==========
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_ibn101a', pretrained_path='/home/ma-user/work/Projects/ReIDNets_Checkpoints_TransReID/ResNet101_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/resnet101_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 0.176 (0.396)	Data 0.000 (0.023)	
Extract Features: [100/128]	Time 0.176 (0.299)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.48489832878113
Clustering criterion: eps: 0.700
==> Statistics for epoch 0: 909 clusters
Epoch: [0][20/200]	Time 0.543 (1.019)	Data 0.001 (0.052)	Loss 2.070 (2.402)
Epoch: [0][40/200]	Time 0.548 (0.821)	Data 0.001 (0.062)	Loss 3.248 (2.661)
Epoch: [0][60/200]	Time 0.543 (0.756)	Data 0.001 (0.068)	Loss 2.360 (2.867)
Epoch: [0][80/200]	Time 0.542 (0.703)	Data 0.000 (0.051)	Loss 2.741 (2.781)
Epoch: [0][100/200]	Time 0.543 (0.686)	Data 0.001 (0.056)	Loss 2.822 (2.703)
Epoch: [0][120/200]	Time 0.543 (0.676)	Data 0.001 (0.060)	Loss 2.276 (2.627)
Epoch: [0][140/200]	Time 0.543 (0.658)	Data 0.000 (0.051)	Loss 2.186 (2.568)
Epoch: [0][160/200]	Time 0.550 (0.653)	Data 0.001 (0.054)	Loss 2.132 (2.507)
Epoch: [0][180/200]	Time 0.547 (0.651)	Data 0.001 (0.057)	Loss 2.316 (2.461)
Epoch: [0][200/200]	Time 0.545 (0.648)	Data 0.001 (0.059)	Loss 1.944 (2.418)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.183 (0.207)	Data 0.000 (0.024)	
Extract Features: [100/128]	Time 0.181 (0.199)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.97141361236572
==> Statistics for epoch 1: 1013 clusters
Epoch: [1][20/200]	Time 0.540 (0.603)	Data 0.001 (0.050)	Loss 0.530 (0.540)
Epoch: [1][40/200]	Time 0.547 (0.612)	Data 0.001 (0.062)	Loss 2.148 (0.836)
Epoch: [1][60/200]	Time 0.540 (0.592)	Data 0.000 (0.042)	Loss 1.985 (1.196)
Epoch: [1][80/200]	Time 0.548 (0.600)	Data 0.001 (0.051)	Loss 1.616 (1.335)
Epoch: [1][100/200]	Time 0.546 (0.606)	Data 0.001 (0.057)	Loss 2.035 (1.448)
Epoch: [1][120/200]	Time 0.544 (0.597)	Data 0.000 (0.048)	Loss 1.566 (1.495)
Epoch: [1][140/200]	Time 0.545 (0.603)	Data 0.001 (0.053)	Loss 1.917 (1.540)
Epoch: [1][160/200]	Time 0.546 (0.605)	Data 0.001 (0.056)	Loss 1.832 (1.567)
Epoch: [1][180/200]	Time 0.545 (0.599)	Data 0.000 (0.050)	Loss 1.580 (1.580)
Epoch: [1][200/200]	Time 0.543 (0.601)	Data 0.001 (0.053)	Loss 1.573 (1.591)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.215)	Data 0.000 (0.030)	
Extract Features: [100/128]	Time 0.184 (0.204)	Data 0.000 (0.018)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.33230137825012
==> Statistics for epoch 2: 1006 clusters
Epoch: [2][20/200]	Time 0.540 (0.605)	Data 0.001 (0.058)	Loss 0.383 (0.480)
Epoch: [2][40/200]	Time 0.550 (0.615)	Data 0.001 (0.069)	Loss 2.142 (0.789)
Epoch: [2][60/200]	Time 0.547 (0.595)	Data 0.000 (0.046)	Loss 1.645 (1.118)
Epoch: [2][80/200]	Time 0.550 (0.605)	Data 0.001 (0.056)	Loss 1.879 (1.267)
Epoch: [2][100/200]	Time 0.548 (0.610)	Data 0.001 (0.061)	Loss 1.402 (1.366)
Epoch: [2][120/200]	Time 0.545 (0.600)	Data 0.000 (0.051)	Loss 1.656 (1.417)
Epoch: [2][140/200]	Time 0.546 (0.603)	Data 0.001 (0.054)	Loss 1.887 (1.458)
Epoch: [2][160/200]	Time 0.547 (0.606)	Data 0.001 (0.057)	Loss 1.297 (1.481)
Epoch: [2][180/200]	Time 0.548 (0.600)	Data 0.000 (0.051)	Loss 1.259 (1.507)
Epoch: [2][200/200]	Time 0.548 (0.604)	Data 0.001 (0.055)	Loss 1.404 (1.517)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.219)	Data 0.000 (0.034)	
Extract Features: [100/128]	Time 0.189 (0.205)	Data 0.000 (0.020)	
Computing jaccard distance...
Jaccard distance computing time cost: 65.72061538696289
==> Statistics for epoch 3: 1062 clusters
Epoch: [3][20/200]	Time 0.550 (0.606)	Data 0.003 (0.055)	Loss 0.430 (0.466)
Epoch: [3][40/200]	Time 0.552 (0.620)	Data 0.001 (0.067)	Loss 1.701 (0.696)
Epoch: [3][60/200]	Time 0.543 (0.598)	Data 0.000 (0.045)	Loss 1.582 (1.046)
Epoch: [3][80/200]	Time 0.542 (0.607)	Data 0.001 (0.056)	Loss 1.471 (1.236)
Epoch: [3][100/200]	Time 2.253 (0.613)	Data 1.681 (0.062)	Loss 1.221 (1.324)
Epoch: [3][120/200]	Time 0.547 (0.603)	Data 0.001 (0.052)	Loss 2.118 (1.399)
Epoch: [3][140/200]	Time 0.549 (0.608)	Data 0.001 (0.055)	Loss 1.466 (1.432)
Epoch: [3][160/200]	Time 0.547 (0.601)	Data 0.000 (0.049)	Loss 1.744 (1.465)
Epoch: [3][180/200]	Time 0.552 (0.606)	Data 0.001 (0.052)	Loss 1.689 (1.492)
Epoch: [3][200/200]	Time 0.549 (0.608)	Data 0.001 (0.056)	Loss 2.059 (1.499)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.178 (0.216)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.183 (0.201)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.59576869010925
==> Statistics for epoch 4: 1051 clusters
Epoch: [4][20/200]	Time 0.539 (0.595)	Data 0.001 (0.050)	Loss 0.447 (0.441)
Epoch: [4][40/200]	Time 0.546 (0.613)	Data 0.001 (0.067)	Loss 1.567 (0.654)
Epoch: [4][60/200]	Time 0.544 (0.591)	Data 0.000 (0.045)	Loss 1.821 (1.015)
Epoch: [4][80/200]	Time 0.547 (0.600)	Data 0.001 (0.054)	Loss 1.420 (1.173)
Epoch: [4][100/200]	Time 0.548 (0.606)	Data 0.001 (0.060)	Loss 1.493 (1.279)
Epoch: [4][120/200]	Time 0.554 (0.598)	Data 0.001 (0.050)	Loss 1.642 (1.351)
Epoch: [4][140/200]	Time 0.549 (0.603)	Data 0.001 (0.055)	Loss 1.898 (1.399)
Epoch: [4][160/200]	Time 0.546 (0.596)	Data 0.000 (0.048)	Loss 2.282 (1.428)
Epoch: [4][180/200]	Time 0.548 (0.601)	Data 0.001 (0.053)	Loss 1.360 (1.450)
Epoch: [4][200/200]	Time 0.552 (0.604)	Data 0.001 (0.055)	Loss 1.121 (1.462)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.181 (0.218)	Data 0.000 (0.031)	
Extract Features: [100/128]	Time 0.180 (0.204)	Data 0.001 (0.018)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.61804223060608
==> Statistics for epoch 5: 1052 clusters
Epoch: [5][20/200]	Time 0.546 (0.597)	Data 0.001 (0.052)	Loss 0.347 (0.393)
Epoch: [5][40/200]	Time 0.543 (0.614)	Data 0.001 (0.069)	Loss 2.057 (0.693)
Epoch: [5][60/200]	Time 0.541 (0.593)	Data 0.000 (0.046)	Loss 1.902 (1.010)
Epoch: [5][80/200]	Time 0.551 (0.605)	Data 0.001 (0.056)	Loss 1.887 (1.198)
Epoch: [5][100/200]	Time 0.546 (0.608)	Data 0.001 (0.060)	Loss 1.642 (1.305)
Epoch: [5][120/200]	Time 0.545 (0.600)	Data 0.001 (0.050)	Loss 1.309 (1.358)
Epoch: [5][140/200]	Time 0.548 (0.604)	Data 0.001 (0.054)	Loss 2.121 (1.403)
Epoch: [5][160/200]	Time 0.544 (0.597)	Data 0.000 (0.048)	Loss 1.724 (1.443)
Epoch: [5][180/200]	Time 0.694 (0.602)	Data 0.001 (0.052)	Loss 1.497 (1.467)
Epoch: [5][200/200]	Time 0.546 (0.605)	Data 0.001 (0.055)	Loss 1.753 (1.492)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.179 (0.211)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.183 (0.199)	Data 0.000 (0.014)	
Computing jaccard distance...
