.000 (0.044)	Loss 0.972 (0.522)
Epoch: [28][80/200]	Time 0.741 (0.800)	Data 0.001 (0.051)	Loss 1.020 (0.631)
Epoch: [28][100/200]	Time 2.378 (0.805)	Data 1.617 (0.057)	Loss 0.818 (0.697)
Epoch: [28][120/200]	Time 0.742 (0.796)	Data 0.001 (0.048)	Loss 1.081 (0.744)
Epoch: [28][140/200]	Time 0.738 (0.799)	Data 0.001 (0.051)	Loss 1.364 (0.793)
Epoch: [28][160/200]	Time 0.739 (0.793)	Data 0.000 (0.045)	Loss 1.006 (0.821)
Epoch: [28][180/200]	Time 0.740 (0.795)	Data 0.001 (0.048)	Loss 0.989 (0.835)
Epoch: [28][200/200]	Time 0.743 (0.798)	Data 0.001 (0.051)	Loss 1.268 (0.854)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.242 (0.278)	Data 0.000 (0.025)	
Extract Features: [100/128]	Time 0.246 (0.263)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.37271332740784
==> Statistics for epoch 29: 1081 clusters
Epoch: [29][20/200]	Time 0.733 (0.791)	Data 0.001 (0.054)	Loss 0.183 (0.163)
Epoch: [29][40/200]	Time 0.737 (0.808)	Data 0.001 (0.064)	Loss 0.792 (0.314)
Epoch: [29][60/200]	Time 0.838 (0.789)	Data 0.000 (0.043)	Loss 1.517 (0.528)
Epoch: [29][80/200]	Time 0.739 (0.797)	Data 0.001 (0.052)	Loss 1.483 (0.663)
Epoch: [29][100/200]	Time 2.309 (0.802)	Data 1.538 (0.057)	Loss 1.048 (0.721)
Epoch: [29][120/200]	Time 0.738 (0.792)	Data 0.001 (0.048)	Loss 0.736 (0.760)
Epoch: [29][140/200]	Time 0.738 (0.797)	Data 0.001 (0.052)	Loss 0.804 (0.805)
Epoch: [29][160/200]	Time 0.739 (0.791)	Data 0.000 (0.046)	Loss 1.548 (0.833)
Epoch: [29][180/200]	Time 0.742 (0.794)	Data 0.001 (0.049)	Loss 1.402 (0.850)
Epoch: [29][200/200]	Time 0.744 (0.796)	Data 0.001 (0.051)	Loss 0.895 (0.869)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.244 (0.285)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.246 (0.269)	Data 0.001 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.14625144004822
==> Statistics for epoch 30: 1088 clusters
Epoch: [30][20/200]	Time 0.735 (0.792)	Data 0.001 (0.050)	Loss 0.112 (0.184)
Epoch: [30][40/200]	Time 0.742 (0.810)	Data 0.001 (0.066)	Loss 1.177 (0.311)
Epoch: [30][60/200]	Time 0.740 (0.790)	Data 0.001 (0.044)	Loss 1.274 (0.556)
Epoch: [30][80/200]	Time 0.745 (0.803)	Data 0.001 (0.055)	Loss 0.635 (0.646)
Epoch: [30][100/200]	Time 0.739 (0.790)	Data 0.000 (0.044)	Loss 0.829 (0.715)
Epoch: [30][120/200]	Time 0.749 (0.798)	Data 0.001 (0.050)	Loss 0.951 (0.781)
Epoch: [30][140/200]	Time 0.742 (0.803)	Data 0.001 (0.055)	Loss 0.988 (0.810)
Epoch: [30][160/200]	Time 0.744 (0.796)	Data 0.001 (0.048)	Loss 1.350 (0.840)
Epoch: [30][180/200]	Time 0.739 (0.801)	Data 0.001 (0.052)	Loss 0.790 (0.859)
Epoch: [30][200/200]	Time 0.740 (0.795)	Data 0.000 (0.047)	Loss 0.756 (0.871)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.249 (0.282)	Data 0.000 (0.024)	
Extract Features: [100/128]	Time 0.250 (0.269)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.12196397781372
==> Statistics for epoch 31: 1075 clusters
