Skip to content

Instantly share code, notes, and snippets.

@imtiazziko

imtiazziko/resnet_18-log-lsmooth-0.0

Last active April 30, 2021 20:45
Show Gist options
  • Save imtiazziko/da86dc1796780786032504853dedfd29 to your computer and use it in GitHub Desktop.
Save imtiazziko/da86dc1796780786032504853dedfd29 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
resnet_18-log-lsmooth-0.0
[2021-04-26 18:32:22 train_lshot.py:38] INFO arch: resnet18
[2021-04-26 18:32:22 train_lshot.py:38] INFO batch_size: 256
[2021-04-26 18:32:22 train_lshot.py:38] INFO beta: -1.0
[2021-04-26 18:32:22 train_lshot.py:38] INFO config: /app/LaplacianShot/configs/mini/softmax/resnet18.config
[2021-04-26 18:32:22 train_lshot.py:38] INFO cutmix_prob: 0
[2021-04-26 18:32:22 train_lshot.py:38] INFO data: /fewshot_xai/fewshot_xai/fewshot_data/data/mini_imagenet
[2021-04-26 18:32:22 train_lshot.py:38] INFO disable_random_resize: False
[2021-04-26 18:32:22 train_lshot.py:38] INFO disable_tqdm: False
[2021-04-26 18:32:22 train_lshot.py:38] INFO disable_train_augment: False
[2021-04-26 18:32:22 train_lshot.py:38] INFO do_meta_train: False
[2021-04-26 18:32:22 train_lshot.py:38] INFO enlarge: True
[2021-04-26 18:32:22 train_lshot.py:38] INFO epochs: 90
[2021-04-26 18:32:22 train_lshot.py:38] INFO eval_fc: False
[2021-04-26 18:32:22 train_lshot.py:38] INFO evaluate: False
[2021-04-26 18:32:22 train_lshot.py:38] INFO jitter: False
[2021-04-26 18:32:22 train_lshot.py:38] INFO knn: 3
[2021-04-26 18:32:22 train_lshot.py:38] INFO label_smooth: 0.0
[2021-04-26 18:32:22 train_lshot.py:38] INFO lmd: 1.0
[2021-04-26 18:32:22 train_lshot.py:38] INFO log_file: /LaplacianShot_protorec.log
[2021-04-26 18:32:22 train_lshot.py:38] INFO lr: 0.1
[2021-04-26 18:32:22 train_lshot.py:38] INFO lr_gamma: 0.1
[2021-04-26 18:32:22 train_lshot.py:38] INFO lr_stepsize: 30
[2021-04-26 18:32:22 train_lshot.py:38] INFO lshot: True
[2021-04-26 18:32:22 train_lshot.py:38] INFO meta_test_iter: 10000
[2021-04-26 18:32:22 train_lshot.py:38] INFO meta_train_iter: 100
[2021-04-26 18:32:22 train_lshot.py:38] INFO meta_train_metric: euclidean
[2021-04-26 18:32:22 train_lshot.py:38] INFO meta_train_query: 15
[2021-04-26 18:32:22 train_lshot.py:38] INFO meta_train_shot: 1
[2021-04-26 18:32:22 train_lshot.py:38] INFO meta_train_way: 30
[2021-04-26 18:32:22 train_lshot.py:38] INFO meta_val_interval: 4
[2021-04-26 18:32:22 train_lshot.py:38] INFO meta_val_iter: 500
[2021-04-26 18:32:22 train_lshot.py:38] INFO meta_val_metric: cosine
[2021-04-26 18:32:22 train_lshot.py:38] INFO meta_val_query: 15
[2021-04-26 18:32:22 train_lshot.py:38] INFO meta_val_shot: 1
[2021-04-26 18:32:22 train_lshot.py:38] INFO meta_val_way: 5
[2021-04-26 18:32:22 train_lshot.py:38] INFO nesterov: False
[2021-04-26 18:32:22 train_lshot.py:38] INFO num_NN: 1
[2021-04-26 18:32:22 train_lshot.py:38] INFO num_classes: 64
[2021-04-26 18:32:22 train_lshot.py:38] INFO optimizer: SGD
[2021-04-26 18:32:22 train_lshot.py:38] INFO plot_converge: False
[2021-04-26 18:32:22 train_lshot.py:38] INFO pretrain: None
[2021-04-26 18:32:22 train_lshot.py:38] INFO print_freq: 10
[2021-04-26 18:32:22 train_lshot.py:38] INFO proto_rect: True
[2021-04-26 18:32:22 train_lshot.py:38] INFO resume:
[2021-04-26 18:32:22 train_lshot.py:38] INFO save_path: /fewshot_xai/fewshot_xai/results/mini/softmax/resnet18-simpleshot-train
[2021-04-26 18:32:22 train_lshot.py:38] INFO scheduler: multi_step
[2021-04-26 18:32:22 train_lshot.py:38] INFO seed: None
[2021-04-26 18:32:22 train_lshot.py:38] INFO split_dir: /app/LaplacianShot/split/mini/
[2021-04-26 18:32:22 train_lshot.py:38] INFO start_epoch: 0
[2021-04-26 18:32:22 train_lshot.py:38] INFO tune_lmd: True
[2021-04-26 18:32:22 train_lshot.py:38] INFO weight_decay: 0.0001
[2021-04-26 18:32:22 train_lshot.py:38] INFO workers: 40
[2021-04-26 18:32:22 train_lshot.py:46] INFO => creating model 'resnet18'
[2021-04-26 18:32:22 train_lshot.py:49] INFO Number of model parameters: 11201664
[2021-04-26 18:32:39 train_lshot.py:257] INFO Epoch: [0][0/150] Time 14.163 (14.163) Data 12.563 (12.563) Loss 4.2834 (4.2834) Prec@1 1.562 (1.562) Prec@5 7.031 (7.031)
[2021-04-26 18:32:45 train_lshot.py:257] INFO Epoch: [0][10/150] Time 0.613 (1.847) Data 0.000 (1.143) Loss 4.2673 (4.2393) Prec@1 4.688 (4.084) Prec@5 13.672 (12.820)
[2021-04-26 18:32:51 train_lshot.py:257] INFO Epoch: [0][20/150] Time 0.636 (1.276) Data 0.000 (0.602) Loss 3.9449 (4.1932) Prec@1 7.031 (4.929) Prec@5 25.781 (15.681)
[2021-04-26 18:32:58 train_lshot.py:257] INFO Epoch: [0][30/150] Time 0.621 (1.070) Data 0.000 (0.409) Loss 3.9462 (4.1229) Prec@1 7.031 (5.418) Prec@5 24.609 (17.792)
[2021-04-26 18:33:04 train_lshot.py:257] INFO Epoch: [0][40/150] Time 0.619 (0.962) Data 0.001 (0.310) Loss 3.8693 (4.0696) Prec@1 10.156 (5.897) Prec@5 28.516 (19.293)
[2021-04-26 18:33:10 train_lshot.py:257] INFO Epoch: [0][50/150] Time 0.620 (0.895) Data 0.000 (0.250) Loss 3.9493 (4.0447) Prec@1 8.203 (5.936) Prec@5 26.172 (20.083)
[2021-04-26 18:33:17 train_lshot.py:257] INFO Epoch: [0][60/150] Time 0.618 (0.851) Data 0.001 (0.209) Loss 3.7808 (4.0158) Prec@1 5.078 (6.148) Prec@5 23.828 (21.222)
[2021-04-26 18:33:23 train_lshot.py:257] INFO Epoch: [0][70/150] Time 0.634 (0.819) Data 0.002 (0.180) Loss 3.6851 (3.9881) Prec@1 10.156 (6.498) Prec@5 34.766 (22.233)
[2021-04-26 18:33:29 train_lshot.py:257] INFO Epoch: [0][80/150] Time 0.619 (0.794) Data 0.001 (0.157) Loss 3.7916 (3.9661) Prec@1 7.812 (6.689) Prec@5 22.266 (22.864)
[2021-04-26 18:33:35 train_lshot.py:257] INFO Epoch: [0][90/150] Time 0.618 (0.775) Data 0.000 (0.140) Loss 3.8381 (3.9448) Prec@1 7.422 (6.963) Prec@5 26.953 (23.605)
[2021-04-26 18:33:41 train_lshot.py:257] INFO Epoch: [0][100/150] Time 0.620 (0.759) Data 0.000 (0.126) Loss 3.7167 (3.9286) Prec@1 7.422 (7.147) Prec@5 29.688 (24.188)
[2021-04-26 18:33:48 train_lshot.py:257] INFO Epoch: [0][110/150] Time 0.622 (0.747) Data 0.000 (0.115) Loss 3.7244 (3.9100) Prec@1 7.422 (7.323) Prec@5 29.688 (24.743)
[2021-04-26 18:33:54 train_lshot.py:257] INFO Epoch: [0][120/150] Time 0.621 (0.736) Data 0.000 (0.105) Loss 3.8324 (3.8959) Prec@1 5.469 (7.490) Prec@5 26.562 (25.200)
[2021-04-26 18:34:00 train_lshot.py:257] INFO Epoch: [0][130/150] Time 0.624 (0.727) Data 0.000 (0.097) Loss 3.7045 (3.8807) Prec@1 11.719 (7.705) Prec@5 32.031 (25.623)
[2021-04-26 18:34:06 train_lshot.py:257] INFO Epoch: [0][140/150] Time 0.618 (0.720) Data 0.000 (0.091) Loss 3.6683 (3.8673) Prec@1 10.547 (7.862) Prec@5 32.812 (26.086)
[2021-04-26 18:34:22 train_lshot.py:257] INFO Epoch: [1][0/150] Time 9.430 (9.430) Data 8.773 (8.773) Loss 3.6162 (3.6162) Prec@1 12.109 (12.109) Prec@5 35.156 (35.156)
[2021-04-26 18:34:28 train_lshot.py:257] INFO Epoch: [1][10/150] Time 0.619 (1.419) Data 0.000 (0.798) Loss 3.6654 (3.6147) Prec@1 10.547 (11.151) Prec@5 31.250 (34.268)
[2021-04-26 18:34:34 train_lshot.py:257] INFO Epoch: [1][20/150] Time 0.619 (1.039) Data 0.000 (0.418) Loss 3.5404 (3.5970) Prec@1 13.672 (11.737) Prec@5 35.938 (34.133)
[2021-04-26 18:34:40 train_lshot.py:257] INFO Epoch: [1][30/150] Time 0.622 (0.905) Data 0.001 (0.284) Loss 3.5946 (3.6079) Prec@1 11.328 (11.316) Prec@5 37.109 (33.783)
[2021-04-26 18:34:46 train_lshot.py:257] INFO Epoch: [1][40/150] Time 0.630 (0.837) Data 0.002 (0.215) Loss 3.6558 (3.6128) Prec@1 11.328 (11.452) Prec@5 35.547 (33.756)
[2021-04-26 18:34:53 train_lshot.py:257] INFO Epoch: [1][50/150] Time 0.621 (0.795) Data 0.001 (0.173) Loss 3.5847 (3.6052) Prec@1 10.938 (11.412) Prec@5 35.156 (34.176)
[2021-04-26 18:34:59 train_lshot.py:257] INFO Epoch: [1][60/150] Time 0.625 (0.767) Data 0.000 (0.145) Loss 3.6993 (3.6044) Prec@1 8.984 (11.270) Prec@5 32.812 (34.189)
[2021-04-26 18:35:05 train_lshot.py:257] INFO Epoch: [1][70/150] Time 0.632 (0.746) Data 0.001 (0.124) Loss 3.4750 (3.5958) Prec@1 13.672 (11.449) Prec@5 39.453 (34.469)
[2021-04-26 18:35:11 train_lshot.py:257] INFO Epoch: [1][80/150] Time 0.623 (0.731) Data 0.000 (0.109) Loss 3.5258 (3.5912) Prec@1 13.672 (11.439) Prec@5 37.109 (34.578)
[2021-04-26 18:35:18 train_lshot.py:257] INFO Epoch: [1][90/150] Time 0.619 (0.719) Data 0.000 (0.097) Loss 3.6236 (3.5848) Prec@1 11.328 (11.517) Prec@5 32.422 (34.800)
[2021-04-26 18:35:24 train_lshot.py:257] INFO Epoch: [1][100/150] Time 0.619 (0.709) Data 0.000 (0.088) Loss 3.5502 (3.5768) Prec@1 11.719 (11.688) Prec@5 35.938 (35.056)
[2021-04-26 18:35:30 train_lshot.py:257] INFO Epoch: [1][110/150] Time 0.622 (0.701) Data 0.000 (0.080) Loss 3.5232 (3.5703) Prec@1 9.766 (11.842) Prec@5 39.062 (35.244)
[2021-04-26 18:35:36 train_lshot.py:257] INFO Epoch: [1][120/150] Time 0.618 (0.694) Data 0.000 (0.073) Loss 3.5988 (3.5651) Prec@1 13.672 (11.964) Prec@5 37.109 (35.385)
[2021-04-26 18:35:42 train_lshot.py:257] INFO Epoch: [1][130/150] Time 0.619 (0.689) Data 0.000 (0.068) Loss 3.5676 (3.5606) Prec@1 13.672 (12.020) Prec@5 36.328 (35.654)
[2021-04-26 18:35:49 train_lshot.py:257] INFO Epoch: [1][140/150] Time 0.619 (0.684) Data 0.000 (0.063) Loss 3.4514 (3.5535) Prec@1 12.891 (12.060) Prec@5 39.453 (35.938)
[2021-04-26 18:36:04 train_lshot.py:257] INFO Epoch: [2][0/150] Time 9.805 (9.805) Data 9.156 (9.156) Loss 3.4582 (3.4582) Prec@1 12.109 (12.109) Prec@5 41.016 (41.016)
[2021-04-26 18:36:11 train_lshot.py:257] INFO Epoch: [2][10/150] Time 0.618 (1.474) Data 0.000 (0.853) Loss 3.3155 (3.3865) Prec@1 14.844 (15.163) Prec@5 41.797 (41.939)
[2021-04-26 18:36:17 train_lshot.py:257] INFO Epoch: [2][20/150] Time 0.618 (1.069) Data 0.000 (0.447) Loss 3.3548 (3.3980) Prec@1 15.625 (15.141) Prec@5 44.141 (41.388)
[2021-04-26 18:36:23 train_lshot.py:257] INFO Epoch: [2][30/150] Time 0.624 (0.925) Data 0.001 (0.303) Loss 3.3546 (3.3914) Prec@1 16.797 (15.449) Prec@5 42.969 (41.507)
[2021-04-26 18:36:29 train_lshot.py:257] INFO Epoch: [2][40/150] Time 0.625 (0.852) Data 0.001 (0.229) Loss 3.3891 (3.3856) Prec@1 13.281 (15.454) Prec@5 39.453 (41.721)
[2021-04-26 18:36:36 train_lshot.py:257] INFO Epoch: [2][50/150] Time 0.626 (0.807) Data 0.001 (0.184) Loss 3.0941 (3.3680) Prec@1 19.141 (15.571) Prec@5 50.781 (42.126)
[2021-04-26 18:36:42 train_lshot.py:257] INFO Epoch: [2][60/150] Time 0.622 (0.777) Data 0.000 (0.154) Loss 3.4776 (3.3575) Prec@1 14.062 (15.836) Prec@5 41.406 (42.706)
[2021-04-26 18:36:48 train_lshot.py:257] INFO Epoch: [2][70/150] Time 0.628 (0.755) Data 0.002 (0.133) Loss 3.3835 (3.3544) Prec@1 14.453 (15.917) Prec@5 42.969 (42.941)
[2021-04-26 18:36:54 train_lshot.py:257] INFO Epoch: [2][80/150] Time 0.622 (0.739) Data 0.001 (0.116) Loss 3.0958 (3.3451) Prec@1 21.094 (16.093) Prec@5 50.000 (43.229)
[2021-04-26 18:37:01 train_lshot.py:257] INFO Epoch: [2][90/150] Time 0.625 (0.726) Data 0.000 (0.104) Loss 3.0699 (3.3323) Prec@1 23.828 (16.363) Prec@5 50.391 (43.686)
[2021-04-26 18:37:07 train_lshot.py:257] INFO Epoch: [2][100/150] Time 0.625 (0.716) Data 0.000 (0.093) Loss 3.1221 (3.3240) Prec@1 20.312 (16.553) Prec@5 52.734 (44.040)
[2021-04-26 18:37:13 train_lshot.py:257] INFO Epoch: [2][110/150] Time 0.622 (0.707) Data 0.000 (0.085) Loss 3.2514 (3.3152) Prec@1 15.625 (16.716) Prec@5 48.047 (44.380)
[2021-04-26 18:37:19 train_lshot.py:257] INFO Epoch: [2][120/150] Time 0.620 (0.700) Data 0.000 (0.078) Loss 3.2425 (3.3023) Prec@1 21.484 (16.968) Prec@5 46.094 (44.799)
[2021-04-26 18:37:25 train_lshot.py:257] INFO Epoch: [2][130/150] Time 0.618 (0.694) Data 0.000 (0.072) Loss 3.0836 (3.2912) Prec@1 20.703 (17.232) Prec@5 50.000 (45.092)
[2021-04-26 18:37:32 train_lshot.py:257] INFO Epoch: [2][140/150] Time 0.619 (0.689) Data 0.000 (0.067) Loss 2.9729 (3.2773) Prec@1 22.266 (17.578) Prec@5 53.125 (45.434)
[2021-04-26 18:37:47 train_lshot.py:257] INFO Epoch: [3][0/150] Time 9.718 (9.718) Data 9.071 (9.071) Loss 2.9820 (2.9820) Prec@1 22.266 (22.266) Prec@5 52.734 (52.734)
[2021-04-26 18:37:54 train_lshot.py:257] INFO Epoch: [3][10/150] Time 0.620 (1.448) Data 0.000 (0.825) Loss 3.0419 (3.0314) Prec@1 18.750 (22.692) Prec@5 50.391 (51.918)
[2021-04-26 18:38:00 train_lshot.py:257] INFO Epoch: [3][20/150] Time 0.625 (1.056) Data 0.000 (0.432) Loss 3.1726 (3.0482) Prec@1 19.531 (22.526) Prec@5 47.266 (51.190)
[2021-04-26 18:38:06 train_lshot.py:257] INFO Epoch: [3][30/150] Time 0.637 (0.917) Data 0.001 (0.293) Loss 2.9638 (3.0460) Prec@1 23.828 (22.152) Prec@5 53.125 (51.663)
[2021-04-26 18:38:12 train_lshot.py:257] INFO Epoch: [3][40/150] Time 0.633 (0.846) Data 0.001 (0.222) Loss 3.1367 (3.0508) Prec@1 19.922 (22.094) Prec@5 49.219 (51.801)
[2021-04-26 18:38:19 train_lshot.py:257] INFO Epoch: [3][50/150] Time 0.623 (0.803) Data 0.000 (0.178) Loss 2.9623 (3.0457) Prec@1 24.219 (22.235) Prec@5 55.078 (52.191)
[2021-04-26 18:38:25 train_lshot.py:257] INFO Epoch: [3][60/150] Time 0.626 (0.773) Data 0.001 (0.149) Loss 2.7803 (3.0356) Prec@1 25.391 (22.541) Prec@5 60.156 (52.549)
[2021-04-26 18:38:31 train_lshot.py:257] INFO Epoch: [3][70/150] Time 0.634 (0.752) Data 0.003 (0.128) Loss 2.9850 (3.0228) Prec@1 21.484 (22.706) Prec@5 54.688 (52.905)
[2021-04-26 18:38:37 train_lshot.py:257] INFO Epoch: [3][80/150] Time 0.627 (0.737) Data 0.001 (0.113) Loss 2.9757 (3.0223) Prec@1 23.438 (22.897) Prec@5 54.688 (52.980)
[2021-04-26 18:38:44 train_lshot.py:257] INFO Epoch: [3][90/150] Time 0.622 (0.724) Data 0.000 (0.100) Loss 2.8505 (3.0088) Prec@1 25.000 (23.030) Prec@5 58.594 (53.507)
[2021-04-26 18:38:50 train_lshot.py:257] INFO Epoch: [3][100/150] Time 0.624 (0.714) Data 0.000 (0.090) Loss 2.8733 (2.9966) Prec@1 25.000 (23.267) Prec@5 60.156 (53.899)
[2021-04-26 18:38:56 train_lshot.py:257] INFO Epoch: [3][110/150] Time 0.625 (0.706) Data 0.000 (0.082) Loss 2.9274 (2.9889) Prec@1 29.688 (23.494) Prec@5 55.078 (54.149)
[2021-04-26 18:39:02 train_lshot.py:257] INFO Epoch: [3][120/150] Time 0.621 (0.699) Data 0.000 (0.075) Loss 2.8748 (2.9832) Prec@1 23.047 (23.550) Prec@5 58.984 (54.268)
[2021-04-26 18:39:08 train_lshot.py:257] INFO Epoch: [3][130/150] Time 0.623 (0.693) Data 0.000 (0.070) Loss 2.8143 (2.9765) Prec@1 28.906 (23.658) Prec@5 58.594 (54.437)
[2021-04-26 18:39:15 train_lshot.py:257] INFO Epoch: [3][140/150] Time 0.624 (0.688) Data 0.000 (0.065) Loss 2.7995 (2.9679) Prec@1 29.688 (23.870) Prec@5 60.156 (54.701)
[2021-04-26 18:40:00 train_lshot.py:119] INFO Meta Val 3: 0.4202400095462799
[2021-04-26 18:40:10 train_lshot.py:257] INFO Epoch: [4][0/150] Time 9.692 (9.692) Data 9.027 (9.027) Loss 2.7911 (2.7911) Prec@1 28.125 (28.125) Prec@5 59.375 (59.375)
[2021-04-26 18:40:17 train_lshot.py:257] INFO Epoch: [4][10/150] Time 0.620 (1.444) Data 0.000 (0.821) Loss 2.9102 (2.7860) Prec@1 29.297 (27.521) Prec@5 57.031 (59.411)
[2021-04-26 18:40:23 train_lshot.py:257] INFO Epoch: [4][20/150] Time 0.628 (1.053) Data 0.001 (0.430) Loss 2.7735 (2.7916) Prec@1 31.250 (27.288) Prec@5 55.859 (59.170)
[2021-04-26 18:40:29 train_lshot.py:257] INFO Epoch: [4][30/150] Time 0.622 (0.914) Data 0.000 (0.292) Loss 2.8963 (2.7995) Prec@1 26.172 (27.218) Prec@5 58.594 (59.362)
[2021-04-26 18:40:35 train_lshot.py:257] INFO Epoch: [4][40/150] Time 0.623 (0.843) Data 0.000 (0.221) Loss 2.7530 (2.8004) Prec@1 28.516 (27.229) Prec@5 57.812 (59.461)
[2021-04-26 18:40:41 train_lshot.py:257] INFO Epoch: [4][50/150] Time 0.622 (0.800) Data 0.000 (0.178) Loss 2.8445 (2.8061) Prec@1 28.516 (27.344) Prec@5 55.469 (59.115)
[2021-04-26 18:40:48 train_lshot.py:257] INFO Epoch: [4][60/150] Time 0.623 (0.772) Data 0.000 (0.149) Loss 2.9046 (2.7964) Prec@1 22.266 (27.376) Prec@5 56.641 (59.317)
[2021-04-26 18:40:54 train_lshot.py:257] INFO Epoch: [4][70/150] Time 0.628 (0.751) Data 0.001 (0.128) Loss 2.7012 (2.7857) Prec@1 24.609 (27.696) Prec@5 61.328 (59.634)
[2021-04-26 18:41:00 train_lshot.py:257] INFO Epoch: [4][80/150] Time 0.622 (0.735) Data 0.001 (0.112) Loss 2.8835 (2.7769) Prec@1 23.047 (27.898) Prec@5 57.812 (59.881)
[2021-04-26 18:41:06 train_lshot.py:257] INFO Epoch: [4][90/150] Time 0.620 (0.723) Data 0.000 (0.100) Loss 2.7177 (2.7698) Prec@1 31.250 (28.142) Prec@5 60.156 (60.092)
[2021-04-26 18:41:13 train_lshot.py:257] INFO Epoch: [4][100/150] Time 0.622 (0.713) Data 0.000 (0.090) Loss 2.6053 (2.7639) Prec@1 31.250 (28.330) Prec@5 66.797 (60.249)
[2021-04-26 18:41:19 train_lshot.py:257] INFO Epoch: [4][110/150] Time 0.621 (0.705) Data 0.000 (0.082) Loss 2.7561 (2.7620) Prec@1 28.906 (28.322) Prec@5 61.328 (60.290)
[2021-04-26 18:41:25 train_lshot.py:257] INFO Epoch: [4][120/150] Time 0.621 (0.698) Data 0.000 (0.075) Loss 2.4904 (2.7559) Prec@1 33.203 (28.441) Prec@5 67.578 (60.411)
[2021-04-26 18:41:31 train_lshot.py:257] INFO Epoch: [4][130/150] Time 0.624 (0.692) Data 0.000 (0.069) Loss 2.7538 (2.7510) Prec@1 32.422 (28.650) Prec@5 58.594 (60.472)
[2021-04-26 18:41:38 train_lshot.py:257] INFO Epoch: [4][140/150] Time 0.623 (0.687) Data 0.000 (0.064) Loss 2.7491 (2.7470) Prec@1 28.125 (28.746) Prec@5 58.984 (60.594)
[2021-04-26 18:41:53 train_lshot.py:257] INFO Epoch: [5][0/150] Time 9.249 (9.249) Data 8.600 (8.600) Loss 2.7035 (2.7035) Prec@1 26.562 (26.562) Prec@5 62.500 (62.500)
[2021-04-26 18:41:59 train_lshot.py:257] INFO Epoch: [5][10/150] Time 0.621 (1.413) Data 0.000 (0.790) Loss 2.6716 (2.6419) Prec@1 33.203 (30.788) Prec@5 60.938 (62.536)
[2021-04-26 18:42:05 train_lshot.py:257] INFO Epoch: [5][20/150] Time 0.624 (1.037) Data 0.001 (0.414) Loss 2.8442 (2.6251) Prec@1 27.344 (31.120) Prec@5 61.719 (63.393)
[2021-04-26 18:42:12 train_lshot.py:257] INFO Epoch: [5][30/150] Time 0.623 (0.904) Data 0.000 (0.281) Loss 2.5765 (2.6141) Prec@1 29.688 (31.515) Prec@5 67.188 (64.050)
[2021-04-26 18:42:18 train_lshot.py:257] INFO Epoch: [5][40/150] Time 0.625 (0.836) Data 0.000 (0.212) Loss 2.4262 (2.6109) Prec@1 36.719 (31.469) Prec@5 66.406 (64.129)
[2021-04-26 18:42:24 train_lshot.py:257] INFO Epoch: [5][50/150] Time 0.625 (0.795) Data 0.000 (0.171) Loss 2.4888 (2.6132) Prec@1 30.469 (31.334) Prec@5 65.625 (64.139)
