==========
Args:Namespace(dataset='market1501', batch_size=256, workers=4, height=256, width=128, num_instances=8, eps=0.6, eps_gap=0.02, k1=30, k2=6, arch='resnet50', pretrained_path='/home/ma-user/work/Projects/ReIDNets_Checkpoints_TransReID/ResNet50_ViTdefault_2468_406080100_bs120_originaldino_noreid.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=10, temp=0.05, data_dir='/home/ma-user/work/Projects/ReIDNet_Finetune/CContrast/data', logs_dir='log/market/resnet50_cion', pooling_type='gem', use_hard=True)
==========
==> Load unlabeled dataset
=> Market1501 loaded
Dataset statistics:
  ----------------------------------------
  subset   | # ids | # images | # cameras
  ----------------------------------------
  train    |   751 |    12936 |         6
  query    |   750 |     3368 |         6
  gallery  |   751 |    15913 |         6
  ----------------------------------------
pooling_type: gem
optimizer: SGD
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.156 (0.453)	Data 0.063 (0.032)	
Computing jaccard distance...
Jaccard distance computing time cost: 21.66786289215088
Clustering criterion: eps: 0.600
==> Statistics for epoch 0: 607 clusters
Epoch: [0][20/200]	Time 0.252 (0.694)	Data 0.001 (0.098)	Loss 4.521 (3.153)
Epoch: [0][40/200]	Time 0.252 (0.505)	Data 0.001 (0.080)	Loss 3.503 (3.652)
Epoch: [0][60/200]	Time 0.251 (0.443)	Data 0.000 (0.074)	Loss 3.337 (3.511)
Epoch: [0][80/200]	Time 0.251 (0.415)	Data 0.000 (0.075)	Loss 3.086 (3.406)
Epoch: [0][100/200]	Time 0.250 (0.397)	Data 0.001 (0.073)	Loss 3.645 (3.334)
Epoch: [0][120/200]	Time 0.250 (0.384)	Data 0.000 (0.072)	Loss 2.481 (3.258)
Epoch: [0][140/200]	Time 0.251 (0.377)	Data 0.000 (0.073)	Loss 2.846 (3.193)
Epoch: [0][160/200]	Time 0.250 (0.369)	Data 0.000 (0.072)	Loss 2.796 (3.130)
Epoch: [0][180/200]	Time 0.251 (0.364)	Data 0.000 (0.071)	Loss 3.037 (3.078)
Epoch: [0][200/200]	Time 0.259 (0.366)	Data 0.000 (0.077)	Loss 2.562 (3.042)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.149)	Data 0.000 (0.034)	
Computing jaccard distance...
Jaccard distance computing time cost: 20.643158435821533
==> Statistics for epoch 1: 638 clusters
Epoch: [1][20/200]	Time 1.953 (0.382)	Data 1.687 (0.122)	Loss 2.681 (0.839)
Epoch: [1][40/200]	Time 0.252 (0.355)	Data 0.001 (0.098)	Loss 2.648 (1.714)
Epoch: [1][60/200]	Time 0.258 (0.345)	Data 0.001 (0.087)	Loss 2.304 (2.012)
Epoch: [1][80/200]	Time 0.254 (0.339)	Data 0.001 (0.082)	Loss 2.412 (2.117)
Epoch: [1][100/200]	Time 0.382 (0.337)	Data 0.001 (0.079)	Loss 2.575 (2.212)
Epoch: [1][120/200]	Time 0.256 (0.335)	Data 0.001 (0.078)	Loss 2.670 (2.246)
Epoch: [1][140/200]	Time 0.251 (0.333)	Data 0.001 (0.076)	Loss 1.762 (2.279)
Epoch: [1][160/200]	Time 0.253 (0.332)	Data 0.001 (0.076)	Loss 2.784 (2.299)
Epoch: [1][180/200]	Time 0.253 (0.331)	Data 0.001 (0.075)	Loss 2.445 (2.309)
Epoch: [1][200/200]	Time 0.253 (0.331)	Data 0.001 (0.074)	Loss 2.243 (2.315)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.139)	Data 0.000 (0.043)	
Computing jaccard distance...
Jaccard distance computing time cost: 20.66020631790161
==> Statistics for epoch 2: 596 clusters
Epoch: [2][20/200]	Time 0.253 (0.374)	Data 0.001 (0.121)	Loss 2.284 (0.744)
Epoch: [2][40/200]	Time 0.254 (0.348)	Data 0.001 (0.092)	Loss 2.660 (1.521)
Epoch: [2][60/200]	Time 0.252 (0.338)	Data 0.001 (0.083)	Loss 2.592 (1.801)
Epoch: [2][80/200]	Time 0.252 (0.334)	Data 0.000 (0.079)	Loss 2.251 (1.940)
Epoch: [2][100/200]	Time 0.252 (0.331)	Data 0.001 (0.075)	Loss 2.124 (2.017)
Epoch: [2][120/200]	Time 0.252 (0.330)	Data 0.000 (0.074)	Loss 2.746 (2.068)
Epoch: [2][140/200]	Time 0.252 (0.330)	Data 0.000 (0.073)	Loss 1.981 (2.091)
Epoch: [2][160/200]	Time 0.251 (0.329)	Data 0.000 (0.073)	Loss 1.964 (2.101)
Epoch: [2][180/200]	Time 0.253 (0.330)	Data 0.000 (0.073)	Loss 2.302 (2.111)
Epoch: [2][200/200]	Time 0.258 (0.335)	Data 0.001 (0.079)	Loss 1.750 (2.116)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.095 (0.136)	Data 0.000 (0.038)	
Computing jaccard distance...
Jaccard distance computing time cost: 20.248859405517578
==> Statistics for epoch 3: 579 clusters
Epoch: [3][20/200]	Time 0.251 (0.363)	Data 0.001 (0.104)	Loss 2.078 (0.650)
Epoch: [3][40/200]	Time 0.251 (0.341)	Data 0.001 (0.084)	Loss 2.335 (1.451)
Epoch: [3][60/200]	Time 0.254 (0.335)	Data 0.000 (0.078)	Loss 2.079 (1.745)
Epoch: [3][80/200]	Time 0.253 (0.334)	Data 0.000 (0.077)	Loss 2.232 (1.857)
Epoch: [3][100/200]	Time 0.254 (0.333)	Data 0.001 (0.075)	Loss 2.246 (1.921)
Epoch: [3][120/200]	Time 0.253 (0.331)	Data 0.000 (0.074)	Loss 2.253 (1.963)
Epoch: [3][140/200]	Time 0.251 (0.329)	Data 0.000 (0.073)	Loss 2.472 (1.988)
Epoch: [3][160/200]	Time 0.251 (0.329)	Data 0.000 (0.072)	Loss 2.371 (2.007)
Epoch: [3][180/200]	Time 0.336 (0.329)	Data 0.000 (0.072)	Loss 2.378 (2.023)
Epoch: [3][200/200]	Time 0.258 (0.335)	Data 0.001 (0.078)	Loss 2.122 (2.033)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.095 (0.137)	Data 0.000 (0.039)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.91169500350952
==> Statistics for epoch 4: 594 clusters
Epoch: [4][20/200]	Time 0.263 (0.381)	Data 0.001 (0.125)	Loss 1.666 (0.564)
Epoch: [4][40/200]	Time 0.253 (0.358)	Data 0.001 (0.098)	Loss 1.841 (1.300)
Epoch: [4][60/200]	Time 0.251 (0.353)	Data 0.001 (0.093)	Loss 1.885 (1.539)
Epoch: [4][80/200]	Time 0.254 (0.347)	Data 0.001 (0.089)	Loss 2.563 (1.658)
Epoch: [4][100/200]	Time 0.252 (0.344)	Data 0.001 (0.085)	Loss 2.233 (1.728)
Epoch: [4][120/200]	Time 0.255 (0.342)	Data 0.000 (0.083)	Loss 1.751 (1.775)
Epoch: [4][140/200]	Time 0.262 (0.341)	Data 0.000 (0.082)	Loss 1.856 (1.807)
Epoch: [4][160/200]	Time 0.349 (0.340)	Data 0.000 (0.082)	Loss 2.436 (1.834)
Epoch: [4][180/200]	Time 0.254 (0.338)	Data 0.000 (0.080)	Loss 1.619 (1.840)
Epoch: [4][200/200]	Time 0.255 (0.346)	Data 0.001 (0.087)	Loss 1.996 (1.850)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.139)	Data 0.000 (0.039)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.86306357383728
==> Statistics for epoch 5: 596 clusters
Epoch: [5][20/200]	Time 0.249 (0.359)	Data 0.001 (0.097)	Loss 1.848 (0.542)
Epoch: [5][40/200]	Time 0.353 (0.341)	Data 0.001 (0.081)	Loss 2.054 (1.200)
Epoch: [5][60/200]	Time 0.251 (0.333)	Data 0.001 (0.075)	Loss 2.312 (1.460)
Epoch: [5][80/200]	Time 0.253 (0.331)	Data 0.001 (0.073)	Loss 2.189 (1.590)
Epoch: [5][100/200]	Time 0.251 (0.329)	Data 0.001 (0.071)	Loss 2.441 (1.657)
Epoch: [5][120/200]	Time 0.254 (0.330)	Data 0.000 (0.071)	Loss 2.271 (1.704)
Epoch: [5][140/200]	Time 0.253 (0.329)	Data 0.000 (0.071)	Loss 1.957 (1.746)