Epoch: [31][20/200]	Time 0.737 (0.801)	Data 0.001 (0.047)	Loss 0.165 (0.180)
Epoch: [31][40/200]	Time 0.742 (0.818)	Data 0.001 (0.065)	Loss 0.828 (0.309)
Epoch: [31][60/200]	Time 0.737 (0.794)	Data 0.000 (0.044)	Loss 0.766 (0.552)
Epoch: [31][80/200]	Time 0.742 (0.802)	Data 0.001 (0.053)	Loss 0.964 (0.676)
Epoch: [31][100/200]	Time 2.368 (0.807)	Data 1.589 (0.059)	Loss 1.009 (0.744)
Epoch: [31][120/200]	Time 0.739 (0.798)	Data 0.001 (0.049)	Loss 0.895 (0.790)
Epoch: [31][140/200]	Time 0.743 (0.803)	Data 0.001 (0.054)	Loss 1.206 (0.830)
Epoch: [31][160/200]	Time 0.742 (0.797)	Data 0.000 (0.048)	Loss 0.962 (0.851)
Epoch: [31][180/200]	Time 0.748 (0.802)	Data 0.001 (0.052)	Loss 0.937 (0.866)
Epoch: [31][200/200]	Time 0.747 (0.806)	Data 0.001 (0.056)	Loss 0.772 (0.878)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.242 (0.281)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.248 (0.266)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.091567277908325
==> Statistics for epoch 32: 1074 clusters
Epoch: [32][20/200]	Time 0.734 (0.797)	Data 0.001 (0.053)	Loss 0.163 (0.182)
Epoch: [32][40/200]	Time 0.737 (0.807)	Data 0.001 (0.065)	Loss 1.010 (0.313)
Epoch: [32][60/200]	Time 0.736 (0.786)	Data 0.000 (0.043)	Loss 1.178 (0.548)
Epoch: [32][80/200]	Time 0.738 (0.795)	Data 0.001 (0.052)	Loss 0.726 (0.666)
Epoch: [32][100/200]	Time 2.355 (0.801)	Data 1.587 (0.057)	Loss 1.021 (0.731)
Epoch: [32][120/200]	Time 0.744 (0.793)	Data 0.001 (0.048)	Loss 1.019 (0.782)
Epoch: [32][140/200]	Time 0.741 (0.796)	Data 0.001 (0.051)	Loss 0.628 (0.819)
Epoch: [32][160/200]	Time 0.741 (0.790)	Data 0.000 (0.045)	Loss 1.099 (0.843)
Epoch: [32][180/200]	Time 0.741 (0.794)	Data 0.001 (0.048)	Loss 0.834 (0.867)
Epoch: [32][200/200]	Time 0.746 (0.797)	Data 0.001 (0.051)	Loss 1.264 (0.878)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.242 (0.280)	Data 0.000 (0.024)	
Extract Features: [100/128]	Time 0.247 (0.266)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.440208435058594
==> Statistics for epoch 33: 1090 clusters
Epoch: [33][20/200]	Time 0.735 (0.811)	Data 0.001 (0.060)	Loss 0.165 (0.183)
Epoch: [33][40/200]	Time 0.745 (0.823)	Data 0.001 (0.074)	Loss 1.157 (0.307)
Epoch: [33][60/200]	Time 0.743 (0.799)	Data 0.001 (0.050)	Loss 0.657 (0.522)
Epoch: [33][80/200]	Time 0.742 (0.809)	Data 0.002 (0.058)	Loss 1.019 (0.654)
Epoch: [33][100/200]	Time 0.741 (0.795)	Data 0.000 (0.047)	Loss 1.084 (0.724)
Epoch: [33][120/200]	Time 0.750 (0.803)	Data 0.001 (0.053)	Loss 1.001 (0.776)
Epoch: [33][140/200]	Time 0.743 (0.806)	Data 0.002 (0.057)	Loss 0.837 (0.803)
Epoch: [33][160/200]	Time 0.737 (0.798)	Data 0.001 (0.050)	Loss 0.956 (0.826)
Epoch: [33][180/200]	Time 0.751 (0.802)	Data 0.001 (0.053)	Loss 0.653 (0.853)
Epoch: [33][200/200]	Time 0.743 (0.796)	Data 0.000 (0.048)	Loss 0.741 (0.868)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.243 (0.284)	Data 0.001 (0.028)	