[2021-04-26 18:42:30 train_lshot.py:257] INFO Epoch: [5][60/150] Time 0.639 (0.767) Data 0.001 (0.143) Loss 2.4330 (2.5980) Prec@1 32.422 (31.717) Prec@5 68.359 (64.504)
[2021-04-26 18:42:37 train_lshot.py:257] INFO Epoch: [5][70/150] Time 0.623 (0.747) Data 0.001 (0.123) Loss 2.4833 (2.5996) Prec@1 32.812 (31.723) Prec@5 66.406 (64.563)
[2021-04-26 18:42:43 train_lshot.py:257] INFO Epoch: [5][80/150] Time 0.623 (0.732) Data 0.001 (0.108) Loss 2.6715 (2.5930) Prec@1 31.250 (32.055) Prec@5 61.719 (64.554)
[2021-04-26 18:42:49 train_lshot.py:257] INFO Epoch: [5][90/150] Time 0.620 (0.720) Data 0.000 (0.096) Loss 2.8354 (2.5931) Prec@1 28.125 (32.048) Prec@5 57.812 (64.663)
[2021-04-26 18:42:55 train_lshot.py:257] INFO Epoch: [5][100/150] Time 0.621 (0.710) Data 0.000 (0.087) Loss 2.6429 (2.5910) Prec@1 32.031 (32.163) Prec@5 64.062 (64.743)
[2021-04-26 18:43:02 train_lshot.py:257] INFO Epoch: [5][110/150] Time 0.625 (0.702) Data 0.000 (0.079) Loss 2.7304 (2.5927) Prec@1 34.766 (32.239) Prec@5 62.891 (64.611)
[2021-04-26 18:43:08 train_lshot.py:257] INFO Epoch: [5][120/150] Time 0.622 (0.696) Data 0.000 (0.072) Loss 2.4861 (2.5890) Prec@1 35.156 (32.370) Prec@5 66.406 (64.679)
[2021-04-26 18:43:14 train_lshot.py:257] INFO Epoch: [5][130/150] Time 0.624 (0.690) Data 0.000 (0.067) Loss 2.4959 (2.5835) Prec@1 32.812 (32.452) Prec@5 63.672 (64.704)
[2021-04-26 18:43:20 train_lshot.py:257] INFO Epoch: [5][140/150] Time 0.624 (0.685) Data 0.000 (0.062) Loss 2.5725 (2.5810) Prec@1 32.812 (32.516) Prec@5 64.062 (64.758)
[2021-04-26 18:43:37 train_lshot.py:257] INFO Epoch: [6][0/150] Time 10.672 (10.672) Data 10.013 (10.013) Loss 2.2907 (2.2907) Prec@1 38.672 (38.672) Prec@5 71.094 (71.094)
[2021-04-26 18:43:43 train_lshot.py:257] INFO Epoch: [6][10/150] Time 0.619 (1.535) Data 0.000 (0.911) Loss 2.3538 (2.4443) Prec@1 36.719 (34.091) Prec@5 72.266 (68.395)
[2021-04-26 18:43:50 train_lshot.py:257] INFO Epoch: [6][20/150] Time 0.623 (1.113) Data 0.000 (0.488) Loss 2.3944 (2.4432) Prec@1 31.250 (34.319) Prec@5 69.141 (68.397)
[2021-04-26 18:43:56 train_lshot.py:257] INFO Epoch: [6][30/150] Time 0.623 (0.955) Data 0.000 (0.331) Loss 2.6110 (2.4351) Prec@1 33.984 (35.055) Prec@5 62.891 (68.107)
[2021-04-26 18:44:02 train_lshot.py:257] INFO Epoch: [6][40/150] Time 0.622 (0.875) Data 0.001 (0.251) Loss 2.3223 (2.4325) Prec@1 38.672 (35.366) Prec@5 71.094 (68.016)
[2021-04-26 18:44:08 train_lshot.py:257] INFO Epoch: [6][50/150] Time 0.621 (0.826) Data 0.001 (0.202) Loss 2.4581 (2.4322) Prec@1 35.938 (35.478) Prec@5 65.625 (67.854)
[2021-04-26 18:44:15 train_lshot.py:257] INFO Epoch: [6][60/150] Time 0.623 (0.793) Data 0.001 (0.169) Loss 2.4283 (2.4306) Prec@1 35.547 (35.483) Prec@5 67.969 (67.873)
[2021-04-26 18:44:21 train_lshot.py:257] INFO Epoch: [6][70/150] Time 0.630 (0.769) Data 0.001 (0.145) Loss 2.4372 (2.4336) Prec@1 36.719 (35.437) Prec@5 62.500 (67.765)
[2021-04-26 18:44:27 train_lshot.py:257] INFO Epoch: [6][80/150] Time 0.627 (0.751) Data 0.001 (0.127) Loss 2.4082 (2.4332) Prec@1 35.547 (35.552) Prec@5 67.578 (67.747)
[2021-04-26 18:44:33 train_lshot.py:257] INFO Epoch: [6][90/150] Time 0.626 (0.737) Data 0.000 (0.113) Loss 2.4138 (2.4348) Prec@1 40.625 (35.568) Prec@5 63.281 (67.664)
[2021-04-26 18:44:40 train_lshot.py:257] INFO Epoch: [6][100/150] Time 0.624 (0.726) Data 0.000 (0.102) Loss 2.3654 (2.4310) Prec@1 35.547 (35.609) Prec@5 71.094 (67.833)
[2021-04-26 18:44:46 train_lshot.py:257] INFO Epoch: [6][110/150] Time 0.623 (0.717) Data 0.000 (0.093) Loss 2.3616 (2.4277) Prec@1 37.891 (35.631) Prec@5 70.703 (67.909)
[2021-04-26 18:44:52 train_lshot.py:257] INFO Epoch: [6][120/150] Time 0.623 (0.709) Data 0.001 (0.085) Loss 2.3172 (2.4228) Prec@1 35.547 (35.699) Prec@5 72.656 (68.040)
[2021-04-26 18:44:58 train_lshot.py:257] INFO Epoch: [6][130/150] Time 0.625 (0.702) Data 0.000 (0.079) Loss 2.3558 (2.4212) Prec@1 39.453 (35.842) Prec@5 67.969 (68.112)
[2021-04-26 18:45:04 train_lshot.py:257] INFO Epoch: [6][140/150] Time 0.623 (0.697) Data 0.000 (0.073) Loss 2.3356 (2.4145) Prec@1 38.281 (35.976) Prec@5 69.531 (68.304)
[2021-04-26 18:45:20 train_lshot.py:257] INFO Epoch: [7][0/150] Time 9.453 (9.453) Data 8.788 (8.788) Loss 2.4572 (2.4572) Prec@1 33.984 (33.984) Prec@5 69.531 (69.531)
[2021-04-26 18:45:26 train_lshot.py:257] INFO Epoch: [7][10/150] Time 0.621 (1.438) Data 0.000 (0.813) Loss 2.2507 (2.3714) Prec@1 37.891 (36.364) Prec@5 70.703 (69.602)
[2021-04-26 18:45:32 train_lshot.py:257] INFO Epoch: [7][20/150] Time 0.622 (1.050) Data 0.001 (0.426) Loss 2.2635 (2.3329) Prec@1 38.281 (37.686) Prec@5 72.266 (70.685)
[2021-04-26 18:45:39 train_lshot.py:257] INFO Epoch: [7][30/150] Time 0.620 (0.912) Data 0.001 (0.289) Loss 2.2932 (2.3250) Prec@1 39.453 (38.143) Prec@5 69.922 (70.665)
[2021-04-26 18:45:45 train_lshot.py:257] INFO Epoch: [7][40/150] Time 0.628 (0.842) Data 0.001 (0.219) Loss 2.2097 (2.3096) Prec@1 43.359 (38.615) Prec@5 74.609 (71.056)
[2021-04-26 18:45:51 train_lshot.py:257] INFO Epoch: [7][50/150] Time 0.623 (0.800) Data 0.000 (0.176) Loss 2.4424 (2.3113) Prec@1 39.062 (38.480) Prec@5 67.969 (71.071)
[2021-04-26 18:45:58 train_lshot.py:257] INFO Epoch: [7][60/150] Time 0.631 (0.772) Data 0.001 (0.147) Loss 2.3670 (2.3026) Prec@1 40.234 (38.870) Prec@5 70.312 (71.215)
[2021-04-26 18:46:04 train_lshot.py:257] INFO Epoch: [7][70/150] Time 0.625 (0.752) Data 0.001 (0.127) Loss 2.2881 (2.2980) Prec@1 39.844 (38.870) Prec@5 68.359 (71.259)
[2021-04-26 18:46:10 train_lshot.py:257] INFO Epoch: [7][80/150] Time 0.624 (0.736) Data 0.000 (0.111) Loss 2.0817 (2.2867) Prec@1 43.750 (39.106) Prec@5 75.391 (71.508)
[2021-04-26 18:46:16 train_lshot.py:257] INFO Epoch: [7][90/150] Time 0.622 (0.723) Data 0.000 (0.099) Loss 2.0800 (2.2835) Prec@1 44.141 (39.166) Prec@5 74.609 (71.424)
[2021-04-26 18:46:22 train_lshot.py:257] INFO Epoch: [7][100/150] Time 0.624 (0.713) Data 0.000 (0.089) Loss 2.3048 (2.2801) Prec@1 40.625 (39.298) Prec@5 70.703 (71.380)
[2021-04-26 18:46:29 train_lshot.py:257] INFO Epoch: [7][110/150] Time 0.624 (0.705) Data 0.000 (0.081) Loss 2.3504 (2.2752) Prec@1 36.328 (39.355) Prec@5 69.531 (71.488)
[2021-04-26 18:46:35 train_lshot.py:257] INFO Epoch: [7][120/150] Time 0.623 (0.698) Data 0.000 (0.074) Loss 2.1509 (2.2663) Prec@1 43.750 (39.663) Prec@5 71.875 (71.601)
[2021-04-26 18:46:41 train_lshot.py:257] INFO Epoch: [7][130/150] Time 0.622 (0.693) Data 0.000 (0.069) Loss 2.4128 (2.2660) Prec@1 39.453 (39.653) Prec@5 67.578 (71.690)
[2021-04-26 18:46:47 train_lshot.py:257] INFO Epoch: [7][140/150] Time 0.622 (0.688) Data 0.000 (0.064) Loss 2.1863 (2.2639) Prec@1 44.141 (39.741) Prec@5 73.828 (71.709)
[2021-04-26 18:47:40 train_lshot.py:119] INFO Meta Val 7: 0.4741600109636784
[2021-04-26 18:47:50 train_lshot.py:257] INFO Epoch: [8][0/150] Time 9.783 (9.783) Data 9.088 (9.088) Loss 2.3018 (2.3018) Prec@1 40.625 (40.625) Prec@5 70.312 (70.312)
[2021-04-26 18:47:56 train_lshot.py:257] INFO Epoch: [8][10/150] Time 0.623 (1.460) Data 0.000 (0.832) Loss 2.0011 (2.1486) Prec@1 47.266 (42.223) Prec@5 78.516 (74.183)
[2021-04-26 18:48:03 train_lshot.py:257] INFO Epoch: [8][20/150] Time 0.625 (1.062) Data 0.001 (0.436) Loss 2.1901 (2.1855) Prec@1 44.141 (40.755) Prec@5 72.656 (73.624)
[2021-04-26 18:48:09 train_lshot.py:257] INFO Epoch: [8][30/150] Time 0.624 (0.920) Data 0.001 (0.296) Loss 2.1494 (2.1748) Prec@1 40.625 (41.406) Prec@5 76.562 (73.538)
[2021-04-26 18:48:15 train_lshot.py:257] INFO Epoch: [8][40/150] Time 0.623 (0.848) Data 0.000 (0.224) Loss 2.1553 (2.1846) Prec@1 46.484 (41.473) Prec@5 73.438 (73.085)
[2021-04-26 18:48:21 train_lshot.py:257] INFO Epoch: [8][50/150] Time 0.631 (0.805) Data 0.001 (0.180) Loss 2.1572 (2.1816) Prec@1 42.188 (41.529) Prec@5 75.000 (73.246)
[2021-04-26 18:48:28 train_lshot.py:257] INFO Epoch: [8][60/150] Time 0.627 (0.775) Data 0.000 (0.151) Loss 2.0543 (2.1801) Prec@1 47.266 (41.598) Prec@5 77.344 (73.258)
[2021-04-26 18:48:34 train_lshot.py:257] INFO Epoch: [8][70/150] Time 0.624 (0.754) Data 0.001 (0.129) Loss 2.1556 (2.1798) Prec@1 42.188 (41.632) Prec@5 75.391 (73.201)
[2021-04-26 18:48:40 train_lshot.py:257] INFO Epoch: [8][80/150] Time 0.620 (0.738) Data 0.000 (0.114) Loss 2.1355 (2.1776) Prec@1 43.750 (41.681) Prec@5 73.047 (73.336)
[2021-04-26 18:48:46 train_lshot.py:257] INFO Epoch: [8][90/150] Time 0.625 (0.725) Data 0.000 (0.101) Loss 2.2869 (2.1715) Prec@1 41.016 (41.913) Prec@5 73.047 (73.450)
[2021-04-26 18:48:53 train_lshot.py:257] INFO Epoch: [8][100/150] Time 0.621 (0.715) Data 0.000 (0.091) Loss 2.0508 (2.1638) Prec@1 45.703 (42.064) Prec@5 75.781 (73.612)
[2021-04-26 18:48:59 train_lshot.py:257] INFO Epoch: [8][110/150] Time 0.625 (0.707) Data 0.000 (0.083) Loss 2.1948 (2.1595) Prec@1 41.016 (42.216) Prec@5 71.875 (73.624)
[2021-04-26 18:49:05 train_lshot.py:257] INFO Epoch: [8][120/150] Time 0.624 (0.700) Data 0.000 (0.076) Loss 2.0957 (2.1516) Prec@1 45.703 (42.517) Prec@5 75.781 (73.760)
[2021-04-26 18:49:11 train_lshot.py:257] INFO Epoch: [8][130/150] Time 0.621 (0.694) Data 0.000 (0.070) Loss 2.1216 (2.1440) Prec@1 41.016 (42.668) Prec@5 74.219 (73.938)
[2021-04-26 18:49:18 train_lshot.py:257] INFO Epoch: [8][140/150] Time 0.620 (0.689) Data 0.000 (0.065) Loss 2.1800 (2.1432) Prec@1 40.625 (42.634) Prec@5 75.000 (73.967)
[2021-04-26 18:49:34 train_lshot.py:257] INFO Epoch: [9][0/150] Time 10.626 (10.626) Data 9.982 (9.982) Loss 2.0070 (2.0070) Prec@1 45.703 (45.703) Prec@5 77.734 (77.734)
[2021-04-26 18:49:40 train_lshot.py:257] INFO Epoch: [9][10/150] Time 0.623 (1.530) Data 0.000 (0.908) Loss 2.0489 (2.0356) Prec@1 46.094 (45.064) Prec@5 76.562 (75.604)
[2021-04-26 18:49:47 train_lshot.py:257] INFO Epoch: [9][20/150] Time 0.621 (1.098) Data 0.000 (0.476) Loss 2.0128 (2.0259) Prec@1 44.922 (45.350) Prec@5 74.609 (76.079)
[2021-04-26 18:49:53 train_lshot.py:257] INFO Epoch: [9][30/150] Time 0.628 (0.946) Data 0.001 (0.323) Loss 2.0827 (2.0455) Prec@1 46.875 (45.237) Prec@5 73.047 (75.605)
[2021-04-26 18:49:59 train_lshot.py:257] INFO Epoch: [9][40/150] Time 0.621 (0.868) Data 0.001 (0.244) Loss 2.0634 (2.0483) Prec@1 44.531 (45.332) Prec@5 76.172 (75.667)
[2021-04-26 18:50:05 train_lshot.py:257] INFO Epoch: [9][50/150] Time 0.631 (0.821) Data 0.001 (0.196) Loss 1.9882 (2.0394) Prec@1 44.141 (45.565) Prec@5 78.125 (75.858)
[2021-04-26 18:50:12 train_lshot.py:257] INFO Epoch: [9][60/150] Time 0.622 (0.788) Data 0.001 (0.164) Loss 2.1288 (2.0400) Prec@1 44.141 (45.402) Prec@5 73.047 (75.807)
[2021-04-26 18:50:18 train_lshot.py:257] INFO Epoch: [9][70/150] Time 0.624 (0.766) Data 0.001 (0.141) Loss 1.9677 (2.0441) Prec@1 52.344 (45.401) Prec@5 76.172 (75.704)
[2021-04-26 18:50:24 train_lshot.py:257] INFO Epoch: [9][80/150] Time 0.623 (0.748) Data 0.000 (0.124) Loss 2.1301 (2.0384) Prec@1 44.141 (45.563) Prec@5 71.484 (75.820)
[2021-04-26 18:50:30 train_lshot.py:257] INFO Epoch: [9][90/150] Time 0.622 (0.734) Data 0.001 (0.110) Loss 2.0843 (2.0336) Prec@1 43.750 (45.669) Prec@5 74.609 (75.867)
[2021-04-26 18:50:37 train_lshot.py:257] INFO Epoch: [9][100/150] Time 0.623 (0.723) Data 0.000 (0.099) Loss 2.1354 (2.0375) Prec@1 39.844 (45.614) Prec@5 75.781 (75.777)
[2021-04-26 18:50:43 train_lshot.py:257] INFO Epoch: [9][110/150] Time 0.620 (0.714) Data 0.000 (0.090) Loss 2.1119 (2.0369) Prec@1 44.531 (45.636) Prec@5 75.781 (75.781)
[2021-04-26 18:50:49 train_lshot.py:257] INFO Epoch: [9][120/150] Time 0.626 (0.707) Data 0.000 (0.083) Loss 1.7291 (2.0315) Prec@1 52.734 (45.755) Prec@5 80.859 (75.865)
[2021-04-26 18:50:55 train_lshot.py:257] INFO Epoch: [9][130/150] Time 0.622 (0.700) Data 0.000 (0.077) Loss 1.9882 (2.0280) Prec@1 44.922 (45.870) Prec@5 78.125 (75.975)
[2021-04-26 18:51:02 train_lshot.py:257] INFO Epoch: [9][140/150] Time 0.624 (0.695) Data 0.000 (0.071) Loss 1.8266 (2.0251) Prec@1 52.734 (45.944) Prec@5 82.031 (76.075)
[2021-04-26 18:51:18 train_lshot.py:257] INFO Epoch: [10][0/150] Time 10.191 (10.191) Data 9.544 (9.544) Loss 2.0648 (2.0648) Prec@1 47.266 (47.266) Prec@5 75.391 (75.391)
[2021-04-26 18:51:24 train_lshot.py:257] INFO Epoch: [10][10/150] Time 0.621 (1.492) Data 0.000 (0.868) Loss 1.8908 (1.9325) Prec@1 48.047 (48.047) Prec@5 78.906 (77.912)
[2021-04-26 18:51:30 train_lshot.py:257] INFO Epoch: [10][20/150] Time 0.622 (1.079) Data 0.001 (0.456) Loss 1.9765 (1.9402) Prec@1 47.266 (48.047) Prec@5 76.172 (77.623)
[2021-04-26 18:51:36 train_lshot.py:257] INFO Epoch: [10][30/150] Time 0.627 (0.932) Data 0.000 (0.309) Loss 1.7881 (1.9312) Prec@1 55.078 (48.274) Prec@5 78.125 (77.772)
[2021-04-26 18:51:43 train_lshot.py:257] INFO Epoch: [10][40/150] Time 0.624 (0.857) Data 0.000 (0.234) Loss 1.8420 (1.9187) Prec@1 50.391 (48.628) Prec@5 76.562 (77.973)
[2021-04-26 18:51:49 train_lshot.py:257] INFO Epoch: [10][50/150] Time 0.626 (0.812) Data 0.001 (0.188) Loss 1.9072 (1.9097) Prec@1 52.734 (48.820) Prec@5 80.078 (78.102)
[2021-04-26 18:51:55 train_lshot.py:257] INFO Epoch: [10][60/150] Time 0.624 (0.781) Data 0.000 (0.157) Loss 1.9051 (1.9075) Prec@1 50.781 (48.809) Prec@5 77.344 (78.119)
[2021-04-26 18:52:02 train_lshot.py:257] INFO Epoch: [10][70/150] Time 0.623 (0.760) Data 0.001 (0.135) Loss 2.1370 (1.9059) Prec@1 43.359 (48.845) Prec@5 73.828 (78.268)
[2021-04-26 18:52:08 train_lshot.py:257] INFO Epoch: [10][80/150] Time 0.623 (0.743) Data 0.001 (0.119) Loss 1.7883 (1.9054) Prec@1 54.688 (48.679) Prec@5 77.734 (78.274)
[2021-04-26 18:52:14 train_lshot.py:257] INFO Epoch: [10][90/150] Time 0.620 (0.730) Data 0.000 (0.106) Loss 1.9615 (1.9056) Prec@1 47.656 (48.652) Prec@5 76.953 (78.310)
[2021-04-26 18:52:20 train_lshot.py:257] INFO Epoch: [10][100/150] Time 0.625 (0.719) Data 0.000 (0.095) Loss 1.7842 (1.9062) Prec@1 50.000 (48.654) Prec@5 82.812 (78.233)
[2021-04-26 18:52:26 train_lshot.py:257] INFO Epoch: [10][110/150] Time 0.628 (0.711) Data 0.000 (0.087) Loss 1.8252 (1.9045) Prec@1 50.781 (48.687) Prec@5 79.297 (78.252)
[2021-04-26 18:52:33 train_lshot.py:257] INFO Epoch: [10][120/150] Time 0.625 (0.704) Data 0.000 (0.080) Loss 1.6872 (1.9017) Prec@1 56.641 (48.747) Prec@5 78.906 (78.296)
[2021-04-26 18:52:39 train_lshot.py:257] INFO Epoch: [10][130/150] Time 0.624 (0.697) Data 0.000 (0.073) Loss 1.7767 (1.8988) Prec@1 54.688 (48.935) Prec@5 79.688 (78.372)
[2021-04-26 18:52:45 train_lshot.py:257] INFO Epoch: [10][140/150] Time 0.624 (0.692) Data 0.000 (0.068) Loss 1.8692 (1.9019) Prec@1 47.266 (48.798) Prec@5 80.859 (78.272)
[2021-04-26 18:53:01 train_lshot.py:257] INFO Epoch: [11][0/150] Time 9.517 (9.517) Data 8.855 (8.855) Loss 2.0273 (2.0273) Prec@1 44.531 (44.531) Prec@5 72.656 (72.656)
[2021-04-26 18:53:07 train_lshot.py:257] INFO Epoch: [11][10/150] Time 0.625 (1.430) Data 0.000 (0.806) Loss 1.6520 (1.8354) Prec@1 54.688 (49.822) Prec@5 83.594 (80.078)
[2021-04-26 18:53:13 train_lshot.py:257] INFO Epoch: [11][20/150] Time 0.624 (1.046) Data 0.001 (0.422) Loss 1.8454 (1.8150) Prec@1 46.094 (50.019) Prec@5 82.812 (80.692)
[2021-04-26 18:53:19 train_lshot.py:257] INFO Epoch: [11][30/150] Time 0.624 (0.910) Data 0.000 (0.286) Loss 1.7779 (1.8274) Prec@1 51.562 (50.290) Prec@5 78.516 (80.154)
[2021-04-26 18:53:26 train_lshot.py:257] INFO Epoch: [11][40/150] Time 0.622 (0.840) Data 0.001 (0.217) Loss 1.8924 (1.8414) Prec@1 48.438 (50.000) Prec@5 79.688 (79.878)
[2021-04-26 18:53:32 train_lshot.py:257] INFO Epoch: [11][50/150] Time 0.621 (0.798) Data 0.000 (0.174) Loss 1.7821 (1.8359) Prec@1 52.734 (50.214) Prec@5 77.344 (80.070)
[2021-04-26 18:53:38 train_lshot.py:257] INFO Epoch: [11][60/150] Time 0.619 (0.770) Data 0.000 (0.146) Loss 1.7348 (1.8323) Prec@1 51.953 (50.570) Prec@5 82.031 (79.848)
[2021-04-26 18:53:44 train_lshot.py:257] INFO Epoch: [11][70/150] Time 0.623 (0.749) Data 0.001 (0.125) Loss 1.7272 (1.8291) Prec@1 55.859 (50.737) Prec@5 80.859 (79.853)
[2021-04-26 18:53:51 train_lshot.py:257] INFO Epoch: [11][80/150] Time 0.623 (0.734) Data 0.000 (0.110) Loss 1.7271 (1.8322) Prec@1 50.781 (50.656) Prec@5 82.031 (79.832)
[2021-04-26 18:53:57 train_lshot.py:257] INFO Epoch: [11][90/150] Time 0.621 (0.722) Data 0.000 (0.098) Loss 1.7737 (1.8337) Prec@1 54.297 (50.631) Prec@5 83.594 (79.808)
[2021-04-26 18:54:03 train_lshot.py:257] INFO Epoch: [11][100/150] Time 0.621 (0.712) Data 0.000 (0.088) Loss 1.9350 (1.8305) Prec@1 48.828 (50.766) Prec@5 77.734 (79.862)
[2021-04-26 18:54:09 train_lshot.py:257] INFO Epoch: [11][110/150] Time 0.624 (0.704) Data 0.000 (0.080) Loss 1.5733 (1.8330) Prec@1 55.469 (50.827) Prec@5 84.766 (79.744)
[2021-04-26 18:54:16 train_lshot.py:257] INFO Epoch: [11][120/150] Time 0.622 (0.697) Data 0.000 (0.074) Loss 1.6573 (1.8308) Prec@1 59.766 (50.917) Prec@5 84.375 (79.723)
[2021-04-26 18:54:22 train_lshot.py:257] INFO Epoch: [11][130/150] Time 0.621 (0.691) Data 0.000 (0.068) Loss 1.9221 (1.8271) Prec@1 44.531 (50.921) Prec@5 78.906 (79.756)
[2021-04-26 18:54:28 train_lshot.py:257] INFO Epoch: [11][140/150] Time 0.620 (0.686) Data 0.000 (0.063) Loss 1.8129 (1.8282) Prec@1 50.391 (50.842) Prec@5 79.688 (79.754)
[2021-04-26 18:55:19 train_lshot.py:119] INFO Meta Val 11: 0.5174400110244751
[2021-04-26 18:55:30 train_lshot.py:257] INFO Epoch: [12][0/150] Time 10.636 (10.636) Data 9.982 (9.982) Loss 1.6380 (1.6380) Prec@1 56.641 (56.641) Prec@5 81.641 (81.641)
[2021-04-26 18:55:36 train_lshot.py:257] INFO Epoch: [12][10/150] Time 0.620 (1.530) Data 0.000 (0.908) Loss 1.6767 (1.7227) Prec@1 51.172 (53.018) Prec@5 83.594 (81.676)
[2021-04-26 18:55:43 train_lshot.py:257] INFO Epoch: [12][20/150] Time 0.619 (1.107) Data 0.000 (0.476) Loss 1.6607 (1.7339) Prec@1 57.422 (53.032) Prec@5 80.469 (81.231)
[2021-04-26 18:55:49 train_lshot.py:257] INFO Epoch: [12][30/150] Time 0.622 (0.951) Data 0.001 (0.323) Loss 1.7394 (1.7352) Prec@1 53.516 (52.835) Prec@5 83.203 (81.389)