Epoch: [5][160/200]	Time 0.253 (0.330)	Data 0.000 (0.071)	Loss 2.280 (1.772)
Epoch: [5][180/200]	Time 0.255 (0.331)	Data 0.000 (0.073)	Loss 2.147 (1.785)
Epoch: [5][200/200]	Time 0.258 (0.338)	Data 0.001 (0.080)	Loss 1.724 (1.796)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.092 (0.132)	Data 0.000 (0.033)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.682878017425537
==> Statistics for epoch 6: 576 clusters
Epoch: [6][20/200]	Time 0.272 (0.369)	Data 0.001 (0.107)	Loss 1.996 (0.491)
Epoch: [6][40/200]	Time 0.253 (0.351)	Data 0.001 (0.091)	Loss 1.897 (1.147)
Epoch: [6][60/200]	Time 0.254 (0.345)	Data 0.001 (0.085)	Loss 1.943 (1.408)
Epoch: [6][80/200]	Time 0.253 (0.342)	Data 0.001 (0.083)	Loss 2.284 (1.533)
Epoch: [6][100/200]	Time 0.256 (0.338)	Data 0.001 (0.079)	Loss 1.743 (1.587)
Epoch: [6][120/200]	Time 0.253 (0.337)	Data 0.000 (0.077)	Loss 1.676 (1.633)
Epoch: [6][140/200]	Time 0.251 (0.334)	Data 0.000 (0.075)	Loss 1.894 (1.656)
Epoch: [6][160/200]	Time 0.253 (0.332)	Data 0.000 (0.074)	Loss 1.563 (1.669)
Epoch: [6][180/200]	Time 0.254 (0.332)	Data 0.000 (0.073)	Loss 1.486 (1.678)
Epoch: [6][200/200]	Time 0.257 (0.338)	Data 0.001 (0.080)	Loss 1.546 (1.695)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.133)	Data 0.000 (0.034)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.5259268283844
==> Statistics for epoch 7: 582 clusters
Epoch: [7][20/200]	Time 0.256 (0.364)	Data 0.001 (0.109)	Loss 1.552 (0.446)
Epoch: [7][40/200]	Time 0.360 (0.349)	Data 0.001 (0.091)	Loss 1.874 (1.053)
Epoch: [7][60/200]	Time 0.254 (0.339)	Data 0.001 (0.082)	Loss 1.633 (1.286)
Epoch: [7][80/200]	Time 0.253 (0.335)	Data 0.001 (0.077)	Loss 1.785 (1.392)
Epoch: [7][100/200]	Time 0.252 (0.332)	Data 0.001 (0.075)	Loss 1.524 (1.467)
Epoch: [7][120/200]	Time 0.252 (0.331)	Data 0.000 (0.073)	Loss 1.841 (1.505)
Epoch: [7][140/200]	Time 0.254 (0.330)	Data 0.000 (0.073)	Loss 1.874 (1.546)
Epoch: [7][160/200]	Time 0.257 (0.329)	Data 0.000 (0.071)	Loss 1.594 (1.573)
Epoch: [7][180/200]	Time 0.254 (0.328)	Data 0.000 (0.071)	Loss 1.929 (1.589)
Epoch: [7][200/200]	Time 0.254 (0.335)	Data 0.001 (0.078)	Loss 1.493 (1.596)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.132)	Data 0.000 (0.034)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.83171558380127
==> Statistics for epoch 8: 589 clusters
Epoch: [8][20/200]	Time 0.257 (0.368)	Data 0.001 (0.103)	Loss 1.644 (0.423)
Epoch: [8][40/200]	Time 0.257 (0.345)	Data 0.001 (0.083)	Loss 1.545 (1.024)
Epoch: [8][60/200]	Time 0.252 (0.337)	Data 0.001 (0.077)	Loss 1.393 (1.264)
Epoch: [8][80/200]	Time 0.252 (0.335)	Data 0.001 (0.077)	Loss 1.681 (1.379)
Epoch: [8][100/200]	Time 0.252 (0.332)	Data 0.001 (0.074)	Loss 1.804 (1.444)
Epoch: [8][120/200]	Time 0.252 (0.331)	Data 0.000 (0.073)	Loss 1.534 (1.489)
Epoch: [8][140/200]	Time 0.254 (0.330)	Data 0.000 (0.072)	Loss 1.558 (1.514)
Epoch: [8][160/200]	Time 0.253 (0.329)	Data 0.000 (0.072)	Loss 1.632 (1.533)
Epoch: [8][180/200]	Time 0.252 (0.329)	Data 0.000 (0.071)	Loss 1.792 (1.550)
Epoch: [8][200/200]	Time 0.254 (0.335)	Data 0.000 (0.078)	Loss 1.588 (1.553)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.095 (0.140)	Data 0.000 (0.041)	
Computing jaccard distance...
Jaccard distance computing time cost: 20.143710613250732
==> Statistics for epoch 9: 587 clusters
Epoch: [9][20/200]	Time 0.253 (0.361)	Data 0.001 (0.105)	Loss 1.574 (0.435)
Epoch: [9][40/200]	Time 0.253 (0.342)	Data 0.001 (0.084)	Loss 1.504 (0.987)
Epoch: [9][60/200]	Time 0.252 (0.333)	Data 0.001 (0.077)	Loss 1.998 (1.223)
Epoch: [9][80/200]	Time 0.253 (0.330)	Data 0.001 (0.075)	Loss 1.506 (1.300)
Epoch: [9][100/200]	Time 0.251 (0.330)	Data 0.001 (0.073)	Loss 1.497 (1.377)
Epoch: [9][120/200]	Time 0.256 (0.328)	Data 0.000 (0.072)	Loss 1.733 (1.416)
Epoch: [9][140/200]	Time 0.251 (0.327)	Data 0.000 (0.071)	Loss 1.358 (1.437)
Epoch: [9][160/200]	Time 0.252 (0.327)	Data 0.000 (0.070)	Loss 1.622 (1.457)
Epoch: [9][180/200]	Time 0.252 (0.326)	Data 0.000 (0.070)	Loss 1.768 (1.484)
Epoch: [9][200/200]	Time 0.254 (0.334)	Data 0.001 (0.077)	Loss 1.706 (1.492)
Extract Features: [50/76]	Time 0.207 (0.136)	Data 0.000 (0.037)	
Mean AP: 86.2%

 * Finished epoch   9  model mAP: 86.2%  best: 86.2% *

==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.096 (0.135)	Data 0.002 (0.035)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.81278133392334
==> Statistics for epoch 10: 590 clusters
Epoch: [10][20/200]	Time 0.254 (0.419)	Data 0.001 (0.120)	Loss 1.457 (0.422)
Epoch: [10][40/200]	Time 0.254 (0.375)	Data 0.001 (0.098)	Loss 1.248 (0.943)
Epoch: [10][60/200]	Time 0.253 (0.362)	Data 0.001 (0.090)	Loss 1.419 (1.169)
Epoch: [10][80/200]	Time 0.254 (0.353)	Data 0.001 (0.085)	Loss 1.363 (1.285)
Epoch: [10][100/200]	Time 0.255 (0.349)	Data 0.001 (0.083)	Loss 1.222 (1.351)
Epoch: [10][120/200]	Time 0.255 (0.348)	Data 0.000 (0.083)	Loss 1.548 (1.379)
Epoch: [10][140/200]	Time 0.251 (0.346)	Data 0.000 (0.082)	Loss 1.223 (1.416)
Epoch: [10][160/200]	Time 0.257 (0.344)	Data 0.000 (0.081)	Loss 1.324 (1.433)
Epoch: [10][180/200]	Time 0.252 (0.344)	Data 0.000 (0.081)	Loss 1.168 (1.452)
Epoch: [10][200/200]	Time 0.254 (0.351)	Data 0.001 (0.088)	Loss 1.500 (1.460)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.134)	Data 0.000 (0.037)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.115118980407715
==> Statistics for epoch 11: 587 clusters
Epoch: [11][20/200]	Time 0.254 (0.373)	Data 0.001 (0.117)	Loss 1.148 (0.343)
Epoch: [11][40/200]	Time 0.252 (0.353)	Data 0.001 (0.096)	Loss 1.549 (0.904)
Epoch: [11][60/200]	Time 0.254 (0.346)	Data 0.001 (0.089)	Loss 1.523 (1.121)
Epoch: [11][80/200]	Time 0.252 (0.345)	Data 0.001 (0.087)	Loss 1.837 (1.229)
Epoch: [11][100/200]	Time 0.253 (0.343)	Data 0.001 (0.085)	Loss 1.499 (1.279)
Epoch: [11][120/200]	Time 0.362 (0.342)	Data 0.000 (0.083)	Loss 1.654 (1.308)
Epoch: [11][140/200]	Time 0.253 (0.340)	Data 0.000 (0.082)	Loss 1.781 (1.338)
Epoch: [11][160/200]	Time 0.253 (0.339)	Data 0.000 (0.081)	Loss 1.407 (1.355)
Epoch: [11][180/200]	Time 0.256 (0.338)	Data 0.000 (0.080)	Loss 1.455 (1.371)
Epoch: [11][200/200]	Time 0.252 (0.346)	Data 0.001 (0.087)	Loss 1.742 (1.383)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.137)	Data 0.000 (0.038)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.35196828842163
==> Statistics for epoch 12: 601 clusters
Epoch: [12][20/200]	Time 0.254 (0.359)	Data 0.002 (0.103)	Loss 1.235 (0.343)
Epoch: [12][40/200]	Time 0.253 (0.343)	Data 0.001 (0.084)	Loss 1.556 (0.896)