Jaccard distance computing time cost: 65.93271565437317
==> Statistics for epoch 6: 1024 clusters
Epoch: [6][20/200]	Time 0.540 (0.596)	Data 0.001 (0.056)	Loss 0.383 (0.420)
Epoch: [6][40/200]	Time 0.541 (0.612)	Data 0.001 (0.068)	Loss 1.583 (0.662)
Epoch: [6][60/200]	Time 0.543 (0.591)	Data 0.000 (0.046)	Loss 1.403 (0.992)
Epoch: [6][80/200]	Time 0.545 (0.600)	Data 0.001 (0.055)	Loss 1.465 (1.143)
Epoch: [6][100/200]	Time 0.545 (0.607)	Data 0.001 (0.060)	Loss 2.003 (1.254)
Epoch: [6][120/200]	Time 0.556 (0.598)	Data 0.002 (0.050)	Loss 2.111 (1.317)
Epoch: [6][140/200]	Time 0.545 (0.603)	Data 0.001 (0.055)	Loss 1.997 (1.343)
Epoch: [6][160/200]	Time 0.545 (0.597)	Data 0.000 (0.048)	Loss 1.905 (1.380)
Epoch: [6][180/200]	Time 0.544 (0.601)	Data 0.001 (0.052)	Loss 1.827 (1.403)
Epoch: [6][200/200]	Time 0.548 (0.603)	Data 0.001 (0.054)	Loss 1.883 (1.429)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.178 (0.216)	Data 0.000 (0.031)	
Extract Features: [100/128]	Time 0.180 (0.201)	Data 0.000 (0.017)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.4155113697052
==> Statistics for epoch 7: 1036 clusters
Epoch: [7][20/200]	Time 0.544 (0.602)	Data 0.001 (0.056)	Loss 0.191 (0.403)
Epoch: [7][40/200]	Time 0.553 (0.617)	Data 0.001 (0.069)	Loss 1.777 (0.618)
Epoch: [7][60/200]	Time 0.542 (0.596)	Data 0.000 (0.046)	Loss 1.907 (0.956)
Epoch: [7][80/200]	Time 0.552 (0.604)	Data 0.001 (0.055)	Loss 1.946 (1.142)
Epoch: [7][100/200]	Time 0.550 (0.611)	Data 0.006 (0.061)	Loss 2.201 (1.251)
Epoch: [7][120/200]	Time 0.547 (0.600)	Data 0.001 (0.051)	Loss 1.720 (1.316)
Epoch: [7][140/200]	Time 0.551 (0.606)	Data 0.001 (0.056)	Loss 1.460 (1.365)
Epoch: [7][160/200]	Time 0.544 (0.599)	Data 0.000 (0.049)	Loss 1.614 (1.394)
Epoch: [7][180/200]	Time 0.548 (0.602)	Data 0.001 (0.052)	Loss 1.368 (1.410)
Epoch: [7][200/200]	Time 0.545 (0.606)	Data 0.001 (0.055)	Loss 1.853 (1.434)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.181 (0.209)	Data 0.001 (0.025)	
Extract Features: [100/128]	Time 0.185 (0.201)	Data 0.000 (0.016)	
Computing jaccard distance...
Jaccard distance computing time cost: 66.36366057395935
==> Statistics for epoch 8: 1064 clusters
Epoch: [8][20/200]	Time 0.543 (0.597)	Data 0.001 (0.045)	Loss 0.395 (0.379)
Epoch: [8][40/200]	Time 0.539 (0.612)	Data 0.001 (0.063)	Loss 2.127 (0.608)
Epoch: [8][60/200]	Time 0.539 (0.592)	Data 0.000 (0.042)	Loss 1.599 (0.922)
Epoch: [8][80/200]	Time 0.664 (0.601)	Data 0.001 (0.051)	Loss 1.584 (1.113)
Epoch: [8][100/200]	Time 2.111 (0.606)	Data 1.532 (0.056)	Loss 1.628 (1.217)
Epoch: [8][120/200]	Time 0.549 (0.598)	Data 0.001 (0.047)	Loss 1.901 (1.301)
Epoch: [8][140/200]	Time 0.548 (0.603)	Data 0.001 (0.052)	Loss 1.479 (1.353)
Epoch: [8][160/200]	Time 0.547 (0.596)	Data 0.000 (0.045)	Loss 1.532 (1.374)
Epoch: [8][180/200]	Time 0.565 (0.600)	Data 0.004 (0.050)	Loss 1.046 (1.397)
Epoch: [8][200/200]	Time 0.671 (0.604)	Data 0.001 (0.053)	Loss 1.269 (1.417)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.177 (0.215)	Data 0.000 (0.034)	
Extract Features: [100/128]	Time 0.179 (0.202)	Data 0.000 (0.019)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.729652881622314
==> Statistics for epoch 9: 1077 clusters
Epoch: [9][20/200]	Time 0.544 (0.599)	Data 0.001 (0.054)	Loss 0.202 (0.306)
Epoch: [9][40/200]	Time 0.679 (0.620)	Data 0.001 (0.068)	Loss 1.072 (0.515)
Epoch: [9][60/200]	Time 0.549 (0.595)	Data 0.000 (0.046)	Loss 1.090 (0.841)
Epoch: [9][80/200]	Time 0.564 (0.606)	Data 0.001 (0.055)	Loss 1.788 (1.013)
Epoch: [9][100/200]	Time 2.162 (0.612)	Data 1.582 (0.060)	Loss 1.571 (1.125)
Epoch: [9][120/200]	Time 0.550 (0.602)	Data 0.001 (0.050)	Loss 1.614 (1.190)
Epoch: [9][140/200]	Time 0.550 (0.607)	Data 0.001 (0.055)	Loss 1.743 (1.234)
Epoch: [9][160/200]	Time 0.547 (0.600)	Data 0.000 (0.048)	Loss 1.479 (1.261)
Epoch: [9][180/200]	Time 0.542 (0.605)	Data 0.001 (0.053)	Loss 1.486 (1.283)
Epoch: [9][200/200]	Time 0.548 (0.608)	Data 0.001 (0.056)	Loss 1.374 (1.308)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.182 (0.218)	Data 0.000 (0.033)	
Extract Features: [100/128]	Time 0.185 (0.203)	Data 0.000 (0.018)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.30641174316406
==> Statistics for epoch 10: 1035 clusters
Epoch: [10][20/200]	Time 0.542 (0.591)	Data 0.001 (0.048)	Loss 0.269 (0.305)
Epoch: [10][40/200]	Time 0.544 (0.612)	Data 0.001 (0.064)	Loss 1.756 (0.522)
Epoch: [10][60/200]	Time 0.545 (0.592)	Data 0.000 (0.043)	Loss 1.376 (0.828)
Epoch: [10][80/200]	Time 0.548 (0.603)	Data 0.001 (0.052)	Loss 1.427 (0.994)
Epoch: [10][100/200]	Time 0.545 (0.609)	Data 0.001 (0.057)	Loss 1.167 (1.085)
Epoch: [10][120/200]	Time 0.548 (0.598)	Data 0.001 (0.048)	Loss 1.215 (1.155)
Epoch: [10][140/200]	Time 0.549 (0.604)	Data 0.001 (0.052)	Loss 1.200 (1.206)
Epoch: [10][160/200]	Time 0.549 (0.597)	Data 0.000 (0.046)	Loss 1.440 (1.236)
Epoch: [10][180/200]	Time 0.545 (0.602)	Data 0.001 (0.050)	Loss 1.760 (1.250)
Epoch: [10][200/200]	Time 0.558 (0.604)	Data 0.001 (0.053)	Loss 1.617 (1.270)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.179 (0.215)	Data 0.000 (0.033)	
Extract Features: [100/128]	Time 0.182 (0.203)	Data 0.000 (0.018)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.69161748886108
==> Statistics for epoch 11: 1018 clusters
Epoch: [11][20/200]	Time 0.539 (0.601)	Data 0.001 (0.053)	Loss 0.223 (0.306)
Epoch: [11][40/200]	Time 0.546 (0.614)	Data 0.001 (0.065)	Loss 1.152 (0.509)
Epoch: [11][60/200]	Time 0.543 (0.593)	Data 0.000 (0.043)	Loss 1.520 (0.801)
Epoch: [11][80/200]	Time 0.547 (0.602)	Data 0.001 (0.053)	Loss 1.198 (0.914)
Epoch: [11][100/200]	Time 0.547 (0.609)	Data 0.001 (0.059)	Loss 1.414 (1.001)
Epoch: [11][120/200]	Time 0.545 (0.599)	Data 0.000 (0.049)	Loss 1.495 (1.053)
Epoch: [11][140/200]	Time 0.546 (0.604)	Data 0.001 (0.054)	Loss 1.131 (1.093)
Epoch: [11][160/200]	Time 0.543 (0.608)	Data 0.001 (0.057)	Loss 1.357 (1.126)
Epoch: [11][180/200]	Time 0.556 (0.601)	Data 0.000 (0.051)	Loss 1.066 (1.144)
Epoch: [11][200/200]	Time 0.549 (0.605)	Data 0.001 (0.054)	Loss 1.152 (1.169)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.233 (0.218)	Data 0.054 (0.032)	
Extract Features: [100/128]	Time 0.181 (0.202)	Data 0.000 (0.018)	
Computing jaccard distance...