[2021-04-26 18:55:55 train_lshot.py:257] INFO Epoch: [12][40/150] Time 0.621 (0.871) Data 0.001 (0.244) Loss 1.6624 (1.7392) Prec@1 55.469 (52.715) Prec@5 82.812 (81.279)
[2021-04-26 18:56:01 train_lshot.py:257] INFO Epoch: [12][50/150] Time 0.622 (0.823) Data 0.000 (0.196) Loss 1.6693 (1.7326) Prec@1 57.422 (53.079) Prec@5 81.641 (81.288)
[2021-04-26 18:56:08 train_lshot.py:257] INFO Epoch: [12][60/150] Time 0.623 (0.790) Data 0.000 (0.164) Loss 1.8347 (1.7251) Prec@1 51.953 (53.343) Prec@5 79.688 (81.410)
[2021-04-26 18:56:14 train_lshot.py:257] INFO Epoch: [12][70/150] Time 0.621 (0.766) Data 0.001 (0.141) Loss 1.7656 (1.7307) Prec@1 50.391 (53.081) Prec@5 80.469 (81.377)
[2021-04-26 18:56:20 train_lshot.py:257] INFO Epoch: [12][80/150] Time 0.624 (0.749) Data 0.000 (0.124) Loss 1.7320 (1.7294) Prec@1 51.953 (53.091) Prec@5 81.250 (81.472)
[2021-04-26 18:56:26 train_lshot.py:257] INFO Epoch: [12][90/150] Time 0.623 (0.735) Data 0.000 (0.110) Loss 1.5657 (1.7251) Prec@1 57.031 (53.138) Prec@5 83.594 (81.542)
[2021-04-26 18:56:32 train_lshot.py:257] INFO Epoch: [12][100/150] Time 0.621 (0.723) Data 0.000 (0.099) Loss 1.6430 (1.7253) Prec@1 54.688 (53.129) Prec@5 82.031 (81.528)
[2021-04-26 18:56:39 train_lshot.py:257] INFO Epoch: [12][110/150] Time 0.622 (0.714) Data 0.000 (0.090) Loss 1.6229 (1.7225) Prec@1 55.078 (53.146) Prec@5 81.641 (81.591)
[2021-04-26 18:56:45 train_lshot.py:257] INFO Epoch: [12][120/150] Time 0.620 (0.707) Data 0.000 (0.083) Loss 1.6492 (1.7241) Prec@1 57.422 (53.193) Prec@5 78.516 (81.515)
[2021-04-26 18:56:51 train_lshot.py:257] INFO Epoch: [12][130/150] Time 0.622 (0.700) Data 0.000 (0.077) Loss 1.7740 (1.7220) Prec@1 51.172 (53.229) Prec@5 82.031 (81.533)
[2021-04-26 18:56:57 train_lshot.py:257] INFO Epoch: [12][140/150] Time 0.621 (0.695) Data 0.000 (0.071) Loss 1.6978 (1.7218) Prec@1 51.562 (53.272) Prec@5 83.203 (81.483)
[2021-04-26 18:57:13 train_lshot.py:257] INFO Epoch: [13][0/150] Time 9.756 (9.756) Data 9.104 (9.104) Loss 1.5538 (1.5538) Prec@1 57.812 (57.812) Prec@5 86.328 (86.328)
[2021-04-26 18:57:19 train_lshot.py:257] INFO Epoch: [13][10/150] Time 0.617 (1.450) Data 0.000 (0.828) Loss 1.6442 (1.6510) Prec@1 57.422 (54.794) Prec@5 81.250 (82.777)
[2021-04-26 18:57:26 train_lshot.py:257] INFO Epoch: [13][20/150] Time 0.624 (1.056) Data 0.002 (0.434) Loss 1.6239 (1.6360) Prec@1 55.469 (55.450) Prec@5 84.375 (82.999)
[2021-04-26 18:57:32 train_lshot.py:257] INFO Epoch: [13][30/150] Time 0.635 (0.917) Data 0.001 (0.294) Loss 1.7132 (1.6480) Prec@1 53.516 (55.481) Prec@5 80.078 (82.825)
[2021-04-26 18:57:38 train_lshot.py:257] INFO Epoch: [13][40/150] Time 0.621 (0.846) Data 0.000 (0.223) Loss 1.8467 (1.6479) Prec@1 50.000 (55.650) Prec@5 79.297 (82.879)
[2021-04-26 18:57:44 train_lshot.py:257] INFO Epoch: [13][50/150] Time 0.641 (0.803) Data 0.001 (0.179) Loss 1.6382 (1.6575) Prec@1 53.516 (55.323) Prec@5 82.422 (82.774)
[2021-04-26 18:57:51 train_lshot.py:257] INFO Epoch: [13][60/150] Time 0.619 (0.774) Data 0.000 (0.150) Loss 1.5876 (1.6632) Prec@1 58.594 (55.161) Prec@5 80.859 (82.576)
[2021-04-26 18:57:57 train_lshot.py:257] INFO Epoch: [13][70/150] Time 0.624 (0.753) Data 0.001 (0.129) Loss 1.5606 (1.6658) Prec@1 59.375 (55.029) Prec@5 83.594 (82.521)
[2021-04-26 18:58:03 train_lshot.py:257] INFO Epoch: [13][80/150] Time 0.622 (0.737) Data 0.000 (0.113) Loss 1.7252 (1.6664) Prec@1 55.469 (55.015) Prec@5 80.469 (82.586)
[2021-04-26 18:58:09 train_lshot.py:257] INFO Epoch: [13][90/150] Time 0.623 (0.724) Data 0.000 (0.101) Loss 1.5306 (1.6606) Prec@1 59.375 (55.160) Prec@5 85.938 (82.722)
[2021-04-26 18:58:16 train_lshot.py:257] INFO Epoch: [13][100/150] Time 0.626 (0.714) Data 0.000 (0.091) Loss 1.6911 (1.6629) Prec@1 57.422 (54.997) Prec@5 79.297 (82.712)
[2021-04-26 18:58:22 train_lshot.py:257] INFO Epoch: [13][110/150] Time 0.623 (0.706) Data 0.000 (0.083) Loss 1.5786 (1.6644) Prec@1 59.375 (55.113) Prec@5 82.812 (82.556)
[2021-04-26 18:58:28 train_lshot.py:257] INFO Epoch: [13][120/150] Time 0.623 (0.699) Data 0.000 (0.076) Loss 1.6196 (1.6640) Prec@1 58.203 (55.133) Prec@5 82.812 (82.467)
[2021-04-26 18:58:34 train_lshot.py:257] INFO Epoch: [13][130/150] Time 0.623 (0.693) Data 0.000 (0.070) Loss 1.4443 (1.6567) Prec@1 60.938 (55.275) Prec@5 85.938 (82.577)
[2021-04-26 18:58:40 train_lshot.py:257] INFO Epoch: [13][140/150] Time 0.622 (0.688) Data 0.000 (0.065) Loss 1.8216 (1.6564) Prec@1 50.000 (55.225) Prec@5 81.641 (82.641)
[2021-04-26 18:58:56 train_lshot.py:257] INFO Epoch: [14][0/150] Time 9.153 (9.153) Data 8.500 (8.500) Loss 1.4622 (1.4622) Prec@1 60.938 (60.938) Prec@5 83.984 (83.984)
[2021-04-26 18:59:02 train_lshot.py:257] INFO Epoch: [14][10/150] Time 0.619 (1.396) Data 0.000 (0.773) Loss 1.6146 (1.5618) Prec@1 50.000 (56.854) Prec@5 83.203 (83.452)
[2021-04-26 18:59:08 train_lshot.py:257] INFO Epoch: [14][20/150] Time 0.628 (1.029) Data 0.001 (0.405) Loss 1.4742 (1.5342) Prec@1 57.812 (57.459) Prec@5 83.984 (84.245)
[2021-04-26 18:59:14 train_lshot.py:257] INFO Epoch: [14][30/150] Time 0.623 (0.898) Data 0.000 (0.275) Loss 1.4099 (1.5347) Prec@1 61.328 (57.497) Prec@5 85.156 (84.249)
[2021-04-26 18:59:20 train_lshot.py:257] INFO Epoch: [14][40/150] Time 0.623 (0.832) Data 0.000 (0.208) Loss 1.7291 (1.5602) Prec@1 52.734 (57.012) Prec@5 80.469 (83.756)
[2021-04-26 18:59:27 train_lshot.py:257] INFO Epoch: [14][50/150] Time 0.628 (0.791) Data 0.001 (0.167) Loss 1.6078 (1.5580) Prec@1 53.906 (57.223) Prec@5 83.984 (83.824)
[2021-04-26 18:59:33 train_lshot.py:257] INFO Epoch: [14][60/150] Time 0.623 (0.764) Data 0.000 (0.140) Loss 2.0404 (1.5712) Prec@1 44.531 (57.018) Prec@5 74.609 (83.645)
[2021-04-26 18:59:39 train_lshot.py:257] INFO Epoch: [14][70/150] Time 0.624 (0.744) Data 0.002 (0.120) Loss 1.5022 (1.5629) Prec@1 61.328 (57.301) Prec@5 87.500 (83.869)
[2021-04-26 18:59:45 train_lshot.py:257] INFO Epoch: [14][80/150] Time 0.619 (0.729) Data 0.000 (0.105) Loss 1.2365 (1.5585) Prec@1 64.062 (57.378) Prec@5 88.672 (83.960)
[2021-04-26 18:59:52 train_lshot.py:257] INFO Epoch: [14][90/150] Time 0.621 (0.718) Data 0.000 (0.094) Loss 1.3819 (1.5577) Prec@1 58.984 (57.418) Prec@5 87.500 (84.032)
[2021-04-26 18:59:58 train_lshot.py:257] INFO Epoch: [14][100/150] Time 0.618 (0.708) Data 0.000 (0.085) Loss 1.5947 (1.5624) Prec@1 53.906 (57.317) Prec@5 85.547 (83.915)
[2021-04-26 19:00:04 train_lshot.py:257] INFO Epoch: [14][110/150] Time 0.623 (0.700) Data 0.000 (0.077) Loss 1.5146 (1.5643) Prec@1 58.594 (57.337) Prec@5 85.156 (83.918)
[2021-04-26 19:00:10 train_lshot.py:257] INFO Epoch: [14][120/150] Time 0.622 (0.694) Data 0.000 (0.071) Loss 1.5343 (1.5660) Prec@1 55.859 (57.196) Prec@5 83.203 (83.849)
[2021-04-26 19:00:17 train_lshot.py:257] INFO Epoch: [14][130/150] Time 0.627 (0.688) Data 0.000 (0.065) Loss 1.7483 (1.5654) Prec@1 55.469 (57.252) Prec@5 80.859 (83.913)
[2021-04-26 19:00:23 train_lshot.py:257] INFO Epoch: [14][140/150] Time 0.619 (0.684) Data 0.000 (0.061) Loss 1.5562 (1.5620) Prec@1 57.812 (57.330) Prec@5 83.594 (83.971)
[2021-04-26 19:00:39 train_lshot.py:257] INFO Epoch: [15][0/150] Time 10.556 (10.556) Data 9.877 (9.877) Loss 1.5434 (1.5434) Prec@1 58.203 (58.203) Prec@5 82.812 (82.812)
[2021-04-26 19:00:46 train_lshot.py:257] INFO Epoch: [15][10/150] Time 0.624 (1.543) Data 0.000 (0.917) Loss 1.4169 (1.5397) Prec@1 58.984 (57.990) Prec@5 87.891 (83.913)
[2021-04-26 19:00:52 train_lshot.py:257] INFO Epoch: [15][20/150] Time 0.625 (1.105) Data 0.000 (0.481) Loss 1.3327 (1.5161) Prec@1 65.234 (58.836) Prec@5 90.625 (84.821)
[2021-04-26 19:00:58 train_lshot.py:257] INFO Epoch: [15][30/150] Time 0.627 (0.951) Data 0.001 (0.326) Loss 1.3868 (1.5165) Prec@1 59.766 (59.136) Prec@5 89.062 (84.955)
[2021-04-26 19:01:05 train_lshot.py:257] INFO Epoch: [15][40/150] Time 0.622 (0.871) Data 0.000 (0.246) Loss 1.5846 (1.5097) Prec@1 54.688 (59.051) Prec@5 83.984 (85.032)
[2021-04-26 19:01:11 train_lshot.py:257] INFO Epoch: [15][50/150] Time 0.622 (0.822) Data 0.000 (0.198) Loss 1.5028 (1.5040) Prec@1 60.547 (59.206) Prec@5 87.891 (85.026)
[2021-04-26 19:01:17 train_lshot.py:257] INFO Epoch: [15][60/150] Time 0.623 (0.790) Data 0.000 (0.166) Loss 1.3671 (1.4998) Prec@1 64.453 (59.305) Prec@5 84.375 (84.964)
[2021-04-26 19:01:23 train_lshot.py:257] INFO Epoch: [15][70/150] Time 0.624 (0.767) Data 0.001 (0.143) Loss 1.4482 (1.5015) Prec@1 64.062 (59.298) Prec@5 84.375 (84.986)
[2021-04-26 19:01:30 train_lshot.py:257] INFO Epoch: [15][80/150] Time 0.622 (0.749) Data 0.000 (0.125) Loss 1.5876 (1.5008) Prec@1 54.297 (59.254) Prec@5 85.547 (84.954)
[2021-04-26 19:01:36 train_lshot.py:257] INFO Epoch: [15][90/150] Time 0.625 (0.735) Data 0.000 (0.111) Loss 1.4274 (1.4957) Prec@1 64.062 (59.358) Prec@5 85.547 (85.070)
[2021-04-26 19:01:42 train_lshot.py:257] INFO Epoch: [15][100/150] Time 0.622 (0.724) Data 0.000 (0.100) Loss 1.5788 (1.4991) Prec@1 59.766 (59.375) Prec@5 81.250 (84.978)
[2021-04-26 19:01:48 train_lshot.py:257] INFO Epoch: [15][110/150] Time 0.623 (0.715) Data 0.000 (0.091) Loss 1.3634 (1.5026) Prec@1 61.719 (59.284) Prec@5 86.328 (84.889)
[2021-04-26 19:01:54 train_lshot.py:257] INFO Epoch: [15][120/150] Time 0.618 (0.707) Data 0.000 (0.084) Loss 1.3506 (1.5054) Prec@1 62.109 (59.181) Prec@5 89.062 (84.927)
[2021-04-26 19:02:01 train_lshot.py:257] INFO Epoch: [15][130/150] Time 0.620 (0.701) Data 0.000 (0.077) Loss 1.6260 (1.5064) Prec@1 55.469 (59.157) Prec@5 81.250 (84.909)
[2021-04-26 19:02:07 train_lshot.py:257] INFO Epoch: [15][140/150] Time 0.622 (0.695) Data 0.000 (0.072) Loss 1.6175 (1.5094) Prec@1 59.375 (59.092) Prec@5 81.641 (84.827)
[2021-04-26 19:02:55 train_lshot.py:119] INFO Meta Val 15: 0.5598666790723801
[2021-04-26 19:03:06 train_lshot.py:257] INFO Epoch: [16][0/150] Time 10.637 (10.637) Data 9.986 (9.986) Loss 1.2580 (1.2580) Prec@1 65.625 (65.625) Prec@5 88.281 (88.281)
[2021-04-26 19:03:12 train_lshot.py:257] INFO Epoch: [16][10/150] Time 0.619 (1.530) Data 0.000 (0.908) Loss 1.3527 (1.4199) Prec@1 65.234 (62.003) Prec@5 88.281 (86.009)
[2021-04-26 19:03:19 train_lshot.py:257] INFO Epoch: [16][20/150] Time 0.626 (1.098) Data 0.001 (0.476) Loss 1.4881 (1.4254) Prec@1 62.891 (61.403) Prec@5 85.156 (86.291)
[2021-04-26 19:03:25 train_lshot.py:257] INFO Epoch: [16][30/150] Time 0.622 (0.945) Data 0.000 (0.323) Loss 1.5150 (1.4373) Prec@1 60.156 (61.114) Prec@5 82.422 (85.723)
[2021-04-26 19:03:31 train_lshot.py:257] INFO Epoch: [16][40/150] Time 0.623 (0.866) Data 0.000 (0.244) Loss 1.2931 (1.4371) Prec@1 63.672 (60.880) Prec@5 87.891 (85.871)
[2021-04-26 19:03:37 train_lshot.py:257] INFO Epoch: [16][50/150] Time 0.631 (0.819) Data 0.001 (0.196) Loss 1.5625 (1.4516) Prec@1 59.766 (60.486) Prec@5 84.375 (85.738)
[2021-04-26 19:03:44 train_lshot.py:257] INFO Epoch: [16][60/150] Time 0.620 (0.788) Data 0.000 (0.164) Loss 1.4235 (1.4509) Prec@1 60.156 (60.374) Prec@5 85.547 (85.739)
[2021-04-26 19:03:50 train_lshot.py:257] INFO Epoch: [16][70/150] Time 0.621 (0.764) Data 0.001 (0.141) Loss 1.6581 (1.4525) Prec@1 55.078 (60.393) Prec@5 81.641 (85.602)
[2021-04-26 19:03:56 train_lshot.py:257] INFO Epoch: [16][80/150] Time 0.620 (0.747) Data 0.000 (0.124) Loss 1.5415 (1.4452) Prec@1 56.250 (60.730) Prec@5 85.156 (85.749)
[2021-04-26 19:04:02 train_lshot.py:257] INFO Epoch: [16][90/150] Time 0.619 (0.733) Data 0.000 (0.110) Loss 1.3789 (1.4410) Prec@1 58.984 (60.796) Prec@5 88.672 (85.873)
[2021-04-26 19:04:08 train_lshot.py:257] INFO Epoch: [16][100/150] Time 0.625 (0.722) Data 0.000 (0.099) Loss 1.3914 (1.4415) Prec@1 62.891 (60.771) Prec@5 87.891 (85.810)
[2021-04-26 19:04:15 train_lshot.py:257] INFO Epoch: [16][110/150] Time 0.623 (0.713) Data 0.000 (0.091) Loss 1.3815 (1.4443) Prec@1 59.375 (60.723) Prec@5 86.719 (85.776)
[2021-04-26 19:04:21 train_lshot.py:257] INFO Epoch: [16][120/150] Time 0.621 (0.706) Data 0.000 (0.083) Loss 1.6109 (1.4477) Prec@1 59.766 (60.670) Prec@5 80.469 (85.708)
[2021-04-26 19:04:27 train_lshot.py:257] INFO Epoch: [16][130/150] Time 0.623 (0.699) Data 0.000 (0.077) Loss 1.5612 (1.4505) Prec@1 58.984 (60.633) Prec@5 83.984 (85.645)
[2021-04-26 19:04:33 train_lshot.py:257] INFO Epoch: [16][140/150] Time 0.622 (0.694) Data 0.000 (0.071) Loss 1.4866 (1.4518) Prec@1 57.812 (60.558) Prec@5 84.766 (85.663)
[2021-04-26 19:04:49 train_lshot.py:257] INFO Epoch: [17][0/150] Time 9.854 (9.854) Data 9.180 (9.180) Loss 1.4373 (1.4373) Prec@1 61.328 (61.328) Prec@5 86.719 (86.719)
[2021-04-26 19:04:55 train_lshot.py:257] INFO Epoch: [17][10/150] Time 0.620 (1.461) Data 0.001 (0.835) Loss 1.3369 (1.3802) Prec@1 64.453 (62.003) Prec@5 87.891 (87.500)
[2021-04-26 19:05:02 train_lshot.py:257] INFO Epoch: [17][20/150] Time 0.620 (1.062) Data 0.000 (0.438) Loss 1.3751 (1.3649) Prec@1 62.500 (62.556) Prec@5 85.156 (87.147)
[2021-04-26 19:05:08 train_lshot.py:257] INFO Epoch: [17][30/150] Time 0.629 (0.921) Data 0.001 (0.297) Loss 1.2345 (1.3351) Prec@1 66.797 (63.206) Prec@5 88.672 (87.487)
[2021-04-26 19:05:14 train_lshot.py:257] INFO Epoch: [17][40/150] Time 0.622 (0.848) Data 0.000 (0.225) Loss 1.4013 (1.3658) Prec@1 63.281 (62.414) Prec@5 85.547 (87.243)
[2021-04-26 19:05:20 train_lshot.py:257] INFO Epoch: [17][50/150] Time 0.623 (0.804) Data 0.001 (0.181) Loss 1.2431 (1.3678) Prec@1 64.844 (62.423) Prec@5 88.672 (87.178)
[2021-04-26 19:05:27 train_lshot.py:257] INFO Epoch: [17][60/150] Time 0.622 (0.775) Data 0.000 (0.151) Loss 1.4365 (1.3714) Prec@1 63.672 (62.391) Prec@5 86.719 (87.148)
[2021-04-26 19:05:33 train_lshot.py:257] INFO Epoch: [17][70/150] Time 0.628 (0.754) Data 0.003 (0.130) Loss 1.4938 (1.3743) Prec@1 60.156 (62.494) Prec@5 86.328 (86.988)
[2021-04-26 19:05:39 train_lshot.py:257] INFO Epoch: [17][80/150] Time 0.620 (0.738) Data 0.000 (0.114) Loss 1.3047 (1.3732) Prec@1 64.844 (62.466) Prec@5 87.891 (86.974)
[2021-04-26 19:05:45 train_lshot.py:257] INFO Epoch: [17][90/150] Time 0.619 (0.725) Data 0.000 (0.101) Loss 1.3830 (1.3777) Prec@1 58.203 (62.157) Prec@5 89.453 (86.972)
[2021-04-26 19:05:51 train_lshot.py:257] INFO Epoch: [17][100/150] Time 0.624 (0.715) Data 0.000 (0.091) Loss 1.3212 (1.3811) Prec@1 66.016 (62.109) Prec@5 85.547 (86.893)
[2021-04-26 19:05:58 train_lshot.py:257] INFO Epoch: [17][110/150] Time 0.623 (0.706) Data 0.000 (0.083) Loss 1.3507 (1.3811) Prec@1 61.719 (62.099) Prec@5 87.500 (86.863)
[2021-04-26 19:06:04 train_lshot.py:257] INFO Epoch: [17][120/150] Time 0.622 (0.699) Data 0.000 (0.076) Loss 1.3898 (1.3844) Prec@1 56.250 (61.945) Prec@5 90.625 (86.829)
[2021-04-26 19:06:10 train_lshot.py:257] INFO Epoch: [17][130/150] Time 0.621 (0.694) Data 0.000 (0.071) Loss 1.4326 (1.3868) Prec@1 59.375 (61.901) Prec@5 87.109 (86.778)
[2021-04-26 19:06:16 train_lshot.py:257] INFO Epoch: [17][140/150] Time 0.622 (0.688) Data 0.000 (0.066) Loss 1.5398 (1.3896) Prec@1 55.078 (61.813) Prec@5 84.766 (86.730)
[2021-04-26 19:06:32 train_lshot.py:257] INFO Epoch: [18][0/150] Time 9.758 (9.758) Data 9.067 (9.067) Loss 1.4131 (1.4131) Prec@1 60.547 (60.547) Prec@5 87.500 (87.500)
[2021-04-26 19:06:38 train_lshot.py:257] INFO Epoch: [18][10/150] Time 0.623 (1.452) Data 0.000 (0.825) Loss 1.2123 (1.3212) Prec@1 63.281 (63.885) Prec@5 91.016 (87.536)
[2021-04-26 19:06:45 train_lshot.py:257] INFO Epoch: [18][20/150] Time 0.624 (1.058) Data 0.000 (0.432) Loss 1.3255 (1.3260) Prec@1 59.766 (63.151) Prec@5 87.109 (87.519)
[2021-04-26 19:06:51 train_lshot.py:257] INFO Epoch: [18][30/150] Time 0.620 (0.918) Data 0.001 (0.293) Loss 1.1793 (1.3218) Prec@1 62.891 (63.483) Prec@5 89.453 (87.500)
[2021-04-26 19:06:57 train_lshot.py:257] INFO Epoch: [18][40/150] Time 0.624 (0.846) Data 0.001 (0.222) Loss 1.5055 (1.3218) Prec@1 60.547 (63.491) Prec@5 84.766 (87.386)
[2021-04-26 19:07:03 train_lshot.py:257] INFO Epoch: [18][50/150] Time 0.623 (0.803) Data 0.000 (0.179) Loss 1.6072 (1.3284) Prec@1 57.812 (63.404) Prec@5 81.641 (87.255)
[2021-04-26 19:07:10 train_lshot.py:257] INFO Epoch: [18][60/150] Time 0.630 (0.774) Data 0.001 (0.149) Loss 1.4305 (1.3406) Prec@1 59.766 (63.108) Prec@5 85.938 (87.225)
[2021-04-26 19:07:16 train_lshot.py:257] INFO Epoch: [18][70/150] Time 0.625 (0.753) Data 0.001 (0.128) Loss 1.3957 (1.3527) Prec@1 62.891 (62.797) Prec@5 85.547 (87.032)
[2021-04-26 19:07:22 train_lshot.py:257] INFO Epoch: [18][80/150] Time 0.623 (0.737) Data 0.000 (0.113) Loss 1.4765 (1.3549) Prec@1 59.766 (62.881) Prec@5 85.156 (86.998)
[2021-04-26 19:07:28 train_lshot.py:257] INFO Epoch: [18][90/150] Time 0.624 (0.724) Data 0.000 (0.100) Loss 1.2531 (1.3607) Prec@1 66.016 (62.805) Prec@5 87.109 (86.921)
[2021-04-26 19:07:35 train_lshot.py:257] INFO Epoch: [18][100/150] Time 0.624 (0.714) Data 0.000 (0.090) Loss 1.1781 (1.3570) Prec@1 64.453 (62.867) Prec@5 90.234 (87.055)
[2021-04-26 19:07:41 train_lshot.py:257] INFO Epoch: [18][110/150] Time 0.625 (0.706) Data 0.000 (0.082) Loss 1.3215 (1.3590) Prec@1 65.234 (62.873) Prec@5 88.281 (87.007)
[2021-04-26 19:07:47 train_lshot.py:257] INFO Epoch: [18][120/150] Time 0.624 (0.699) Data 0.000 (0.075) Loss 1.2054 (1.3552) Prec@1 69.922 (63.023) Prec@5 89.844 (87.067)
[2021-04-26 19:07:53 train_lshot.py:257] INFO Epoch: [18][130/150] Time 0.621 (0.693) Data 0.000 (0.070) Loss 1.4046 (1.3558) Prec@1 62.891 (63.004) Prec@5 87.500 (87.050)
[2021-04-26 19:07:59 train_lshot.py:257] INFO Epoch: [18][140/150] Time 0.621 (0.688) Data 0.000 (0.065) Loss 1.2645 (1.3572) Prec@1 65.234 (62.927) Prec@5 86.719 (86.996)
[2021-04-26 19:08:16 train_lshot.py:257] INFO Epoch: [19][0/150] Time 10.436 (10.436) Data 9.784 (9.784) Loss 1.3093 (1.3093) Prec@1 61.719 (61.719) Prec@5 87.500 (87.500)
[2021-04-26 19:08:22 train_lshot.py:257] INFO Epoch: [19][10/150] Time 0.621 (1.514) Data 0.000 (0.890) Loss 1.3118 (1.2854) Prec@1 63.281 (64.489) Prec@5 86.328 (87.713)
[2021-04-26 19:08:28 train_lshot.py:257] INFO Epoch: [19][20/150] Time 0.625 (1.090) Data 0.001 (0.466) Loss 1.3745 (1.3285) Prec@1 61.719 (63.281) Prec@5 86.719 (87.016)