Extract Features: [100/128]	Time 0.254 (0.268)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.293558835983276
==> Statistics for epoch 34: 1091 clusters
Epoch: [34][20/200]	Time 0.738 (0.800)	Data 0.001 (0.054)	Loss 0.178 (0.198)
Epoch: [34][40/200]	Time 0.746 (0.815)	Data 0.001 (0.067)	Loss 0.776 (0.288)
Epoch: [34][60/200]	Time 0.744 (0.795)	Data 0.001 (0.045)	Loss 1.189 (0.547)
Epoch: [34][80/200]	Time 0.743 (0.802)	Data 0.001 (0.054)	Loss 1.136 (0.656)
Epoch: [34][100/200]	Time 0.740 (0.791)	Data 0.000 (0.044)	Loss 0.903 (0.722)
Epoch: [34][120/200]	Time 0.742 (0.799)	Data 0.001 (0.051)	Loss 1.368 (0.778)
Epoch: [34][140/200]	Time 0.739 (0.803)	Data 0.001 (0.056)	Loss 1.433 (0.811)
Epoch: [34][160/200]	Time 0.742 (0.797)	Data 0.001 (0.049)	Loss 1.019 (0.834)
Epoch: [34][180/200]	Time 0.870 (0.800)	Data 0.001 (0.052)	Loss 0.730 (0.851)
Epoch: [34][200/200]	Time 0.737 (0.795)	Data 0.000 (0.047)	Loss 0.792 (0.865)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.247 (0.282)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.248 (0.267)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.36284875869751
==> Statistics for epoch 35: 1081 clusters
Epoch: [35][20/200]	Time 0.739 (0.802)	Data 0.001 (0.051)	Loss 0.218 (0.170)
Epoch: [35][40/200]	Time 0.740 (0.816)	Data 0.001 (0.065)	Loss 0.960 (0.306)
Epoch: [35][60/200]	Time 0.735 (0.795)	Data 0.000 (0.044)	Loss 1.015 (0.530)
Epoch: [35][80/200]	Time 0.737 (0.803)	Data 0.001 (0.054)	Loss 0.695 (0.637)
Epoch: [35][100/200]	Time 2.244 (0.807)	Data 1.468 (0.058)	Loss 1.281 (0.707)
Epoch: [35][120/200]	Time 0.741 (0.798)	Data 0.001 (0.049)	Loss 1.061 (0.758)
Epoch: [35][140/200]	Time 0.743 (0.804)	Data 0.001 (0.054)	Loss 1.135 (0.792)
Epoch: [35][160/200]	Time 0.742 (0.797)	Data 0.000 (0.048)	Loss 1.324 (0.817)
Epoch: [35][180/200]	Time 0.741 (0.801)	Data 0.001 (0.052)	Loss 0.870 (0.831)
Epoch: [35][200/200]	Time 0.747 (0.804)	Data 0.001 (0.055)	Loss 1.178 (0.850)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.245 (0.283)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.250 (0.269)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.89063858985901
==> Statistics for epoch 36: 1074 clusters
Epoch: [36][20/200]	Time 0.746 (0.794)	Data 0.001 (0.046)	Loss 0.194 (0.174)
Epoch: [36][40/200]	Time 0.737 (0.809)	Data 0.001 (0.064)	Loss 1.105 (0.324)
Epoch: [36][60/200]	Time 0.739 (0.785)	Data 0.000 (0.043)	Loss 0.774 (0.523)
Epoch: [36][80/200]	Time 0.748 (0.795)	Data 0.002 (0.051)	Loss 0.741 (0.636)
Epoch: [36][100/200]	Time 2.275 (0.802)	Data 1.493 (0.056)	Loss 1.301 (0.721)
Epoch: [36][120/200]	Time 0.745 (0.793)	Data 0.001 (0.047)	Loss 1.230 (0.759)
Epoch: [36][140/200]	Time 0.746 (0.797)	Data 0.001 (0.051)	Loss 1.133 (0.798)
Epoch: [36][160/200]	Time 0.745 (0.792)	Data 0.000 (0.045)	Loss 1.352 (0.822)
Epoch: [36][180/200]	Time 0.750 (0.796)	Data 0.001 (0.050)	Loss 1.269 (0.838)