Epoch: [12][60/200]	Time 0.358 (0.337)	Data 0.001 (0.078)	Loss 1.587 (1.128)
Epoch: [12][80/200]	Time 0.254 (0.333)	Data 0.001 (0.075)	Loss 1.465 (1.212)
Epoch: [12][100/200]	Time 0.252 (0.334)	Data 0.001 (0.075)	Loss 1.634 (1.270)
Epoch: [12][120/200]	Time 0.253 (0.331)	Data 0.000 (0.073)	Loss 1.094 (1.307)
Epoch: [12][140/200]	Time 0.252 (0.330)	Data 0.000 (0.072)	Loss 1.350 (1.330)
Epoch: [12][160/200]	Time 0.251 (0.330)	Data 0.000 (0.072)	Loss 1.361 (1.358)
Epoch: [12][180/200]	Time 0.253 (0.329)	Data 0.000 (0.072)	Loss 1.314 (1.371)
Epoch: [12][200/200]	Time 0.255 (0.336)	Data 0.001 (0.079)	Loss 1.149 (1.380)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.130)	Data 0.000 (0.033)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.74369740486145
==> Statistics for epoch 13: 599 clusters
Epoch: [13][20/200]	Time 0.252 (0.355)	Data 0.001 (0.097)	Loss 1.380 (0.375)
Epoch: [13][40/200]	Time 0.252 (0.336)	Data 0.001 (0.080)	Loss 1.518 (0.878)
Epoch: [13][60/200]	Time 0.253 (0.334)	Data 0.001 (0.077)	Loss 1.423 (1.044)
Epoch: [13][80/200]	Time 0.254 (0.334)	Data 0.000 (0.076)	Loss 1.297 (1.149)
Epoch: [13][100/200]	Time 0.252 (0.332)	Data 0.000 (0.075)	Loss 1.086 (1.193)
Epoch: [13][120/200]	Time 0.253 (0.330)	Data 0.000 (0.073)	Loss 1.581 (1.249)
Epoch: [13][140/200]	Time 0.253 (0.330)	Data 0.000 (0.073)	Loss 1.662 (1.277)
Epoch: [13][160/200]	Time 0.252 (0.329)	Data 0.000 (0.072)	Loss 1.400 (1.297)
Epoch: [13][180/200]	Time 0.253 (0.329)	Data 0.000 (0.072)	Loss 1.281 (1.326)
Epoch: [13][200/200]	Time 0.253 (0.336)	Data 0.000 (0.078)	Loss 1.566 (1.341)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.147 (0.137)	Data 0.054 (0.041)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.300599575042725
==> Statistics for epoch 14: 600 clusters
Epoch: [14][20/200]	Time 0.264 (0.379)	Data 0.001 (0.114)	Loss 1.405 (0.338)
Epoch: [14][40/200]	Time 0.255 (0.357)	Data 0.002 (0.097)	Loss 1.299 (0.831)
Epoch: [14][60/200]	Time 0.251 (0.350)	Data 0.001 (0.089)	Loss 1.473 (1.040)
Epoch: [14][80/200]	Time 0.255 (0.346)	Data 0.001 (0.085)	Loss 1.176 (1.139)
Epoch: [14][100/200]	Time 0.255 (0.344)	Data 0.001 (0.085)	Loss 1.341 (1.193)
Epoch: [14][120/200]	Time 0.254 (0.343)	Data 0.000 (0.084)	Loss 1.324 (1.227)
Epoch: [14][140/200]	Time 0.253 (0.342)	Data 0.000 (0.083)	Loss 0.866 (1.260)
Epoch: [14][160/200]	Time 0.260 (0.341)	Data 0.001 (0.082)	Loss 1.154 (1.281)
Epoch: [14][180/200]	Time 0.253 (0.340)	Data 0.000 (0.081)	Loss 1.601 (1.294)
Epoch: [14][200/200]	Time 0.254 (0.347)	Data 0.001 (0.088)	Loss 1.455 (1.307)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.105 (0.133)	Data 0.012 (0.036)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.239639282226562
==> Statistics for epoch 15: 600 clusters
Epoch: [15][20/200]	Time 0.259 (0.372)	Data 0.001 (0.114)	Loss 1.293 (0.332)
Epoch: [15][40/200]	Time 0.256 (0.352)	Data 0.001 (0.096)	Loss 1.409 (0.841)
Epoch: [15][60/200]	Time 0.254 (0.347)	Data 0.001 (0.090)	Loss 1.456 (1.020)
Epoch: [15][80/200]	Time 0.254 (0.345)	Data 0.001 (0.087)	Loss 1.564 (1.118)
Epoch: [15][100/200]	Time 0.253 (0.342)	Data 0.001 (0.085)	Loss 1.745 (1.169)
Epoch: [15][120/200]	Time 0.254 (0.344)	Data 0.000 (0.086)	Loss 1.313 (1.216)
Epoch: [15][140/200]	Time 0.254 (0.342)	Data 0.000 (0.085)	Loss 1.570 (1.251)
Epoch: [15][160/200]	Time 0.253 (0.341)	Data 0.000 (0.084)	Loss 1.177 (1.261)
Epoch: [15][180/200]	Time 0.255 (0.341)	Data 0.000 (0.083)	Loss 1.461 (1.270)
Epoch: [15][200/200]	Time 0.252 (0.348)	Data 0.001 (0.090)	Loss 1.466 (1.286)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.095 (0.134)	Data 0.000 (0.036)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.662294387817383
==> Statistics for epoch 16: 594 clusters
Epoch: [16][20/200]	Time 0.255 (0.382)	Data 0.001 (0.127)	Loss 1.312 (0.336)
Epoch: [16][40/200]	Time 0.255 (0.355)	Data 0.001 (0.097)	Loss 1.373 (0.795)
Epoch: [16][60/200]	Time 0.252 (0.346)	Data 0.001 (0.090)	Loss 1.011 (0.967)
Epoch: [16][80/200]	Time 0.253 (0.341)	Data 0.001 (0.085)	Loss 1.363 (1.057)
Epoch: [16][100/200]	Time 0.254 (0.340)	Data 0.001 (0.083)	Loss 1.078 (1.112)
Epoch: [16][120/200]	Time 0.254 (0.338)	Data 0.000 (0.081)	Loss 1.341 (1.162)
Epoch: [16][140/200]	Time 0.251 (0.338)	Data 0.000 (0.081)	Loss 1.683 (1.191)
Epoch: [16][160/200]	Time 0.252 (0.336)	Data 0.000 (0.079)	Loss 1.238 (1.218)
Epoch: [16][180/200]	Time 0.254 (0.335)	Data 0.000 (0.078)	Loss 1.414 (1.232)
Epoch: [16][200/200]	Time 0.254 (0.344)	Data 0.001 (0.086)	Loss 1.561 (1.237)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.139)	Data 0.000 (0.042)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.062381744384766
==> Statistics for epoch 17: 599 clusters
Epoch: [17][20/200]	Time 0.260 (0.377)	Data 0.001 (0.120)	Loss 1.265 (0.312)
Epoch: [17][40/200]	Time 0.347 (0.353)	Data 0.000 (0.094)	Loss 1.410 (0.791)
Epoch: [17][60/200]	Time 0.266 (0.342)	Data 0.000 (0.085)	Loss 1.483 (0.980)
Epoch: [17][80/200]	Time 0.252 (0.338)	Data 0.000 (0.081)	Loss 1.185 (1.056)
Epoch: [17][100/200]	Time 0.254 (0.336)	Data 0.001 (0.079)	Loss 1.183 (1.111)
Epoch: [17][120/200]	Time 0.254 (0.335)	Data 0.000 (0.078)	Loss 1.227 (1.137)
Epoch: [17][140/200]	Time 0.253 (0.335)	Data 0.000 (0.078)	Loss 1.634 (1.163)
Epoch: [17][160/200]	Time 0.253 (0.335)	Data 0.000 (0.078)	Loss 1.618 (1.189)
Epoch: [17][180/200]	Time 0.265 (0.335)	Data 0.000 (0.078)	Loss 1.472 (1.204)
Epoch: [17][200/200]	Time 0.255 (0.342)	Data 0.000 (0.085)	Loss 1.754 (1.220)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.166 (0.140)	Data 0.073 (0.041)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.289568424224854
==> Statistics for epoch 18: 597 clusters
Epoch: [18][20/200]	Time 0.251 (0.366)	Data 0.001 (0.109)	Loss 1.504 (0.337)
Epoch: [18][40/200]	Time 0.251 (0.344)	Data 0.000 (0.086)	Loss 1.320 (0.812)
Epoch: [18][60/200]	Time 0.253 (0.337)	Data 0.001 (0.080)	Loss 1.157 (0.950)
Epoch: [18][80/200]	Time 0.252 (0.336)	Data 0.001 (0.078)	Loss 1.458 (1.046)
Epoch: [18][100/200]	Time 0.252 (0.335)	Data 0.001 (0.078)	Loss 1.429 (1.078)
Epoch: [18][120/200]	Time 0.254 (0.336)	Data 0.000 (0.078)	Loss 1.500 (1.100)
Epoch: [18][140/200]	Time 0.252 (0.336)	Data 0.000 (0.079)	Loss 1.561 (1.121)
Epoch: [18][160/200]	Time 0.251 (0.335)	Data 0.000 (0.077)	Loss 1.427 (1.149)
Epoch: [18][180/200]	Time 0.253 (0.334)	Data 0.000 (0.076)	Loss 1.256 (1.165)
Epoch: [18][200/200]	Time 0.259 (0.341)	Data 0.000 (0.084)	Loss 1.286 (1.175)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.137)	Data 0.000 (0.038)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.214812517166138