[2021-04-26 19:08:35 train_lshot.py:257] INFO Epoch: [19][30/150] Time 0.621 (0.939) Data 0.000 (0.316) Loss 1.2785 (1.3084) Prec@1 64.453 (63.911) Prec@5 87.500 (87.450)
[2021-04-26 19:08:41 train_lshot.py:257] INFO Epoch: [19][40/150] Time 0.622 (0.862) Data 0.001 (0.239) Loss 1.3435 (1.3061) Prec@1 65.625 (64.015) Prec@5 86.719 (87.567)
[2021-04-26 19:08:47 train_lshot.py:257] INFO Epoch: [19][50/150] Time 0.620 (0.815) Data 0.000 (0.192) Loss 1.2617 (1.3083) Prec@1 61.719 (63.879) Prec@5 88.672 (87.653)
[2021-04-26 19:08:53 train_lshot.py:257] INFO Epoch: [19][60/150] Time 0.621 (0.784) Data 0.000 (0.161) Loss 1.3891 (1.3207) Prec@1 60.547 (63.633) Prec@5 87.109 (87.558)
[2021-04-26 19:09:00 train_lshot.py:257] INFO Epoch: [19][70/150] Time 0.623 (0.762) Data 0.002 (0.138) Loss 1.1643 (1.3189) Prec@1 67.578 (63.892) Prec@5 89.062 (87.478)
[2021-04-26 19:09:06 train_lshot.py:257] INFO Epoch: [19][80/150] Time 0.622 (0.744) Data 0.000 (0.121) Loss 1.5305 (1.3283) Prec@1 56.641 (63.802) Prec@5 84.766 (87.394)
[2021-04-26 19:09:12 train_lshot.py:257] INFO Epoch: [19][90/150] Time 0.621 (0.731) Data 0.000 (0.108) Loss 1.4657 (1.3269) Prec@1 57.422 (63.663) Prec@5 85.547 (87.444)
[2021-04-26 19:09:18 train_lshot.py:257] INFO Epoch: [19][100/150] Time 0.621 (0.720) Data 0.000 (0.097) Loss 1.2794 (1.3283) Prec@1 65.234 (63.633) Prec@5 90.234 (87.415)
[2021-04-26 19:09:24 train_lshot.py:257] INFO Epoch: [19][110/150] Time 0.625 (0.712) Data 0.000 (0.089) Loss 1.3617 (1.3296) Prec@1 60.156 (63.545) Prec@5 89.062 (87.401)
[2021-04-26 19:09:31 train_lshot.py:257] INFO Epoch: [19][120/150] Time 0.624 (0.704) Data 0.000 (0.081) Loss 1.3083 (1.3311) Prec@1 61.719 (63.462) Prec@5 88.281 (87.426)
[2021-04-26 19:09:37 train_lshot.py:257] INFO Epoch: [19][130/150] Time 0.620 (0.698) Data 0.000 (0.075) Loss 1.1710 (1.3199) Prec@1 66.797 (63.764) Prec@5 89.062 (87.628)
[2021-04-26 19:09:43 train_lshot.py:257] INFO Epoch: [19][140/150] Time 0.619 (0.693) Data 0.000 (0.070) Loss 1.2394 (1.3147) Prec@1 64.453 (63.916) Prec@5 85.547 (87.658)
[2021-04-26 19:10:29 train_lshot.py:119] INFO Meta Val 19: 0.5765333459079266
[2021-04-26 19:10:39 train_lshot.py:257] INFO Epoch: [20][0/150] Time 9.454 (9.454) Data 8.800 (8.800) Loss 1.2022 (1.2022) Prec@1 67.578 (67.578) Prec@5 89.453 (89.453)
[2021-04-26 19:10:46 train_lshot.py:257] INFO Epoch: [20][10/150] Time 0.620 (1.426) Data 0.000 (0.801) Loss 1.2316 (1.2796) Prec@1 66.797 (64.134) Prec@5 87.891 (88.317)
[2021-04-26 19:10:52 train_lshot.py:257] INFO Epoch: [20][20/150] Time 0.622 (1.043) Data 0.000 (0.420) Loss 1.2907 (1.2764) Prec@1 63.672 (64.528) Prec@5 89.844 (88.597)
[2021-04-26 19:10:58 train_lshot.py:257] INFO Epoch: [20][30/150] Time 0.622 (0.909) Data 0.001 (0.285) Loss 1.2329 (1.2736) Prec@1 64.844 (64.705) Prec@5 89.453 (88.256)
[2021-04-26 19:11:04 train_lshot.py:257] INFO Epoch: [20][40/150] Time 0.616 (0.839) Data 0.000 (0.215) Loss 1.2694 (1.2744) Prec@1 64.453 (64.768) Prec@5 88.281 (88.215)
[2021-04-26 19:11:11 train_lshot.py:257] INFO Epoch: [20][50/150] Time 0.629 (0.797) Data 0.001 (0.173) Loss 1.2285 (1.2732) Prec@1 66.797 (64.951) Prec@5 92.578 (88.442)
[2021-04-26 19:11:17 train_lshot.py:257] INFO Epoch: [20][60/150] Time 0.623 (0.769) Data 0.000 (0.145) Loss 1.3338 (1.2712) Prec@1 62.500 (65.113) Prec@5 90.234 (88.493)
[2021-04-26 19:11:23 train_lshot.py:257] INFO Epoch: [20][70/150] Time 0.634 (0.749) Data 0.002 (0.125) Loss 1.1807 (1.2743) Prec@1 63.281 (64.943) Prec@5 91.016 (88.408)
[2021-04-26 19:11:29 train_lshot.py:257] INFO Epoch: [20][80/150] Time 0.620 (0.733) Data 0.000 (0.109) Loss 1.2159 (1.2727) Prec@1 68.750 (65.032) Prec@5 90.234 (88.392)
[2021-04-26 19:11:36 train_lshot.py:257] INFO Epoch: [20][90/150] Time 0.620 (0.721) Data 0.000 (0.097) Loss 1.4643 (1.2751) Prec@1 61.328 (65.015) Prec@5 82.812 (88.333)
[2021-04-26 19:11:42 train_lshot.py:257] INFO Epoch: [20][100/150] Time 0.624 (0.711) Data 0.000 (0.088) Loss 1.4668 (1.2780) Prec@1 60.938 (64.933) Prec@5 82.812 (88.332)
[2021-04-26 19:11:48 train_lshot.py:257] INFO Epoch: [20][110/150] Time 0.626 (0.703) Data 0.000 (0.080) Loss 1.1577 (1.2802) Prec@1 67.578 (64.858) Prec@5 89.844 (88.228)
[2021-04-26 19:11:54 train_lshot.py:257] INFO Epoch: [20][120/150] Time 0.625 (0.696) Data 0.000 (0.073) Loss 1.2560 (1.2793) Prec@1 65.234 (64.889) Prec@5 86.719 (88.201)
[2021-04-26 19:12:00 train_lshot.py:257] INFO Epoch: [20][130/150] Time 0.624 (0.691) Data 0.000 (0.068) Loss 1.2763 (1.2811) Prec@1 64.062 (64.808) Prec@5 90.234 (88.162)
[2021-04-26 19:12:07 train_lshot.py:257] INFO Epoch: [20][140/150] Time 0.622 (0.686) Data 0.000 (0.063) Loss 1.2981 (1.2770) Prec@1 65.234 (64.943) Prec@5 87.500 (88.187)
[2021-04-26 19:12:23 train_lshot.py:257] INFO Epoch: [21][0/150] Time 10.038 (10.038) Data 9.383 (9.383) Loss 1.2690 (1.2690) Prec@1 66.406 (66.406) Prec@5 86.328 (86.328)
[2021-04-26 19:12:29 train_lshot.py:257] INFO Epoch: [21][10/150] Time 0.625 (1.477) Data 0.000 (0.854) Loss 1.1962 (1.1827) Prec@1 67.969 (67.898) Prec@5 88.672 (89.453)
[2021-04-26 19:12:35 train_lshot.py:257] INFO Epoch: [21][20/150] Time 0.628 (1.070) Data 0.000 (0.447) Loss 1.1872 (1.2119) Prec@1 67.969 (66.760) Prec@5 90.625 (88.988)
[2021-04-26 19:12:41 train_lshot.py:257] INFO Epoch: [21][30/150] Time 0.622 (0.925) Data 0.000 (0.303) Loss 1.2694 (1.2111) Prec@1 62.891 (66.784) Prec@5 89.844 (88.962)
[2021-04-26 19:12:48 train_lshot.py:257] INFO Epoch: [21][40/150] Time 0.626 (0.852) Data 0.000 (0.229) Loss 1.1437 (1.2066) Prec@1 69.141 (67.006) Prec@5 88.672 (89.139)
[2021-04-26 19:12:54 train_lshot.py:257] INFO Epoch: [21][50/150] Time 0.631 (0.807) Data 0.000 (0.184) Loss 1.2918 (1.2066) Prec@1 63.281 (66.866) Prec@5 89.453 (89.216)
[2021-04-26 19:13:00 train_lshot.py:257] INFO Epoch: [21][60/150] Time 0.620 (0.777) Data 0.000 (0.154) Loss 1.1060 (1.2143) Prec@1 69.922 (66.489) Prec@5 91.797 (89.171)
[2021-04-26 19:13:06 train_lshot.py:257] INFO Epoch: [21][70/150] Time 0.632 (0.756) Data 0.002 (0.133) Loss 1.2516 (1.2077) Prec@1 68.750 (66.736) Prec@5 88.281 (89.167)
[2021-04-26 19:13:13 train_lshot.py:257] INFO Epoch: [21][80/150] Time 0.618 (0.739) Data 0.001 (0.116) Loss 1.2196 (1.2135) Prec@1 67.578 (66.652) Prec@5 87.500 (89.178)
[2021-04-26 19:13:19 train_lshot.py:257] INFO Epoch: [21][90/150] Time 0.619 (0.726) Data 0.000 (0.104) Loss 1.3410 (1.2191) Prec@1 64.062 (66.445) Prec@5 87.109 (89.037)
[2021-04-26 19:13:25 train_lshot.py:257] INFO Epoch: [21][100/150] Time 0.623 (0.716) Data 0.000 (0.093) Loss 1.1773 (1.2220) Prec@1 68.359 (66.395) Prec@5 90.625 (89.020)
[2021-04-26 19:13:31 train_lshot.py:257] INFO Epoch: [21][110/150] Time 0.624 (0.708) Data 0.000 (0.085) Loss 1.0780 (1.2243) Prec@1 70.703 (66.290) Prec@5 90.234 (88.915)
[2021-04-26 19:13:37 train_lshot.py:257] INFO Epoch: [21][120/150] Time 0.622 (0.700) Data 0.000 (0.078) Loss 1.1061 (1.2280) Prec@1 68.359 (66.206) Prec@5 89.844 (88.807)
[2021-04-26 19:13:44 train_lshot.py:257] INFO Epoch: [21][130/150] Time 0.618 (0.694) Data 0.000 (0.072) Loss 1.2122 (1.2340) Prec@1 65.625 (66.001) Prec@5 87.891 (88.734)
[2021-04-26 19:13:50 train_lshot.py:257] INFO Epoch: [21][140/150] Time 0.621 (0.689) Data 0.000 (0.067) Loss 1.1410 (1.2348) Prec@1 71.875 (66.021) Prec@5 89.062 (88.722)
[2021-04-26 19:14:06 train_lshot.py:257] INFO Epoch: [22][0/150] Time 9.686 (9.686) Data 9.023 (9.023) Loss 1.1704 (1.1704) Prec@1 68.750 (68.750) Prec@5 89.844 (89.844)
[2021-04-26 19:14:12 train_lshot.py:257] INFO Epoch: [22][10/150] Time 0.618 (1.444) Data 0.000 (0.821) Loss 1.2672 (1.1689) Prec@1 64.844 (67.791) Prec@5 89.062 (89.773)
[2021-04-26 19:14:18 train_lshot.py:257] INFO Epoch: [22][20/150] Time 0.623 (1.053) Data 0.000 (0.430) Loss 1.0532 (1.1688) Prec@1 67.969 (67.746) Prec@5 90.234 (89.267)
[2021-04-26 19:14:24 train_lshot.py:257] INFO Epoch: [22][30/150] Time 0.627 (0.915) Data 0.001 (0.292) Loss 1.1672 (1.1744) Prec@1 69.922 (67.906) Prec@5 89.844 (89.239)
[2021-04-26 19:14:31 train_lshot.py:257] INFO Epoch: [22][40/150] Time 0.629 (0.844) Data 0.001 (0.221) Loss 1.3343 (1.1777) Prec@1 61.328 (67.473) Prec@5 88.672 (89.320)
[2021-04-26 19:14:37 train_lshot.py:257] INFO Epoch: [22][50/150] Time 0.623 (0.801) Data 0.001 (0.178) Loss 1.3041 (1.1869) Prec@1 66.016 (67.287) Prec@5 86.719 (89.131)
[2021-04-26 19:14:43 train_lshot.py:257] INFO Epoch: [22][60/150] Time 0.623 (0.772) Data 0.000 (0.149) Loss 1.1742 (1.1871) Prec@1 67.969 (67.309) Prec@5 89.062 (89.127)
[2021-04-26 19:14:49 train_lshot.py:257] INFO Epoch: [22][70/150] Time 0.622 (0.751) Data 0.001 (0.128) Loss 1.3357 (1.1920) Prec@1 65.234 (67.270) Prec@5 85.547 (89.079)
[2021-04-26 19:14:55 train_lshot.py:257] INFO Epoch: [22][80/150] Time 0.620 (0.735) Data 0.000 (0.112) Loss 1.2509 (1.1952) Prec@1 60.547 (67.101) Prec@5 90.625 (89.106)
[2021-04-26 19:15:02 train_lshot.py:257] INFO Epoch: [22][90/150] Time 0.621 (0.723) Data 0.000 (0.100) Loss 1.1937 (1.1899) Prec@1 66.797 (67.269) Prec@5 89.062 (89.178)
[2021-04-26 19:15:08 train_lshot.py:257] INFO Epoch: [22][100/150] Time 0.621 (0.713) Data 0.000 (0.090) Loss 1.1497 (1.1893) Prec@1 69.141 (67.342) Prec@5 88.672 (89.124)
[2021-04-26 19:15:14 train_lshot.py:257] INFO Epoch: [22][110/150] Time 0.624 (0.705) Data 0.000 (0.082) Loss 1.1678 (1.1859) Prec@1 66.016 (67.363) Prec@5 87.500 (89.122)
[2021-04-26 19:15:20 train_lshot.py:257] INFO Epoch: [22][120/150] Time 0.621 (0.698) Data 0.000 (0.075) Loss 1.3519 (1.1946) Prec@1 62.500 (67.149) Prec@5 87.109 (89.053)
[2021-04-26 19:15:27 train_lshot.py:257] INFO Epoch: [22][130/150] Time 0.623 (0.692) Data 0.000 (0.069) Loss 1.1660 (1.1966) Prec@1 67.578 (67.119) Prec@5 90.625 (89.065)
[2021-04-26 19:15:33 train_lshot.py:257] INFO Epoch: [22][140/150] Time 0.618 (0.687) Data 0.000 (0.064) Loss 1.2415 (1.1988) Prec@1 62.891 (67.002) Prec@5 88.281 (89.026)
[2021-04-26 19:15:49 train_lshot.py:257] INFO Epoch: [23][0/150] Time 9.852 (9.852) Data 9.193 (9.193) Loss 1.0708 (1.0708) Prec@1 67.578 (67.578) Prec@5 91.797 (91.797)
[2021-04-26 19:15:55 train_lshot.py:257] INFO Epoch: [23][10/150] Time 0.623 (1.459) Data 0.000 (0.836) Loss 1.0743 (1.1281) Prec@1 67.969 (68.821) Prec@5 90.625 (90.661)
[2021-04-26 19:16:01 train_lshot.py:257] INFO Epoch: [23][20/150] Time 0.621 (1.061) Data 0.000 (0.438) Loss 1.1843 (1.1379) Prec@1 70.312 (68.973) Prec@5 90.234 (90.141)
[2021-04-26 19:16:07 train_lshot.py:257] INFO Epoch: [23][30/150] Time 0.622 (0.921) Data 0.000 (0.297) Loss 1.1118 (1.1358) Prec@1 69.531 (68.826) Prec@5 92.188 (90.209)
[2021-04-26 19:16:14 train_lshot.py:257] INFO Epoch: [23][40/150] Time 0.623 (0.848) Data 0.001 (0.225) Loss 1.1637 (1.1288) Prec@1 67.188 (68.855) Prec@5 90.625 (90.187)
[2021-04-26 19:16:20 train_lshot.py:257] INFO Epoch: [23][50/150] Time 0.620 (0.804) Data 0.000 (0.181) Loss 1.0127 (1.1310) Prec@1 71.094 (68.788) Prec@5 92.969 (90.165)
[2021-04-26 19:16:26 train_lshot.py:257] INFO Epoch: [23][60/150] Time 0.622 (0.774) Data 0.000 (0.151) Loss 1.0597 (1.1302) Prec@1 69.531 (68.776) Prec@5 89.844 (90.138)
[2021-04-26 19:16:32 train_lshot.py:257] INFO Epoch: [23][70/150] Time 0.623 (0.753) Data 0.001 (0.130) Loss 1.0869 (1.1361) Prec@1 69.141 (68.436) Prec@5 89.844 (90.009)
[2021-04-26 19:16:38 train_lshot.py:257] INFO Epoch: [23][80/150] Time 0.623 (0.737) Data 0.000 (0.114) Loss 1.0399 (1.1359) Prec@1 70.312 (68.509) Prec@5 89.453 (90.008)
[2021-04-26 19:16:45 train_lshot.py:257] INFO Epoch: [23][90/150] Time 0.621 (0.724) Data 0.000 (0.102) Loss 1.0343 (1.1382) Prec@1 72.656 (68.462) Prec@5 91.406 (89.994)
[2021-04-26 19:16:51 train_lshot.py:257] INFO Epoch: [23][100/150] Time 0.620 (0.714) Data 0.000 (0.091) Loss 1.1295 (1.1433) Prec@1 68.750 (68.371) Prec@5 90.625 (89.944)
[2021-04-26 19:16:57 train_lshot.py:257] INFO Epoch: [23][110/150] Time 0.628 (0.706) Data 0.000 (0.083) Loss 1.2263 (1.1483) Prec@1 66.797 (68.275) Prec@5 89.453 (89.893)
[2021-04-26 19:17:03 train_lshot.py:257] INFO Epoch: [23][120/150] Time 0.621 (0.699) Data 0.000 (0.076) Loss 1.1167 (1.1492) Prec@1 71.875 (68.275) Prec@5 88.281 (89.879)
[2021-04-26 19:17:10 train_lshot.py:257] INFO Epoch: [23][130/150] Time 0.623 (0.693) Data 0.000 (0.071) Loss 1.1742 (1.1532) Prec@1 66.406 (68.154) Prec@5 89.453 (89.781)
[2021-04-26 19:17:16 train_lshot.py:257] INFO Epoch: [23][140/150] Time 0.620 (0.688) Data 0.000 (0.066) Loss 1.3231 (1.1581) Prec@1 61.719 (67.991) Prec@5 88.281 (89.738)
[2021-04-26 19:18:02 train_lshot.py:119] INFO Meta Val 23: 0.5730400134921074
[2021-04-26 19:18:12 train_lshot.py:257] INFO Epoch: [24][0/150] Time 9.912 (9.912) Data 9.243 (9.243) Loss 1.0936 (1.0936) Prec@1 67.578 (67.578) Prec@5 93.359 (93.359)
[2021-04-26 19:18:18 train_lshot.py:257] INFO Epoch: [24][10/150] Time 0.622 (1.463) Data 0.000 (0.841) Loss 1.2594 (1.0805) Prec@1 65.625 (68.857) Prec@5 88.672 (91.371)
[2021-04-26 19:18:24 train_lshot.py:257] INFO Epoch: [24][20/150] Time 0.621 (1.063) Data 0.000 (0.441) Loss 1.1750 (1.0757) Prec@1 67.578 (69.568) Prec@5 89.062 (91.090)
[2021-04-26 19:18:31 train_lshot.py:257] INFO Epoch: [24][30/150] Time 0.624 (0.921) Data 0.001 (0.299) Loss 1.1759 (1.1037) Prec@1 66.797 (68.826) Prec@5 89.062 (90.537)
[2021-04-26 19:18:37 train_lshot.py:257] INFO Epoch: [24][40/150] Time 0.621 (0.848) Data 0.001 (0.226) Loss 1.1975 (1.1105) Prec@1 67.578 (68.607) Prec@5 88.672 (90.549)
[2021-04-26 19:18:43 train_lshot.py:257] INFO Epoch: [24][50/150] Time 0.624 (0.804) Data 0.001 (0.182) Loss 1.1423 (1.1185) Prec@1 67.578 (68.451) Prec@5 90.234 (90.441)
[2021-04-26 19:18:49 train_lshot.py:257] INFO Epoch: [24][60/150] Time 0.622 (0.774) Data 0.000 (0.152) Loss 1.1507 (1.1297) Prec@1 70.703 (68.283) Prec@5 87.109 (90.273)
[2021-04-26 19:18:56 train_lshot.py:257] INFO Epoch: [24][70/150] Time 0.623 (0.753) Data 0.001 (0.131) Loss 0.9694 (1.1401) Prec@1 73.438 (68.040) Prec@5 91.406 (90.036)
[2021-04-26 19:19:02 train_lshot.py:257] INFO Epoch: [24][80/150] Time 0.618 (0.737) Data 0.000 (0.115) Loss 0.9960 (1.1326) Prec@1 72.266 (68.311) Prec@5 91.406 (90.109)
[2021-04-26 19:19:08 train_lshot.py:257] INFO Epoch: [24][90/150] Time 0.620 (0.724) Data 0.000 (0.102) Loss 1.1123 (1.1345) Prec@1 68.359 (68.286) Prec@5 91.797 (89.985)
[2021-04-26 19:19:14 train_lshot.py:257] INFO Epoch: [24][100/150] Time 0.620 (0.714) Data 0.000 (0.092) Loss 1.3127 (1.1352) Prec@1 65.234 (68.325) Prec@5 86.328 (89.956)
[2021-04-26 19:19:20 train_lshot.py:257] INFO Epoch: [24][110/150] Time 0.618 (0.705) Data 0.000 (0.084) Loss 1.3863 (1.1388) Prec@1 60.938 (68.254) Prec@5 86.328 (89.928)
[2021-04-26 19:19:27 train_lshot.py:257] INFO Epoch: [24][120/150] Time 0.623 (0.698) Data 0.000 (0.077) Loss 1.1684 (1.1425) Prec@1 68.750 (68.140) Prec@5 88.281 (89.918)
[2021-04-26 19:19:33 train_lshot.py:257] INFO Epoch: [24][130/150] Time 0.619 (0.693) Data 0.000 (0.071) Loss 1.3153 (1.1389) Prec@1 66.797 (68.282) Prec@5 87.109 (89.957)
[2021-04-26 19:19:39 train_lshot.py:257] INFO Epoch: [24][140/150] Time 0.620 (0.687) Data 0.000 (0.066) Loss 1.1830 (1.1397) Prec@1 68.359 (68.307) Prec@5 88.281 (89.960)
[2021-04-26 19:19:55 train_lshot.py:257] INFO Epoch: [25][0/150] Time 9.596 (9.596) Data 8.932 (8.932) Loss 0.8965 (0.8965) Prec@1 74.219 (74.219) Prec@5 94.922 (94.922)
[2021-04-26 19:20:01 train_lshot.py:257] INFO Epoch: [25][10/150] Time 0.617 (1.435) Data 0.000 (0.813) Loss 0.8957 (1.0672) Prec@1 73.438 (70.703) Prec@5 92.969 (90.732)
[2021-04-26 19:20:07 train_lshot.py:257] INFO Epoch: [25][20/150] Time 0.623 (1.050) Data 0.001 (0.426) Loss 1.1097 (1.0751) Prec@1 67.578 (70.573) Prec@5 91.797 (90.662)
[2021-04-26 19:20:13 train_lshot.py:257] INFO Epoch: [25][30/150] Time 0.625 (0.913) Data 0.000 (0.289) Loss 1.1395 (1.0726) Prec@1 67.969 (70.439) Prec@5 89.844 (90.877)
[2021-04-26 19:20:20 train_lshot.py:257] INFO Epoch: [25][40/150] Time 0.622 (0.842) Data 0.001 (0.219) Loss 1.2346 (1.0884) Prec@1 62.891 (69.970) Prec@5 89.062 (90.463)
[2021-04-26 19:20:26 train_lshot.py:257] INFO Epoch: [25][50/150] Time 0.620 (0.799) Data 0.000 (0.176) Loss 0.9759 (1.0842) Prec@1 73.828 (70.121) Prec@5 91.406 (90.564)
[2021-04-26 19:20:32 train_lshot.py:257] INFO Epoch: [25][60/150] Time 0.621 (0.770) Data 0.000 (0.147) Loss 1.0296 (1.0835) Prec@1 70.312 (69.941) Prec@5 89.844 (90.574)
[2021-04-26 19:20:38 train_lshot.py:257] INFO Epoch: [25][70/150] Time 0.635 (0.750) Data 0.003 (0.126) Loss 1.0824 (1.0840) Prec@1 70.312 (69.883) Prec@5 90.234 (90.586)
[2021-04-26 19:20:45 train_lshot.py:257] INFO Epoch: [25][80/150] Time 0.621 (0.734) Data 0.000 (0.111) Loss 1.0829 (1.0872) Prec@1 71.094 (69.729) Prec@5 92.578 (90.572)
[2021-04-26 19:20:51 train_lshot.py:257] INFO Epoch: [25][90/150] Time 0.621 (0.722) Data 0.000 (0.099) Loss 1.3240 (1.0876) Prec@1 62.891 (69.570) Prec@5 91.406 (90.616)
[2021-04-26 19:20:57 train_lshot.py:257] INFO Epoch: [25][100/150] Time 0.619 (0.712) Data 0.000 (0.089) Loss 1.1702 (1.0917) Prec@1 67.969 (69.465) Prec@5 91.016 (90.575)
[2021-04-26 19:21:03 train_lshot.py:257] INFO Epoch: [25][110/150] Time 0.617 (0.704) Data 0.000 (0.081) Loss 0.9962 (1.0890) Prec@1 72.656 (69.602) Prec@5 91.406 (90.558)
[2021-04-26 19:21:10 train_lshot.py:257] INFO Epoch: [25][120/150] Time 0.620 (0.697) Data 0.000 (0.074) Loss 1.1433 (1.0910) Prec@1 70.703 (69.576) Prec@5 87.500 (90.554)
[2021-04-26 19:21:16 train_lshot.py:257] INFO Epoch: [25][130/150] Time 0.619 (0.691) Data 0.000 (0.069) Loss 1.2047 (1.0924) Prec@1 67.969 (69.594) Prec@5 88.281 (90.544)
[2021-04-26 19:21:22 train_lshot.py:257] INFO Epoch: [25][140/150] Time 0.619 (0.686) Data 0.000 (0.064) Loss 1.1593 (1.0914) Prec@1 66.406 (69.614) Prec@5 87.891 (90.553)
[2021-04-26 19:21:37 train_lshot.py:257] INFO Epoch: [26][0/150] Time 9.163 (9.163) Data 8.498 (8.498) Loss 1.0812 (1.0812) Prec@1 68.750 (68.750) Prec@5 90.625 (90.625)