Epoch: [36][200/200]	Time 0.741 (0.800)	Data 0.001 (0.053)	Loss 1.109 (0.845)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.243 (0.279)	Data 0.000 (0.024)	
Extract Features: [100/128]	Time 0.242 (0.266)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.98370575904846
==> Statistics for epoch 37: 1087 clusters
Epoch: [37][20/200]	Time 0.740 (0.789)	Data 0.001 (0.049)	Loss 0.135 (0.186)
Epoch: [37][40/200]	Time 0.738 (0.805)	Data 0.001 (0.064)	Loss 0.750 (0.313)
Epoch: [37][60/200]	Time 0.737 (0.783)	Data 0.000 (0.043)	Loss 1.198 (0.546)
Epoch: [37][80/200]	Time 0.737 (0.792)	Data 0.001 (0.051)	Loss 1.068 (0.651)
Epoch: [37][100/200]	Time 2.303 (0.798)	Data 1.523 (0.056)	Loss 0.775 (0.716)
Epoch: [37][120/200]	Time 0.741 (0.789)	Data 0.001 (0.047)	Loss 0.895 (0.756)
Epoch: [37][140/200]	Time 0.751 (0.794)	Data 0.001 (0.051)	Loss 1.004 (0.800)
Epoch: [37][160/200]	Time 0.839 (0.788)	Data 0.000 (0.045)	Loss 0.890 (0.819)
Epoch: [37][180/200]	Time 0.749 (0.793)	Data 0.002 (0.049)	Loss 0.829 (0.839)
Epoch: [37][200/200]	Time 0.753 (0.798)	Data 0.001 (0.053)	Loss 1.031 (0.858)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.245 (0.279)	Data 0.000 (0.024)	
Extract Features: [100/128]	Time 0.257 (0.265)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.2031524181366
==> Statistics for epoch 38: 1067 clusters
Epoch: [38][20/200]	Time 0.729 (0.795)	Data 0.001 (0.051)	Loss 0.150 (0.164)
Epoch: [38][40/200]	Time 0.740 (0.804)	Data 0.001 (0.063)	Loss 0.739 (0.310)
Epoch: [38][60/200]	Time 0.741 (0.787)	Data 0.000 (0.042)	Loss 0.970 (0.532)
Epoch: [38][80/200]	Time 0.742 (0.799)	Data 0.001 (0.052)	Loss 0.981 (0.646)
Epoch: [38][100/200]	Time 2.477 (0.806)	Data 1.677 (0.058)	Loss 0.623 (0.697)
Epoch: [38][120/200]	Time 0.750 (0.798)	Data 0.001 (0.049)	Loss 1.518 (0.758)
Epoch: [38][140/200]	Time 0.740 (0.804)	Data 0.001 (0.055)	Loss 1.332 (0.787)
Epoch: [38][160/200]	Time 0.741 (0.797)	Data 0.000 (0.048)	Loss 1.076 (0.804)
Epoch: [38][180/200]	Time 0.742 (0.801)	Data 0.001 (0.052)	Loss 0.789 (0.819)
Epoch: [38][200/200]	Time 0.752 (0.804)	Data 0.001 (0.055)	Loss 1.107 (0.838)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.245 (0.284)	Data 0.001 (0.028)	
Extract Features: [100/128]	Time 0.246 (0.269)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.953566789627075
==> Statistics for epoch 39: 1084 clusters
Epoch: [39][20/200]	Time 0.737 (0.803)	Data 0.001 (0.053)	Loss 0.135 (0.161)
Epoch: [39][40/200]	Time 0.738 (0.816)	Data 0.001 (0.068)	Loss 0.843 (0.291)
Epoch: [39][60/200]	Time 0.745 (0.796)	Data 0.000 (0.046)	Loss 0.885 (0.521)
Epoch: [39][80/200]	Time 0.738 (0.803)	Data 0.001 (0.054)	Loss 0.720 (0.616)
Epoch: [39][100/200]	Time 2.484 (0.809)	Data 1.696 (0.060)	Loss 1.155 (0.684)
Epoch: [39][120/200]	Time 0.742 (0.800)	Data 0.001 (0.051)	Loss 1.342 (0.736)
Epoch: [39][140/200]	Time 0.742 (0.804)	Data 0.001 (0.055)	Loss 1.185 (0.770)
Epoch: [39][160/200]	Time 0.879 (0.798)	Data 0.000 (0.048)	Loss 1.034 (0.794)