==> Statistics for epoch 19: 598 clusters
Epoch: [19][20/200]	Time 0.253 (0.365)	Data 0.001 (0.102)	Loss 1.830 (0.330)
Epoch: [19][40/200]	Time 0.253 (0.343)	Data 0.001 (0.084)	Loss 1.501 (0.774)
Epoch: [19][60/200]	Time 0.252 (0.336)	Data 0.001 (0.078)	Loss 1.129 (0.949)
Epoch: [19][80/200]	Time 0.252 (0.333)	Data 0.001 (0.075)	Loss 1.704 (1.032)
Epoch: [19][100/200]	Time 0.254 (0.332)	Data 0.001 (0.074)	Loss 1.328 (1.074)
Epoch: [19][120/200]	Time 0.252 (0.331)	Data 0.000 (0.073)	Loss 1.096 (1.104)
Epoch: [19][140/200]	Time 0.253 (0.330)	Data 0.000 (0.072)	Loss 1.322 (1.138)
Epoch: [19][160/200]	Time 0.252 (0.329)	Data 0.000 (0.072)	Loss 1.334 (1.153)
Epoch: [19][180/200]	Time 0.252 (0.329)	Data 0.000 (0.072)	Loss 1.207 (1.164)
Epoch: [19][200/200]	Time 0.254 (0.335)	Data 0.000 (0.077)	Loss 1.213 (1.175)
Extract Features: [50/76]	Time 0.099 (0.130)	Data 0.006 (0.032)	
Mean AP: 88.9%

 * Finished epoch  19  model mAP: 88.9%  best: 88.9% *

==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.129)	Data 0.000 (0.031)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.135918617248535
==> Statistics for epoch 20: 596 clusters
Epoch: [20][20/200]	Time 0.251 (0.360)	Data 0.001 (0.104)	Loss 0.933 (0.261)
Epoch: [20][40/200]	Time 0.253 (0.345)	Data 0.001 (0.089)	Loss 1.412 (0.703)
Epoch: [20][60/200]	Time 0.252 (0.338)	Data 0.001 (0.082)	Loss 1.606 (0.881)
Epoch: [20][80/200]	Time 0.252 (0.334)	Data 0.000 (0.079)	Loss 1.180 (0.945)
Epoch: [20][100/200]	Time 0.252 (0.334)	Data 0.000 (0.077)	Loss 1.026 (1.011)
Epoch: [20][120/200]	Time 0.254 (0.332)	Data 0.000 (0.076)	Loss 0.979 (1.040)
Epoch: [20][140/200]	Time 0.253 (0.331)	Data 0.000 (0.075)	Loss 1.218 (1.072)
Epoch: [20][160/200]	Time 0.253 (0.332)	Data 0.000 (0.076)	Loss 1.485 (1.091)
Epoch: [20][180/200]	Time 0.253 (0.332)	Data 0.000 (0.076)	Loss 1.173 (1.101)
Epoch: [20][200/200]	Time 0.256 (0.339)	Data 0.001 (0.082)	Loss 1.155 (1.108)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.133 (0.139)	Data 0.040 (0.042)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.23172688484192
==> Statistics for epoch 21: 602 clusters
Epoch: [21][20/200]	Time 0.270 (0.371)	Data 0.018 (0.115)	Loss 1.199 (0.267)
Epoch: [21][40/200]	Time 0.255 (0.354)	Data 0.001 (0.095)	Loss 1.206 (0.710)
Epoch: [21][60/200]	Time 0.253 (0.347)	Data 0.001 (0.090)	Loss 1.445 (0.878)
Epoch: [21][80/200]	Time 0.253 (0.346)	Data 0.001 (0.088)	Loss 1.048 (0.961)
Epoch: [21][100/200]	Time 0.254 (0.341)	Data 0.001 (0.084)	Loss 1.078 (1.011)
Epoch: [21][120/200]	Time 0.252 (0.341)	Data 0.000 (0.083)	Loss 1.617 (1.052)
Epoch: [21][140/200]	Time 0.303 (0.341)	Data 0.000 (0.082)	Loss 1.290 (1.065)
Epoch: [21][160/200]	Time 0.253 (0.340)	Data 0.000 (0.081)	Loss 0.895 (1.086)
Epoch: [21][180/200]	Time 0.255 (0.339)	Data 0.000 (0.081)	Loss 1.149 (1.104)
Epoch: [21][200/200]	Time 0.258 (0.347)	Data 0.000 (0.088)	Loss 1.248 (1.115)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.139 (0.137)	Data 0.045 (0.040)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.605407238006592
==> Statistics for epoch 22: 606 clusters
Epoch: [22][20/200]	Time 0.252 (0.384)	Data 0.001 (0.128)	Loss 0.927 (0.234)
Epoch: [22][40/200]	Time 0.254 (0.359)	Data 0.001 (0.102)	Loss 1.047 (0.682)
Epoch: [22][60/200]	Time 0.254 (0.349)	Data 0.001 (0.093)	Loss 1.272 (0.851)
Epoch: [22][80/200]	Time 0.253 (0.347)	Data 0.001 (0.090)	Loss 1.149 (0.939)
Epoch: [22][100/200]	Time 0.254 (0.344)	Data 0.001 (0.087)	Loss 0.852 (0.994)
Epoch: [22][120/200]	Time 0.252 (0.343)	Data 0.000 (0.085)	Loss 1.375 (1.028)
Epoch: [22][140/200]	Time 0.253 (0.342)	Data 0.000 (0.084)	Loss 1.365 (1.050)
Epoch: [22][160/200]	Time 0.253 (0.340)	Data 0.000 (0.083)	Loss 1.267 (1.066)
Epoch: [22][180/200]	Time 0.251 (0.341)	Data 0.000 (0.083)	Loss 1.345 (1.074)
Epoch: [22][200/200]	Time 0.261 (0.347)	Data 0.001 (0.089)	Loss 1.066 (1.084)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.137)	Data 0.000 (0.038)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.663255214691162
==> Statistics for epoch 23: 601 clusters
Epoch: [23][20/200]	Time 0.255 (0.375)	Data 0.001 (0.113)	Loss 1.019 (0.255)
Epoch: [23][40/200]	Time 0.255 (0.355)	Data 0.001 (0.097)	Loss 1.097 (0.661)
Epoch: [23][60/200]	Time 0.254 (0.349)	Data 0.001 (0.090)	Loss 1.323 (0.867)
Epoch: [23][80/200]	Time 0.254 (0.346)	Data 0.001 (0.087)	Loss 0.719 (0.938)
Epoch: [23][100/200]	Time 0.251 (0.342)	Data 0.001 (0.084)	Loss 1.286 (0.994)
Epoch: [23][120/200]	Time 0.258 (0.341)	Data 0.001 (0.083)	Loss 1.170 (1.018)
Epoch: [23][140/200]	Time 0.254 (0.338)	Data 0.000 (0.080)	Loss 1.083 (1.039)
Epoch: [23][160/200]	Time 0.252 (0.339)	Data 0.000 (0.080)	Loss 1.367 (1.063)
Epoch: [23][180/200]	Time 0.253 (0.338)	Data 0.000 (0.080)	Loss 0.871 (1.083)
Epoch: [23][200/200]	Time 0.257 (0.346)	Data 0.001 (0.087)	Loss 1.220 (1.099)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.138)	Data 0.000 (0.039)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.472398281097412
==> Statistics for epoch 24: 606 clusters
Epoch: [24][20/200]	Time 0.255 (0.372)	Data 0.001 (0.108)	Loss 0.947 (0.279)
Epoch: [24][40/200]	Time 0.254 (0.350)	Data 0.001 (0.088)	Loss 1.334 (0.685)
Epoch: [24][60/200]	Time 0.254 (0.340)	Data 0.001 (0.081)	Loss 1.080 (0.859)
Epoch: [24][80/200]	Time 0.254 (0.339)	Data 0.001 (0.080)	Loss 1.160 (0.922)
Epoch: [24][100/200]	Time 0.255 (0.336)	Data 0.001 (0.078)	Loss 1.168 (0.966)
Epoch: [24][120/200]	Time 0.252 (0.334)	Data 0.000 (0.076)	Loss 0.917 (0.996)
Epoch: [24][140/200]	Time 0.252 (0.332)	Data 0.000 (0.075)	Loss 0.895 (1.021)
Epoch: [24][160/200]	Time 0.251 (0.332)	Data 0.000 (0.074)	Loss 1.766 (1.041)
Epoch: [24][180/200]	Time 0.254 (0.331)	Data 0.000 (0.073)	Loss 1.191 (1.068)
Epoch: [24][200/200]	Time 0.258 (0.338)	Data 0.001 (0.080)	Loss 1.345 (1.079)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.134)	Data 0.000 (0.036)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.67409873008728
==> Statistics for epoch 25: 605 clusters
Epoch: [25][20/200]	Time 0.257 (0.381)	Data 0.001 (0.119)	Loss 1.164 (0.251)
Epoch: [25][40/200]	Time 0.280 (0.354)	Data 0.001 (0.095)	Loss 1.288 (0.647)
Epoch: [25][60/200]	Time 0.251 (0.341)	Data 0.001 (0.084)	Loss 1.321 (0.814)
Epoch: [25][80/200]	Time 0.251 (0.338)	Data 0.001 (0.081)	Loss 1.187 (0.901)
Epoch: [25][100/200]	Time 0.254 (0.335)	Data 0.001 (0.079)	Loss 1.574 (0.958)
Epoch: [25][120/200]	Time 0.253 (0.334)	Data 0.000 (0.076)	Loss 1.262 (0.994)
Epoch: [25][140/200]	Time 0.252 (0.331)	Data 0.000 (0.074)	Loss 0.975 (1.015)