[2021-04-26 19:21:43 train_lshot.py:257] INFO Epoch: [26][10/150] Time 0.620 (1.397) Data 0.000 (0.773) Loss 1.1042 (1.0600) Prec@1 69.922 (70.810) Prec@5 91.016 (91.335)
[2021-04-26 19:21:49 train_lshot.py:257] INFO Epoch: [26][20/150] Time 0.621 (1.028) Data 0.000 (0.405) Loss 1.1190 (1.0394) Prec@1 68.359 (71.094) Prec@5 91.406 (91.760)
[2021-04-26 19:21:56 train_lshot.py:257] INFO Epoch: [26][30/150] Time 0.620 (0.898) Data 0.000 (0.275) Loss 0.9245 (1.0471) Prec@1 69.141 (70.716) Prec@5 94.922 (91.356)
[2021-04-26 19:22:02 train_lshot.py:257] INFO Epoch: [26][40/150] Time 0.628 (0.831) Data 0.001 (0.208) Loss 1.0657 (1.0581) Prec@1 73.438 (70.617) Prec@5 91.406 (91.254)
[2021-04-26 19:22:08 train_lshot.py:257] INFO Epoch: [26][50/150] Time 0.622 (0.790) Data 0.000 (0.167) Loss 1.1494 (1.0650) Prec@1 66.797 (70.450) Prec@5 89.062 (91.054)
[2021-04-26 19:22:14 train_lshot.py:257] INFO Epoch: [26][60/150] Time 0.622 (0.763) Data 0.001 (0.140) Loss 1.1238 (1.0669) Prec@1 64.844 (70.293) Prec@5 89.844 (91.048)
[2021-04-26 19:22:21 train_lshot.py:257] INFO Epoch: [26][70/150] Time 0.631 (0.743) Data 0.002 (0.120) Loss 1.0253 (1.0724) Prec@1 73.828 (70.219) Prec@5 90.625 (90.944)
[2021-04-26 19:22:27 train_lshot.py:257] INFO Epoch: [26][80/150] Time 0.627 (0.728) Data 0.001 (0.106) Loss 0.9771 (1.0774) Prec@1 69.922 (70.134) Prec@5 92.578 (90.832)
[2021-04-26 19:22:33 train_lshot.py:257] INFO Epoch: [26][90/150] Time 0.620 (0.717) Data 0.000 (0.094) Loss 1.0939 (1.0830) Prec@1 69.141 (69.995) Prec@5 90.625 (90.719)
[2021-04-26 19:22:39 train_lshot.py:257] INFO Epoch: [26][100/150] Time 0.623 (0.707) Data 0.000 (0.085) Loss 0.8965 (1.0808) Prec@1 71.484 (70.050) Prec@5 94.141 (90.691)
[2021-04-26 19:22:46 train_lshot.py:257] INFO Epoch: [26][110/150] Time 0.625 (0.700) Data 0.000 (0.077) Loss 1.2420 (1.0847) Prec@1 65.234 (69.932) Prec@5 88.281 (90.695)
[2021-04-26 19:22:52 train_lshot.py:257] INFO Epoch: [26][120/150] Time 0.624 (0.693) Data 0.000 (0.071) Loss 1.0828 (1.0849) Prec@1 68.359 (69.873) Prec@5 92.969 (90.680)
[2021-04-26 19:22:58 train_lshot.py:257] INFO Epoch: [26][130/150] Time 0.624 (0.688) Data 0.000 (0.065) Loss 1.1385 (1.0852) Prec@1 69.531 (69.871) Prec@5 87.109 (90.649)
[2021-04-26 19:23:04 train_lshot.py:257] INFO Epoch: [26][140/150] Time 0.623 (0.683) Data 0.000 (0.061) Loss 1.1278 (1.0879) Prec@1 69.141 (69.850) Prec@5 88.672 (90.611)
[2021-04-26 19:23:20 train_lshot.py:257] INFO Epoch: [27][0/150] Time 10.226 (10.226) Data 9.579 (9.579) Loss 0.9996 (0.9996) Prec@1 71.484 (71.484) Prec@5 90.625 (90.625)
[2021-04-26 19:23:27 train_lshot.py:257] INFO Epoch: [27][10/150] Time 0.623 (1.492) Data 0.000 (0.871) Loss 1.0467 (1.0456) Prec@1 71.875 (70.916) Prec@5 90.234 (91.335)
[2021-04-26 19:23:33 train_lshot.py:257] INFO Epoch: [27][20/150] Time 0.625 (1.079) Data 0.001 (0.457) Loss 1.1186 (1.0635) Prec@1 69.922 (70.666) Prec@5 88.672 (90.867)
[2021-04-26 19:23:39 train_lshot.py:257] INFO Epoch: [27][30/150] Time 0.621 (0.932) Data 0.001 (0.310) Loss 0.9738 (1.0502) Prec@1 71.094 (71.069) Prec@5 93.750 (90.965)
[2021-04-26 19:23:45 train_lshot.py:257] INFO Epoch: [27][40/150] Time 0.625 (0.857) Data 0.001 (0.234) Loss 0.9787 (1.0536) Prec@1 71.875 (70.751) Prec@5 89.844 (90.806)
[2021-04-26 19:23:52 train_lshot.py:257] INFO Epoch: [27][50/150] Time 0.637 (0.811) Data 0.001 (0.188) Loss 1.1000 (1.0477) Prec@1 69.922 (70.841) Prec@5 89.844 (91.000)
[2021-04-26 19:23:58 train_lshot.py:257] INFO Epoch: [27][60/150] Time 0.632 (0.781) Data 0.002 (0.158) Loss 1.1261 (1.0487) Prec@1 66.797 (70.882) Prec@5 91.016 (90.939)
[2021-04-26 19:24:04 train_lshot.py:257] INFO Epoch: [27][70/150] Time 0.620 (0.759) Data 0.002 (0.136) Loss 1.0910 (1.0489) Prec@1 71.094 (70.863) Prec@5 90.234 (91.065)
[2021-04-26 19:24:10 train_lshot.py:257] INFO Epoch: [27][80/150] Time 0.620 (0.742) Data 0.000 (0.119) Loss 1.0670 (1.0472) Prec@1 71.094 (70.886) Prec@5 91.016 (91.218)
[2021-04-26 19:24:17 train_lshot.py:257] INFO Epoch: [27][90/150] Time 0.623 (0.729) Data 0.000 (0.106) Loss 1.1279 (1.0522) Prec@1 69.922 (70.768) Prec@5 90.625 (91.213)
[2021-04-26 19:24:23 train_lshot.py:257] INFO Epoch: [27][100/150] Time 0.621 (0.718) Data 0.000 (0.095) Loss 0.9699 (1.0534) Prec@1 73.438 (70.750) Prec@5 93.359 (91.155)
[2021-04-26 19:24:29 train_lshot.py:257] INFO Epoch: [27][110/150] Time 0.618 (0.709) Data 0.000 (0.087) Loss 1.1295 (1.0535) Prec@1 67.578 (70.738) Prec@5 89.453 (91.146)
[2021-04-26 19:24:35 train_lshot.py:257] INFO Epoch: [27][120/150] Time 0.622 (0.702) Data 0.000 (0.080) Loss 0.9846 (1.0540) Prec@1 74.219 (70.726) Prec@5 91.406 (91.080)
[2021-04-26 19:24:41 train_lshot.py:257] INFO Epoch: [27][130/150] Time 0.619 (0.696) Data 0.000 (0.074) Loss 1.0959 (1.0563) Prec@1 68.750 (70.670) Prec@5 91.016 (91.042)
[2021-04-26 19:24:48 train_lshot.py:257] INFO Epoch: [27][140/150] Time 0.619 (0.691) Data 0.000 (0.068) Loss 1.0436 (1.0614) Prec@1 70.703 (70.529) Prec@5 92.578 (90.991)
[2021-04-26 19:25:32 train_lshot.py:119] INFO Meta Val 27: 0.5778666793107986
[2021-04-26 19:25:43 train_lshot.py:257] INFO Epoch: [28][0/150] Time 10.201 (10.201) Data 9.578 (9.578) Loss 0.9098 (0.9098) Prec@1 75.000 (75.000) Prec@5 94.922 (94.922)
[2021-04-26 19:25:49 train_lshot.py:257] INFO Epoch: [28][10/150] Time 0.620 (1.489) Data 0.000 (0.871) Loss 0.9894 (1.0062) Prec@1 72.266 (71.946) Prec@5 92.188 (91.513)
[2021-04-26 19:25:55 train_lshot.py:257] INFO Epoch: [28][20/150] Time 0.628 (1.077) Data 0.002 (0.457) Loss 0.9823 (1.0013) Prec@1 73.047 (71.949) Prec@5 91.016 (91.369)
[2021-04-26 19:26:01 train_lshot.py:257] INFO Epoch: [28][30/150] Time 0.627 (0.931) Data 0.000 (0.309) Loss 1.1064 (1.0227) Prec@1 69.922 (71.333) Prec@5 89.062 (91.242)
[2021-04-26 19:26:08 train_lshot.py:257] INFO Epoch: [28][40/150] Time 0.622 (0.856) Data 0.001 (0.234) Loss 1.0676 (1.0273) Prec@1 69.922 (71.275) Prec@5 92.578 (91.225)
[2021-04-26 19:26:14 train_lshot.py:257] INFO Epoch: [28][50/150] Time 0.620 (0.811) Data 0.000 (0.188) Loss 1.0344 (1.0214) Prec@1 71.484 (71.523) Prec@5 91.016 (91.330)
[2021-04-26 19:26:20 train_lshot.py:257] INFO Epoch: [28][60/150] Time 0.619 (0.780) Data 0.000 (0.158) Loss 0.9481 (1.0140) Prec@1 74.609 (71.657) Prec@5 93.359 (91.470)
[2021-04-26 19:26:26 train_lshot.py:257] INFO Epoch: [28][70/150] Time 0.626 (0.758) Data 0.001 (0.135) Loss 1.2029 (1.0096) Prec@1 67.969 (71.759) Prec@5 85.547 (91.450)
[2021-04-26 19:26:33 train_lshot.py:257] INFO Epoch: [28][80/150] Time 0.625 (0.741) Data 0.000 (0.119) Loss 1.0699 (1.0120) Prec@1 69.922 (71.668) Prec@5 91.797 (91.387)
[2021-04-26 19:26:39 train_lshot.py:257] INFO Epoch: [28][90/150] Time 0.624 (0.728) Data 0.000 (0.106) Loss 0.9454 (1.0164) Prec@1 73.828 (71.600) Prec@5 94.141 (91.389)
[2021-04-26 19:26:45 train_lshot.py:257] INFO Epoch: [28][100/150] Time 0.621 (0.717) Data 0.000 (0.095) Loss 1.1494 (1.0217) Prec@1 68.359 (71.461) Prec@5 89.844 (91.286)
[2021-04-26 19:26:51 train_lshot.py:257] INFO Epoch: [28][110/150] Time 0.622 (0.709) Data 0.000 (0.087) Loss 1.1545 (1.0276) Prec@1 71.484 (71.344) Prec@5 88.281 (91.167)
[2021-04-26 19:26:58 train_lshot.py:257] INFO Epoch: [28][120/150] Time 0.625 (0.702) Data 0.000 (0.080) Loss 0.9458 (1.0273) Prec@1 73.828 (71.404) Prec@5 92.578 (91.196)
[2021-04-26 19:27:04 train_lshot.py:257] INFO Epoch: [28][130/150] Time 0.625 (0.696) Data 0.000 (0.074) Loss 1.0283 (1.0300) Prec@1 71.484 (71.288) Prec@5 92.188 (91.189)
[2021-04-26 19:27:10 train_lshot.py:257] INFO Epoch: [28][140/150] Time 0.620 (0.690) Data 0.000 (0.068) Loss 0.9410 (1.0299) Prec@1 73.828 (71.302) Prec@5 94.141 (91.210)
[2021-04-26 19:27:26 train_lshot.py:257] INFO Epoch: [29][0/150] Time 9.715 (9.715) Data 9.067 (9.067) Loss 0.9497 (0.9497) Prec@1 70.703 (70.703) Prec@5 95.312 (95.312)
[2021-04-26 19:27:32 train_lshot.py:257] INFO Epoch: [29][10/150] Time 0.620 (1.446) Data 0.000 (0.825) Loss 0.9056 (0.9731) Prec@1 74.219 (73.082) Prec@5 94.531 (92.614)
[2021-04-26 19:27:38 train_lshot.py:257] INFO Epoch: [29][20/150] Time 0.631 (1.054) Data 0.001 (0.433) Loss 1.0203 (0.9612) Prec@1 75.391 (73.065) Prec@5 92.188 (92.374)
[2021-04-26 19:27:44 train_lshot.py:257] INFO Epoch: [29][30/150] Time 0.622 (0.915) Data 0.001 (0.293) Loss 1.0037 (0.9853) Prec@1 71.875 (72.555) Prec@5 92.188 (91.759)
[2021-04-26 19:27:51 train_lshot.py:257] INFO Epoch: [29][40/150] Time 0.619 (0.844) Data 0.001 (0.222) Loss 1.0697 (0.9869) Prec@1 68.750 (72.523) Prec@5 89.844 (91.797)
[2021-04-26 19:27:57 train_lshot.py:257] INFO Epoch: [29][50/150] Time 0.620 (0.801) Data 0.000 (0.178) Loss 1.0908 (0.9913) Prec@1 64.844 (72.227) Prec@5 92.969 (91.850)
[2021-04-26 19:28:03 train_lshot.py:257] INFO Epoch: [29][60/150] Time 0.625 (0.772) Data 0.001 (0.149) Loss 0.9298 (0.9909) Prec@1 74.609 (72.355) Prec@5 94.531 (91.829)
[2021-04-26 19:28:09 train_lshot.py:257] INFO Epoch: [29][70/150] Time 0.625 (0.752) Data 0.001 (0.128) Loss 0.8605 (0.9945) Prec@1 75.781 (72.304) Prec@5 92.969 (91.742)
[2021-04-26 19:28:16 train_lshot.py:257] INFO Epoch: [29][80/150] Time 0.623 (0.736) Data 0.000 (0.113) Loss 0.9668 (0.9957) Prec@1 73.047 (72.251) Prec@5 91.797 (91.734)
[2021-04-26 19:28:22 train_lshot.py:257] INFO Epoch: [29][90/150] Time 0.620 (0.723) Data 0.000 (0.100) Loss 0.9428 (0.9983) Prec@1 75.391 (72.240) Prec@5 91.406 (91.655)
[2021-04-26 19:28:28 train_lshot.py:257] INFO Epoch: [29][100/150] Time 0.625 (0.713) Data 0.000 (0.090) Loss 1.1012 (0.9981) Prec@1 70.312 (72.250) Prec@5 89.844 (91.642)
[2021-04-26 19:28:34 train_lshot.py:257] INFO Epoch: [29][110/150] Time 0.623 (0.705) Data 0.000 (0.082) Loss 0.9265 (0.9989) Prec@1 74.219 (72.245) Prec@5 92.969 (91.610)
[2021-04-26 19:28:40 train_lshot.py:257] INFO Epoch: [29][120/150] Time 0.618 (0.698) Data 0.000 (0.075) Loss 0.8699 (0.9998) Prec@1 76.953 (72.246) Prec@5 92.188 (91.613)
[2021-04-26 19:28:47 train_lshot.py:257] INFO Epoch: [29][130/150] Time 0.620 (0.692) Data 0.000 (0.070) Loss 0.9993 (0.9981) Prec@1 73.438 (72.337) Prec@5 91.406 (91.657)
[2021-04-26 19:28:53 train_lshot.py:257] INFO Epoch: [29][140/150] Time 0.622 (0.687) Data 0.000 (0.065) Loss 1.0973 (0.9989) Prec@1 73.438 (72.354) Prec@5 89.844 (91.631)
[2021-04-26 19:29:09 train_lshot.py:257] INFO Epoch: [30][0/150] Time 10.195 (10.195) Data 9.537 (9.537) Loss 0.9678 (0.9678) Prec@1 72.266 (72.266) Prec@5 94.531 (94.531)
[2021-04-26 19:29:15 train_lshot.py:257] INFO Epoch: [30][10/150] Time 0.617 (1.490) Data 0.000 (0.867) Loss 0.9314 (0.9294) Prec@1 73.828 (74.112) Prec@5 92.188 (92.436)
[2021-04-26 19:29:21 train_lshot.py:257] INFO Epoch: [30][20/150] Time 0.621 (1.077) Data 0.000 (0.455) Loss 1.0752 (0.9507) Prec@1 70.703 (73.698) Prec@5 90.625 (91.983)
[2021-04-26 19:29:28 train_lshot.py:257] INFO Epoch: [30][30/150] Time 0.621 (0.931) Data 0.000 (0.308) Loss 0.7924 (0.9494) Prec@1 77.734 (73.816) Prec@5 93.359 (92.112)
[2021-04-26 19:29:34 train_lshot.py:257] INFO Epoch: [30][40/150] Time 0.628 (0.856) Data 0.001 (0.233) Loss 1.0772 (0.9687) Prec@1 68.359 (73.075) Prec@5 90.234 (91.864)
[2021-04-26 19:29:40 train_lshot.py:257] INFO Epoch: [30][50/150] Time 0.615 (0.810) Data 0.001 (0.188) Loss 0.9096 (0.9602) Prec@1 74.609 (73.292) Prec@5 92.578 (91.965)
[2021-04-26 19:29:46 train_lshot.py:257] INFO Epoch: [30][60/150] Time 0.620 (0.780) Data 0.000 (0.157) Loss 0.9733 (0.9673) Prec@1 73.047 (73.066) Prec@5 89.062 (91.938)
[2021-04-26 19:29:53 train_lshot.py:257] INFO Epoch: [30][70/150] Time 0.629 (0.758) Data 0.003 (0.135) Loss 0.9441 (0.9678) Prec@1 74.219 (72.975) Prec@5 92.188 (91.995)
[2021-04-26 19:29:59 train_lshot.py:257] INFO Epoch: [30][80/150] Time 0.620 (0.741) Data 0.001 (0.118) Loss 1.0174 (0.9675) Prec@1 71.484 (73.003) Prec@5 89.062 (91.942)
[2021-04-26 19:30:05 train_lshot.py:257] INFO Epoch: [30][90/150] Time 0.627 (0.728) Data 0.001 (0.105) Loss 1.0307 (0.9716) Prec@1 72.656 (72.910) Prec@5 92.578 (91.908)
[2021-04-26 19:30:11 train_lshot.py:257] INFO Epoch: [30][100/150] Time 0.626 (0.717) Data 0.000 (0.095) Loss 1.1371 (0.9674) Prec@1 69.531 (73.016) Prec@5 90.625 (92.002)
[2021-04-26 19:30:18 train_lshot.py:257] INFO Epoch: [30][110/150] Time 0.626 (0.709) Data 0.000 (0.086) Loss 0.9324 (0.9729) Prec@1 71.094 (72.917) Prec@5 91.406 (91.864)
[2021-04-26 19:30:24 train_lshot.py:257] INFO Epoch: [30][120/150] Time 0.620 (0.701) Data 0.000 (0.079) Loss 1.0576 (0.9783) Prec@1 68.750 (72.718) Prec@5 92.188 (91.849)
[2021-04-26 19:30:30 train_lshot.py:257] INFO Epoch: [30][130/150] Time 0.620 (0.695) Data 0.000 (0.073) Loss 1.0618 (0.9823) Prec@1 67.969 (72.591) Prec@5 92.969 (91.767)
[2021-04-26 19:30:36 train_lshot.py:257] INFO Epoch: [30][140/150] Time 0.620 (0.690) Data 0.000 (0.068) Loss 1.0730 (0.9842) Prec@1 69.141 (72.529) Prec@5 91.406 (91.744)
[2021-04-26 19:30:52 train_lshot.py:257] INFO Epoch: [31][0/150] Time 10.090 (10.090) Data 9.442 (9.442) Loss 0.7970 (0.7970) Prec@1 78.516 (78.516) Prec@5 95.703 (95.703)
[2021-04-26 19:30:58 train_lshot.py:257] INFO Epoch: [31][10/150] Time 0.620 (1.480) Data 0.001 (0.859) Loss 0.8515 (0.9358) Prec@1 78.125 (75.213) Prec@5 93.750 (92.152)
[2021-04-26 19:31:05 train_lshot.py:257] INFO Epoch: [31][20/150] Time 0.621 (1.072) Data 0.000 (0.450) Loss 1.0217 (0.9309) Prec@1 73.438 (75.037) Prec@5 90.234 (92.206)
[2021-04-26 19:31:11 train_lshot.py:257] INFO Epoch: [31][30/150] Time 0.627 (0.928) Data 0.000 (0.305) Loss 0.8878 (0.9297) Prec@1 74.609 (74.345) Prec@5 92.188 (92.402)
[2021-04-26 19:31:17 train_lshot.py:257] INFO Epoch: [31][40/150] Time 0.628 (0.855) Data 0.001 (0.231) Loss 0.8296 (0.9265) Prec@1 76.562 (74.295) Prec@5 96.094 (92.635)
[2021-04-26 19:31:23 train_lshot.py:257] INFO Epoch: [31][50/150] Time 0.622 (0.810) Data 0.000 (0.186) Loss 1.1150 (0.9315) Prec@1 70.312 (74.081) Prec@5 89.453 (92.570)
[2021-04-26 19:31:30 train_lshot.py:257] INFO Epoch: [31][60/150] Time 0.620 (0.779) Data 0.000 (0.155) Loss 1.0966 (0.9341) Prec@1 68.750 (74.014) Prec@5 92.969 (92.578)
[2021-04-26 19:31:36 train_lshot.py:257] INFO Epoch: [31][70/150] Time 0.627 (0.757) Data 0.002 (0.134) Loss 0.9443 (0.9357) Prec@1 75.000 (74.026) Prec@5 91.797 (92.479)
[2021-04-26 19:31:42 train_lshot.py:257] INFO Epoch: [31][80/150] Time 0.620 (0.741) Data 0.001 (0.117) Loss 0.8700 (0.9345) Prec@1 74.609 (74.151) Prec@5 92.969 (92.443)
[2021-04-26 19:31:48 train_lshot.py:257] INFO Epoch: [31][90/150] Time 0.623 (0.728) Data 0.000 (0.104) Loss 0.8462 (0.9357) Prec@1 76.562 (74.077) Prec@5 92.578 (92.402)
[2021-04-26 19:31:55 train_lshot.py:257] INFO Epoch: [31][100/150] Time 0.620 (0.717) Data 0.000 (0.094) Loss 0.9753 (0.9405) Prec@1 72.656 (73.898) Prec@5 90.234 (92.327)
[2021-04-26 19:32:01 train_lshot.py:257] INFO Epoch: [31][110/150] Time 0.620 (0.708) Data 0.000 (0.086) Loss 0.9700 (0.9441) Prec@1 75.391 (73.726) Prec@5 91.016 (92.290)
[2021-04-26 19:32:07 train_lshot.py:257] INFO Epoch: [31][120/150] Time 0.620 (0.701) Data 0.000 (0.079) Loss 0.8723 (0.9445) Prec@1 76.172 (73.702) Prec@5 92.578 (92.297)
[2021-04-26 19:32:13 train_lshot.py:257] INFO Epoch: [31][130/150] Time 0.622 (0.695) Data 0.000 (0.073) Loss 0.9450 (0.9481) Prec@1 74.609 (73.587) Prec@5 92.188 (92.247)
[2021-04-26 19:32:19 train_lshot.py:257] INFO Epoch: [31][140/150] Time 0.621 (0.690) Data 0.000 (0.067) Loss 1.0578 (0.9520) Prec@1 68.750 (73.421) Prec@5 91.406 (92.218)
[2021-04-26 19:33:03 train_lshot.py:119] INFO Meta Val 31: 0.5857866785526276
[2021-04-26 19:33:14 train_lshot.py:257] INFO Epoch: [32][0/150] Time 9.651 (9.651) Data 9.022 (9.022) Loss 0.9879 (0.9879) Prec@1 72.656 (72.656) Prec@5 91.797 (91.797)
[2021-04-26 19:33:20 train_lshot.py:257] INFO Epoch: [32][10/150] Time 0.618 (1.440) Data 0.000 (0.821) Loss 0.8756 (0.9737) Prec@1 75.000 (72.621) Prec@5 93.359 (91.477)
[2021-04-26 19:33:26 train_lshot.py:257] INFO Epoch: [32][20/150] Time 0.623 (1.051) Data 0.001 (0.430) Loss 0.8803 (0.9379) Prec@1 75.000 (73.121) Prec@5 93.359 (92.188)
[2021-04-26 19:33:32 train_lshot.py:257] INFO Epoch: [32][30/150] Time 0.627 (0.913) Data 0.000 (0.292) Loss 0.7588 (0.9419) Prec@1 78.906 (73.009) Prec@5 94.531 (92.150)
[2021-04-26 19:33:38 train_lshot.py:257] INFO Epoch: [32][40/150] Time 0.622 (0.842) Data 0.000 (0.221) Loss 0.7851 (0.9408) Prec@1 78.516 (73.190) Prec@5 92.578 (92.245)
[2021-04-26 19:33:45 train_lshot.py:257] INFO Epoch: [32][50/150] Time 0.630 (0.799) Data 0.001 (0.177) Loss 0.8801 (0.9394) Prec@1 73.438 (73.192) Prec@5 92.578 (92.264)
[2021-04-26 19:33:51 train_lshot.py:257] INFO Epoch: [32][60/150] Time 0.621 (0.770) Data 0.000 (0.148) Loss 0.9701 (0.9432) Prec@1 71.094 (73.418) Prec@5 89.062 (92.213)
[2021-04-26 19:33:57 train_lshot.py:257] INFO Epoch: [32][70/150] Time 0.623 (0.750) Data 0.001 (0.128) Loss 0.9004 (0.9420) Prec@1 74.219 (73.520) Prec@5 92.969 (92.232)
[2021-04-26 19:34:03 train_lshot.py:257] INFO Epoch: [32][80/150] Time 0.620 (0.734) Data 0.000 (0.112) Loss 1.0767 (0.9430) Prec@1 72.656 (73.587) Prec@5 89.453 (92.231)
[2021-04-26 19:34:10 train_lshot.py:257] INFO Epoch: [32][90/150] Time 0.622 (0.721) Data 0.000 (0.100) Loss 1.0766 (0.9422) Prec@1 72.266 (73.622) Prec@5 89.844 (92.235)
[2021-04-26 19:34:16 train_lshot.py:257] INFO Epoch: [32][100/150] Time 0.619 (0.711) Data 0.000 (0.090) Loss 1.0878 (0.9442) Prec@1 66.797 (73.526) Prec@5 92.188 (92.246)
[2021-04-26 19:34:22 train_lshot.py:257] INFO Epoch: [32][110/150] Time 0.621 (0.703) Data 0.000 (0.082) Loss 0.8904 (0.9443) Prec@1 75.391 (73.518) Prec@5 92.188 (92.223)
[2021-04-26 19:34:28 train_lshot.py:257] INFO Epoch: [32][120/150] Time 0.622 (0.697) Data 0.000 (0.075) Loss 0.9337 (0.9427) Prec@1 72.656 (73.538) Prec@5 93.750 (92.213)
[2021-04-26 19:34:34 train_lshot.py:257] INFO Epoch: [32][130/150] Time 0.620 (0.691) Data 0.000 (0.069) Loss 1.0531 (0.9479) Prec@1 72.656 (73.378) Prec@5 89.844 (92.170)