Jaccard distance computing time cost: 65.0176739692688
==> Statistics for epoch 12: 1058 clusters
Epoch: [12][20/200]	Time 0.545 (0.595)	Data 0.001 (0.051)	Loss 0.284 (0.308)
Epoch: [12][40/200]	Time 0.549 (0.612)	Data 0.001 (0.066)	Loss 0.815 (0.466)
Epoch: [12][60/200]	Time 0.545 (0.589)	Data 0.000 (0.044)	Loss 1.377 (0.804)
Epoch: [12][80/200]	Time 0.549 (0.601)	Data 0.001 (0.054)	Loss 1.592 (0.961)
Epoch: [12][100/200]	Time 2.190 (0.608)	Data 1.627 (0.059)	Loss 1.245 (1.049)
Epoch: [12][120/200]	Time 0.546 (0.599)	Data 0.001 (0.050)	Loss 1.471 (1.118)
Epoch: [12][140/200]	Time 0.546 (0.603)	Data 0.001 (0.054)	Loss 1.498 (1.170)
Epoch: [12][160/200]	Time 0.543 (0.597)	Data 0.000 (0.047)	Loss 1.129 (1.203)
Epoch: [12][180/200]	Time 0.549 (0.600)	Data 0.001 (0.051)	Loss 2.068 (1.231)
Epoch: [12][200/200]	Time 0.544 (0.603)	Data 0.001 (0.054)	Loss 1.193 (1.249)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.214)	Data 0.000 (0.031)	
Extract Features: [100/128]	Time 0.181 (0.201)	Data 0.000 (0.019)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.80852174758911
==> Statistics for epoch 13: 1055 clusters
Epoch: [13][20/200]	Time 0.539 (0.598)	Data 0.001 (0.053)	Loss 0.209 (0.295)
Epoch: [13][40/200]	Time 0.547 (0.614)	Data 0.001 (0.069)	Loss 1.333 (0.530)
Epoch: [13][60/200]	Time 0.544 (0.593)	Data 0.000 (0.047)	Loss 1.385 (0.832)
Epoch: [13][80/200]	Time 0.550 (0.602)	Data 0.001 (0.055)	Loss 1.572 (0.983)
Epoch: [13][100/200]	Time 0.545 (0.608)	Data 0.001 (0.060)	Loss 1.565 (1.063)
Epoch: [13][120/200]	Time 0.547 (0.598)	Data 0.001 (0.050)	Loss 1.803 (1.123)
Epoch: [13][140/200]	Time 0.545 (0.602)	Data 0.001 (0.054)	Loss 1.553 (1.175)
Epoch: [13][160/200]	Time 0.542 (0.596)	Data 0.000 (0.047)	Loss 1.325 (1.201)
Epoch: [13][180/200]	Time 0.547 (0.600)	Data 0.001 (0.052)	Loss 1.386 (1.222)
Epoch: [13][200/200]	Time 0.543 (0.603)	Data 0.001 (0.055)	Loss 1.318 (1.235)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.181 (0.213)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.182 (0.203)	Data 0.000 (0.017)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.46316456794739
==> Statistics for epoch 14: 1022 clusters
Epoch: [14][20/200]	Time 0.540 (0.597)	Data 0.001 (0.052)	Loss 0.397 (0.298)
Epoch: [14][40/200]	Time 0.542 (0.611)	Data 0.001 (0.063)	Loss 1.305 (0.518)
Epoch: [14][60/200]	Time 0.543 (0.591)	Data 0.000 (0.042)	Loss 1.094 (0.789)
Epoch: [14][80/200]	Time 0.546 (0.599)	Data 0.001 (0.052)	Loss 1.106 (0.905)
Epoch: [14][100/200]	Time 0.546 (0.605)	Data 0.001 (0.057)	Loss 1.728 (0.989)
Epoch: [14][120/200]	Time 0.544 (0.596)	Data 0.000 (0.048)	Loss 1.224 (1.045)
Epoch: [14][140/200]	Time 0.544 (0.599)	Data 0.001 (0.052)	Loss 1.079 (1.084)
Epoch: [14][160/200]	Time 0.542 (0.603)	Data 0.001 (0.055)	Loss 1.767 (1.124)
Epoch: [14][180/200]	Time 0.545 (0.597)	Data 0.000 (0.049)	Loss 1.381 (1.143)
Epoch: [14][200/200]	Time 0.550 (0.601)	Data 0.001 (0.052)	Loss 1.238 (1.160)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.261 (0.212)	Data 0.084 (0.027)	
Extract Features: [100/128]	Time 0.182 (0.199)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.14198207855225
==> Statistics for epoch 15: 1046 clusters
Epoch: [15][20/200]	Time 0.543 (0.595)	Data 0.001 (0.051)	Loss 0.203 (0.272)
Epoch: [15][40/200]	Time 0.544 (0.611)	Data 0.001 (0.065)	Loss 1.159 (0.460)
Epoch: [15][60/200]	Time 0.547 (0.592)	Data 0.000 (0.043)	Loss 1.833 (0.742)
Epoch: [15][80/200]	Time 0.710 (0.603)	Data 0.001 (0.052)	Loss 1.094 (0.898)
Epoch: [15][100/200]	Time 0.545 (0.607)	Data 0.001 (0.058)	Loss 1.194 (0.974)
Epoch: [15][120/200]	Time 0.550 (0.598)	Data 0.001 (0.048)	Loss 1.475 (1.037)
Epoch: [15][140/200]	Time 0.546 (0.602)	Data 0.001 (0.052)	Loss 1.065 (1.089)
Epoch: [15][160/200]	Time 0.548 (0.596)	Data 0.000 (0.046)	Loss 1.458 (1.122)
Epoch: [15][180/200]	Time 0.544 (0.600)	Data 0.001 (0.050)	Loss 0.981 (1.152)
Epoch: [15][200/200]	Time 0.545 (0.602)	Data 0.001 (0.053)	Loss 1.524 (1.172)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.182 (0.211)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.180 (0.201)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 65.44691872596741
==> Statistics for epoch 16: 1035 clusters
Epoch: [16][20/200]	Time 0.541 (0.600)	Data 0.001 (0.049)	Loss 0.366 (0.277)
Epoch: [16][40/200]	Time 0.543 (0.615)	Data 0.001 (0.064)	Loss 1.153 (0.483)
Epoch: [16][60/200]	Time 0.545 (0.594)	Data 0.000 (0.043)	Loss 0.699 (0.760)
Epoch: [16][80/200]	Time 0.560 (0.603)	Data 0.003 (0.053)	Loss 1.097 (0.878)
Epoch: [16][100/200]	Time 0.547 (0.610)	Data 0.001 (0.060)	Loss 1.299 (0.961)
Epoch: [16][120/200]	Time 0.551 (0.600)	Data 0.001 (0.050)	Loss 1.343 (1.034)
Epoch: [16][140/200]	Time 0.545 (0.605)	Data 0.001 (0.055)	Loss 1.501 (1.074)
Epoch: [16][160/200]	Time 0.549 (0.599)	Data 0.000 (0.048)	Loss 1.768 (1.110)
Epoch: [16][180/200]	Time 0.549 (0.602)	Data 0.001 (0.052)	Loss 1.189 (1.136)
Epoch: [16][200/200]	Time 0.546 (0.606)	Data 0.001 (0.055)	Loss 1.197 (1.141)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.215)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.183 (0.202)	Data 0.003 (0.016)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.12016725540161
==> Statistics for epoch 17: 1045 clusters
Epoch: [17][20/200]	Time 0.543 (0.598)	Data 0.001 (0.052)	Loss 0.188 (0.267)
Epoch: [17][40/200]	Time 0.546 (0.615)	Data 0.001 (0.067)	Loss 1.018 (0.443)
Epoch: [17][60/200]	Time 0.546 (0.594)	Data 0.000 (0.045)	Loss 1.099 (0.707)
Epoch: [17][80/200]	Time 0.544 (0.606)	Data 0.001 (0.056)	Loss 1.625 (0.869)
Epoch: [17][100/200]	Time 0.541 (0.611)	Data 0.001 (0.060)	Loss 1.321 (0.960)
Epoch: [17][120/200]	Time 0.547 (0.600)	Data 0.001 (0.050)	Loss 1.307 (1.019)
Epoch: [17][140/200]	Time 0.543 (0.603)	Data 0.001 (0.053)	Loss 1.293 (1.062)
Epoch: [17][160/200]	Time 0.549 (0.595)	Data 0.000 (0.047)	Loss 1.186 (1.086)
Epoch: [17][180/200]	Time 0.547 (0.599)	Data 0.001 (0.050)	Loss 1.600 (1.111)
Epoch: [17][200/200]	Time 0.548 (0.602)	Data 0.001 (0.053)	Loss 1.095 (1.133)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.213)	Data 0.001 (0.029)	
Extract Features: [100/128]	Time 0.179 (0.202)	Data 0.001 (0.017)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.47889471054077
==> Statistics for epoch 18: 1056 clusters
Epoch: [18][20/200]	Time 0.543 (0.598)	Data 0.001 (0.048)	Loss 0.208 (0.245)
Epoch: [18][40/200]	Time 0.539 (0.611)	Data 0.001 (0.063)	Loss 1.500 (0.449)
Epoch: [18][60/200]	Time 0.546 (0.589)	Data 0.000 (0.042)	Loss 1.412 (0.729)
Epoch: [18][80/200]	Time 0.545 (0.598)	Data 0.001 (0.051)	Loss 1.044 (0.856)
Epoch: [18][100/200]	Time 2.144 (0.604)	Data 1.573 (0.056)	Loss 1.129 (0.932)
Epoch: [18][120/200]	Time 0.545 (0.596)	Data 0.001 (0.047)	Loss 1.189 (0.981)