Epoch: [39][180/200]	Time 0.742 (0.800)	Data 0.001 (0.051)	Loss 0.949 (0.816)
Epoch: [39][200/200]	Time 0.747 (0.804)	Data 0.001 (0.053)	Loss 0.797 (0.842)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.245 (0.278)	Data 0.000 (0.024)	
Extract Features: [100/128]	Time 0.245 (0.266)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.99696445465088
==> Statistics for epoch 40: 1071 clusters
Epoch: [40][20/200]	Time 0.749 (0.798)	Data 0.001 (0.048)	Loss 0.185 (0.162)
Epoch: [40][40/200]	Time 0.892 (0.815)	Data 0.001 (0.063)	Loss 1.194 (0.300)
Epoch: [40][60/200]	Time 0.741 (0.791)	Data 0.000 (0.043)	Loss 0.787 (0.509)
Epoch: [40][80/200]	Time 0.745 (0.799)	Data 0.001 (0.051)	Loss 0.915 (0.633)
Epoch: [40][100/200]	Time 2.245 (0.804)	Data 1.468 (0.056)	Loss 1.048 (0.691)
Epoch: [40][120/200]	Time 0.911 (0.796)	Data 0.001 (0.047)	Loss 0.962 (0.737)
Epoch: [40][140/200]	Time 0.745 (0.802)	Data 0.001 (0.052)	Loss 1.115 (0.763)
Epoch: [40][160/200]	Time 0.742 (0.796)	Data 0.000 (0.046)	Loss 0.857 (0.783)
Epoch: [40][180/200]	Time 0.739 (0.800)	Data 0.001 (0.049)	Loss 0.732 (0.802)
Epoch: [40][200/200]	Time 0.740 (0.803)	Data 0.001 (0.053)	Loss 1.239 (0.824)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.244 (0.281)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.375 (0.268)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.457937717437744
==> Statistics for epoch 41: 1081 clusters
Epoch: [41][20/200]	Time 0.739 (0.796)	Data 0.001 (0.053)	Loss 0.261 (0.181)
Epoch: [41][40/200]	Time 0.736 (0.810)	Data 0.001 (0.065)	Loss 1.225 (0.318)
Epoch: [41][60/200]	Time 0.736 (0.788)	Data 0.000 (0.044)	Loss 1.115 (0.548)
Epoch: [41][80/200]	Time 0.739 (0.799)	Data 0.001 (0.053)	Loss 0.992 (0.639)
Epoch: [41][100/200]	Time 2.375 (0.805)	Data 1.586 (0.058)	Loss 1.072 (0.716)
Epoch: [41][120/200]	Time 0.737 (0.797)	Data 0.001 (0.049)	Loss 1.418 (0.767)
Epoch: [41][140/200]	Time 0.740 (0.801)	Data 0.001 (0.053)	Loss 0.934 (0.798)
Epoch: [41][160/200]	Time 0.739 (0.794)	Data 0.000 (0.047)	Loss 1.237 (0.825)
Epoch: [41][180/200]	Time 0.743 (0.798)	Data 0.001 (0.051)	Loss 1.006 (0.843)
Epoch: [41][200/200]	Time 0.739 (0.801)	Data 0.001 (0.054)	Loss 1.013 (0.856)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.248 (0.281)	Data 0.000 (0.024)	
Extract Features: [100/128]	Time 0.244 (0.268)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.768963098526
==> Statistics for epoch 42: 1086 clusters
Epoch: [42][20/200]	Time 0.731 (0.802)	Data 0.001 (0.047)	Loss 0.193 (0.168)
Epoch: [42][40/200]	Time 0.742 (0.811)	Data 0.001 (0.060)	Loss 0.960 (0.312)
Epoch: [42][60/200]	Time 0.735 (0.791)	Data 0.000 (0.040)	Loss 1.126 (0.526)
Epoch: [42][80/200]	Time 0.739 (0.800)	Data 0.001 (0.049)	Loss 0.913 (0.626)
Epoch: [42][100/200]	Time 2.373 (0.806)	Data 1.597 (0.055)	Loss 1.101 (0.704)
Epoch: [42][120/200]	Time 0.739 (0.795)	Data 0.001 (0.046)	Loss 1.058 (0.758)