[2021-04-26 19:34:41 train_lshot.py:257] INFO Epoch: [32][140/150] Time 0.622 (0.686) Data 0.000 (0.064) Loss 1.0967 (0.9503) Prec@1 67.578 (73.374) Prec@5 90.234 (92.151)
[2021-04-26 19:34:56 train_lshot.py:257] INFO Epoch: [33][0/150] Time 9.467 (9.467) Data 8.796 (8.796) Loss 0.8921 (0.8921) Prec@1 76.562 (76.562) Prec@5 94.531 (94.531)
[2021-04-26 19:35:02 train_lshot.py:257] INFO Epoch: [33][10/150] Time 0.622 (1.424) Data 0.000 (0.800) Loss 0.9226 (0.9119) Prec@1 71.875 (73.970) Prec@5 92.969 (92.898)
[2021-04-26 19:35:09 train_lshot.py:257] INFO Epoch: [33][20/150] Time 0.622 (1.043) Data 0.001 (0.419) Loss 0.9556 (0.8946) Prec@1 72.656 (74.405) Prec@5 92.969 (93.080)
[2021-04-26 19:35:15 train_lshot.py:257] INFO Epoch: [33][30/150] Time 0.621 (0.907) Data 0.000 (0.284) Loss 0.9782 (0.9058) Prec@1 73.828 (74.534) Prec@5 92.969 (93.082)
[2021-04-26 19:35:21 train_lshot.py:257] INFO Epoch: [33][40/150] Time 0.627 (0.838) Data 0.000 (0.215) Loss 0.9205 (0.9087) Prec@1 73.047 (74.352) Prec@5 91.406 (92.969)
[2021-04-26 19:35:27 train_lshot.py:257] INFO Epoch: [33][50/150] Time 0.624 (0.796) Data 0.001 (0.173) Loss 0.9694 (0.9196) Prec@1 74.219 (74.180) Prec@5 91.797 (92.808)
[2021-04-26 19:35:34 train_lshot.py:257] INFO Epoch: [33][60/150] Time 0.631 (0.771) Data 0.001 (0.148) Loss 0.9626 (0.9248) Prec@1 70.703 (73.956) Prec@5 91.406 (92.668)
[2021-04-26 19:35:40 train_lshot.py:257] INFO Epoch: [33][70/150] Time 0.621 (0.750) Data 0.001 (0.127) Loss 0.9270 (0.9210) Prec@1 74.219 (73.955) Prec@5 92.578 (92.749)
[2021-04-26 19:35:46 train_lshot.py:257] INFO Epoch: [33][80/150] Time 0.628 (0.735) Data 0.001 (0.112) Loss 1.1215 (0.9220) Prec@1 69.141 (73.987) Prec@5 88.281 (92.752)
[2021-04-26 19:35:52 train_lshot.py:257] INFO Epoch: [33][90/150] Time 0.620 (0.722) Data 0.000 (0.099) Loss 1.1384 (0.9296) Prec@1 69.922 (73.931) Prec@5 90.234 (92.647)
[2021-04-26 19:35:59 train_lshot.py:257] INFO Epoch: [33][100/150] Time 0.621 (0.712) Data 0.000 (0.090) Loss 1.0287 (0.9308) Prec@1 72.656 (73.886) Prec@5 90.234 (92.640)
[2021-04-26 19:36:05 train_lshot.py:257] INFO Epoch: [33][110/150] Time 0.624 (0.704) Data 0.000 (0.082) Loss 1.1172 (0.9311) Prec@1 66.406 (73.860) Prec@5 89.844 (92.620)
[2021-04-26 19:36:11 train_lshot.py:257] INFO Epoch: [33][120/150] Time 0.624 (0.697) Data 0.000 (0.075) Loss 0.8491 (0.9335) Prec@1 76.172 (73.828) Prec@5 93.750 (92.575)
[2021-04-26 19:36:17 train_lshot.py:257] INFO Epoch: [33][130/150] Time 0.623 (0.691) Data 0.000 (0.069) Loss 0.8401 (0.9313) Prec@1 77.344 (73.924) Prec@5 92.188 (92.554)
[2021-04-26 19:36:23 train_lshot.py:257] INFO Epoch: [33][140/150] Time 0.619 (0.686) Data 0.000 (0.064) Loss 0.8793 (0.9337) Prec@1 76.172 (73.936) Prec@5 91.797 (92.514)
[2021-04-26 19:36:39 train_lshot.py:257] INFO Epoch: [34][0/150] Time 9.167 (9.167) Data 8.517 (8.517) Loss 0.8476 (0.8476) Prec@1 76.172 (76.172) Prec@5 94.141 (94.141)
[2021-04-26 19:36:45 train_lshot.py:257] INFO Epoch: [34][10/150] Time 0.622 (1.397) Data 0.000 (0.775) Loss 0.7938 (0.8664) Prec@1 78.516 (75.675) Prec@5 94.922 (93.572)
[2021-04-26 19:36:51 train_lshot.py:257] INFO Epoch: [34][20/150] Time 0.622 (1.028) Data 0.000 (0.406) Loss 0.8027 (0.8768) Prec@1 79.688 (75.967) Prec@5 92.578 (93.118)
[2021-04-26 19:36:57 train_lshot.py:257] INFO Epoch: [34][30/150] Time 0.627 (0.898) Data 0.000 (0.275) Loss 0.8326 (0.8582) Prec@1 78.516 (76.121) Prec@5 92.969 (93.422)
[2021-04-26 19:37:03 train_lshot.py:257] INFO Epoch: [34][40/150] Time 0.620 (0.831) Data 0.000 (0.208) Loss 0.8468 (0.8574) Prec@1 75.781 (75.962) Prec@5 95.312 (93.331)
[2021-04-26 19:37:10 train_lshot.py:257] INFO Epoch: [34][50/150] Time 0.623 (0.790) Data 0.000 (0.168) Loss 0.7908 (0.8633) Prec@1 75.391 (75.919) Prec@5 95.312 (93.375)
[2021-04-26 19:37:16 train_lshot.py:257] INFO Epoch: [34][60/150] Time 0.621 (0.763) Data 0.001 (0.140) Loss 1.0365 (0.8736) Prec@1 71.094 (75.570) Prec@5 91.797 (93.206)
[2021-04-26 19:37:22 train_lshot.py:257] INFO Epoch: [34][70/150] Time 0.621 (0.743) Data 0.001 (0.121) Loss 0.8672 (0.8794) Prec@1 73.047 (75.308) Prec@5 93.359 (93.117)
[2021-04-26 19:37:28 train_lshot.py:257] INFO Epoch: [34][80/150] Time 0.623 (0.728) Data 0.001 (0.106) Loss 0.9209 (0.8873) Prec@1 74.219 (75.149) Prec@5 92.969 (92.983)
[2021-04-26 19:37:35 train_lshot.py:257] INFO Epoch: [34][90/150] Time 0.617 (0.716) Data 0.000 (0.094) Loss 1.0679 (0.8932) Prec@1 69.922 (74.888) Prec@5 90.234 (92.973)
[2021-04-26 19:37:41 train_lshot.py:257] INFO Epoch: [34][100/150] Time 0.622 (0.707) Data 0.000 (0.085) Loss 0.8023 (0.8959) Prec@1 74.609 (74.694) Prec@5 94.531 (92.992)
[2021-04-26 19:37:47 train_lshot.py:257] INFO Epoch: [34][110/150] Time 0.619 (0.699) Data 0.000 (0.077) Loss 0.7624 (0.8921) Prec@1 75.000 (74.750) Prec@5 93.750 (92.965)
[2021-04-26 19:37:53 train_lshot.py:257] INFO Epoch: [34][120/150] Time 0.618 (0.692) Data 0.000 (0.071) Loss 0.9446 (0.8938) Prec@1 74.609 (74.771) Prec@5 91.797 (92.924)
[2021-04-26 19:37:59 train_lshot.py:257] INFO Epoch: [34][130/150] Time 0.619 (0.687) Data 0.000 (0.065) Loss 0.8849 (0.8961) Prec@1 74.219 (74.699) Prec@5 93.750 (92.909)
[2021-04-26 19:38:06 train_lshot.py:257] INFO Epoch: [34][140/150] Time 0.621 (0.682) Data 0.000 (0.061) Loss 0.8823 (0.9013) Prec@1 77.344 (74.623) Prec@5 92.578 (92.841)
[2021-04-26 19:38:21 train_lshot.py:257] INFO Epoch: [35][0/150] Time 9.460 (9.460) Data 8.797 (8.797) Loss 0.7558 (0.7558) Prec@1 79.688 (79.688) Prec@5 95.312 (95.312)
[2021-04-26 19:38:27 train_lshot.py:257] INFO Epoch: [35][10/150] Time 0.617 (1.423) Data 0.000 (0.800) Loss 0.8606 (0.8174) Prec@1 78.516 (77.344) Prec@5 92.578 (93.750)
[2021-04-26 19:38:33 train_lshot.py:257] INFO Epoch: [35][20/150] Time 0.627 (1.042) Data 0.001 (0.420) Loss 1.0534 (0.8474) Prec@1 73.828 (76.525) Prec@5 91.797 (93.341)
[2021-04-26 19:38:40 train_lshot.py:257] INFO Epoch: [35][30/150] Time 0.621 (0.907) Data 0.000 (0.284) Loss 0.8497 (0.8589) Prec@1 76.562 (76.033) Prec@5 94.922 (93.158)
[2021-04-26 19:38:46 train_lshot.py:257] INFO Epoch: [35][40/150] Time 0.623 (0.837) Data 0.000 (0.215) Loss 0.9396 (0.8529) Prec@1 70.703 (76.058) Prec@5 91.016 (93.216)
[2021-04-26 19:38:52 train_lshot.py:257] INFO Epoch: [35][50/150] Time 0.620 (0.795) Data 0.001 (0.173) Loss 0.7279 (0.8544) Prec@1 80.859 (76.134) Prec@5 96.094 (93.283)
[2021-04-26 19:38:58 train_lshot.py:257] INFO Epoch: [35][60/150] Time 0.625 (0.767) Data 0.000 (0.145) Loss 0.8291 (0.8554) Prec@1 75.391 (76.101) Prec@5 94.141 (93.347)
[2021-04-26 19:39:05 train_lshot.py:257] INFO Epoch: [35][70/150] Time 0.622 (0.746) Data 0.001 (0.124) Loss 0.8826 (0.8667) Prec@1 78.906 (75.842) Prec@5 92.578 (93.282)
[2021-04-26 19:39:11 train_lshot.py:257] INFO Epoch: [35][80/150] Time 0.622 (0.731) Data 0.001 (0.109) Loss 1.0335 (0.8715) Prec@1 70.703 (75.772) Prec@5 90.234 (93.128)
[2021-04-26 19:39:17 train_lshot.py:257] INFO Epoch: [35][90/150] Time 0.623 (0.719) Data 0.000 (0.097) Loss 0.9735 (0.8783) Prec@1 73.438 (75.554) Prec@5 91.797 (92.973)
[2021-04-26 19:39:23 train_lshot.py:257] INFO Epoch: [35][100/150] Time 0.621 (0.709) Data 0.000 (0.088) Loss 0.9689 (0.8801) Prec@1 70.312 (75.437) Prec@5 93.750 (92.976)
[2021-04-26 19:39:29 train_lshot.py:257] INFO Epoch: [35][110/150] Time 0.626 (0.701) Data 0.000 (0.080) Loss 1.1423 (0.8887) Prec@1 67.578 (75.190) Prec@5 90.625 (92.884)
[2021-04-26 19:39:36 train_lshot.py:257] INFO Epoch: [35][120/150] Time 0.620 (0.695) Data 0.000 (0.073) Loss 0.8278 (0.8933) Prec@1 77.344 (75.058) Prec@5 93.359 (92.791)
[2021-04-26 19:39:42 train_lshot.py:257] INFO Epoch: [35][130/150] Time 0.618 (0.689) Data 0.000 (0.068) Loss 0.8700 (0.8930) Prec@1 77.344 (75.075) Prec@5 91.797 (92.784)
[2021-04-26 19:39:48 train_lshot.py:257] INFO Epoch: [35][140/150] Time 0.621 (0.684) Data 0.000 (0.063) Loss 0.9229 (0.8930) Prec@1 73.438 (75.014) Prec@5 91.406 (92.803)
[2021-04-26 19:40:34 train_lshot.py:119] INFO Meta Val 35: 0.5841333457827568
[2021-04-26 19:40:45 train_lshot.py:257] INFO Epoch: [36][0/150] Time 10.318 (10.318) Data 9.665 (9.665) Loss 0.7439 (0.7439) Prec@1 79.297 (79.297) Prec@5 94.531 (94.531)
[2021-04-26 19:40:51 train_lshot.py:257] INFO Epoch: [36][10/150] Time 0.620 (1.499) Data 0.000 (0.879) Loss 0.8386 (0.8279) Prec@1 77.344 (77.095) Prec@5 93.750 (93.004)
[2021-04-26 19:40:57 train_lshot.py:257] INFO Epoch: [36][20/150] Time 0.626 (1.081) Data 0.001 (0.461) Loss 0.8979 (0.8484) Prec@1 73.828 (76.339) Prec@5 92.578 (93.025)
[2021-04-26 19:41:03 train_lshot.py:257] INFO Epoch: [36][30/150] Time 0.621 (0.933) Data 0.000 (0.312) Loss 0.9203 (0.8500) Prec@1 77.344 (76.399) Prec@5 92.969 (92.994)
[2021-04-26 19:41:10 train_lshot.py:257] INFO Epoch: [36][40/150] Time 0.618 (0.857) Data 0.001 (0.236) Loss 0.7222 (0.8534) Prec@1 81.641 (76.353) Prec@5 92.578 (92.950)
[2021-04-26 19:41:16 train_lshot.py:257] INFO Epoch: [36][50/150] Time 0.619 (0.811) Data 0.000 (0.190) Loss 0.8256 (0.8535) Prec@1 75.391 (76.210) Prec@5 94.141 (93.068)
[2021-04-26 19:41:22 train_lshot.py:257] INFO Epoch: [36][60/150] Time 0.612 (0.780) Data 0.000 (0.159) Loss 0.9500 (0.8528) Prec@1 73.438 (76.210) Prec@5 92.188 (93.090)
[2021-04-26 19:41:28 train_lshot.py:257] INFO Epoch: [36][70/150] Time 0.622 (0.758) Data 0.002 (0.137) Loss 0.8369 (0.8584) Prec@1 79.688 (76.150) Prec@5 93.359 (92.991)
[2021-04-26 19:41:35 train_lshot.py:257] INFO Epoch: [36][80/150] Time 0.620 (0.741) Data 0.000 (0.120) Loss 0.6927 (0.8566) Prec@1 81.250 (76.143) Prec@5 95.703 (93.080)
[2021-04-26 19:41:41 train_lshot.py:257] INFO Epoch: [36][90/150] Time 0.621 (0.728) Data 0.000 (0.107) Loss 0.7986 (0.8599) Prec@1 76.562 (76.030) Prec@5 95.312 (93.136)
[2021-04-26 19:41:47 train_lshot.py:257] INFO Epoch: [36][100/150] Time 0.620 (0.717) Data 0.000 (0.096) Loss 0.9253 (0.8627) Prec@1 71.875 (75.882) Prec@5 92.578 (93.143)
[2021-04-26 19:41:53 train_lshot.py:257] INFO Epoch: [36][110/150] Time 0.623 (0.708) Data 0.000 (0.088) Loss 0.8541 (0.8631) Prec@1 76.953 (75.918) Prec@5 92.969 (93.187)
[2021-04-26 19:41:59 train_lshot.py:257] INFO Epoch: [36][120/150] Time 0.623 (0.701) Data 0.000 (0.080) Loss 1.0125 (0.8688) Prec@1 72.656 (75.704) Prec@5 90.625 (93.111)
[2021-04-26 19:42:06 train_lshot.py:257] INFO Epoch: [36][130/150] Time 0.622 (0.695) Data 0.000 (0.074) Loss 0.8045 (0.8693) Prec@1 74.219 (75.716) Prec@5 95.312 (93.106)
[2021-04-26 19:42:12 train_lshot.py:257] INFO Epoch: [36][140/150] Time 0.624 (0.690) Data 0.000 (0.069) Loss 0.8461 (0.8709) Prec@1 75.391 (75.662) Prec@5 95.703 (93.116)
[2021-04-26 19:42:27 train_lshot.py:257] INFO Epoch: [37][0/150] Time 9.242 (9.242) Data 8.598 (8.598) Loss 0.7057 (0.7057) Prec@1 80.469 (80.469) Prec@5 94.922 (94.922)
[2021-04-26 19:42:33 train_lshot.py:257] INFO Epoch: [37][10/150] Time 0.617 (1.404) Data 0.000 (0.783) Loss 0.7839 (0.8403) Prec@1 79.297 (76.278) Prec@5 94.922 (93.359)
[2021-04-26 19:42:39 train_lshot.py:257] INFO Epoch: [37][20/150] Time 0.625 (1.031) Data 0.001 (0.410) Loss 0.6338 (0.8110) Prec@1 82.422 (77.158) Prec@5 95.703 (93.955)
[2021-04-26 19:42:46 train_lshot.py:257] INFO Epoch: [37][30/150] Time 0.629 (0.900) Data 0.001 (0.278) Loss 0.8508 (0.8131) Prec@1 75.781 (77.205) Prec@5 90.625 (93.725)
[2021-04-26 19:42:52 train_lshot.py:257] INFO Epoch: [37][40/150] Time 0.622 (0.832) Data 0.000 (0.210) Loss 0.7532 (0.8220) Prec@1 78.906 (76.829) Prec@5 96.094 (93.779)
[2021-04-26 19:42:58 train_lshot.py:257] INFO Epoch: [37][50/150] Time 0.626 (0.791) Data 0.001 (0.169) Loss 0.9194 (0.8273) Prec@1 72.266 (76.654) Prec@5 93.359 (93.704)
[2021-04-26 19:43:04 train_lshot.py:257] INFO Epoch: [37][60/150] Time 0.619 (0.764) Data 0.000 (0.142) Loss 0.8206 (0.8305) Prec@1 75.000 (76.415) Prec@5 94.531 (93.680)
[2021-04-26 19:43:11 train_lshot.py:257] INFO Epoch: [37][70/150] Time 0.622 (0.744) Data 0.001 (0.122) Loss 0.7260 (0.8360) Prec@1 80.859 (76.375) Prec@5 95.312 (93.585)
[2021-04-26 19:43:17 train_lshot.py:257] INFO Epoch: [37][80/150] Time 0.623 (0.729) Data 0.000 (0.107) Loss 0.7468 (0.8370) Prec@1 77.734 (76.427) Prec@5 95.312 (93.523)
[2021-04-26 19:43:23 train_lshot.py:257] INFO Epoch: [37][90/150] Time 0.621 (0.717) Data 0.000 (0.095) Loss 0.9737 (0.8425) Prec@1 71.484 (76.275) Prec@5 91.797 (93.441)
[2021-04-26 19:43:29 train_lshot.py:257] INFO Epoch: [37][100/150] Time 0.620 (0.708) Data 0.000 (0.086) Loss 0.7815 (0.8446) Prec@1 76.172 (76.160) Prec@5 93.359 (93.425)
[2021-04-26 19:43:35 train_lshot.py:257] INFO Epoch: [37][110/150] Time 0.619 (0.700) Data 0.000 (0.078) Loss 0.7461 (0.8430) Prec@1 79.297 (76.168) Prec@5 95.312 (93.377)
[2021-04-26 19:43:42 train_lshot.py:257] INFO Epoch: [37][120/150] Time 0.620 (0.693) Data 0.000 (0.072) Loss 0.7416 (0.8469) Prec@1 77.344 (76.078) Prec@5 95.703 (93.330)
[2021-04-26 19:43:48 train_lshot.py:257] INFO Epoch: [37][130/150] Time 0.624 (0.688) Data 0.001 (0.066) Loss 0.7799 (0.8521) Prec@1 76.562 (75.906) Prec@5 94.922 (93.285)
[2021-04-26 19:43:54 train_lshot.py:257] INFO Epoch: [37][140/150] Time 0.621 (0.683) Data 0.000 (0.061) Loss 0.9175 (0.8531) Prec@1 75.000 (75.903) Prec@5 91.406 (93.287)
[2021-04-26 19:44:11 train_lshot.py:257] INFO Epoch: [38][0/150] Time 10.494 (10.494) Data 9.848 (9.848) Loss 0.7942 (0.7942) Prec@1 75.781 (75.781) Prec@5 93.359 (93.359)
[2021-04-26 19:44:17 train_lshot.py:257] INFO Epoch: [38][10/150] Time 0.622 (1.517) Data 0.000 (0.896) Loss 0.8818 (0.8059) Prec@1 80.469 (78.338) Prec@5 91.016 (93.786)
[2021-04-26 19:44:23 train_lshot.py:257] INFO Epoch: [38][20/150] Time 0.634 (1.092) Data 0.001 (0.469) Loss 0.8447 (0.8050) Prec@1 75.781 (77.809) Prec@5 92.969 (93.880)
[2021-04-26 19:44:29 train_lshot.py:257] INFO Epoch: [38][30/150] Time 0.621 (0.940) Data 0.001 (0.318) Loss 0.8135 (0.8053) Prec@1 76.953 (77.394) Prec@5 93.750 (93.826)
[2021-04-26 19:44:36 train_lshot.py:257] INFO Epoch: [38][40/150] Time 0.622 (0.864) Data 0.001 (0.241) Loss 0.8020 (0.8171) Prec@1 79.297 (77.115) Prec@5 94.141 (93.578)
[2021-04-26 19:44:42 train_lshot.py:257] INFO Epoch: [38][50/150] Time 0.622 (0.816) Data 0.000 (0.194) Loss 0.7533 (0.8134) Prec@1 80.078 (77.191) Prec@5 94.531 (93.689)
[2021-04-26 19:44:48 train_lshot.py:257] INFO Epoch: [38][60/150] Time 0.628 (0.785) Data 0.001 (0.162) Loss 0.8935 (0.8209) Prec@1 76.562 (77.216) Prec@5 92.578 (93.583)
[2021-04-26 19:44:54 train_lshot.py:257] INFO Epoch: [38][70/150] Time 0.628 (0.762) Data 0.002 (0.139) Loss 0.9210 (0.8224) Prec@1 75.000 (77.179) Prec@5 92.578 (93.574)
[2021-04-26 19:45:00 train_lshot.py:257] INFO Epoch: [38][80/150] Time 0.620 (0.745) Data 0.000 (0.122) Loss 0.8421 (0.8222) Prec@1 77.734 (77.083) Prec@5 93.750 (93.528)
[2021-04-26 19:45:07 train_lshot.py:257] INFO Epoch: [38][90/150] Time 0.619 (0.731) Data 0.000 (0.109) Loss 0.8232 (0.8256) Prec@1 78.125 (76.923) Prec@5 93.359 (93.471)
[2021-04-26 19:45:13 train_lshot.py:257] INFO Epoch: [38][100/150] Time 0.622 (0.720) Data 0.000 (0.098) Loss 0.8533 (0.8238) Prec@1 73.828 (76.922) Prec@5 91.797 (93.499)
[2021-04-26 19:45:19 train_lshot.py:257] INFO Epoch: [38][110/150] Time 0.617 (0.711) Data 0.000 (0.089) Loss 0.8325 (0.8255) Prec@1 72.656 (76.816) Prec@5 94.922 (93.472)
[2021-04-26 19:45:25 train_lshot.py:257] INFO Epoch: [38][120/150] Time 0.620 (0.704) Data 0.000 (0.082) Loss 0.8387 (0.8259) Prec@1 76.562 (76.869) Prec@5 92.969 (93.424)
[2021-04-26 19:45:31 train_lshot.py:257] INFO Epoch: [38][130/150] Time 0.617 (0.698) Data 0.000 (0.076) Loss 0.7312 (0.8252) Prec@1 78.906 (76.944) Prec@5 94.922 (93.455)
[2021-04-26 19:45:38 train_lshot.py:257] INFO Epoch: [38][140/150] Time 0.620 (0.692) Data 0.000 (0.070) Loss 0.8091 (0.8287) Prec@1 78.516 (76.817) Prec@5 92.578 (93.440)
[2021-04-26 19:45:53 train_lshot.py:257] INFO Epoch: [39][0/150] Time 9.639 (9.639) Data 8.992 (8.992) Loss 0.8457 (0.8457) Prec@1 78.125 (78.125) Prec@5 93.750 (93.750)
[2021-04-26 19:46:00 train_lshot.py:257] INFO Epoch: [39][10/150] Time 0.624 (1.439) Data 0.001 (0.818) Loss 0.8244 (0.8328) Prec@1 78.125 (76.420) Prec@5 92.578 (93.643)
[2021-04-26 19:46:06 train_lshot.py:257] INFO Epoch: [39][20/150] Time 0.618 (1.049) Data 0.001 (0.429) Loss 0.8494 (0.8277) Prec@1 75.781 (76.302) Prec@5 93.750 (93.843)
[2021-04-26 19:46:12 train_lshot.py:257] INFO Epoch: [39][30/150] Time 0.621 (0.912) Data 0.001 (0.291) Loss 0.7110 (0.8203) Prec@1 80.469 (76.726) Prec@5 95.703 (94.002)
[2021-04-26 19:46:18 train_lshot.py:257] INFO Epoch: [39][40/150] Time 0.622 (0.841) Data 0.001 (0.220) Loss 0.8526 (0.8218) Prec@1 76.562 (77.039) Prec@5 94.141 (93.988)
[2021-04-26 19:46:24 train_lshot.py:257] INFO Epoch: [39][50/150] Time 0.623 (0.798) Data 0.000 (0.177) Loss 0.8275 (0.8174) Prec@1 77.734 (77.129) Prec@5 94.531 (93.972)
[2021-04-26 19:46:31 train_lshot.py:257] INFO Epoch: [39][60/150] Time 0.623 (0.770) Data 0.000 (0.148) Loss 0.8227 (0.8206) Prec@1 77.734 (77.088) Prec@5 94.141 (93.923)
[2021-04-26 19:46:37 train_lshot.py:257] INFO Epoch: [39][70/150] Time 0.624 (0.749) Data 0.001 (0.127) Loss 0.8163 (0.8248) Prec@1 77.344 (76.986) Prec@5 92.578 (93.822)
[2021-04-26 19:46:43 train_lshot.py:257] INFO Epoch: [39][80/150] Time 0.619 (0.733) Data 0.000 (0.112) Loss 0.9001 (0.8278) Prec@1 74.609 (76.780) Prec@5 91.406 (93.760)
[2021-04-26 19:46:49 train_lshot.py:257] INFO Epoch: [39][90/150] Time 0.616 (0.721) Data 0.000 (0.099) Loss 0.8001 (0.8275) Prec@1 77.344 (76.700) Prec@5 95.703 (93.802)
[2021-04-26 19:46:55 train_lshot.py:257] INFO Epoch: [39][100/150] Time 0.619 (0.711) Data 0.000 (0.090) Loss 0.9761 (0.8318) Prec@1 71.484 (76.532) Prec@5 92.578 (93.769)
[2021-04-26 19:47:02 train_lshot.py:257] INFO Epoch: [39][110/150] Time 0.620 (0.703) Data 0.000 (0.081) Loss 0.8570 (0.8353) Prec@1 74.219 (76.527) Prec@5 93.750 (93.725)