Epoch: [18][140/200]	Time 0.549 (0.600)	Data 0.001 (0.052)	Loss 1.484 (1.041)
Epoch: [18][160/200]	Time 0.541 (0.594)	Data 0.000 (0.045)	Loss 1.190 (1.063)
Epoch: [18][180/200]	Time 0.541 (0.598)	Data 0.001 (0.049)	Loss 1.872 (1.085)
Epoch: [18][200/200]	Time 0.554 (0.600)	Data 0.001 (0.052)	Loss 1.273 (1.114)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.221 (0.213)	Data 0.044 (0.027)	
Extract Features: [100/128]	Time 0.180 (0.200)	Data 0.000 (0.016)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.72241640090942
==> Statistics for epoch 19: 1032 clusters
Epoch: [19][20/200]	Time 0.546 (0.593)	Data 0.001 (0.048)	Loss 0.355 (0.232)
Epoch: [19][40/200]	Time 0.542 (0.611)	Data 0.001 (0.064)	Loss 1.189 (0.428)
Epoch: [19][60/200]	Time 0.545 (0.592)	Data 0.000 (0.043)	Loss 1.170 (0.712)
Epoch: [19][80/200]	Time 0.545 (0.603)	Data 0.001 (0.053)	Loss 1.285 (0.843)
Epoch: [19][100/200]	Time 0.545 (0.610)	Data 0.001 (0.059)	Loss 1.003 (0.910)
Epoch: [19][120/200]	Time 0.546 (0.599)	Data 0.001 (0.049)	Loss 0.959 (0.973)
Epoch: [19][140/200]	Time 0.545 (0.603)	Data 0.001 (0.053)	Loss 1.585 (1.011)
Epoch: [19][160/200]	Time 0.552 (0.597)	Data 0.000 (0.046)	Loss 1.321 (1.032)
Epoch: [19][180/200]	Time 0.545 (0.601)	Data 0.001 (0.050)	Loss 1.267 (1.053)
Epoch: [19][200/200]	Time 0.545 (0.604)	Data 0.001 (0.052)	Loss 1.150 (1.061)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.179 (0.220)	Data 0.000 (0.035)	
Extract Features: [100/128]	Time 0.180 (0.206)	Data 0.000 (0.020)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.86191391944885
==> Statistics for epoch 20: 1079 clusters
Epoch: [20][20/200]	Time 0.547 (0.593)	Data 0.001 (0.048)	Loss 0.208 (0.246)
Epoch: [20][40/200]	Time 0.546 (0.612)	Data 0.001 (0.064)	Loss 0.946 (0.413)
Epoch: [20][60/200]	Time 0.544 (0.592)	Data 0.000 (0.043)	Loss 1.355 (0.683)
Epoch: [20][80/200]	Time 0.548 (0.601)	Data 0.001 (0.052)	Loss 1.237 (0.809)
Epoch: [20][100/200]	Time 2.241 (0.609)	Data 1.679 (0.059)	Loss 1.643 (0.908)
Epoch: [20][120/200]	Time 0.547 (0.600)	Data 0.001 (0.049)	Loss 1.671 (0.974)
Epoch: [20][140/200]	Time 0.545 (0.605)	Data 0.001 (0.054)	Loss 1.500 (1.015)
Epoch: [20][160/200]	Time 0.547 (0.597)	Data 0.000 (0.047)	Loss 1.068 (1.042)
Epoch: [20][180/200]	Time 0.546 (0.601)	Data 0.001 (0.051)	Loss 1.193 (1.060)
Epoch: [20][200/200]	Time 0.544 (0.604)	Data 0.001 (0.054)	Loss 1.366 (1.081)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.218)	Data 0.000 (0.035)	
Extract Features: [100/128]	Time 0.184 (0.205)	Data 0.000 (0.020)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.61623644828796
==> Statistics for epoch 21: 1066 clusters
Epoch: [21][20/200]	Time 0.545 (0.599)	Data 0.001 (0.048)	Loss 0.190 (0.208)
Epoch: [21][40/200]	Time 0.543 (0.614)	Data 0.001 (0.062)	Loss 1.137 (0.385)
Epoch: [21][60/200]	Time 0.544 (0.591)	Data 0.000 (0.042)	Loss 1.640 (0.672)
Epoch: [21][80/200]	Time 0.541 (0.601)	Data 0.001 (0.051)	Loss 0.961 (0.804)
Epoch: [21][100/200]	Time 2.146 (0.606)	Data 1.569 (0.057)	Loss 1.147 (0.881)
Epoch: [21][120/200]	Time 0.546 (0.598)	Data 0.001 (0.047)	Loss 1.435 (0.946)
Epoch: [21][140/200]	Time 0.548 (0.605)	Data 0.001 (0.054)	Loss 1.277 (0.990)
Epoch: [21][160/200]	Time 0.550 (0.598)	Data 0.000 (0.047)	Loss 0.940 (1.016)
Epoch: [21][180/200]	Time 0.543 (0.601)	Data 0.001 (0.050)	Loss 1.341 (1.039)
Epoch: [21][200/200]	Time 0.548 (0.603)	Data 0.001 (0.053)	Loss 1.363 (1.053)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.185 (0.213)	Data 0.001 (0.024)	
Extract Features: [100/128]	Time 0.183 (0.199)	Data 0.000 (0.012)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.28290152549744
==> Statistics for epoch 22: 1067 clusters
Epoch: [22][20/200]	Time 0.540 (0.591)	Data 0.001 (0.049)	Loss 0.262 (0.225)
Epoch: [22][40/200]	Time 0.544 (0.608)	Data 0.001 (0.063)	Loss 1.154 (0.398)
Epoch: [22][60/200]	Time 0.544 (0.589)	Data 0.000 (0.042)	Loss 1.160 (0.671)
Epoch: [22][80/200]	Time 0.542 (0.597)	Data 0.001 (0.051)	Loss 1.568 (0.820)
Epoch: [22][100/200]	Time 2.125 (0.604)	Data 1.546 (0.056)	Loss 1.175 (0.895)
Epoch: [22][120/200]	Time 0.552 (0.596)	Data 0.001 (0.047)	Loss 1.372 (0.957)
Epoch: [22][140/200]	Time 0.545 (0.601)	Data 0.001 (0.052)	Loss 1.180 (1.013)
Epoch: [22][160/200]	Time 0.545 (0.595)	Data 0.000 (0.045)	Loss 0.823 (1.040)
Epoch: [22][180/200]	Time 0.553 (0.600)	Data 0.001 (0.050)	Loss 1.370 (1.063)
Epoch: [22][200/200]	Time 0.550 (0.604)	Data 0.001 (0.054)	Loss 1.359 (1.089)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.284 (0.211)	Data 0.104 (0.028)	
Extract Features: [100/128]	Time 0.180 (0.198)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.64609384536743
==> Statistics for epoch 23: 1060 clusters
Epoch: [23][20/200]	Time 0.540 (0.612)	Data 0.001 (0.062)	Loss 0.256 (0.227)
Epoch: [23][40/200]	Time 0.540 (0.622)	Data 0.001 (0.071)	Loss 1.567 (0.392)
Epoch: [23][60/200]	Time 0.554 (0.596)	Data 0.001 (0.048)	Loss 1.391 (0.673)
Epoch: [23][80/200]	Time 0.545 (0.605)	Data 0.001 (0.055)	Loss 1.793 (0.806)
Epoch: [23][100/200]	Time 2.181 (0.610)	Data 1.615 (0.060)	Loss 1.110 (0.871)
Epoch: [23][120/200]	Time 0.547 (0.600)	Data 0.001 (0.051)	Loss 1.010 (0.939)
Epoch: [23][140/200]	Time 0.550 (0.604)	Data 0.001 (0.055)	Loss 1.469 (0.984)
Epoch: [23][160/200]	Time 0.548 (0.598)	Data 0.000 (0.048)	Loss 1.370 (1.007)
Epoch: [23][180/200]	Time 0.548 (0.602)	Data 0.001 (0.052)	Loss 1.455 (1.025)
Epoch: [23][200/200]	Time 0.552 (0.605)	Data 0.001 (0.054)	Loss 1.575 (1.046)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.178 (0.224)	Data 0.000 (0.039)	
Extract Features: [100/128]	Time 0.307 (0.210)	Data 0.000 (0.024)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.18113136291504
==> Statistics for epoch 24: 1073 clusters
Epoch: [24][20/200]	Time 0.541 (0.599)	Data 0.001 (0.053)	Loss 0.212 (0.205)
Epoch: [24][40/200]	Time 0.544 (0.611)	Data 0.001 (0.067)	Loss 1.123 (0.349)
Epoch: [24][60/200]	Time 0.543 (0.590)	Data 0.000 (0.045)	Loss 1.091 (0.618)
Epoch: [24][80/200]	Time 0.547 (0.601)	Data 0.001 (0.053)	Loss 1.224 (0.773)
Epoch: [24][100/200]	Time 2.227 (0.607)	Data 1.666 (0.059)	Loss 1.188 (0.847)
Epoch: [24][120/200]	Time 0.541 (0.598)	Data 0.001 (0.050)	Loss 1.287 (0.920)
Epoch: [24][140/200]	Time 0.551 (0.602)	Data 0.001 (0.054)	Loss 0.961 (0.966)
Epoch: [24][160/200]	Time 0.541 (0.596)	Data 0.000 (0.048)	Loss 1.554 (1.002)
Epoch: [24][180/200]	Time 0.541 (0.600)	Data 0.001 (0.051)	Loss 1.112 (1.029)
Epoch: [24][200/200]	Time 0.548 (0.603)	Data 0.001 (0.054)	Loss 1.352 (1.046)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.365 (0.222)	Data 0.024 (0.034)	
Extract Features: [100/128]	Time 0.180 (0.204)	Data 0.000 (0.019)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.94702363014221
==> Statistics for epoch 25: 1069 clusters