Epoch: [42][140/200]	Time 0.745 (0.799)	Data 0.001 (0.050)	Loss 1.036 (0.800)
Epoch: [42][160/200]	Time 0.740 (0.794)	Data 0.000 (0.044)	Loss 0.959 (0.818)
Epoch: [42][180/200]	Time 0.739 (0.799)	Data 0.001 (0.049)	Loss 1.149 (0.831)
Epoch: [42][200/200]	Time 0.735 (0.802)	Data 0.001 (0.052)	Loss 0.688 (0.843)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.344 (0.274)	Data 0.000 (0.023)	
Extract Features: [100/128]	Time 0.245 (0.262)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.73651909828186
==> Statistics for epoch 43: 1085 clusters
Epoch: [43][20/200]	Time 0.751 (0.800)	Data 0.001 (0.053)	Loss 0.089 (0.177)
Epoch: [43][40/200]	Time 0.739 (0.817)	Data 0.001 (0.068)	Loss 0.971 (0.308)
Epoch: [43][60/200]	Time 0.740 (0.794)	Data 0.000 (0.045)	Loss 1.022 (0.553)
Epoch: [43][80/200]	Time 0.746 (0.803)	Data 0.001 (0.055)	Loss 1.216 (0.648)
Epoch: [43][100/200]	Time 2.476 (0.809)	Data 1.664 (0.060)	Loss 1.081 (0.708)
Epoch: [43][120/200]	Time 0.742 (0.801)	Data 0.001 (0.051)	Loss 1.069 (0.754)
Epoch: [43][140/200]	Time 0.742 (0.805)	Data 0.001 (0.055)	Loss 1.301 (0.784)
Epoch: [43][160/200]	Time 0.738 (0.798)	Data 0.000 (0.049)	Loss 0.901 (0.808)
Epoch: [43][180/200]	Time 0.749 (0.800)	Data 0.001 (0.051)	Loss 0.889 (0.828)
Epoch: [43][200/200]	Time 0.743 (0.803)	Data 0.001 (0.054)	Loss 0.607 (0.846)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.246 (0.278)	Data 0.000 (0.023)	
Extract Features: [100/128]	Time 0.252 (0.266)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.78255891799927
==> Statistics for epoch 44: 1076 clusters
Epoch: [44][20/200]	Time 0.737 (0.806)	Data 0.001 (0.055)	Loss 0.124 (0.161)
Epoch: [44][40/200]	Time 0.744 (0.820)	Data 0.001 (0.071)	Loss 0.677 (0.295)
Epoch: [44][60/200]	Time 0.740 (0.798)	Data 0.000 (0.048)	Loss 0.963 (0.513)
Epoch: [44][80/200]	Time 0.742 (0.806)	Data 0.001 (0.056)	Loss 1.276 (0.626)
Epoch: [44][100/200]	Time 2.465 (0.813)	Data 1.697 (0.062)	Loss 1.230 (0.707)
Epoch: [44][120/200]	Time 0.740 (0.801)	Data 0.001 (0.052)	Loss 0.948 (0.739)
Epoch: [44][140/200]	Time 0.744 (0.804)	Data 0.001 (0.056)	Loss 0.943 (0.782)
Epoch: [44][160/200]	Time 0.737 (0.796)	Data 0.000 (0.049)	Loss 1.040 (0.802)
Epoch: [44][180/200]	Time 0.743 (0.800)	Data 0.001 (0.052)	Loss 0.898 (0.820)
Epoch: [44][200/200]	Time 0.751 (0.803)	Data 0.001 (0.056)	Loss 1.032 (0.835)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.245 (0.283)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.245 (0.269)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 59.21822953224182
==> Statistics for epoch 45: 1083 clusters
Epoch: [45][20/200]	Time 0.835 (0.799)	Data 0.001 (0.055)	Loss 0.218 (0.150)
Epoch: [45][40/200]	Time 0.732 (0.810)	Data 0.001 (0.069)	Loss 1.314 (0.306)
Epoch: [45][60/200]	Time 0.731 (0.787)	Data 0.000 (0.046)	Loss 1.004 (0.544)
Epoch: [45][80/200]	Time 0.742 (0.795)	Data 0.001 (0.054)	Loss 0.923 (0.653)