[2021-04-26 19:47:08 train_lshot.py:257] INFO Epoch: [39][120/150] Time 0.617 (0.696) Data 0.000 (0.075) Loss 0.8424 (0.8351) Prec@1 75.000 (76.524) Prec@5 91.406 (93.676)
[2021-04-26 19:47:14 train_lshot.py:257] INFO Epoch: [39][130/150] Time 0.620 (0.690) Data 0.000 (0.069) Loss 0.7201 (0.8348) Prec@1 79.297 (76.512) Prec@5 95.703 (93.684)
[2021-04-26 19:47:20 train_lshot.py:257] INFO Epoch: [39][140/150] Time 0.620 (0.685) Data 0.000 (0.064) Loss 0.8568 (0.8324) Prec@1 76.562 (76.543) Prec@5 93.359 (93.697)
[2021-04-26 19:48:14 train_lshot.py:119] INFO Meta Val 39: 0.6143466805219651
[2021-04-26 19:48:25 train_lshot.py:257] INFO Epoch: [40][0/150] Time 10.115 (10.115) Data 9.445 (9.445) Loss 0.8909 (0.8909) Prec@1 77.734 (77.734) Prec@5 90.625 (90.625)
[2021-04-26 19:48:31 train_lshot.py:257] INFO Epoch: [40][10/150] Time 0.618 (1.482) Data 0.000 (0.859) Loss 0.7413 (0.8031) Prec@1 82.031 (77.983) Prec@5 94.531 (93.643)
[2021-04-26 19:48:37 train_lshot.py:257] INFO Epoch: [40][20/150] Time 0.625 (1.072) Data 0.001 (0.450) Loss 0.8799 (0.7847) Prec@1 74.219 (78.385) Prec@5 91.406 (93.843)
[2021-04-26 19:48:44 train_lshot.py:257] INFO Epoch: [40][30/150] Time 0.618 (0.927) Data 0.000 (0.305) Loss 0.6494 (0.7813) Prec@1 80.859 (78.251) Prec@5 94.531 (94.090)
[2021-04-26 19:48:50 train_lshot.py:257] INFO Epoch: [40][40/150] Time 0.620 (0.852) Data 0.000 (0.231) Loss 0.6556 (0.7864) Prec@1 81.250 (78.030) Prec@5 95.312 (94.026)
[2021-04-26 19:48:56 train_lshot.py:257] INFO Epoch: [40][50/150] Time 0.633 (0.808) Data 0.001 (0.186) Loss 0.8689 (0.7905) Prec@1 75.000 (77.811) Prec@5 92.969 (94.072)
[2021-04-26 19:49:02 train_lshot.py:257] INFO Epoch: [40][60/150] Time 0.618 (0.777) Data 0.001 (0.155) Loss 0.8962 (0.7950) Prec@1 74.609 (77.626) Prec@5 92.578 (94.038)
[2021-04-26 19:49:09 train_lshot.py:257] INFO Epoch: [40][70/150] Time 0.621 (0.756) Data 0.001 (0.134) Loss 0.9652 (0.7932) Prec@1 72.266 (77.707) Prec@5 92.578 (94.097)
[2021-04-26 19:49:15 train_lshot.py:257] INFO Epoch: [40][80/150] Time 0.619 (0.739) Data 0.000 (0.117) Loss 0.8277 (0.8012) Prec@1 78.906 (77.435) Prec@5 92.578 (93.996)
[2021-04-26 19:49:21 train_lshot.py:257] INFO Epoch: [40][90/150] Time 0.618 (0.726) Data 0.000 (0.104) Loss 0.7664 (0.8073) Prec@1 76.953 (77.301) Prec@5 94.531 (93.883)
[2021-04-26 19:49:27 train_lshot.py:257] INFO Epoch: [40][100/150] Time 0.625 (0.716) Data 0.000 (0.094) Loss 0.9150 (0.8103) Prec@1 74.219 (77.251) Prec@5 93.359 (93.812)
[2021-04-26 19:49:33 train_lshot.py:257] INFO Epoch: [40][110/150] Time 0.620 (0.707) Data 0.000 (0.086) Loss 0.7496 (0.8075) Prec@1 81.641 (77.404) Prec@5 92.578 (93.761)
[2021-04-26 19:49:40 train_lshot.py:257] INFO Epoch: [40][120/150] Time 0.621 (0.700) Data 0.000 (0.079) Loss 0.8121 (0.8079) Prec@1 76.953 (77.399) Prec@5 93.750 (93.698)
[2021-04-26 19:49:46 train_lshot.py:257] INFO Epoch: [40][130/150] Time 0.619 (0.694) Data 0.000 (0.073) Loss 0.8231 (0.8115) Prec@1 76.172 (77.248) Prec@5 93.750 (93.696)
[2021-04-26 19:49:52 train_lshot.py:257] INFO Epoch: [40][140/150] Time 0.619 (0.689) Data 0.000 (0.067) Loss 0.7801 (0.8139) Prec@1 80.078 (77.155) Prec@5 92.188 (93.692)
[2021-04-26 19:50:08 train_lshot.py:257] INFO Epoch: [41][0/150] Time 10.280 (10.280) Data 9.633 (9.633) Loss 0.8891 (0.8891) Prec@1 74.219 (74.219) Prec@5 93.359 (93.359)
[2021-04-26 19:50:15 train_lshot.py:257] INFO Epoch: [41][10/150] Time 0.621 (1.496) Data 0.001 (0.876) Loss 0.8874 (0.8051) Prec@1 73.828 (77.734) Prec@5 93.359 (94.283)
[2021-04-26 19:50:21 train_lshot.py:257] INFO Epoch: [41][20/150] Time 0.618 (1.080) Data 0.000 (0.459) Loss 0.7697 (0.7924) Prec@1 79.297 (78.144) Prec@5 92.969 (93.917)
[2021-04-26 19:50:27 train_lshot.py:257] INFO Epoch: [41][30/150] Time 0.620 (0.933) Data 0.000 (0.311) Loss 0.8174 (0.8010) Prec@1 76.562 (77.785) Prec@5 94.531 (94.015)
[2021-04-26 19:50:33 train_lshot.py:257] INFO Epoch: [41][40/150] Time 0.626 (0.857) Data 0.001 (0.236) Loss 0.7112 (0.7954) Prec@1 77.734 (77.839) Prec@5 96.484 (94.112)
[2021-04-26 19:50:39 train_lshot.py:257] INFO Epoch: [41][50/150] Time 0.618 (0.811) Data 0.000 (0.189) Loss 0.8001 (0.7938) Prec@1 75.781 (77.773) Prec@5 94.922 (94.110)
[2021-04-26 19:50:46 train_lshot.py:257] INFO Epoch: [41][60/150] Time 0.622 (0.780) Data 0.001 (0.159) Loss 0.7498 (0.7935) Prec@1 78.125 (77.754) Prec@5 95.312 (94.109)
[2021-04-26 19:50:52 train_lshot.py:257] INFO Epoch: [41][70/150] Time 0.625 (0.758) Data 0.001 (0.136) Loss 0.7174 (0.7957) Prec@1 82.812 (77.762) Prec@5 93.750 (93.992)
[2021-04-26 19:50:58 train_lshot.py:257] INFO Epoch: [41][80/150] Time 0.627 (0.741) Data 0.000 (0.119) Loss 0.7373 (0.7955) Prec@1 78.906 (77.773) Prec@5 94.922 (94.035)
[2021-04-26 19:51:04 train_lshot.py:257] INFO Epoch: [41][90/150] Time 0.622 (0.728) Data 0.000 (0.106) Loss 0.7711 (0.7958) Prec@1 80.859 (77.769) Prec@5 93.359 (94.008)
[2021-04-26 19:51:11 train_lshot.py:257] INFO Epoch: [41][100/150] Time 0.617 (0.717) Data 0.000 (0.096) Loss 0.6909 (0.7946) Prec@1 80.078 (77.746) Prec@5 94.922 (94.059)
[2021-04-26 19:51:17 train_lshot.py:257] INFO Epoch: [41][110/150] Time 0.622 (0.709) Data 0.000 (0.087) Loss 0.8504 (0.7976) Prec@1 77.344 (77.646) Prec@5 93.359 (94.035)
[2021-04-26 19:51:23 train_lshot.py:257] INFO Epoch: [41][120/150] Time 0.620 (0.701) Data 0.000 (0.080) Loss 0.7999 (0.7997) Prec@1 78.516 (77.618) Prec@5 93.359 (93.989)
[2021-04-26 19:51:29 train_lshot.py:257] INFO Epoch: [41][130/150] Time 0.622 (0.695) Data 0.000 (0.074) Loss 0.7033 (0.7995) Prec@1 80.078 (77.624) Prec@5 94.922 (94.009)
[2021-04-26 19:51:35 train_lshot.py:257] INFO Epoch: [41][140/150] Time 0.620 (0.690) Data 0.000 (0.069) Loss 0.8433 (0.8000) Prec@1 74.219 (77.593) Prec@5 94.141 (94.013)
[2021-04-26 19:51:51 train_lshot.py:257] INFO Epoch: [42][0/150] Time 9.398 (9.398) Data 8.744 (8.744) Loss 0.8523 (0.8523) Prec@1 75.000 (75.000) Prec@5 94.141 (94.141)
[2021-04-26 19:51:57 train_lshot.py:257] INFO Epoch: [42][10/150] Time 0.618 (1.416) Data 0.000 (0.795) Loss 0.7749 (0.7569) Prec@1 77.344 (78.161) Prec@5 93.359 (94.567)
[2021-04-26 19:52:03 train_lshot.py:257] INFO Epoch: [42][20/150] Time 0.617 (1.038) Data 0.000 (0.417) Loss 0.8094 (0.7697) Prec@1 78.516 (78.181) Prec@5 93.750 (94.308)
[2021-04-26 19:52:09 train_lshot.py:257] INFO Epoch: [42][30/150] Time 0.625 (0.904) Data 0.001 (0.283) Loss 0.7926 (0.7610) Prec@1 76.562 (78.188) Prec@5 94.141 (94.355)
[2021-04-26 19:52:16 train_lshot.py:257] INFO Epoch: [42][40/150] Time 0.620 (0.836) Data 0.000 (0.214) Loss 0.6865 (0.7683) Prec@1 82.812 (78.144) Prec@5 93.750 (94.255)
[2021-04-26 19:52:22 train_lshot.py:257] INFO Epoch: [42][50/150] Time 0.621 (0.794) Data 0.000 (0.172) Loss 0.7181 (0.7645) Prec@1 77.734 (78.355) Prec@5 93.750 (94.210)
[2021-04-26 19:52:28 train_lshot.py:257] INFO Epoch: [42][60/150] Time 0.623 (0.766) Data 0.000 (0.144) Loss 0.7798 (0.7662) Prec@1 75.781 (78.362) Prec@5 93.359 (94.217)
[2021-04-26 19:52:34 train_lshot.py:257] INFO Epoch: [42][70/150] Time 0.622 (0.746) Data 0.003 (0.124) Loss 0.8044 (0.7785) Prec@1 77.734 (78.031) Prec@5 92.969 (94.069)
[2021-04-26 19:52:41 train_lshot.py:257] INFO Epoch: [42][80/150] Time 0.620 (0.730) Data 0.000 (0.108) Loss 0.8098 (0.7859) Prec@1 76.562 (77.913) Prec@5 94.141 (93.957)
[2021-04-26 19:52:47 train_lshot.py:257] INFO Epoch: [42][90/150] Time 0.621 (0.718) Data 0.000 (0.097) Loss 0.9276 (0.7926) Prec@1 75.000 (77.743) Prec@5 92.188 (93.849)
[2021-04-26 19:52:53 train_lshot.py:257] INFO Epoch: [42][100/150] Time 0.618 (0.709) Data 0.000 (0.087) Loss 0.7174 (0.7922) Prec@1 79.688 (77.750) Prec@5 94.531 (93.901)
[2021-04-26 19:52:59 train_lshot.py:257] INFO Epoch: [42][110/150] Time 0.620 (0.701) Data 0.000 (0.079) Loss 0.7605 (0.7898) Prec@1 78.125 (77.748) Prec@5 94.922 (93.926)
[2021-04-26 19:53:05 train_lshot.py:257] INFO Epoch: [42][120/150] Time 0.620 (0.694) Data 0.000 (0.073) Loss 0.9114 (0.7900) Prec@1 73.438 (77.731) Prec@5 91.797 (93.908)
[2021-04-26 19:53:12 train_lshot.py:257] INFO Epoch: [42][130/150] Time 0.623 (0.689) Data 0.000 (0.067) Loss 0.6565 (0.7890) Prec@1 81.641 (77.779) Prec@5 94.141 (93.893)
[2021-04-26 19:53:18 train_lshot.py:257] INFO Epoch: [42][140/150] Time 0.619 (0.684) Data 0.000 (0.062) Loss 0.8689 (0.7926) Prec@1 75.000 (77.676) Prec@5 93.359 (93.880)
[2021-04-26 19:53:33 train_lshot.py:257] INFO Epoch: [43][0/150] Time 9.671 (9.671) Data 9.017 (9.017) Loss 0.6997 (0.6997) Prec@1 80.078 (80.078) Prec@5 95.703 (95.703)
[2021-04-26 19:53:40 train_lshot.py:257] INFO Epoch: [43][10/150] Time 0.617 (1.442) Data 0.000 (0.820) Loss 0.7254 (0.7277) Prec@1 79.688 (79.403) Prec@5 96.094 (94.709)
[2021-04-26 19:53:46 train_lshot.py:257] INFO Epoch: [43][20/150] Time 0.626 (1.051) Data 0.001 (0.430) Loss 0.7077 (0.7268) Prec@1 76.953 (79.297) Prec@5 96.875 (94.940)
[2021-04-26 19:53:52 train_lshot.py:257] INFO Epoch: [43][30/150] Time 0.621 (0.913) Data 0.000 (0.291) Loss 0.7337 (0.7351) Prec@1 77.734 (79.209) Prec@5 95.312 (94.733)
[2021-04-26 19:53:58 train_lshot.py:257] INFO Epoch: [43][40/150] Time 0.624 (0.842) Data 0.000 (0.220) Loss 0.8032 (0.7387) Prec@1 78.906 (79.259) Prec@5 94.531 (94.627)
[2021-04-26 19:54:05 train_lshot.py:257] INFO Epoch: [43][50/150] Time 0.625 (0.799) Data 0.001 (0.177) Loss 0.7147 (0.7464) Prec@1 78.906 (78.983) Prec@5 95.703 (94.562)
[2021-04-26 19:54:11 train_lshot.py:257] INFO Epoch: [43][60/150] Time 0.620 (0.770) Data 0.000 (0.148) Loss 0.7343 (0.7507) Prec@1 80.469 (78.887) Prec@5 92.188 (94.518)
[2021-04-26 19:54:17 train_lshot.py:257] INFO Epoch: [43][70/150] Time 0.638 (0.750) Data 0.001 (0.128) Loss 0.7795 (0.7523) Prec@1 77.734 (78.851) Prec@5 93.750 (94.449)
[2021-04-26 19:54:23 train_lshot.py:257] INFO Epoch: [43][80/150] Time 0.620 (0.734) Data 0.000 (0.112) Loss 0.7453 (0.7579) Prec@1 79.688 (78.617) Prec@5 94.141 (94.382)
[2021-04-26 19:54:30 train_lshot.py:257] INFO Epoch: [43][90/150] Time 0.621 (0.722) Data 0.000 (0.100) Loss 0.8058 (0.7618) Prec@1 75.391 (78.529) Prec@5 94.531 (94.351)
[2021-04-26 19:54:36 train_lshot.py:257] INFO Epoch: [43][100/150] Time 0.616 (0.712) Data 0.000 (0.090) Loss 0.8175 (0.7631) Prec@1 77.344 (78.481) Prec@5 95.312 (94.419)
[2021-04-26 19:54:42 train_lshot.py:257] INFO Epoch: [43][110/150] Time 0.622 (0.703) Data 0.000 (0.082) Loss 0.7982 (0.7640) Prec@1 77.734 (78.519) Prec@5 93.750 (94.369)
[2021-04-26 19:54:48 train_lshot.py:257] INFO Epoch: [43][120/150] Time 0.620 (0.697) Data 0.000 (0.075) Loss 0.6853 (0.7677) Prec@1 81.641 (78.393) Prec@5 94.141 (94.283)
[2021-04-26 19:54:54 train_lshot.py:257] INFO Epoch: [43][130/150] Time 0.620 (0.691) Data 0.000 (0.069) Loss 0.9046 (0.7686) Prec@1 75.391 (78.334) Prec@5 91.797 (94.260)
[2021-04-26 19:55:01 train_lshot.py:257] INFO Epoch: [43][140/150] Time 0.619 (0.686) Data 0.000 (0.064) Loss 0.9618 (0.7698) Prec@1 73.438 (78.283) Prec@5 91.797 (94.238)
[2021-04-26 19:55:46 train_lshot.py:119] INFO Meta Val 43: 0.6128000144958496
[2021-04-26 19:55:56 train_lshot.py:257] INFO Epoch: [44][0/150] Time 10.293 (10.293) Data 9.638 (9.638) Loss 0.9232 (0.9232) Prec@1 76.953 (76.953) Prec@5 91.406 (91.406)
[2021-04-26 19:56:02 train_lshot.py:257] INFO Epoch: [44][10/150] Time 0.619 (1.499) Data 0.000 (0.877) Loss 0.6848 (0.7660) Prec@1 82.422 (78.693) Prec@5 94.531 (94.141)
[2021-04-26 19:56:09 train_lshot.py:257] INFO Epoch: [44][20/150] Time 0.620 (1.081) Data 0.000 (0.459) Loss 0.8181 (0.7609) Prec@1 76.953 (78.813) Prec@5 95.312 (94.401)
[2021-04-26 19:56:15 train_lshot.py:257] INFO Epoch: [44][30/150] Time 0.627 (0.934) Data 0.001 (0.311) Loss 0.7267 (0.7543) Prec@1 79.297 (79.083) Prec@5 94.922 (94.317)
[2021-04-26 19:56:21 train_lshot.py:257] INFO Epoch: [44][40/150] Time 0.619 (0.858) Data 0.001 (0.236) Loss 0.8407 (0.7623) Prec@1 76.953 (78.744) Prec@5 92.188 (94.236)
[2021-04-26 19:56:27 train_lshot.py:257] INFO Epoch: [44][50/150] Time 0.624 (0.812) Data 0.000 (0.190) Loss 0.8959 (0.7720) Prec@1 75.391 (78.470) Prec@5 92.969 (94.233)
[2021-04-26 19:56:34 train_lshot.py:257] INFO Epoch: [44][60/150] Time 0.627 (0.781) Data 0.001 (0.159) Loss 0.6952 (0.7680) Prec@1 78.125 (78.509) Prec@5 95.703 (94.333)
[2021-04-26 19:56:40 train_lshot.py:257] INFO Epoch: [44][70/150] Time 0.628 (0.759) Data 0.002 (0.136) Loss 0.7363 (0.7728) Prec@1 78.906 (78.466) Prec@5 94.531 (94.295)
[2021-04-26 19:56:46 train_lshot.py:257] INFO Epoch: [44][80/150] Time 0.618 (0.742) Data 0.000 (0.120) Loss 0.8769 (0.7733) Prec@1 75.000 (78.424) Prec@5 93.359 (94.271)
[2021-04-26 19:56:52 train_lshot.py:257] INFO Epoch: [44][90/150] Time 0.625 (0.729) Data 0.000 (0.106) Loss 0.9806 (0.7750) Prec@1 73.438 (78.340) Prec@5 91.016 (94.244)
[2021-04-26 19:56:58 train_lshot.py:257] INFO Epoch: [44][100/150] Time 0.623 (0.718) Data 0.000 (0.096) Loss 0.6451 (0.7720) Prec@1 82.422 (78.423) Prec@5 95.312 (94.280)
[2021-04-26 19:57:05 train_lshot.py:257] INFO Epoch: [44][110/150] Time 0.623 (0.709) Data 0.000 (0.087) Loss 0.8071 (0.7752) Prec@1 77.734 (78.371) Prec@5 94.922 (94.295)
[2021-04-26 19:57:11 train_lshot.py:257] INFO Epoch: [44][120/150] Time 0.619 (0.702) Data 0.000 (0.080) Loss 0.8158 (0.7728) Prec@1 73.828 (78.425) Prec@5 93.359 (94.305)
[2021-04-26 19:57:17 train_lshot.py:257] INFO Epoch: [44][130/150] Time 0.627 (0.696) Data 0.000 (0.074) Loss 0.7595 (0.7790) Prec@1 78.516 (78.211) Prec@5 95.703 (94.206)
[2021-04-26 19:57:23 train_lshot.py:257] INFO Epoch: [44][140/150] Time 0.620 (0.690) Data 0.000 (0.069) Loss 0.8593 (0.7787) Prec@1 75.781 (78.155) Prec@5 93.750 (94.221)
[2021-04-26 19:57:39 train_lshot.py:257] INFO Epoch: [45][0/150] Time 9.812 (9.812) Data 9.164 (9.164) Loss 0.7117 (0.7117) Prec@1 79.688 (79.688) Prec@5 94.531 (94.531)
[2021-04-26 19:57:45 train_lshot.py:257] INFO Epoch: [45][10/150] Time 0.618 (1.455) Data 0.000 (0.834) Loss 0.7412 (0.7614) Prec@1 78.125 (78.374) Prec@5 93.750 (94.318)
[2021-04-26 19:57:51 train_lshot.py:257] INFO Epoch: [45][20/150] Time 0.625 (1.058) Data 0.001 (0.437) Loss 0.7889 (0.7723) Prec@1 81.250 (78.367) Prec@5 92.969 (94.327)
[2021-04-26 19:57:58 train_lshot.py:257] INFO Epoch: [45][30/150] Time 0.636 (0.918) Data 0.001 (0.296) Loss 0.8352 (0.7777) Prec@1 76.562 (78.226) Prec@5 94.531 (94.141)
[2021-04-26 19:58:04 train_lshot.py:257] INFO Epoch: [45][40/150] Time 0.622 (0.845) Data 0.001 (0.224) Loss 0.7143 (0.7583) Prec@1 78.906 (78.821) Prec@5 96.094 (94.398)
[2021-04-26 19:58:10 train_lshot.py:257] INFO Epoch: [45][50/150] Time 0.622 (0.802) Data 0.000 (0.180) Loss 0.7041 (0.7606) Prec@1 78.516 (78.631) Prec@5 95.312 (94.347)
[2021-04-26 19:58:16 train_lshot.py:257] INFO Epoch: [45][60/150] Time 0.623 (0.773) Data 0.001 (0.151) Loss 0.7547 (0.7545) Prec@1 77.344 (78.669) Prec@5 94.922 (94.429)
[2021-04-26 19:58:23 train_lshot.py:257] INFO Epoch: [45][70/150] Time 0.622 (0.752) Data 0.001 (0.130) Loss 0.7763 (0.7587) Prec@1 77.734 (78.549) Prec@5 94.531 (94.344)
[2021-04-26 19:58:29 train_lshot.py:257] INFO Epoch: [45][80/150] Time 0.623 (0.736) Data 0.000 (0.114) Loss 0.8281 (0.7553) Prec@1 76.562 (78.733) Prec@5 94.922 (94.416)
[2021-04-26 19:58:35 train_lshot.py:257] INFO Epoch: [45][90/150] Time 0.623 (0.723) Data 0.000 (0.101) Loss 0.6720 (0.7589) Prec@1 78.125 (78.614) Prec@5 96.484 (94.402)
[2021-04-26 19:58:41 train_lshot.py:257] INFO Epoch: [45][100/150] Time 0.620 (0.713) Data 0.000 (0.091) Loss 0.9030 (0.7607) Prec@1 76.172 (78.624) Prec@5 92.578 (94.384)
[2021-04-26 19:58:47 train_lshot.py:257] INFO Epoch: [45][110/150] Time 0.620 (0.704) Data 0.000 (0.083) Loss 0.7482 (0.7607) Prec@1 76.953 (78.625) Prec@5 94.141 (94.405)
[2021-04-26 19:58:54 train_lshot.py:257] INFO Epoch: [45][120/150] Time 0.619 (0.697) Data 0.000 (0.076) Loss 0.7477 (0.7645) Prec@1 79.688 (78.503) Prec@5 94.141 (94.318)
[2021-04-26 19:59:00 train_lshot.py:257] INFO Epoch: [45][130/150] Time 0.619 (0.692) Data 0.000 (0.070) Loss 0.8781 (0.7651) Prec@1 75.391 (78.489) Prec@5 94.141 (94.305)
[2021-04-26 19:59:06 train_lshot.py:257] INFO Epoch: [45][140/150] Time 0.620 (0.687) Data 0.000 (0.065) Loss 0.8301 (0.7679) Prec@1 74.609 (78.344) Prec@5 94.922 (94.285)
[2021-04-26 19:59:22 train_lshot.py:257] INFO Epoch: [46][0/150] Time 9.480 (9.480) Data 8.823 (8.823) Loss 0.5628 (0.5628) Prec@1 84.375 (84.375) Prec@5 95.703 (95.703)
[2021-04-26 19:59:28 train_lshot.py:257] INFO Epoch: [46][10/150] Time 0.620 (1.423) Data 0.000 (0.803) Loss 0.6721 (0.6829) Prec@1 83.203 (80.895) Prec@5 95.312 (95.064)
[2021-04-26 19:59:34 train_lshot.py:257] INFO Epoch: [46][20/150] Time 0.616 (1.041) Data 0.001 (0.421) Loss 0.7323 (0.6907) Prec@1 78.125 (80.878) Prec@5 94.531 (94.661)
[2021-04-26 19:59:40 train_lshot.py:257] INFO Epoch: [46][30/150] Time 0.621 (0.907) Data 0.000 (0.285) Loss 0.6987 (0.6737) Prec@1 80.469 (81.363) Prec@5 93.750 (94.745)
[2021-04-26 19:59:46 train_lshot.py:257] INFO Epoch: [46][40/150] Time 0.621 (0.837) Data 0.000 (0.216) Loss 0.6596 (0.6657) Prec@1 82.031 (81.517) Prec@5 95.703 (94.912)
[2021-04-26 19:59:53 train_lshot.py:257] INFO Epoch: [46][50/150] Time 0.618 (0.795) Data 0.000 (0.174) Loss 0.5642 (0.6484) Prec@1 83.984 (81.832) Prec@5 95.312 (95.136)
[2021-04-26 19:59:59 train_lshot.py:257] INFO Epoch: [46][60/150] Time 0.619 (0.767) Data 0.000 (0.145) Loss 0.5304 (0.6371) Prec@1 84.375 (82.243) Prec@5 95.703 (95.345)
[2021-04-26 20:00:05 train_lshot.py:257] INFO Epoch: [46][70/150] Time 0.628 (0.747) Data 0.002 (0.125) Loss 0.6177 (0.6295) Prec@1 83.984 (82.328) Prec@5 94.922 (95.500)
[2021-04-26 20:00:11 train_lshot.py:257] INFO Epoch: [46][80/150] Time 0.621 (0.731) Data 0.000 (0.109) Loss 0.5901 (0.6296) Prec@1 87.109 (82.441) Prec@5 95.312 (95.486)
[2021-04-26 20:00:17 train_lshot.py:257] INFO Epoch: [46][90/150] Time 0.624 (0.719) Data 0.000 (0.097) Loss 0.4938 (0.6183) Prec@1 85.938 (82.744) Prec@5 96.094 (95.557)