Epoch: [25][20/200]	Time 0.545 (0.596)	Data 0.001 (0.052)	Loss 0.109 (0.224)
Epoch: [25][40/200]	Time 0.550 (0.615)	Data 0.002 (0.067)	Loss 1.033 (0.359)
Epoch: [25][60/200]	Time 0.543 (0.594)	Data 0.000 (0.045)	Loss 1.248 (0.665)
Epoch: [25][80/200]	Time 0.547 (0.604)	Data 0.001 (0.053)	Loss 1.212 (0.805)
Epoch: [25][100/200]	Time 2.303 (0.611)	Data 1.724 (0.060)	Loss 1.407 (0.893)
Epoch: [25][120/200]	Time 0.544 (0.602)	Data 0.001 (0.050)	Loss 1.262 (0.959)
Epoch: [25][140/200]	Time 0.690 (0.608)	Data 0.001 (0.055)	Loss 1.468 (1.015)
Epoch: [25][160/200]	Time 0.547 (0.601)	Data 0.000 (0.048)	Loss 1.066 (1.041)
Epoch: [25][180/200]	Time 0.545 (0.605)	Data 0.001 (0.052)	Loss 1.118 (1.071)
Epoch: [25][200/200]	Time 0.546 (0.608)	Data 0.001 (0.055)	Loss 1.021 (1.082)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.287 (0.214)	Data 0.000 (0.029)	
Extract Features: [100/128]	Time 0.178 (0.200)	Data 0.000 (0.016)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.52090406417847
==> Statistics for epoch 26: 1078 clusters
Epoch: [26][20/200]	Time 0.540 (0.602)	Data 0.001 (0.049)	Loss 0.157 (0.232)
Epoch: [26][40/200]	Time 0.542 (0.613)	Data 0.001 (0.065)	Loss 1.529 (0.403)
Epoch: [26][60/200]	Time 0.543 (0.591)	Data 0.000 (0.044)	Loss 1.131 (0.675)
Epoch: [26][80/200]	Time 0.545 (0.600)	Data 0.001 (0.052)	Loss 1.437 (0.817)
Epoch: [26][100/200]	Time 2.346 (0.607)	Data 1.781 (0.060)	Loss 1.480 (0.892)
Epoch: [26][120/200]	Time 0.545 (0.598)	Data 0.001 (0.050)	Loss 1.186 (0.942)
Epoch: [26][140/200]	Time 0.545 (0.603)	Data 0.001 (0.054)	Loss 1.034 (0.998)
Epoch: [26][160/200]	Time 0.546 (0.597)	Data 0.000 (0.048)	Loss 0.867 (1.035)
Epoch: [26][180/200]	Time 0.553 (0.601)	Data 0.001 (0.052)	Loss 1.405 (1.059)
Epoch: [26][200/200]	Time 0.571 (0.605)	Data 0.001 (0.055)	Loss 1.470 (1.074)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.184 (0.215)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.186 (0.201)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.07428216934204
==> Statistics for epoch 27: 1072 clusters
Epoch: [27][20/200]	Time 0.546 (0.600)	Data 0.001 (0.056)	Loss 0.267 (0.227)
Epoch: [27][40/200]	Time 0.545 (0.617)	Data 0.001 (0.068)	Loss 1.425 (0.396)
Epoch: [27][60/200]	Time 0.662 (0.595)	Data 0.000 (0.046)	Loss 1.133 (0.650)
Epoch: [27][80/200]	Time 0.549 (0.604)	Data 0.001 (0.055)	Loss 0.862 (0.769)
Epoch: [27][100/200]	Time 2.197 (0.611)	Data 1.621 (0.061)	Loss 1.114 (0.862)
Epoch: [27][120/200]	Time 0.547 (0.600)	Data 0.001 (0.051)	Loss 1.368 (0.929)
Epoch: [27][140/200]	Time 0.548 (0.606)	Data 0.001 (0.055)	Loss 1.484 (0.979)
Epoch: [27][160/200]	Time 0.548 (0.599)	Data 0.000 (0.048)	Loss 0.985 (1.011)
Epoch: [27][180/200]	Time 0.547 (0.603)	Data 0.001 (0.053)	Loss 1.234 (1.039)
Epoch: [27][200/200]	Time 0.549 (0.606)	Data 0.001 (0.055)	Loss 1.136 (1.059)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.287 (0.215)	Data 0.105 (0.029)	
Extract Features: [100/128]	Time 0.180 (0.201)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.561776638031006
==> Statistics for epoch 28: 1083 clusters
Epoch: [28][20/200]	Time 0.545 (0.609)	Data 0.001 (0.058)	Loss 0.221 (0.217)
Epoch: [28][40/200]	Time 0.553 (0.620)	Data 0.001 (0.071)	Loss 1.486 (0.380)
Epoch: [28][60/200]	Time 0.546 (0.599)	Data 0.000 (0.048)	Loss 0.937 (0.636)
Epoch: [28][80/200]	Time 0.547 (0.609)	Data 0.001 (0.057)	Loss 0.913 (0.768)
Epoch: [28][100/200]	Time 2.338 (0.614)	Data 1.744 (0.063)	Loss 1.092 (0.856)
Epoch: [28][120/200]	Time 0.546 (0.604)	Data 0.001 (0.053)	Loss 1.502 (0.913)
Epoch: [28][140/200]	Time 0.549 (0.609)	Data 0.001 (0.057)	Loss 1.174 (0.970)
Epoch: [28][160/200]	Time 0.547 (0.601)	Data 0.000 (0.050)	Loss 1.598 (1.003)
Epoch: [28][180/200]	Time 0.545 (0.606)	Data 0.001 (0.053)	Loss 1.076 (1.025)
Epoch: [28][200/200]	Time 0.551 (0.608)	Data 0.001 (0.056)	Loss 1.180 (1.048)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.179 (0.218)	Data 0.001 (0.034)	
Extract Features: [100/128]	Time 0.189 (0.203)	Data 0.000 (0.017)	
Computing jaccard distance...
Jaccard distance computing time cost: 63.312201261520386
==> Statistics for epoch 29: 1081 clusters
Epoch: [29][20/200]	Time 0.546 (0.600)	Data 0.001 (0.055)	Loss 0.136 (0.205)
Epoch: [29][40/200]	Time 0.540 (0.619)	Data 0.001 (0.071)	Loss 1.098 (0.356)
Epoch: [29][60/200]	Time 0.548 (0.597)	Data 0.000 (0.048)	Loss 0.814 (0.642)
Epoch: [29][80/200]	Time 0.546 (0.606)	Data 0.001 (0.057)	Loss 1.353 (0.781)
Epoch: [29][100/200]	Time 2.244 (0.611)	Data 1.677 (0.062)	Loss 1.512 (0.868)
Epoch: [29][120/200]	Time 0.545 (0.601)	Data 0.001 (0.052)	Loss 1.381 (0.921)
Epoch: [29][140/200]	Time 0.547 (0.607)	Data 0.001 (0.057)	Loss 1.246 (0.970)
Epoch: [29][160/200]	Time 0.542 (0.600)	Data 0.000 (0.050)	Loss 1.427 (1.005)
Epoch: [29][180/200]	Time 0.544 (0.604)	Data 0.001 (0.054)	Loss 1.385 (1.027)
Epoch: [29][200/200]	Time 0.553 (0.607)	Data 0.001 (0.057)	Loss 0.934 (1.048)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.182 (0.221)	Data 0.000 (0.034)	
Extract Features: [100/128]	Time 0.184 (0.205)	Data 0.000 (0.019)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.79280972480774
==> Statistics for epoch 30: 1080 clusters
Epoch: [30][20/200]	Time 0.545 (0.607)	Data 0.001 (0.055)	Loss 0.215 (0.218)
Epoch: [30][40/200]	Time 0.547 (0.621)	Data 0.001 (0.069)	Loss 0.879 (0.376)
Epoch: [30][60/200]	Time 0.655 (0.598)	Data 0.000 (0.046)	Loss 0.979 (0.659)
Epoch: [30][80/200]	Time 0.550 (0.606)	Data 0.001 (0.056)	Loss 1.378 (0.802)
Epoch: [30][100/200]	Time 2.342 (0.612)	Data 1.778 (0.062)	Loss 1.084 (0.894)
Epoch: [30][120/200]	Time 0.548 (0.603)	Data 0.001 (0.052)	Loss 1.570 (0.964)
Epoch: [30][140/200]	Time 0.549 (0.608)	Data 0.001 (0.057)	Loss 1.590 (1.015)
Epoch: [30][160/200]	Time 0.683 (0.601)	Data 0.000 (0.050)	Loss 1.329 (1.040)
Epoch: [30][180/200]	Time 0.550 (0.605)	Data 0.001 (0.055)	Loss 0.783 (1.062)
Epoch: [30][200/200]	Time 0.549 (0.608)	Data 0.001 (0.057)	Loss 1.332 (1.082)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.298 (0.220)	Data 0.000 (0.035)	
Extract Features: [100/128]	Time 0.183 (0.204)	Data 0.000 (0.019)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.304754972457886
==> Statistics for epoch 31: 1080 clusters
Epoch: [31][20/200]	Time 0.546 (0.596)	Data 0.001 (0.052)	Loss 0.159 (0.204)
Epoch: [31][40/200]	Time 0.543 (0.615)	Data 0.001 (0.067)	Loss 1.100 (0.363)
Epoch: [31][60/200]	Time 0.546 (0.591)	Data 0.000 (0.045)	Loss 1.341 (0.647)
Epoch: [31][80/200]	Time 0.547 (0.602)	Data 0.001 (0.053)	Loss 1.201 (0.791)
Epoch: [31][100/200]	Time 2.127 (0.606)	Data 1.548 (0.058)	Loss 1.098 (0.851)
Epoch: [31][120/200]	Time 0.549 (0.597)	Data 0.001 (0.049)	Loss 0.978 (0.911)
Epoch: [31][140/200]	Time 0.550 (0.603)	Data 0.001 (0.055)	Loss 1.322 (0.959)