Epoch: [25][160/200]	Time 0.252 (0.331)	Data 0.000 (0.074)	Loss 1.160 (1.029)
Epoch: [25][180/200]	Time 0.252 (0.330)	Data 0.000 (0.073)	Loss 1.271 (1.045)
Epoch: [25][200/200]	Time 0.257 (0.336)	Data 0.001 (0.078)	Loss 1.278 (1.063)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.130 (0.135)	Data 0.037 (0.039)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.509093046188354
==> Statistics for epoch 26: 605 clusters
Epoch: [26][20/200]	Time 0.253 (0.363)	Data 0.001 (0.108)	Loss 0.660 (0.233)
Epoch: [26][40/200]	Time 0.256 (0.358)	Data 0.001 (0.099)	Loss 1.011 (0.666)
Epoch: [26][60/200]	Time 0.252 (0.348)	Data 0.001 (0.091)	Loss 1.246 (0.830)
Epoch: [26][80/200]	Time 0.252 (0.342)	Data 0.001 (0.085)	Loss 0.836 (0.892)
Epoch: [26][100/200]	Time 0.253 (0.338)	Data 0.001 (0.081)	Loss 1.261 (0.942)
Epoch: [26][120/200]	Time 0.254 (0.334)	Data 0.000 (0.078)	Loss 1.171 (0.980)
Epoch: [26][140/200]	Time 0.251 (0.332)	Data 0.000 (0.076)	Loss 0.885 (1.005)
Epoch: [26][160/200]	Time 0.255 (0.332)	Data 0.000 (0.075)	Loss 1.387 (1.029)
Epoch: [26][180/200]	Time 0.254 (0.333)	Data 0.000 (0.076)	Loss 1.172 (1.049)
Epoch: [26][200/200]	Time 0.252 (0.340)	Data 0.001 (0.083)	Loss 1.141 (1.059)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.138)	Data 0.000 (0.038)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.058602809906006
==> Statistics for epoch 27: 607 clusters
Epoch: [27][20/200]	Time 0.285 (0.384)	Data 0.001 (0.119)	Loss 1.048 (0.252)
Epoch: [27][40/200]	Time 0.253 (0.352)	Data 0.001 (0.092)	Loss 0.992 (0.660)
Epoch: [27][60/200]	Time 0.253 (0.348)	Data 0.001 (0.088)	Loss 1.312 (0.832)
Epoch: [27][80/200]	Time 0.253 (0.343)	Data 0.001 (0.083)	Loss 1.425 (0.925)
Epoch: [27][100/200]	Time 0.256 (0.340)	Data 0.001 (0.081)	Loss 1.115 (0.980)
Epoch: [27][120/200]	Time 0.254 (0.338)	Data 0.000 (0.079)	Loss 1.074 (1.012)
Epoch: [27][140/200]	Time 0.253 (0.337)	Data 0.000 (0.077)	Loss 1.363 (1.034)
Epoch: [27][160/200]	Time 0.252 (0.337)	Data 0.000 (0.078)	Loss 1.659 (1.042)
Epoch: [27][180/200]	Time 0.255 (0.336)	Data 0.000 (0.078)	Loss 1.036 (1.052)
Epoch: [27][200/200]	Time 0.256 (0.344)	Data 0.000 (0.086)	Loss 1.200 (1.064)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.177 (0.137)	Data 0.000 (0.038)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.35882830619812
==> Statistics for epoch 28: 609 clusters
Epoch: [28][20/200]	Time 1.877 (0.383)	Data 1.579 (0.123)	Loss 1.094 (0.209)
Epoch: [28][40/200]	Time 0.254 (0.356)	Data 0.001 (0.099)	Loss 0.947 (0.666)
Epoch: [28][60/200]	Time 0.278 (0.348)	Data 0.001 (0.090)	Loss 1.110 (0.842)
Epoch: [28][80/200]	Time 0.251 (0.343)	Data 0.001 (0.086)	Loss 0.977 (0.927)
Epoch: [28][100/200]	Time 0.251 (0.343)	Data 0.001 (0.085)	Loss 1.130 (0.969)
Epoch: [28][120/200]	Time 0.253 (0.340)	Data 0.001 (0.083)	Loss 0.728 (1.008)
Epoch: [28][140/200]	Time 0.253 (0.340)	Data 0.001 (0.083)	Loss 1.191 (1.031)
Epoch: [28][160/200]	Time 0.253 (0.341)	Data 0.001 (0.083)	Loss 1.057 (1.052)
Epoch: [28][180/200]	Time 0.251 (0.339)	Data 0.001 (0.081)	Loss 1.561 (1.073)
Epoch: [28][200/200]	Time 0.254 (0.339)	Data 0.001 (0.081)	Loss 1.087 (1.084)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.144 (0.136)	Data 0.051 (0.039)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.169952630996704
==> Statistics for epoch 29: 611 clusters
Epoch: [29][20/200]	Time 1.786 (0.372)	Data 1.469 (0.115)	Loss 0.984 (0.212)
Epoch: [29][40/200]	Time 0.253 (0.347)	Data 0.001 (0.090)	Loss 1.303 (0.663)
Epoch: [29][60/200]	Time 0.254 (0.345)	Data 0.001 (0.086)	Loss 1.233 (0.824)
Epoch: [29][80/200]	Time 0.253 (0.340)	Data 0.001 (0.083)	Loss 1.160 (0.905)
Epoch: [29][100/200]	Time 0.252 (0.339)	Data 0.001 (0.081)	Loss 1.227 (0.967)
Epoch: [29][120/200]	Time 0.251 (0.338)	Data 0.001 (0.081)	Loss 1.284 (1.001)
Epoch: [29][140/200]	Time 0.254 (0.337)	Data 0.001 (0.080)	Loss 1.108 (1.034)
Epoch: [29][160/200]	Time 0.253 (0.337)	Data 0.001 (0.080)	Loss 1.347 (1.054)
Epoch: [29][180/200]	Time 0.254 (0.337)	Data 0.001 (0.079)	Loss 1.295 (1.065)
Epoch: [29][200/200]	Time 0.255 (0.336)	Data 0.001 (0.079)	Loss 1.304 (1.084)
Extract Features: [50/76]	Time 0.094 (0.136)	Data 0.000 (0.039)	
Mean AP: 90.3%

 * Finished epoch  29  model mAP: 90.3%  best: 90.3% *

==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.132 (0.134)	Data 0.039 (0.035)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.085705757141113
==> Statistics for epoch 30: 611 clusters
Epoch: [30][20/200]	Time 1.795 (0.385)	Data 1.502 (0.123)	Loss 1.146 (0.216)
Epoch: [30][40/200]	Time 0.267 (0.357)	Data 0.001 (0.097)	Loss 1.087 (0.690)
Epoch: [30][60/200]	Time 0.258 (0.347)	Data 0.001 (0.088)	Loss 1.240 (0.850)
Epoch: [30][80/200]	Time 0.259 (0.343)	Data 0.001 (0.083)	Loss 1.162 (0.938)
Epoch: [30][100/200]	Time 0.254 (0.339)	Data 0.001 (0.080)	Loss 1.246 (0.980)
Epoch: [30][120/200]	Time 0.254 (0.337)	Data 0.001 (0.078)	Loss 1.280 (1.012)
Epoch: [30][140/200]	Time 0.254 (0.336)	Data 0.001 (0.077)	Loss 1.036 (1.032)
Epoch: [30][160/200]	Time 0.259 (0.334)	Data 0.001 (0.076)	Loss 1.584 (1.047)
Epoch: [30][180/200]	Time 0.254 (0.334)	Data 0.001 (0.075)	Loss 1.141 (1.062)
Epoch: [30][200/200]	Time 0.269 (0.333)	Data 0.001 (0.075)	Loss 1.082 (1.061)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.139)	Data 0.000 (0.040)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.346002101898193
==> Statistics for epoch 31: 609 clusters
Epoch: [31][20/200]	Time 1.762 (0.368)	Data 1.478 (0.112)	Loss 1.388 (0.234)
Epoch: [31][40/200]	Time 0.256 (0.352)	Data 0.001 (0.094)	Loss 1.164 (0.678)
Epoch: [31][60/200]	Time 0.256 (0.344)	Data 0.001 (0.086)	Loss 1.130 (0.832)
Epoch: [31][80/200]	Time 0.254 (0.341)	Data 0.001 (0.083)	Loss 1.118 (0.911)
Epoch: [31][100/200]	Time 0.258 (0.338)	Data 0.001 (0.080)	Loss 1.244 (0.959)
Epoch: [31][120/200]	Time 0.255 (0.336)	Data 0.001 (0.077)	Loss 1.362 (0.994)
Epoch: [31][140/200]	Time 0.252 (0.334)	Data 0.001 (0.076)	Loss 1.154 (1.015)
Epoch: [31][160/200]	Time 0.255 (0.333)	Data 0.001 (0.075)	Loss 1.243 (1.033)
Epoch: [31][180/200]	Time 0.252 (0.333)	Data 0.001 (0.075)	Loss 1.159 (1.048)
Epoch: [31][200/200]	Time 0.251 (0.333)	Data 0.000 (0.075)	Loss 0.866 (1.058)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.131)	Data 0.000 (0.032)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.30360770225525
==> Statistics for epoch 32: 610 clusters
Epoch: [32][20/200]	Time 1.640 (0.368)	Data 1.374 (0.112)	Loss 1.122 (0.216)
Epoch: [32][40/200]	Time 0.253 (0.346)	Data 0.001 (0.089)	Loss 1.117 (0.681)