Epoch: [45][100/200]	Time 2.235 (0.800)	Data 1.443 (0.058)	Loss 1.063 (0.724)
Epoch: [45][120/200]	Time 0.740 (0.790)	Data 0.001 (0.048)	Loss 0.937 (0.763)
Epoch: [45][140/200]	Time 0.743 (0.795)	Data 0.001 (0.053)	Loss 0.961 (0.782)
Epoch: [45][160/200]	Time 0.738 (0.787)	Data 0.000 (0.046)	Loss 0.650 (0.803)
Epoch: [45][180/200]	Time 0.741 (0.790)	Data 0.001 (0.049)	Loss 1.024 (0.816)
Epoch: [45][200/200]	Time 0.743 (0.793)	Data 0.001 (0.052)	Loss 0.860 (0.832)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.242 (0.276)	Data 0.000 (0.023)	
Extract Features: [100/128]	Time 0.411 (0.265)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 58.77708148956299
==> Statistics for epoch 46: 1079 clusters
Epoch: [46][20/200]	Time 0.849 (0.807)	Data 0.001 (0.057)	Loss 0.118 (0.182)
Epoch: [46][40/200]	Time 0.737 (0.815)	Data 0.001 (0.071)	Loss 1.269 (0.311)
Epoch: [46][60/200]	Time 0.737 (0.793)	Data 0.000 (0.048)	Loss 1.182 (0.531)
Epoch: [46][80/200]	Time 0.739 (0.804)	Data 0.001 (0.057)	Loss 0.895 (0.647)
Epoch: [46][100/200]	Time 2.532 (0.812)	Data 1.750 (0.064)	Loss 1.315 (0.709)
Epoch: [46][120/200]	Time 0.876 (0.802)	Data 0.001 (0.053)	Loss 1.336 (0.765)
Epoch: [46][140/200]	Time 0.741 (0.806)	Data 0.001 (0.058)	Loss 1.039 (0.790)
Epoch: [46][160/200]	Time 0.750 (0.798)	Data 0.000 (0.050)	Loss 0.983 (0.818)
Epoch: [46][180/200]	Time 0.742 (0.801)	Data 0.001 (0.053)	Loss 1.168 (0.836)
Epoch: [46][200/200]	Time 0.752 (0.805)	Data 0.001 (0.056)	Loss 0.980 (0.844)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.249 (0.279)	Data 0.000 (0.024)	
Extract Features: [100/128]	Time 0.246 (0.266)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.42958950996399
==> Statistics for epoch 47: 1080 clusters
Epoch: [47][20/200]	Time 0.841 (0.798)	Data 0.001 (0.048)	Loss 0.309 (0.179)
Epoch: [47][40/200]	Time 0.744 (0.815)	Data 0.001 (0.068)	Loss 1.353 (0.301)
Epoch: [47][60/200]	Time 0.741 (0.793)	Data 0.000 (0.046)	Loss 0.806 (0.515)
Epoch: [47][80/200]	Time 0.749 (0.802)	Data 0.001 (0.054)	Loss 0.820 (0.607)
Epoch: [47][100/200]	Time 2.508 (0.808)	Data 1.709 (0.061)	Loss 0.595 (0.687)
Epoch: [47][120/200]	Time 0.742 (0.798)	Data 0.001 (0.051)	Loss 0.773 (0.745)
Epoch: [47][140/200]	Time 0.741 (0.802)	Data 0.001 (0.055)	Loss 1.286 (0.786)
Epoch: [47][160/200]	Time 0.744 (0.795)	Data 0.000 (0.048)	Loss 0.748 (0.800)
Epoch: [47][180/200]	Time 0.742 (0.799)	Data 0.001 (0.052)	Loss 1.046 (0.828)
Epoch: [47][200/200]	Time 0.744 (0.801)	Data 0.001 (0.055)	Loss 0.630 (0.841)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.242 (0.277)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.244 (0.264)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.81524133682251
==> Statistics for epoch 48: 1079 clusters
Epoch: [48][20/200]	Time 0.741 (0.793)	Data 0.001 (0.047)	Loss 0.104 (0.150)
Epoch: [48][40/200]	Time 0.737 (0.808)	Data 0.001 (0.065)	Loss 0.891 (0.285)