Epoch: [31][160/200]	Time 0.544 (0.596)	Data 0.000 (0.048)	Loss 1.391 (0.986)
Epoch: [31][180/200]	Time 0.546 (0.601)	Data 0.001 (0.052)	Loss 1.372 (1.015)
Epoch: [31][200/200]	Time 0.548 (0.604)	Data 0.001 (0.054)	Loss 1.112 (1.036)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.215)	Data 0.001 (0.031)	
Extract Features: [100/128]	Time 0.181 (0.202)	Data 0.000 (0.018)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.88860082626343
==> Statistics for epoch 32: 1077 clusters
Epoch: [32][20/200]	Time 0.550 (0.599)	Data 0.001 (0.053)	Loss 0.198 (0.213)
Epoch: [32][40/200]	Time 0.543 (0.622)	Data 0.001 (0.072)	Loss 1.240 (0.376)
Epoch: [32][60/200]	Time 0.546 (0.599)	Data 0.000 (0.049)	Loss 1.022 (0.658)
Epoch: [32][80/200]	Time 0.543 (0.609)	Data 0.001 (0.058)	Loss 1.058 (0.794)
Epoch: [32][100/200]	Time 2.091 (0.612)	Data 1.503 (0.062)	Loss 1.810 (0.885)
Epoch: [32][120/200]	Time 0.549 (0.601)	Data 0.001 (0.052)	Loss 1.174 (0.928)
Epoch: [32][140/200]	Time 0.551 (0.605)	Data 0.001 (0.055)	Loss 0.972 (0.970)
Epoch: [32][160/200]	Time 0.549 (0.599)	Data 0.000 (0.049)	Loss 1.430 (1.000)
Epoch: [32][180/200]	Time 0.547 (0.603)	Data 0.001 (0.053)	Loss 1.440 (1.027)
Epoch: [32][200/200]	Time 0.552 (0.608)	Data 0.001 (0.057)	Loss 1.035 (1.038)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.216)	Data 0.000 (0.033)	
Extract Features: [100/128]	Time 0.188 (0.205)	Data 0.000 (0.018)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.550931215286255
==> Statistics for epoch 33: 1081 clusters
Epoch: [33][20/200]	Time 0.543 (0.595)	Data 0.001 (0.051)	Loss 0.293 (0.225)
Epoch: [33][40/200]	Time 0.553 (0.616)	Data 0.001 (0.068)	Loss 1.089 (0.383)
Epoch: [33][60/200]	Time 0.547 (0.592)	Data 0.000 (0.046)	Loss 1.126 (0.652)
Epoch: [33][80/200]	Time 0.548 (0.604)	Data 0.001 (0.056)	Loss 0.957 (0.772)
Epoch: [33][100/200]	Time 2.148 (0.610)	Data 1.568 (0.060)	Loss 1.239 (0.871)
Epoch: [33][120/200]	Time 0.545 (0.599)	Data 0.001 (0.050)	Loss 1.027 (0.928)
Epoch: [33][140/200]	Time 0.548 (0.604)	Data 0.001 (0.055)	Loss 1.375 (0.967)
Epoch: [33][160/200]	Time 0.712 (0.598)	Data 0.000 (0.048)	Loss 1.012 (0.994)
Epoch: [33][180/200]	Time 0.549 (0.602)	Data 0.001 (0.052)	Loss 1.163 (1.018)
Epoch: [33][200/200]	Time 0.544 (0.605)	Data 0.001 (0.055)	Loss 1.176 (1.037)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.214)	Data 0.000 (0.030)	
Extract Features: [100/128]	Time 0.187 (0.201)	Data 0.000 (0.017)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.76288366317749
==> Statistics for epoch 34: 1080 clusters
Epoch: [34][20/200]	Time 0.546 (0.604)	Data 0.001 (0.055)	Loss 0.111 (0.203)
Epoch: [34][40/200]	Time 0.544 (0.620)	Data 0.001 (0.070)	Loss 1.146 (0.348)
Epoch: [34][60/200]	Time 0.543 (0.598)	Data 0.000 (0.047)	Loss 1.251 (0.620)
Epoch: [34][80/200]	Time 0.546 (0.604)	Data 0.001 (0.054)	Loss 0.897 (0.752)
Epoch: [34][100/200]	Time 2.083 (0.609)	Data 1.501 (0.059)	Loss 1.491 (0.838)
Epoch: [34][120/200]	Time 0.546 (0.599)	Data 0.001 (0.049)	Loss 1.232 (0.896)
Epoch: [34][140/200]	Time 0.547 (0.604)	Data 0.001 (0.054)	Loss 1.025 (0.944)
Epoch: [34][160/200]	Time 0.545 (0.596)	Data 0.000 (0.047)	Loss 1.768 (0.980)
Epoch: [34][180/200]	Time 0.547 (0.600)	Data 0.002 (0.050)	Loss 1.391 (1.011)
Epoch: [34][200/200]	Time 0.548 (0.603)	Data 0.001 (0.053)	Loss 1.039 (1.029)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.233 (0.216)	Data 0.057 (0.032)	
Extract Features: [100/128]	Time 0.180 (0.202)	Data 0.000 (0.018)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.14977025985718
==> Statistics for epoch 35: 1090 clusters
Epoch: [35][20/200]	Time 0.539 (0.597)	Data 0.001 (0.047)	Loss 0.324 (0.225)
Epoch: [35][40/200]	Time 0.539 (0.610)	Data 0.001 (0.061)	Loss 1.193 (0.339)
Epoch: [35][60/200]	Time 0.545 (0.588)	Data 0.001 (0.041)	Loss 1.166 (0.637)
Epoch: [35][80/200]	Time 0.542 (0.600)	Data 0.001 (0.052)	Loss 1.278 (0.771)
Epoch: [35][100/200]	Time 0.543 (0.590)	Data 0.000 (0.042)	Loss 1.341 (0.856)
Epoch: [35][120/200]	Time 0.547 (0.596)	Data 0.001 (0.048)	Loss 0.953 (0.903)
Epoch: [35][140/200]	Time 0.547 (0.603)	Data 0.001 (0.053)	Loss 1.173 (0.938)
Epoch: [35][160/200]	Time 0.552 (0.596)	Data 0.001 (0.047)	Loss 1.170 (0.970)
Epoch: [35][180/200]	Time 0.546 (0.601)	Data 0.001 (0.051)	Loss 1.050 (0.989)
Epoch: [35][200/200]	Time 0.548 (0.595)	Data 0.000 (0.046)	Loss 1.095 (1.005)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.182 (0.215)	Data 0.000 (0.031)	
Extract Features: [100/128]	Time 0.183 (0.202)	Data 0.000 (0.017)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.06582498550415
==> Statistics for epoch 36: 1073 clusters
Epoch: [36][20/200]	Time 0.542 (0.599)	Data 0.001 (0.054)	Loss 0.095 (0.210)
Epoch: [36][40/200]	Time 0.542 (0.615)	Data 0.001 (0.068)	Loss 1.321 (0.365)
Epoch: [36][60/200]	Time 0.542 (0.592)	Data 0.000 (0.046)	Loss 1.605 (0.632)
Epoch: [36][80/200]	Time 0.548 (0.604)	Data 0.003 (0.056)	Loss 1.407 (0.776)
Epoch: [36][100/200]	Time 2.143 (0.610)	Data 1.552 (0.060)	Loss 1.552 (0.860)
Epoch: [36][120/200]	Time 0.548 (0.599)	Data 0.001 (0.050)	Loss 1.186 (0.906)
Epoch: [36][140/200]	Time 0.543 (0.605)	Data 0.001 (0.055)	Loss 1.325 (0.947)
Epoch: [36][160/200]	Time 0.561 (0.597)	Data 0.000 (0.048)	Loss 1.263 (0.974)
Epoch: [36][180/200]	Time 0.545 (0.602)	Data 0.001 (0.052)	Loss 1.548 (0.990)
Epoch: [36][200/200]	Time 0.551 (0.606)	Data 0.001 (0.055)	Loss 0.808 (1.015)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.182 (0.221)	Data 0.000 (0.036)	
Extract Features: [100/128]	Time 0.179 (0.206)	Data 0.000 (0.021)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.54276371002197
==> Statistics for epoch 37: 1080 clusters
Epoch: [37][20/200]	Time 0.541 (0.598)	Data 0.001 (0.051)	Loss 0.100 (0.198)
Epoch: [37][40/200]	Time 0.541 (0.609)	Data 0.001 (0.065)	Loss 1.034 (0.357)
Epoch: [37][60/200]	Time 0.543 (0.589)	Data 0.000 (0.043)	Loss 1.383 (0.607)
Epoch: [37][80/200]	Time 0.551 (0.598)	Data 0.001 (0.052)	Loss 1.042 (0.725)
Epoch: [37][100/200]	Time 2.084 (0.602)	Data 1.510 (0.057)	Loss 1.447 (0.813)
Epoch: [37][120/200]	Time 0.542 (0.592)	Data 0.001 (0.048)	Loss 1.188 (0.884)
Epoch: [37][140/200]	Time 0.549 (0.598)	Data 0.001 (0.052)	Loss 1.462 (0.924)
Epoch: [37][160/200]	Time 0.541 (0.592)	Data 0.000 (0.046)	Loss 1.414 (0.955)
Epoch: [37][180/200]	Time 0.548 (0.596)	Data 0.001 (0.050)	Loss 1.252 (0.986)
Epoch: [37][200/200]	Time 0.543 (0.599)	Data 0.001 (0.052)	Loss 1.218 (1.000)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.181 (0.214)	Data 0.000 (0.031)	
Extract Features: [100/128]	Time 0.181 (0.201)	Data 0.000 (0.017)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.70264458656311
==> Statistics for epoch 38: 1082 clusters