Epoch: [32][60/200]	Time 0.254 (0.339)	Data 0.001 (0.082)	Loss 1.241 (0.851)
Epoch: [32][80/200]	Time 0.252 (0.334)	Data 0.001 (0.077)	Loss 1.395 (0.945)
Epoch: [32][100/200]	Time 0.263 (0.332)	Data 0.001 (0.076)	Loss 1.050 (0.991)
Epoch: [32][120/200]	Time 0.253 (0.331)	Data 0.001 (0.074)	Loss 1.022 (1.011)
Epoch: [32][140/200]	Time 0.256 (0.330)	Data 0.001 (0.073)	Loss 1.462 (1.032)
Epoch: [32][160/200]	Time 0.254 (0.329)	Data 0.001 (0.072)	Loss 1.070 (1.044)
Epoch: [32][180/200]	Time 0.252 (0.329)	Data 0.001 (0.072)	Loss 1.265 (1.062)
Epoch: [32][200/200]	Time 0.253 (0.328)	Data 0.001 (0.071)	Loss 0.988 (1.070)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.132)	Data 0.000 (0.036)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.02237558364868
==> Statistics for epoch 33: 610 clusters
Epoch: [33][20/200]	Time 1.702 (0.370)	Data 1.426 (0.115)	Loss 1.157 (0.209)
Epoch: [33][40/200]	Time 0.258 (0.353)	Data 0.001 (0.097)	Loss 1.375 (0.640)
Epoch: [33][60/200]	Time 0.260 (0.346)	Data 0.001 (0.090)	Loss 1.154 (0.813)
Epoch: [33][80/200]	Time 0.255 (0.342)	Data 0.001 (0.086)	Loss 1.169 (0.900)
Epoch: [33][100/200]	Time 0.257 (0.341)	Data 0.001 (0.084)	Loss 1.083 (0.945)
Epoch: [33][120/200]	Time 0.255 (0.341)	Data 0.001 (0.083)	Loss 1.026 (0.986)
Epoch: [33][140/200]	Time 0.254 (0.339)	Data 0.001 (0.082)	Loss 1.166 (1.004)
Epoch: [33][160/200]	Time 0.254 (0.337)	Data 0.001 (0.080)	Loss 1.323 (1.023)
Epoch: [33][180/200]	Time 0.255 (0.337)	Data 0.001 (0.080)	Loss 1.038 (1.040)
Epoch: [33][200/200]	Time 0.252 (0.337)	Data 0.001 (0.080)	Loss 1.225 (1.052)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.136)	Data 0.000 (0.037)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.469305515289307
==> Statistics for epoch 34: 611 clusters
Epoch: [34][20/200]	Time 1.825 (0.376)	Data 1.525 (0.115)	Loss 1.224 (0.217)
Epoch: [34][40/200]	Time 0.257 (0.356)	Data 0.001 (0.098)	Loss 1.008 (0.653)
Epoch: [34][60/200]	Time 0.257 (0.345)	Data 0.000 (0.087)	Loss 1.093 (0.811)
Epoch: [34][80/200]	Time 0.255 (0.343)	Data 0.000 (0.085)	Loss 1.609 (0.899)
Epoch: [34][100/200]	Time 0.256 (0.342)	Data 0.000 (0.083)	Loss 1.520 (0.948)
Epoch: [34][120/200]	Time 0.254 (0.340)	Data 0.000 (0.082)	Loss 0.748 (0.983)
Epoch: [34][140/200]	Time 0.255 (0.341)	Data 0.001 (0.083)	Loss 1.133 (1.010)
Epoch: [34][160/200]	Time 0.252 (0.339)	Data 0.000 (0.081)	Loss 0.945 (1.023)
Epoch: [34][180/200]	Time 0.254 (0.338)	Data 0.001 (0.080)	Loss 0.995 (1.034)
Epoch: [34][200/200]	Time 0.255 (0.337)	Data 0.001 (0.078)	Loss 1.385 (1.046)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.137 (0.137)	Data 0.044 (0.038)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.47031044960022
==> Statistics for epoch 35: 614 clusters
Epoch: [35][20/200]	Time 1.589 (0.369)	Data 1.306 (0.112)	Loss 1.193 (0.218)
Epoch: [35][40/200]	Time 0.252 (0.346)	Data 0.001 (0.088)	Loss 1.041 (0.634)
Epoch: [35][60/200]	Time 0.257 (0.339)	Data 0.001 (0.082)	Loss 1.169 (0.801)
Epoch: [35][80/200]	Time 0.253 (0.336)	Data 0.001 (0.079)	Loss 1.135 (0.905)
Epoch: [35][100/200]	Time 0.261 (0.334)	Data 0.001 (0.077)	Loss 1.380 (0.952)
Epoch: [35][120/200]	Time 0.254 (0.332)	Data 0.001 (0.075)	Loss 1.131 (0.977)
Epoch: [35][140/200]	Time 0.252 (0.331)	Data 0.001 (0.074)	Loss 1.205 (0.995)
Epoch: [35][160/200]	Time 0.255 (0.330)	Data 0.001 (0.073)	Loss 1.062 (1.017)
Epoch: [35][180/200]	Time 0.254 (0.330)	Data 0.001 (0.073)	Loss 1.160 (1.028)
Epoch: [35][200/200]	Time 0.253 (0.330)	Data 0.001 (0.072)	Loss 0.940 (1.037)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.130)	Data 0.000 (0.033)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.413527488708496
==> Statistics for epoch 36: 611 clusters
Epoch: [36][20/200]	Time 1.665 (0.367)	Data 1.383 (0.111)	Loss 1.351 (0.237)
Epoch: [36][40/200]	Time 0.255 (0.354)	Data 0.001 (0.096)	Loss 1.107 (0.676)
Epoch: [36][60/200]	Time 0.364 (0.343)	Data 0.001 (0.085)	Loss 1.112 (0.835)
Epoch: [36][80/200]	Time 0.254 (0.337)	Data 0.001 (0.080)	Loss 1.015 (0.929)
Epoch: [36][100/200]	Time 0.254 (0.336)	Data 0.001 (0.078)	Loss 1.502 (0.964)
Epoch: [36][120/200]	Time 0.253 (0.334)	Data 0.001 (0.076)	Loss 1.181 (0.996)
Epoch: [36][140/200]	Time 0.252 (0.333)	Data 0.000 (0.075)	Loss 1.199 (1.013)
Epoch: [36][160/200]	Time 0.275 (0.332)	Data 0.001 (0.075)	Loss 1.263 (1.036)
Epoch: [36][180/200]	Time 0.253 (0.332)	Data 0.001 (0.075)	Loss 1.616 (1.046)
Epoch: [36][200/200]	Time 0.269 (0.332)	Data 0.001 (0.074)	Loss 1.052 (1.058)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.139)	Data 0.000 (0.041)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.21026086807251
==> Statistics for epoch 37: 612 clusters
Epoch: [37][20/200]	Time 1.870 (0.374)	Data 1.584 (0.118)	Loss 1.425 (0.211)
Epoch: [37][40/200]	Time 0.255 (0.359)	Data 0.001 (0.100)	Loss 2.012 (0.639)
Epoch: [37][60/200]	Time 0.257 (0.347)	Data 0.001 (0.090)	Loss 1.267 (0.812)
Epoch: [37][80/200]	Time 0.255 (0.345)	Data 0.001 (0.087)	Loss 1.439 (0.892)
Epoch: [37][100/200]	Time 0.256 (0.341)	Data 0.001 (0.083)	Loss 1.149 (0.959)
Epoch: [37][120/200]	Time 0.251 (0.338)	Data 0.001 (0.081)	Loss 1.331 (0.987)
Epoch: [37][140/200]	Time 0.254 (0.337)	Data 0.001 (0.080)	Loss 1.255 (1.016)
Epoch: [37][160/200]	Time 0.252 (0.335)	Data 0.001 (0.078)	Loss 1.099 (1.035)
Epoch: [37][180/200]	Time 0.253 (0.335)	Data 0.001 (0.078)	Loss 1.209 (1.050)
Epoch: [37][200/200]	Time 0.254 (0.334)	Data 0.001 (0.077)	Loss 1.070 (1.063)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.129)	Data 0.000 (0.033)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.350609064102173
==> Statistics for epoch 38: 604 clusters
Epoch: [38][20/200]	Time 0.258 (0.371)	Data 0.001 (0.115)	Loss 0.684 (0.214)
Epoch: [38][40/200]	Time 0.263 (0.357)	Data 0.001 (0.101)	Loss 1.219 (0.639)
Epoch: [38][60/200]	Time 0.255 (0.349)	Data 0.001 (0.091)	Loss 1.393 (0.784)
Epoch: [38][80/200]	Time 0.254 (0.344)	Data 0.001 (0.087)	Loss 1.118 (0.875)
Epoch: [38][100/200]	Time 0.256 (0.341)	Data 0.001 (0.083)	Loss 1.138 (0.921)
Epoch: [38][120/200]	Time 0.256 (0.338)	Data 0.000 (0.080)	Loss 1.110 (0.967)
Epoch: [38][140/200]	Time 0.252 (0.338)	Data 0.000 (0.080)	Loss 1.076 (0.992)
Epoch: [38][160/200]	Time 0.250 (0.338)	Data 0.000 (0.079)	Loss 1.112 (1.009)
Epoch: [38][180/200]	Time 0.255 (0.336)	Data 0.000 (0.078)	Loss 0.712 (1.020)
Epoch: [38][200/200]	Time 0.254 (0.342)	Data 0.001 (0.084)	Loss 1.026 (1.031)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.133)	Data 0.000 (0.037)	
Computing jaccard distance...