Epoch: [48][60/200]	Time 0.738 (0.790)	Data 0.000 (0.044)	Loss 0.816 (0.501)
Epoch: [48][80/200]	Time 0.748 (0.800)	Data 0.001 (0.054)	Loss 1.136 (0.613)
Epoch: [48][100/200]	Time 2.395 (0.807)	Data 1.616 (0.060)	Loss 0.931 (0.679)
Epoch: [48][120/200]	Time 0.744 (0.796)	Data 0.001 (0.050)	Loss 1.105 (0.727)
Epoch: [48][140/200]	Time 0.744 (0.802)	Data 0.001 (0.056)	Loss 0.795 (0.759)
Epoch: [48][160/200]	Time 0.739 (0.795)	Data 0.000 (0.049)	Loss 0.836 (0.777)
Epoch: [48][180/200]	Time 0.748 (0.799)	Data 0.001 (0.052)	Loss 1.066 (0.801)
Epoch: [48][200/200]	Time 0.748 (0.802)	Data 0.001 (0.056)	Loss 1.303 (0.819)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.250 (0.282)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.249 (0.267)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.7371883392334
==> Statistics for epoch 49: 1079 clusters
Epoch: [49][20/200]	Time 0.741 (0.800)	Data 0.001 (0.055)	Loss 0.191 (0.167)
Epoch: [49][40/200]	Time 0.739 (0.815)	Data 0.001 (0.069)	Loss 0.823 (0.312)
Epoch: [49][60/200]	Time 0.736 (0.795)	Data 0.000 (0.046)	Loss 0.741 (0.525)
Epoch: [49][80/200]	Time 0.740 (0.802)	Data 0.001 (0.053)	Loss 0.795 (0.622)
Epoch: [49][100/200]	Time 2.550 (0.809)	Data 1.783 (0.060)	Loss 1.188 (0.690)
Epoch: [49][120/200]	Time 0.742 (0.800)	Data 0.001 (0.051)	Loss 1.234 (0.736)
Epoch: [49][140/200]	Time 0.742 (0.804)	Data 0.001 (0.055)	Loss 1.216 (0.759)
Epoch: [49][160/200]	Time 0.742 (0.797)	Data 0.000 (0.049)	Loss 0.887 (0.793)
Epoch: [49][180/200]	Time 0.749 (0.802)	Data 0.001 (0.053)	Loss 0.905 (0.812)
Epoch: [49][200/200]	Time 0.747 (0.806)	Data 0.001 (0.056)	Loss 0.957 (0.832)
Extract Features: [50/367]	Time 0.245 (0.282)	Data 0.000 (0.028)	
Extract Features: [100/367]	Time 0.251 (0.269)	Data 0.000 (0.014)	
Extract Features: [150/367]	Time 0.323 (0.273)	Data 0.001 (0.010)	
Extract Features: [200/367]	Time 0.243 (0.272)	Data 0.000 (0.007)	
Extract Features: [250/367]	Time 0.247 (0.273)	Data 0.000 (0.006)	
Extract Features: [300/367]	Time 0.244 (0.274)	Data 0.000 (0.005)	
Extract Features: [350/367]	Time 0.247 (0.274)	Data 0.000 (0.004)	
Mean AP: 71.7%

 * Finished epoch  49  model mAP: 71.7%  best: 71.7% *

==> Test with the best model:
=> Loaded checkpoint 'log/msmt17/resnet152_ibn_cion/model_best.pth.tar'
Extract Features: [50/367]	Time 0.243 (0.284)	Data 0.000 (0.032)	
Extract Features: [100/367]	Time 0.243 (0.268)	Data 0.000 (0.016)	
Extract Features: [150/367]	Time 0.251 (0.264)	Data 0.000 (0.011)	
Extract Features: [200/367]	Time 0.245 (0.262)	Data 0.000 (0.008)	
Extract Features: [250/367]	Time 0.247 (0.260)	Data 0.001 (0.007)	
Extract Features: [300/367]	Time 0.250 (0.259)	Data 0.000 (0.006)	
Extract Features: [350/367]	Time 0.248 (0.258)	Data 0.000 (0.005)	
Mean AP: 71.7%
CMC Scores:
  top-1          89.0%
  top-5          94.0%
  top-10         95.2%
Total running time:  3:52:23.469114