Epoch: [38][20/200]	Time 0.545 (0.593)	Data 0.001 (0.048)	Loss 0.197 (0.202)
Epoch: [38][40/200]	Time 0.547 (0.609)	Data 0.002 (0.063)	Loss 1.041 (0.358)
Epoch: [38][60/200]	Time 0.541 (0.588)	Data 0.000 (0.043)	Loss 1.100 (0.606)
Epoch: [38][80/200]	Time 0.546 (0.598)	Data 0.001 (0.052)	Loss 1.591 (0.766)
Epoch: [38][100/200]	Time 2.174 (0.604)	Data 1.601 (0.058)	Loss 0.828 (0.856)
Epoch: [38][120/200]	Time 0.540 (0.595)	Data 0.001 (0.049)	Loss 1.118 (0.915)
Epoch: [38][140/200]	Time 0.546 (0.599)	Data 0.001 (0.053)	Loss 1.549 (0.956)
Epoch: [38][160/200]	Time 0.545 (0.593)	Data 0.000 (0.046)	Loss 1.270 (0.994)
Epoch: [38][180/200]	Time 0.547 (0.597)	Data 0.001 (0.049)	Loss 1.032 (1.013)
Epoch: [38][200/200]	Time 0.551 (0.600)	Data 0.001 (0.052)	Loss 1.029 (1.031)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.179 (0.214)	Data 0.001 (0.026)	
Extract Features: [100/128]	Time 0.181 (0.199)	Data 0.000 (0.013)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.30839991569519
==> Statistics for epoch 39: 1083 clusters
Epoch: [39][20/200]	Time 0.542 (0.593)	Data 0.001 (0.047)	Loss 0.250 (0.191)
Epoch: [39][40/200]	Time 0.546 (0.613)	Data 0.001 (0.064)	Loss 1.231 (0.351)
Epoch: [39][60/200]	Time 0.547 (0.592)	Data 0.000 (0.043)	Loss 0.880 (0.601)
Epoch: [39][80/200]	Time 0.548 (0.601)	Data 0.001 (0.052)	Loss 1.367 (0.741)
Epoch: [39][100/200]	Time 2.208 (0.608)	Data 1.638 (0.058)	Loss 1.350 (0.826)
Epoch: [39][120/200]	Time 0.553 (0.599)	Data 0.001 (0.048)	Loss 1.398 (0.890)
Epoch: [39][140/200]	Time 0.545 (0.604)	Data 0.001 (0.053)	Loss 1.076 (0.934)
Epoch: [39][160/200]	Time 0.545 (0.597)	Data 0.000 (0.046)	Loss 1.092 (0.971)
Epoch: [39][180/200]	Time 0.547 (0.602)	Data 0.001 (0.052)	Loss 1.062 (0.992)
Epoch: [39][200/200]	Time 0.548 (0.606)	Data 0.001 (0.055)	Loss 0.742 (1.006)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.244 (0.210)	Data 0.068 (0.027)	
Extract Features: [100/128]	Time 0.180 (0.198)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.321205139160156
==> Statistics for epoch 40: 1090 clusters
Epoch: [40][20/200]	Time 0.542 (0.607)	Data 0.001 (0.056)	Loss 0.141 (0.190)
Epoch: [40][40/200]	Time 0.545 (0.620)	Data 0.001 (0.069)	Loss 1.536 (0.331)
Epoch: [40][60/200]	Time 0.544 (0.594)	Data 0.001 (0.046)	Loss 1.148 (0.588)
Epoch: [40][80/200]	Time 0.548 (0.604)	Data 0.001 (0.056)	Loss 0.791 (0.725)
Epoch: [40][100/200]	Time 0.548 (0.594)	Data 0.000 (0.045)	Loss 1.594 (0.812)
Epoch: [40][120/200]	Time 0.548 (0.602)	Data 0.001 (0.052)	Loss 0.997 (0.873)
Epoch: [40][140/200]	Time 0.546 (0.607)	Data 0.001 (0.057)	Loss 0.873 (0.920)
Epoch: [40][160/200]	Time 0.546 (0.600)	Data 0.001 (0.050)	Loss 1.231 (0.955)
Epoch: [40][180/200]	Time 0.547 (0.604)	Data 0.001 (0.054)	Loss 1.143 (0.983)
Epoch: [40][200/200]	Time 0.546 (0.598)	Data 0.000 (0.049)	Loss 1.497 (1.005)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.178 (0.218)	Data 0.000 (0.032)	
Extract Features: [100/128]	Time 0.182 (0.203)	Data 0.000 (0.018)	
Computing jaccard distance...
Jaccard distance computing time cost: 60.61638832092285
==> Statistics for epoch 41: 1090 clusters
Epoch: [41][20/200]	Time 0.540 (0.591)	Data 0.000 (0.050)	Loss 0.206 (0.203)
Epoch: [41][40/200]	Time 0.544 (0.607)	Data 0.001 (0.066)	Loss 1.660 (0.362)
Epoch: [41][60/200]	Time 0.542 (0.587)	Data 0.001 (0.044)	Loss 0.839 (0.621)
Epoch: [41][80/200]	Time 0.542 (0.598)	Data 0.001 (0.053)	Loss 1.398 (0.762)
Epoch: [41][100/200]	Time 0.546 (0.587)	Data 0.000 (0.043)	Loss 1.124 (0.838)
Epoch: [41][120/200]	Time 0.547 (0.595)	Data 0.001 (0.049)	Loss 1.345 (0.887)
Epoch: [41][140/200]	Time 0.545 (0.601)	Data 0.001 (0.054)	Loss 1.234 (0.927)
Epoch: [41][160/200]	Time 0.549 (0.595)	Data 0.001 (0.048)	Loss 1.524 (0.960)
Epoch: [41][180/200]	Time 0.546 (0.599)	Data 0.001 (0.051)	Loss 0.894 (0.984)
Epoch: [41][200/200]	Time 0.547 (0.594)	Data 0.000 (0.046)	Loss 1.470 (1.002)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.179 (0.216)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.183 (0.204)	Data 0.000 (0.017)	
Computing jaccard distance...
Jaccard distance computing time cost: 62.352555990219116
==> Statistics for epoch 42: 1088 clusters
Epoch: [42][20/200]	Time 0.535 (0.597)	Data 0.001 (0.053)	Loss 0.209 (0.199)
Epoch: [42][40/200]	Time 0.544 (0.618)	Data 0.001 (0.071)	Loss 1.170 (0.333)
Epoch: [42][60/200]	Time 0.673 (0.596)	Data 0.001 (0.048)	Loss 1.017 (0.606)
Epoch: [42][80/200]	Time 0.545 (0.603)	Data 0.001 (0.056)	Loss 0.965 (0.747)
Epoch: [42][100/200]	Time 0.544 (0.593)	Data 0.000 (0.045)	Loss 1.424 (0.846)
Epoch: [42][120/200]	Time 0.549 (0.598)	Data 0.001 (0.050)	Loss 1.196 (0.894)
Epoch: [42][140/200]	Time 0.559 (0.603)	Data 0.001 (0.055)	Loss 1.167 (0.937)
Epoch: [42][160/200]	Time 0.550 (0.597)	Data 0.001 (0.048)	Loss 0.826 (0.968)
Epoch: [42][180/200]	Time 0.545 (0.601)	Data 0.001 (0.052)	Loss 1.207 (0.993)
Epoch: [42][200/200]	Time 0.547 (0.596)	Data 0.000 (0.047)	Loss 1.546 (1.012)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.212)	Data 0.000 (0.026)	
Extract Features: [100/128]	Time 0.181 (0.199)	Data 0.000 (0.015)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.405935525894165
==> Statistics for epoch 43: 1091 clusters
Epoch: [43][20/200]	Time 0.539 (0.593)	Data 0.001 (0.050)	Loss 0.150 (0.208)
Epoch: [43][40/200]	Time 0.542 (0.612)	Data 0.001 (0.066)	Loss 1.377 (0.353)
Epoch: [43][60/200]	Time 0.541 (0.591)	Data 0.001 (0.045)	Loss 0.974 (0.624)
Epoch: [43][80/200]	Time 0.547 (0.600)	Data 0.001 (0.052)	Loss 0.950 (0.754)
Epoch: [43][100/200]	Time 0.545 (0.590)	Data 0.000 (0.042)	Loss 1.317 (0.833)
Epoch: [43][120/200]	Time 0.545 (0.595)	Data 0.001 (0.048)	Loss 0.981 (0.904)
Epoch: [43][140/200]	Time 0.545 (0.598)	Data 0.001 (0.051)	Loss 1.547 (0.946)
Epoch: [43][160/200]	Time 0.550 (0.593)	Data 0.001 (0.045)	Loss 1.196 (0.979)
Epoch: [43][180/200]	Time 0.545 (0.598)	Data 0.001 (0.049)	Loss 1.095 (0.998)
Epoch: [43][200/200]	Time 0.549 (0.593)	Data 0.000 (0.044)	Loss 1.405 (1.022)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.179 (0.215)	Data 0.000 (0.032)	
Extract Features: [100/128]	Time 0.182 (0.203)	Data 0.000 (0.019)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.98237657546997
==> Statistics for epoch 44: 1095 clusters
Epoch: [44][20/200]	Time 0.537 (0.603)	Data 0.000 (0.054)	Loss 0.194 (0.227)
Epoch: [44][40/200]	Time 0.543 (0.615)	Data 0.001 (0.067)	Loss 1.555 (0.350)
Epoch: [44][60/200]	Time 0.542 (0.593)	Data 0.001 (0.045)	Loss 1.196 (0.644)
Epoch: [44][80/200]	Time 0.545 (0.604)	Data 0.001 (0.054)	Loss 1.518 (0.768)
Epoch: [44][100/200]	Time 0.655 (0.593)	Data 0.000 (0.043)	Loss 1.020 (0.850)
Epoch: [44][120/200]	Time 0.551 (0.599)	Data 0.001 (0.049)	Loss 1.284 (0.912)
Epoch: [44][140/200]	Time 0.545 (0.604)	Data 0.001 (0.054)	Loss 0.817 (0.949)