Jaccard distance computing time cost: 18.982524871826172
==> Statistics for epoch 39: 610 clusters
Epoch: [39][20/200]	Time 1.635 (0.364)	Data 1.356 (0.108)	Loss 0.834 (0.193)
Epoch: [39][40/200]	Time 0.252 (0.346)	Data 0.001 (0.088)	Loss 1.239 (0.650)
Epoch: [39][60/200]	Time 0.260 (0.339)	Data 0.000 (0.082)	Loss 1.275 (0.808)
Epoch: [39][80/200]	Time 0.252 (0.335)	Data 0.001 (0.079)	Loss 1.330 (0.890)
Epoch: [39][100/200]	Time 0.253 (0.333)	Data 0.001 (0.077)	Loss 1.219 (0.931)
Epoch: [39][120/200]	Time 0.254 (0.331)	Data 0.001 (0.075)	Loss 1.009 (0.971)
Epoch: [39][140/200]	Time 0.256 (0.330)	Data 0.001 (0.074)	Loss 0.920 (0.989)
Epoch: [39][160/200]	Time 0.255 (0.329)	Data 0.001 (0.072)	Loss 1.286 (1.011)
Epoch: [39][180/200]	Time 0.255 (0.329)	Data 0.001 (0.072)	Loss 1.658 (1.024)
Epoch: [39][200/200]	Time 0.256 (0.328)	Data 0.001 (0.072)	Loss 1.559 (1.036)
Extract Features: [50/76]	Time 0.093 (0.132)	Data 0.000 (0.034)	
Mean AP: 90.4%

 * Finished epoch  39  model mAP: 90.4%  best: 90.4% *

==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.132)	Data 0.000 (0.036)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.70596694946289
==> Statistics for epoch 40: 611 clusters
Epoch: [40][20/200]	Time 1.643 (0.361)	Data 1.367 (0.105)	Loss 0.993 (0.193)
Epoch: [40][40/200]	Time 0.258 (0.346)	Data 0.001 (0.089)	Loss 1.265 (0.619)
Epoch: [40][60/200]	Time 0.258 (0.338)	Data 0.001 (0.082)	Loss 1.119 (0.805)
Epoch: [40][80/200]	Time 0.255 (0.333)	Data 0.001 (0.077)	Loss 1.115 (0.890)
Epoch: [40][100/200]	Time 0.261 (0.331)	Data 0.001 (0.074)	Loss 1.280 (0.935)
Epoch: [40][120/200]	Time 0.255 (0.331)	Data 0.001 (0.074)	Loss 1.186 (0.981)
Epoch: [40][140/200]	Time 0.253 (0.331)	Data 0.001 (0.074)	Loss 1.238 (1.009)
Epoch: [40][160/200]	Time 0.255 (0.330)	Data 0.001 (0.073)	Loss 1.047 (1.023)
Epoch: [40][180/200]	Time 0.253 (0.329)	Data 0.001 (0.072)	Loss 0.827 (1.036)
Epoch: [40][200/200]	Time 0.253 (0.328)	Data 0.001 (0.072)	Loss 0.899 (1.040)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.131)	Data 0.000 (0.034)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.196138381958008
==> Statistics for epoch 41: 608 clusters
Epoch: [41][20/200]	Time 1.674 (0.373)	Data 1.385 (0.108)	Loss 0.839 (0.186)
Epoch: [41][40/200]	Time 0.254 (0.351)	Data 0.001 (0.090)	Loss 1.270 (0.649)
Epoch: [41][60/200]	Time 0.254 (0.341)	Data 0.000 (0.083)	Loss 1.192 (0.809)
Epoch: [41][80/200]	Time 0.255 (0.338)	Data 0.001 (0.080)	Loss 1.338 (0.895)
Epoch: [41][100/200]	Time 0.252 (0.337)	Data 0.001 (0.078)	Loss 1.228 (0.929)
Epoch: [41][120/200]	Time 0.253 (0.335)	Data 0.001 (0.077)	Loss 0.933 (0.961)
Epoch: [41][140/200]	Time 0.252 (0.334)	Data 0.001 (0.076)	Loss 1.172 (0.984)
Epoch: [41][160/200]	Time 0.254 (0.333)	Data 0.001 (0.075)	Loss 1.352 (1.013)
Epoch: [41][180/200]	Time 0.257 (0.332)	Data 0.001 (0.075)	Loss 1.035 (1.030)
Epoch: [41][200/200]	Time 0.254 (0.333)	Data 0.001 (0.075)	Loss 1.166 (1.044)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.134)	Data 0.000 (0.037)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.63330841064453
==> Statistics for epoch 42: 609 clusters
Epoch: [42][20/200]	Time 1.610 (0.362)	Data 1.334 (0.106)	Loss 1.160 (0.208)
Epoch: [42][40/200]	Time 0.253 (0.342)	Data 0.001 (0.084)	Loss 1.238 (0.640)
Epoch: [42][60/200]	Time 0.257 (0.334)	Data 0.001 (0.076)	Loss 0.900 (0.792)
Epoch: [42][80/200]	Time 0.254 (0.334)	Data 0.001 (0.076)	Loss 1.219 (0.896)
Epoch: [42][100/200]	Time 0.251 (0.332)	Data 0.001 (0.074)	Loss 1.357 (0.944)
Epoch: [42][120/200]	Time 0.254 (0.331)	Data 0.001 (0.073)	Loss 1.419 (0.985)
Epoch: [42][140/200]	Time 0.254 (0.330)	Data 0.001 (0.072)	Loss 1.240 (1.007)
Epoch: [42][160/200]	Time 0.258 (0.330)	Data 0.001 (0.072)	Loss 1.339 (1.019)
Epoch: [42][180/200]	Time 0.254 (0.331)	Data 0.001 (0.074)	Loss 1.318 (1.031)
Epoch: [42][200/200]	Time 0.257 (0.331)	Data 0.001 (0.073)	Loss 1.120 (1.045)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.140)	Data 0.000 (0.043)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.563498497009277
==> Statistics for epoch 43: 609 clusters
Epoch: [43][20/200]	Time 1.505 (0.353)	Data 1.219 (0.096)	Loss 0.862 (0.193)
Epoch: [43][40/200]	Time 0.348 (0.344)	Data 0.001 (0.087)	Loss 1.323 (0.642)
Epoch: [43][60/200]	Time 0.255 (0.340)	Data 0.001 (0.083)	Loss 1.086 (0.788)
Epoch: [43][80/200]	Time 0.255 (0.338)	Data 0.001 (0.082)	Loss 1.168 (0.869)
Epoch: [43][100/200]	Time 0.253 (0.338)	Data 0.001 (0.080)	Loss 1.405 (0.925)
Epoch: [43][120/200]	Time 0.254 (0.336)	Data 0.001 (0.079)	Loss 1.293 (0.969)
Epoch: [43][140/200]	Time 0.254 (0.336)	Data 0.001 (0.080)	Loss 0.967 (0.997)
Epoch: [43][160/200]	Time 0.253 (0.337)	Data 0.001 (0.080)	Loss 0.884 (1.017)
Epoch: [43][180/200]	Time 0.256 (0.337)	Data 0.001 (0.079)	Loss 1.266 (1.033)
Epoch: [43][200/200]	Time 0.256 (0.336)	Data 0.001 (0.078)	Loss 1.031 (1.047)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.138)	Data 0.000 (0.040)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.040539026260376
==> Statistics for epoch 44: 612 clusters
Epoch: [44][20/200]	Time 1.767 (0.375)	Data 1.480 (0.112)	Loss 0.921 (0.203)
Epoch: [44][40/200]	Time 0.253 (0.351)	Data 0.001 (0.093)	Loss 0.861 (0.645)
Epoch: [44][60/200]	Time 0.253 (0.346)	Data 0.000 (0.088)	Loss 1.148 (0.790)
Epoch: [44][80/200]	Time 0.252 (0.340)	Data 0.001 (0.083)	Loss 0.979 (0.856)
Epoch: [44][100/200]	Time 0.253 (0.338)	Data 0.001 (0.080)	Loss 1.444 (0.922)
Epoch: [44][120/200]	Time 0.254 (0.336)	Data 0.001 (0.079)	Loss 1.395 (0.963)
Epoch: [44][140/200]	Time 0.253 (0.335)	Data 0.000 (0.078)	Loss 1.286 (0.988)
Epoch: [44][160/200]	Time 0.253 (0.334)	Data 0.001 (0.077)	Loss 0.982 (1.008)
Epoch: [44][180/200]	Time 0.251 (0.332)	Data 0.001 (0.075)	Loss 0.984 (1.016)
Epoch: [44][200/200]	Time 0.253 (0.331)	Data 0.001 (0.075)	Loss 0.914 (1.022)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.135)	Data 0.000 (0.036)	
Computing jaccard distance...
Jaccard distance computing time cost: 20.17736506462097
==> Statistics for epoch 45: 612 clusters
Epoch: [45][20/200]	Time 1.613 (0.376)	Data 1.338 (0.115)	Loss 1.097 (0.197)
Epoch: [45][40/200]	Time 0.257 (0.352)	Data 0.001 (0.094)	Loss 0.941 (0.624)
Epoch: [45][60/200]	Time 0.275 (0.343)	Data 0.001 (0.084)	Loss 0.920 (0.769)
Epoch: [45][80/200]	Time 0.254 (0.338)	Data 0.001 (0.080)	Loss 1.026 (0.862)
Epoch: [45][100/200]	Time 0.253 (0.335)	Data 0.001 (0.078)	Loss 1.174 (0.913)
Epoch: [45][120/200]	Time 0.254 (0.333)	Data 0.001 (0.076)	Loss 1.057 (0.942)
Epoch: [45][140/200]	Time 0.252 (0.332)	Data 0.001 (0.075)	Loss 0.926 (0.966)
Epoch: [45][160/200]	Time 0.253 (0.331)	Data 0.001 (0.074)	Loss 1.224 (0.991)
Epoch: [45][180/200]	Time 0.253 (0.331)	Data 0.001 (0.074)	Loss 1.266 (1.011)
Epoch: [45][200/200]	Time 0.253 (0.330)	Data 0.001 (0.073)	Loss 1.202 (1.020)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.094 (0.129)	Data 0.000 (0.032)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.16795516014099
==> Statistics for epoch 46: 610 clusters
Epoch: [46][20/200]	Time 1.580 (0.362)	Data 1.236 (0.103)	Loss 1.372 (0.218)
Epoch: [46][40/200]	Time 0.253 (0.340)	Data 0.001 (0.082)	Loss 1.259 (0.655)
Epoch: [46][60/200]	Time 0.255 (0.335)	Data 0.001 (0.077)	Loss 1.054 (0.805)
Epoch: [46][80/200]	Time 0.362 (0.333)	Data 0.001 (0.074)	Loss 1.027 (0.885)
Epoch: [46][100/200]	Time 0.253 (0.331)	Data 0.001 (0.072)	Loss 1.057 (0.928)
Epoch: [46][120/200]	Time 0.254 (0.333)	Data 0.001 (0.074)	Loss 1.092 (0.967)
Epoch: [46][140/200]	Time 0.253 (0.332)	Data 0.001 (0.073)	Loss 0.927 (0.983)
Epoch: [46][160/200]	Time 0.255 (0.331)	Data 0.001 (0.073)	Loss 1.074 (1.001)
Epoch: [46][180/200]	Time 0.254 (0.330)	Data 0.001 (0.072)	Loss 1.245 (1.015)
Epoch: [46][200/200]	Time 0.253 (0.329)	Data 0.001 (0.071)	Loss 0.965 (1.023)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.150 (0.129)	Data 0.058 (0.032)	
Computing jaccard distance...
Jaccard distance computing time cost: 18.984604597091675
==> Statistics for epoch 47: 613 clusters
Epoch: [47][20/200]	Time 1.648 (0.360)	Data 1.371 (0.105)	Loss 1.229 (0.219)
Epoch: [47][40/200]	Time 0.252 (0.344)	Data 0.001 (0.087)	Loss 1.042 (0.631)
Epoch: [47][60/200]	Time 0.257 (0.337)	Data 0.001 (0.080)	Loss 0.967 (0.765)
Epoch: [47][80/200]	Time 0.252 (0.334)	Data 0.001 (0.078)	Loss 1.789 (0.861)
Epoch: [47][100/200]	Time 0.252 (0.334)	Data 0.001 (0.077)	Loss 0.926 (0.914)
Epoch: [47][120/200]	Time 0.252 (0.334)	Data 0.001 (0.077)	Loss 1.078 (0.952)
Epoch: [47][140/200]	Time 0.253 (0.334)	Data 0.001 (0.077)	Loss 1.104 (0.967)
Epoch: [47][160/200]	Time 0.251 (0.333)	Data 0.001 (0.076)	Loss 1.155 (0.996)
Epoch: [47][180/200]	Time 0.254 (0.332)	Data 0.001 (0.075)	Loss 0.984 (1.015)
Epoch: [47][200/200]	Time 0.254 (0.331)	Data 0.001 (0.074)	Loss 1.088 (1.022)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.093 (0.139)	Data 0.000 (0.041)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.5452299118042
==> Statistics for epoch 48: 611 clusters
Epoch: [48][20/200]	Time 1.531 (0.366)	Data 1.254 (0.107)	Loss 1.065 (0.200)
Epoch: [48][40/200]	Time 0.253 (0.342)	Data 0.001 (0.085)	Loss 1.231 (0.645)
Epoch: [48][60/200]	Time 0.253 (0.336)	Data 0.001 (0.079)	Loss 1.045 (0.796)
Epoch: [48][80/200]	Time 0.255 (0.333)	Data 0.001 (0.077)	Loss 1.142 (0.888)
Epoch: [48][100/200]	Time 0.255 (0.331)	Data 0.001 (0.075)	Loss 1.109 (0.942)
Epoch: [48][120/200]	Time 0.254 (0.333)	Data 0.001 (0.076)	Loss 1.176 (0.975)
Epoch: [48][140/200]	Time 0.250 (0.334)	Data 0.001 (0.077)	Loss 1.175 (0.998)
Epoch: [48][160/200]	Time 0.255 (0.332)	Data 0.001 (0.075)	Loss 1.273 (1.014)
Epoch: [48][180/200]	Time 0.256 (0.332)	Data 0.001 (0.075)	Loss 1.093 (1.023)
Epoch: [48][200/200]	Time 0.254 (0.332)	Data 0.001 (0.075)	Loss 0.965 (1.039)
==> Create pseudo labels for unlabeled data
Extract Features: [50/51]	Time 0.106 (0.135)	Data 0.013 (0.035)	
Computing jaccard distance...
Jaccard distance computing time cost: 19.454848766326904
==> Statistics for epoch 49: 616 clusters
Epoch: [49][20/200]	Time 1.686 (0.369)	Data 1.399 (0.111)	Loss 1.041 (0.202)
Epoch: [49][40/200]	Time 0.254 (0.347)	Data 0.001 (0.089)	Loss 1.161 (0.637)
Epoch: [49][60/200]	Time 0.255 (0.338)	Data 0.001 (0.081)	Loss 1.093 (0.808)
Epoch: [49][80/200]	Time 0.266 (0.335)	Data 0.001 (0.079)	Loss 0.914 (0.889)
Epoch: [49][100/200]	Time 0.261 (0.336)	Data 0.001 (0.078)	Loss 1.268 (0.940)
Epoch: [49][120/200]	Time 0.252 (0.336)	Data 0.001 (0.077)	Loss 0.872 (0.966)
Epoch: [49][140/200]	Time 0.255 (0.334)	Data 0.001 (0.075)	Loss 0.953 (1.005)
Epoch: [49][160/200]	Time 0.255 (0.333)	Data 0.001 (0.075)	Loss 0.982 (1.018)
Epoch: [49][180/200]	Time 0.254 (0.333)	Data 0.001 (0.074)	Loss 1.137 (1.030)
Epoch: [49][200/200]	Time 0.254 (0.331)	Data 0.001 (0.073)	Loss 1.455 (1.033)
Extract Features: [50/76]	Time 0.095 (0.134)	Data 0.000 (0.035)	
Mean AP: 90.6%

 * Finished epoch  49  model mAP: 90.6%  best: 90.6% *

==> Test with the best model:
=> Loaded checkpoint 'log/market/resnet50_cion/model_best.pth.tar'
Extract Features: [50/76]	Time 0.094 (0.133)	Data 0.000 (0.036)	
Mean AP: 90.6%
CMC Scores:
  top-1          95.7%
  top-5          98.7%
  top-10         99.2%
Total running time:  1:23:14.384576