Epoch: [44][160/200]	Time 0.553 (0.597)	Data 0.001 (0.048)	Loss 1.234 (0.985)
Epoch: [44][180/200]	Time 0.547 (0.601)	Data 0.001 (0.051)	Loss 1.415 (1.007)
Epoch: [44][200/200]	Time 0.545 (0.596)	Data 0.000 (0.046)	Loss 1.360 (1.023)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.184 (0.215)	Data 0.000 (0.029)	
Extract Features: [100/128]	Time 0.180 (0.203)	Data 0.000 (0.017)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.8616714477539
==> Statistics for epoch 45: 1077 clusters
Epoch: [45][20/200]	Time 0.543 (0.597)	Data 0.001 (0.054)	Loss 0.204 (0.223)
Epoch: [45][40/200]	Time 0.541 (0.609)	Data 0.001 (0.065)	Loss 0.836 (0.342)
Epoch: [45][60/200]	Time 0.544 (0.587)	Data 0.000 (0.044)	Loss 1.059 (0.620)
Epoch: [45][80/200]	Time 0.544 (0.597)	Data 0.001 (0.052)	Loss 0.870 (0.726)
Epoch: [45][100/200]	Time 2.215 (0.605)	Data 1.649 (0.058)	Loss 1.035 (0.819)
Epoch: [45][120/200]	Time 0.549 (0.597)	Data 0.001 (0.049)	Loss 1.525 (0.878)
Epoch: [45][140/200]	Time 0.553 (0.603)	Data 0.001 (0.054)	Loss 1.323 (0.915)
Epoch: [45][160/200]	Time 0.541 (0.597)	Data 0.000 (0.047)	Loss 1.598 (0.948)
Epoch: [45][180/200]	Time 0.546 (0.601)	Data 0.001 (0.052)	Loss 1.063 (0.970)
Epoch: [45][200/200]	Time 0.549 (0.603)	Data 0.001 (0.055)	Loss 1.423 (0.993)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.213)	Data 0.000 (0.028)	
Extract Features: [100/128]	Time 0.181 (0.201)	Data 0.000 (0.017)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.47369980812073
==> Statistics for epoch 46: 1086 clusters
Epoch: [46][20/200]	Time 0.545 (0.592)	Data 0.001 (0.047)	Loss 0.156 (0.204)
Epoch: [46][40/200]	Time 0.546 (0.616)	Data 0.001 (0.068)	Loss 1.150 (0.362)
Epoch: [46][60/200]	Time 0.546 (0.595)	Data 0.000 (0.045)	Loss 1.108 (0.629)
Epoch: [46][80/200]	Time 0.553 (0.603)	Data 0.001 (0.055)	Loss 1.092 (0.752)
Epoch: [46][100/200]	Time 2.207 (0.608)	Data 1.617 (0.060)	Loss 1.257 (0.828)
Epoch: [46][120/200]	Time 0.547 (0.598)	Data 0.001 (0.050)	Loss 1.118 (0.890)
Epoch: [46][140/200]	Time 0.545 (0.604)	Data 0.001 (0.055)	Loss 1.224 (0.926)
Epoch: [46][160/200]	Time 0.547 (0.597)	Data 0.000 (0.048)	Loss 1.049 (0.948)
Epoch: [46][180/200]	Time 0.549 (0.601)	Data 0.001 (0.052)	Loss 1.352 (0.973)
Epoch: [46][200/200]	Time 0.547 (0.605)	Data 0.001 (0.055)	Loss 0.971 (0.993)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.215)	Data 0.000 (0.027)	
Extract Features: [100/128]	Time 0.182 (0.202)	Data 0.000 (0.016)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.50002598762512
==> Statistics for epoch 47: 1086 clusters
Epoch: [47][20/200]	Time 0.539 (0.592)	Data 0.001 (0.050)	Loss 0.154 (0.185)
Epoch: [47][40/200]	Time 0.541 (0.608)	Data 0.001 (0.062)	Loss 1.208 (0.339)
Epoch: [47][60/200]	Time 0.659 (0.588)	Data 0.000 (0.041)	Loss 1.037 (0.607)
Epoch: [47][80/200]	Time 0.542 (0.597)	Data 0.001 (0.050)	Loss 1.369 (0.754)
Epoch: [47][100/200]	Time 2.174 (0.605)	Data 1.593 (0.056)	Loss 1.536 (0.839)
Epoch: [47][120/200]	Time 0.556 (0.596)	Data 0.003 (0.047)	Loss 1.740 (0.898)
Epoch: [47][140/200]	Time 0.549 (0.601)	Data 0.001 (0.052)	Loss 1.149 (0.948)
Epoch: [47][160/200]	Time 0.545 (0.595)	Data 0.000 (0.045)	Loss 1.086 (0.975)
Epoch: [47][180/200]	Time 0.549 (0.598)	Data 0.001 (0.049)	Loss 1.356 (0.997)
Epoch: [47][200/200]	Time 0.546 (0.602)	Data 0.001 (0.052)	Loss 1.426 (1.026)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.185 (0.215)	Data 0.000 (0.030)	
Extract Features: [100/128]	Time 0.181 (0.203)	Data 0.000 (0.017)	
Computing jaccard distance...
Jaccard distance computing time cost: 64.92908525466919
==> Statistics for epoch 48: 1085 clusters
Epoch: [48][20/200]	Time 0.542 (0.606)	Data 0.001 (0.055)	Loss 0.245 (0.230)
Epoch: [48][40/200]	Time 0.545 (0.618)	Data 0.001 (0.070)	Loss 1.054 (0.390)
Epoch: [48][60/200]	Time 0.547 (0.596)	Data 0.000 (0.047)	Loss 1.215 (0.665)
Epoch: [48][80/200]	Time 0.549 (0.605)	Data 0.001 (0.056)	Loss 1.097 (0.783)
Epoch: [48][100/200]	Time 2.145 (0.611)	Data 1.565 (0.060)	Loss 0.970 (0.864)
Epoch: [48][120/200]	Time 0.550 (0.601)	Data 0.001 (0.050)	Loss 0.841 (0.922)
Epoch: [48][140/200]	Time 0.550 (0.607)	Data 0.001 (0.055)	Loss 0.939 (0.951)
Epoch: [48][160/200]	Time 0.543 (0.600)	Data 0.000 (0.048)	Loss 1.175 (0.985)
Epoch: [48][180/200]	Time 0.550 (0.603)	Data 0.001 (0.052)	Loss 0.833 (1.009)
Epoch: [48][200/200]	Time 0.555 (0.606)	Data 0.001 (0.055)	Loss 1.136 (1.027)
==> Create pseudo labels for unlabeled data
Extract Features: [50/128]	Time 0.180 (0.216)	Data 0.000 (0.029)	
Extract Features: [100/128]	Time 0.181 (0.203)	Data 0.001 (0.017)	
Computing jaccard distance...
Jaccard distance computing time cost: 61.783045530319214
==> Statistics for epoch 49: 1090 clusters
Epoch: [49][20/200]	Time 0.550 (0.603)	Data 0.001 (0.053)	Loss 0.203 (0.205)
Epoch: [49][40/200]	Time 0.542 (0.612)	Data 0.001 (0.065)	Loss 1.482 (0.345)
Epoch: [49][60/200]	Time 0.545 (0.591)	Data 0.001 (0.044)	Loss 1.519 (0.612)
Epoch: [49][80/200]	Time 0.549 (0.601)	Data 0.001 (0.053)	Loss 1.191 (0.741)
Epoch: [49][100/200]	Time 0.546 (0.592)	Data 0.000 (0.042)	Loss 0.996 (0.829)
Epoch: [49][120/200]	Time 0.547 (0.597)	Data 0.001 (0.049)	Loss 1.270 (0.888)
Epoch: [49][140/200]	Time 0.544 (0.602)	Data 0.001 (0.054)	Loss 1.026 (0.927)
Epoch: [49][160/200]	Time 0.547 (0.595)	Data 0.001 (0.047)	Loss 0.859 (0.957)
Epoch: [49][180/200]	Time 0.551 (0.600)	Data 0.001 (0.051)	Loss 1.259 (0.979)
Epoch: [49][200/200]	Time 0.544 (0.595)	Data 0.000 (0.046)	Loss 0.860 (0.994)
Extract Features: [50/367]	Time 0.181 (0.213)	Data 0.000 (0.030)	
Extract Features: [100/367]	Time 0.186 (0.200)	Data 0.000 (0.015)	
Extract Features: [150/367]	Time 0.257 (0.199)	Data 0.000 (0.010)	
Extract Features: [200/367]	Time 0.180 (0.201)	Data 0.000 (0.008)	
Extract Features: [250/367]	Time 0.183 (0.200)	Data 0.000 (0.006)	
Extract Features: [300/367]	Time 0.181 (0.201)	Data 0.000 (0.005)	
Extract Features: [350/367]	Time 0.183 (0.201)	Data 0.004 (0.005)	
Mean AP: 69.7%

 * Finished epoch  49  model mAP: 69.7%  best: 69.7% *

==> Test with the best model:
=> Loaded checkpoint 'log/msmt17/resnet101_ibn_cion/model_best.pth.tar'
Extract Features: [50/367]	Time 0.180 (0.222)	Data 0.000 (0.040)	
Extract Features: [100/367]	Time 0.186 (0.204)	Data 0.001 (0.021)	
Extract Features: [150/367]	Time 0.184 (0.198)	Data 0.001 (0.014)	
Extract Features: [200/367]	Time 0.178 (0.195)	Data 0.000 (0.011)	
Extract Features: [250/367]	Time 0.188 (0.194)	Data 0.000 (0.009)	
Extract Features: [300/367]	Time 0.186 (0.192)	Data 0.000 (0.007)	
Extract Features: [350/367]	Time 0.187 (0.191)	Data 0.000 (0.006)	
Mean AP: 69.7%
CMC Scores:
  top-1          88.2%
  top-5          93.5%
  top-10         94.8%
Total running time:  3:13:26.347361