[2021-04-26 20:00:24 train_lshot.py:257] INFO Epoch: [46][100/150] Time 0.621 (0.709) Data 0.000 (0.088) Loss 0.4798 (0.6115) Prec@1 87.109 (82.882) Prec@5 97.656 (95.614)
[2021-04-26 20:00:30 train_lshot.py:257] INFO Epoch: [46][110/150] Time 0.620 (0.701) Data 0.000 (0.080) Loss 0.5972 (0.6092) Prec@1 82.422 (82.936) Prec@5 95.703 (95.619)
[2021-04-26 20:00:36 train_lshot.py:257] INFO Epoch: [46][120/150] Time 0.618 (0.694) Data 0.000 (0.073) Loss 0.7392 (0.6083) Prec@1 82.031 (83.035) Prec@5 94.141 (95.626)
[2021-04-26 20:00:42 train_lshot.py:257] INFO Epoch: [46][130/150] Time 0.618 (0.689) Data 0.000 (0.068) Loss 0.5742 (0.6045) Prec@1 83.984 (83.138) Prec@5 97.656 (95.670)
[2021-04-26 20:00:48 train_lshot.py:257] INFO Epoch: [46][140/150] Time 0.620 (0.684) Data 0.000 (0.063) Loss 0.6102 (0.5991) Prec@1 82.422 (83.317) Prec@5 94.922 (95.734)
[2021-04-26 20:01:03 train_lshot.py:257] INFO Epoch: [47][0/150] Time 9.008 (9.008) Data 8.357 (8.357) Loss 0.4804 (0.4804) Prec@1 85.547 (85.547) Prec@5 97.266 (97.266)
[2021-04-26 20:01:10 train_lshot.py:257] INFO Epoch: [47][10/150] Time 0.619 (1.386) Data 0.001 (0.765) Loss 0.4997 (0.5577) Prec@1 85.938 (84.837) Prec@5 96.875 (96.023)
[2021-04-26 20:01:16 train_lshot.py:257] INFO Epoch: [47][20/150] Time 0.624 (1.022) Data 0.001 (0.401) Loss 0.5795 (0.5600) Prec@1 86.328 (84.952) Prec@5 94.922 (95.945)
[2021-04-26 20:01:22 train_lshot.py:257] INFO Epoch: [47][30/150] Time 0.621 (0.893) Data 0.001 (0.272) Loss 0.5409 (0.5444) Prec@1 84.766 (85.244) Prec@5 97.656 (96.258)
[2021-04-26 20:01:28 train_lshot.py:257] INFO Epoch: [47][40/150] Time 0.623 (0.827) Data 0.000 (0.206) Loss 0.4965 (0.5501) Prec@1 87.500 (85.032) Prec@5 96.484 (96.246)
[2021-04-26 20:01:35 train_lshot.py:257] INFO Epoch: [47][50/150] Time 0.618 (0.786) Data 0.000 (0.165) Loss 0.4935 (0.5467) Prec@1 85.156 (85.164) Prec@5 98.047 (96.293)
[2021-04-26 20:01:41 train_lshot.py:257] INFO Epoch: [47][60/150] Time 0.622 (0.759) Data 0.000 (0.138) Loss 0.5703 (0.5468) Prec@1 84.375 (85.195) Prec@5 94.922 (96.158)
[2021-04-26 20:01:47 train_lshot.py:257] INFO Epoch: [47][70/150] Time 0.619 (0.740) Data 0.002 (0.119) Loss 0.5279 (0.5385) Prec@1 84.766 (85.404) Prec@5 96.484 (96.270)
[2021-04-26 20:01:53 train_lshot.py:257] INFO Epoch: [47][80/150] Time 0.623 (0.725) Data 0.000 (0.104) Loss 0.5610 (0.5369) Prec@1 84.375 (85.470) Prec@5 94.922 (96.209)
[2021-04-26 20:01:59 train_lshot.py:257] INFO Epoch: [47][90/150] Time 0.625 (0.714) Data 0.000 (0.093) Loss 0.4925 (0.5394) Prec@1 87.891 (85.362) Prec@5 96.094 (96.180)
[2021-04-26 20:02:06 train_lshot.py:257] INFO Epoch: [47][100/150] Time 0.625 (0.704) Data 0.000 (0.084) Loss 0.5334 (0.5376) Prec@1 85.938 (85.442) Prec@5 97.266 (96.179)
[2021-04-26 20:02:12 train_lshot.py:257] INFO Epoch: [47][110/150] Time 0.623 (0.697) Data 0.000 (0.076) Loss 0.5452 (0.5379) Prec@1 85.156 (85.420) Prec@5 96.094 (96.147)
[2021-04-26 20:02:18 train_lshot.py:257] INFO Epoch: [47][120/150] Time 0.620 (0.691) Data 0.000 (0.070) Loss 0.5781 (0.5381) Prec@1 83.203 (85.363) Prec@5 96.875 (96.155)
[2021-04-26 20:02:24 train_lshot.py:257] INFO Epoch: [47][130/150] Time 0.618 (0.685) Data 0.000 (0.065) Loss 0.5283 (0.5372) Prec@1 84.766 (85.419) Prec@5 97.656 (96.171)
[2021-04-26 20:02:30 train_lshot.py:257] INFO Epoch: [47][140/150] Time 0.622 (0.681) Data 0.000 (0.060) Loss 0.5819 (0.5376) Prec@1 83.984 (85.383) Prec@5 96.484 (96.152)
[2021-04-26 20:03:21 train_lshot.py:119] INFO Meta Val 47: 0.6169866805076599
[2021-04-26 20:03:31 train_lshot.py:257] INFO Epoch: [48][0/150] Time 9.378 (9.378) Data 8.719 (8.719) Loss 0.5333 (0.5333) Prec@1 85.156 (85.156) Prec@5 96.094 (96.094)
[2021-04-26 20:03:38 train_lshot.py:257] INFO Epoch: [48][10/150] Time 0.615 (1.413) Data 0.000 (0.793) Loss 0.4775 (0.5027) Prec@1 88.672 (86.186) Prec@5 96.875 (96.058)
[2021-04-26 20:03:44 train_lshot.py:257] INFO Epoch: [48][20/150] Time 0.620 (1.036) Data 0.000 (0.416) Loss 0.6420 (0.5349) Prec@1 81.641 (85.417) Prec@5 96.875 (95.889)
[2021-04-26 20:03:50 train_lshot.py:257] INFO Epoch: [48][30/150] Time 0.620 (0.902) Data 0.000 (0.282) Loss 0.4524 (0.5236) Prec@1 88.281 (85.786) Prec@5 98.047 (96.169)
[2021-04-26 20:03:56 train_lshot.py:257] INFO Epoch: [48][40/150] Time 0.619 (0.834) Data 0.001 (0.213) Loss 0.4854 (0.5261) Prec@1 87.109 (85.823) Prec@5 97.266 (96.160)
[2021-04-26 20:04:02 train_lshot.py:257] INFO Epoch: [48][50/150] Time 0.621 (0.793) Data 0.001 (0.172) Loss 0.4891 (0.5271) Prec@1 88.281 (85.861) Prec@5 98.047 (96.209)
[2021-04-26 20:04:09 train_lshot.py:257] INFO Epoch: [48][60/150] Time 0.621 (0.765) Data 0.000 (0.144) Loss 0.5245 (0.5292) Prec@1 85.547 (85.816) Prec@5 95.703 (96.196)
[2021-04-26 20:04:15 train_lshot.py:257] INFO Epoch: [48][70/150] Time 0.622 (0.745) Data 0.001 (0.123) Loss 0.3997 (0.5270) Prec@1 89.844 (85.822) Prec@5 97.656 (96.182)
[2021-04-26 20:04:21 train_lshot.py:257] INFO Epoch: [48][80/150] Time 0.618 (0.730) Data 0.000 (0.108) Loss 0.4663 (0.5251) Prec@1 89.453 (85.942) Prec@5 96.094 (96.267)
[2021-04-26 20:04:27 train_lshot.py:257] INFO Epoch: [48][90/150] Time 0.621 (0.718) Data 0.000 (0.096) Loss 0.4689 (0.5216) Prec@1 87.891 (86.062) Prec@5 96.875 (96.317)
[2021-04-26 20:04:34 train_lshot.py:257] INFO Epoch: [48][100/150] Time 0.619 (0.708) Data 0.000 (0.087) Loss 0.4322 (0.5243) Prec@1 87.500 (85.968) Prec@5 96.484 (96.318)
[2021-04-26 20:04:40 train_lshot.py:257] INFO Epoch: [48][110/150] Time 0.617 (0.700) Data 0.000 (0.079) Loss 0.5177 (0.5199) Prec@1 85.156 (86.099) Prec@5 95.703 (96.386)
[2021-04-26 20:04:46 train_lshot.py:257] INFO Epoch: [48][120/150] Time 0.623 (0.694) Data 0.000 (0.073) Loss 0.4426 (0.5179) Prec@1 89.453 (86.147) Prec@5 96.484 (96.413)
[2021-04-26 20:04:52 train_lshot.py:257] INFO Epoch: [48][130/150] Time 0.620 (0.688) Data 0.000 (0.067) Loss 0.4940 (0.5149) Prec@1 86.328 (86.164) Prec@5 96.875 (96.461)
[2021-04-26 20:04:58 train_lshot.py:257] INFO Epoch: [48][140/150] Time 0.621 (0.683) Data 0.000 (0.062) Loss 0.6090 (0.5162) Prec@1 83.984 (86.137) Prec@5 95.703 (96.451)
[2021-04-26 20:05:14 train_lshot.py:257] INFO Epoch: [49][0/150] Time 9.539 (9.539) Data 8.889 (8.889) Loss 0.4740 (0.4740) Prec@1 88.672 (88.672) Prec@5 97.266 (97.266)
[2021-04-26 20:05:20 train_lshot.py:257] INFO Epoch: [49][10/150] Time 0.616 (1.430) Data 0.000 (0.809) Loss 0.6048 (0.5107) Prec@1 82.812 (86.328) Prec@5 94.531 (96.413)
[2021-04-26 20:05:26 train_lshot.py:257] INFO Epoch: [49][20/150] Time 0.618 (1.047) Data 0.000 (0.424) Loss 0.5178 (0.5054) Prec@1 86.719 (86.551) Prec@5 96.875 (96.522)
[2021-04-26 20:05:33 train_lshot.py:257] INFO Epoch: [49][30/150] Time 0.630 (0.911) Data 0.001 (0.287) Loss 0.5702 (0.5036) Prec@1 84.375 (86.467) Prec@5 94.531 (96.535)
[2021-04-26 20:05:39 train_lshot.py:257] INFO Epoch: [49][40/150] Time 0.619 (0.840) Data 0.000 (0.217) Loss 0.3372 (0.5026) Prec@1 89.844 (86.500) Prec@5 97.266 (96.446)
[2021-04-26 20:05:45 train_lshot.py:257] INFO Epoch: [49][50/150] Time 0.631 (0.798) Data 0.001 (0.175) Loss 0.4974 (0.5011) Prec@1 86.328 (86.558) Prec@5 96.875 (96.477)
[2021-04-26 20:05:51 train_lshot.py:257] INFO Epoch: [49][60/150] Time 0.626 (0.769) Data 0.001 (0.146) Loss 0.5543 (0.5007) Prec@1 85.547 (86.482) Prec@5 92.969 (96.433)
[2021-04-26 20:05:58 train_lshot.py:257] INFO Epoch: [49][70/150] Time 0.621 (0.748) Data 0.001 (0.126) Loss 0.4547 (0.4957) Prec@1 89.453 (86.664) Prec@5 97.266 (96.517)
[2021-04-26 20:06:04 train_lshot.py:257] INFO Epoch: [49][80/150] Time 0.618 (0.733) Data 0.001 (0.110) Loss 0.4479 (0.4916) Prec@1 88.672 (86.704) Prec@5 97.656 (96.586)
[2021-04-26 20:06:10 train_lshot.py:257] INFO Epoch: [49][90/150] Time 0.621 (0.720) Data 0.000 (0.098) Loss 0.4703 (0.4886) Prec@1 86.719 (86.732) Prec@5 96.875 (96.626)
[2021-04-26 20:06:16 train_lshot.py:257] INFO Epoch: [49][100/150] Time 0.621 (0.711) Data 0.000 (0.088) Loss 0.4704 (0.4884) Prec@1 87.500 (86.746) Prec@5 97.266 (96.639)
[2021-04-26 20:06:22 train_lshot.py:257] INFO Epoch: [49][110/150] Time 0.620 (0.702) Data 0.000 (0.081) Loss 0.4696 (0.4896) Prec@1 87.500 (86.666) Prec@5 97.266 (96.632)
[2021-04-26 20:06:29 train_lshot.py:257] INFO Epoch: [49][120/150] Time 0.619 (0.696) Data 0.000 (0.074) Loss 0.4753 (0.4916) Prec@1 91.016 (86.651) Prec@5 96.094 (96.597)
[2021-04-26 20:06:35 train_lshot.py:257] INFO Epoch: [49][130/150] Time 0.619 (0.690) Data 0.000 (0.068) Loss 0.5398 (0.4964) Prec@1 87.109 (86.492) Prec@5 94.922 (96.553)
[2021-04-26 20:06:41 train_lshot.py:257] INFO Epoch: [49][140/150] Time 0.622 (0.685) Data 0.000 (0.063) Loss 0.4506 (0.4953) Prec@1 86.719 (86.519) Prec@5 97.656 (96.565)
[2021-04-26 20:06:57 train_lshot.py:257] INFO Epoch: [50][0/150] Time 9.744 (9.744) Data 9.088 (9.088) Loss 0.3889 (0.3889) Prec@1 91.406 (91.406) Prec@5 97.656 (97.656)
[2021-04-26 20:07:03 train_lshot.py:257] INFO Epoch: [50][10/150] Time 0.621 (1.448) Data 0.000 (0.827) Loss 0.5171 (0.4576) Prec@1 87.109 (87.216) Prec@5 95.312 (97.230)
[2021-04-26 20:07:09 train_lshot.py:257] INFO Epoch: [50][20/150] Time 0.621 (1.054) Data 0.000 (0.433) Loss 0.4389 (0.4498) Prec@1 88.672 (87.705) Prec@5 97.266 (97.191)
[2021-04-26 20:07:15 train_lshot.py:257] INFO Epoch: [50][30/150] Time 0.617 (0.915) Data 0.000 (0.294) Loss 0.5604 (0.4516) Prec@1 85.547 (87.613) Prec@5 94.922 (97.165)
[2021-04-26 20:07:22 train_lshot.py:257] INFO Epoch: [50][40/150] Time 0.623 (0.843) Data 0.001 (0.222) Loss 0.3806 (0.4605) Prec@1 89.062 (87.376) Prec@5 97.656 (97.046)
[2021-04-26 20:07:28 train_lshot.py:257] INFO Epoch: [50][50/150] Time 0.619 (0.800) Data 0.000 (0.179) Loss 0.5345 (0.4645) Prec@1 84.766 (87.171) Prec@5 96.094 (97.051)
[2021-04-26 20:07:34 train_lshot.py:257] INFO Epoch: [50][60/150] Time 0.621 (0.771) Data 0.000 (0.150) Loss 0.5042 (0.4736) Prec@1 86.328 (86.981) Prec@5 96.875 (96.894)
[2021-04-26 20:07:40 train_lshot.py:257] INFO Epoch: [50][70/150] Time 0.621 (0.750) Data 0.001 (0.129) Loss 0.5416 (0.4763) Prec@1 83.594 (86.779) Prec@5 96.094 (96.869)
[2021-04-26 20:07:46 train_lshot.py:257] INFO Epoch: [50][80/150] Time 0.623 (0.734) Data 0.000 (0.113) Loss 0.5218 (0.4779) Prec@1 86.719 (86.796) Prec@5 95.703 (96.865)
[2021-04-26 20:07:53 train_lshot.py:257] INFO Epoch: [50][90/150] Time 0.616 (0.722) Data 0.000 (0.100) Loss 0.4658 (0.4750) Prec@1 86.719 (86.908) Prec@5 97.266 (96.879)
[2021-04-26 20:07:59 train_lshot.py:257] INFO Epoch: [50][100/150] Time 0.621 (0.712) Data 0.000 (0.090) Loss 0.5355 (0.4805) Prec@1 85.547 (86.800) Prec@5 94.922 (96.751)
[2021-04-26 20:08:05 train_lshot.py:257] INFO Epoch: [50][110/150] Time 0.621 (0.704) Data 0.000 (0.082) Loss 0.4481 (0.4804) Prec@1 88.281 (86.800) Prec@5 97.656 (96.745)
[2021-04-26 20:08:11 train_lshot.py:257] INFO Epoch: [50][120/150] Time 0.623 (0.697) Data 0.000 (0.076) Loss 0.5035 (0.4800) Prec@1 85.938 (86.848) Prec@5 98.047 (96.759)
[2021-04-26 20:08:17 train_lshot.py:257] INFO Epoch: [50][130/150] Time 0.624 (0.691) Data 0.000 (0.070) Loss 0.6355 (0.4819) Prec@1 84.766 (86.808) Prec@5 93.750 (96.741)
[2021-04-26 20:08:24 train_lshot.py:257] INFO Epoch: [50][140/150] Time 0.619 (0.686) Data 0.000 (0.065) Loss 0.5280 (0.4811) Prec@1 85.938 (86.791) Prec@5 96.875 (96.772)
[2021-04-26 20:08:40 train_lshot.py:257] INFO Epoch: [51][0/150] Time 10.370 (10.370) Data 9.707 (9.707) Loss 0.5253 (0.5253) Prec@1 86.328 (86.328) Prec@5 98.047 (98.047)
[2021-04-26 20:08:46 train_lshot.py:257] INFO Epoch: [51][10/150] Time 0.615 (1.505) Data 0.000 (0.883) Loss 0.5199 (0.5135) Prec@1 87.500 (86.470) Prec@5 94.922 (96.307)
[2021-04-26 20:08:52 train_lshot.py:257] INFO Epoch: [51][20/150] Time 0.620 (1.084) Data 0.000 (0.463) Loss 0.4620 (0.4951) Prec@1 88.281 (86.607) Prec@5 97.266 (96.577)
[2021-04-26 20:08:59 train_lshot.py:257] INFO Epoch: [51][30/150] Time 0.626 (0.936) Data 0.001 (0.314) Loss 0.4298 (0.4883) Prec@1 89.062 (86.820) Prec@5 97.656 (96.636)
[2021-04-26 20:09:05 train_lshot.py:257] INFO Epoch: [51][40/150] Time 0.620 (0.859) Data 0.000 (0.237) Loss 0.5265 (0.4897) Prec@1 86.719 (86.700) Prec@5 98.438 (96.703)
[2021-04-26 20:09:11 train_lshot.py:257] INFO Epoch: [51][50/150] Time 0.624 (0.813) Data 0.001 (0.191) Loss 0.5300 (0.4865) Prec@1 87.891 (86.673) Prec@5 97.266 (96.959)
[2021-04-26 20:09:17 train_lshot.py:257] INFO Epoch: [51][60/150] Time 0.648 (0.782) Data 0.000 (0.160) Loss 0.3443 (0.4765) Prec@1 91.406 (86.968) Prec@5 98.828 (96.977)
[2021-04-26 20:09:24 train_lshot.py:257] INFO Epoch: [51][70/150] Time 0.621 (0.760) Data 0.001 (0.137) Loss 0.4843 (0.4753) Prec@1 85.938 (87.016) Prec@5 97.266 (96.991)
[2021-04-26 20:09:30 train_lshot.py:257] INFO Epoch: [51][80/150] Time 0.619 (0.743) Data 0.000 (0.120) Loss 0.4201 (0.4708) Prec@1 89.844 (87.201) Prec@5 97.656 (97.005)
[2021-04-26 20:09:36 train_lshot.py:257] INFO Epoch: [51][90/150] Time 0.618 (0.730) Data 0.000 (0.107) Loss 0.5105 (0.4711) Prec@1 86.328 (87.161) Prec@5 96.094 (96.991)
[2021-04-26 20:09:42 train_lshot.py:257] INFO Epoch: [51][100/150] Time 0.622 (0.719) Data 0.000 (0.097) Loss 0.4788 (0.4705) Prec@1 87.109 (87.206) Prec@5 95.703 (96.979)
[2021-04-26 20:09:49 train_lshot.py:257] INFO Epoch: [51][110/150] Time 0.618 (0.710) Data 0.000 (0.088) Loss 0.4559 (0.4705) Prec@1 86.719 (87.148) Prec@5 97.656 (96.988)
[2021-04-26 20:09:55 train_lshot.py:257] INFO Epoch: [51][120/150] Time 0.621 (0.703) Data 0.000 (0.081) Loss 0.4579 (0.4708) Prec@1 86.719 (87.164) Prec@5 98.047 (96.985)
[2021-04-26 20:10:01 train_lshot.py:257] INFO Epoch: [51][130/150] Time 0.617 (0.696) Data 0.000 (0.075) Loss 0.5322 (0.4715) Prec@1 84.766 (87.127) Prec@5 96.094 (96.961)
[2021-04-26 20:10:07 train_lshot.py:257] INFO Epoch: [51][140/150] Time 0.618 (0.691) Data 0.000 (0.069) Loss 0.4223 (0.4714) Prec@1 90.625 (87.173) Prec@5 96.875 (96.944)
[2021-04-26 20:10:51 train_lshot.py:119] INFO Meta Val 51: 0.6235200133919716
[2021-04-26 20:11:02 train_lshot.py:257] INFO Epoch: [52][0/150] Time 9.813 (9.813) Data 9.177 (9.177) Loss 0.4129 (0.4129) Prec@1 90.625 (90.625) Prec@5 98.047 (98.047)
[2021-04-26 20:11:08 train_lshot.py:257] INFO Epoch: [52][10/150] Time 0.620 (1.456) Data 0.001 (0.835) Loss 0.5062 (0.4764) Prec@1 88.281 (87.145) Prec@5 95.703 (96.982)
[2021-04-26 20:11:14 train_lshot.py:257] INFO Epoch: [52][20/150] Time 0.620 (1.058) Data 0.001 (0.438) Loss 0.5220 (0.4765) Prec@1 85.938 (87.202) Prec@5 95.703 (96.801)
[2021-04-26 20:11:21 train_lshot.py:257] INFO Epoch: [52][30/150] Time 0.619 (0.918) Data 0.000 (0.297) Loss 0.5172 (0.4743) Prec@1 89.453 (87.412) Prec@5 96.094 (96.736)
[2021-04-26 20:11:27 train_lshot.py:257] INFO Epoch: [52][40/150] Time 0.621 (0.845) Data 0.001 (0.224) Loss 0.5365 (0.4646) Prec@1 83.594 (87.586) Prec@5 95.312 (96.846)
[2021-04-26 20:11:33 train_lshot.py:257] INFO Epoch: [52][50/150] Time 0.624 (0.802) Data 0.001 (0.181) Loss 0.4815 (0.4601) Prec@1 85.547 (87.691) Prec@5 97.266 (96.929)
[2021-04-26 20:11:39 train_lshot.py:257] INFO Epoch: [52][60/150] Time 0.619 (0.773) Data 0.001 (0.151) Loss 0.5490 (0.4581) Prec@1 85.938 (87.820) Prec@5 95.312 (96.958)
[2021-04-26 20:11:45 train_lshot.py:257] INFO Epoch: [52][70/150] Time 0.632 (0.751) Data 0.003 (0.130) Loss 0.4975 (0.4619) Prec@1 85.547 (87.660) Prec@5 95.703 (96.886)
[2021-04-26 20:11:52 train_lshot.py:257] INFO Epoch: [52][80/150] Time 0.619 (0.735) Data 0.000 (0.114) Loss 0.5286 (0.4631) Prec@1 87.109 (87.693) Prec@5 95.703 (96.851)
[2021-04-26 20:11:58 train_lshot.py:257] INFO Epoch: [52][90/150] Time 0.620 (0.723) Data 0.000 (0.101) Loss 0.3837 (0.4638) Prec@1 89.453 (87.629) Prec@5 98.047 (96.888)
[2021-04-26 20:12:04 train_lshot.py:257] INFO Epoch: [52][100/150] Time 0.621 (0.713) Data 0.000 (0.091) Loss 0.5145 (0.4678) Prec@1 85.547 (87.581) Prec@5 95.312 (96.852)
[2021-04-26 20:12:10 train_lshot.py:257] INFO Epoch: [52][110/150] Time 0.620 (0.704) Data 0.000 (0.083) Loss 0.5174 (0.4700) Prec@1 85.547 (87.440) Prec@5 95.312 (96.822)
[2021-04-26 20:12:16 train_lshot.py:257] INFO Epoch: [52][120/150] Time 0.618 (0.697) Data 0.000 (0.076) Loss 0.4175 (0.4698) Prec@1 90.625 (87.452) Prec@5 98.047 (96.830)
[2021-04-26 20:12:23 train_lshot.py:257] INFO Epoch: [52][130/150] Time 0.620 (0.691) Data 0.000 (0.071) Loss 0.4080 (0.4680) Prec@1 88.672 (87.479) Prec@5 97.266 (96.866)
[2021-04-26 20:12:29 train_lshot.py:257] INFO Epoch: [52][140/150] Time 0.621 (0.686) Data 0.000 (0.066) Loss 0.4065 (0.4678) Prec@1 90.234 (87.492) Prec@5 97.266 (96.867)
[2021-04-26 20:12:44 train_lshot.py:257] INFO Epoch: [53][0/150] Time 9.287 (9.287) Data 8.641 (8.641) Loss 0.5261 (0.5261) Prec@1 86.719 (86.719) Prec@5 96.875 (96.875)
[2021-04-26 20:12:50 train_lshot.py:257] INFO Epoch: [53][10/150] Time 0.623 (1.406) Data 0.000 (0.786) Loss 0.3942 (0.4550) Prec@1 90.234 (88.033) Prec@5 96.875 (96.733)
[2021-04-26 20:12:57 train_lshot.py:257] INFO Epoch: [53][20/150] Time 0.625 (1.032) Data 0.000 (0.412) Loss 0.4489 (0.4465) Prec@1 86.719 (88.188) Prec@5 95.703 (96.745)
[2021-04-26 20:13:03 train_lshot.py:257] INFO Epoch: [53][30/150] Time 0.625 (0.900) Data 0.001 (0.279) Loss 0.6246 (0.4640) Prec@1 84.766 (87.702) Prec@5 95.312 (96.535)
[2021-04-26 20:13:09 train_lshot.py:257] INFO Epoch: [53][40/150] Time 0.621 (0.832) Data 0.001 (0.211) Loss 0.4818 (0.4631) Prec@1 85.938 (87.681) Prec@5 97.266 (96.589)
[2021-04-26 20:13:15 train_lshot.py:257] INFO Epoch: [53][50/150] Time 0.620 (0.792) Data 0.000 (0.170) Loss 0.4725 (0.4592) Prec@1 88.672 (87.737) Prec@5 95.703 (96.706)
[2021-04-26 20:13:22 train_lshot.py:257] INFO Epoch: [53][60/150] Time 0.620 (0.764) Data 0.000 (0.142) Loss 0.3638 (0.4607) Prec@1 91.406 (87.692) Prec@5 97.656 (96.683)
[2021-04-26 20:13:28 train_lshot.py:257] INFO Epoch: [53][70/150] Time 0.624 (0.744) Data 0.001 (0.122) Loss 0.4229 (0.4639) Prec@1 87.109 (87.621) Prec@5 96.875 (96.644)
[2021-04-26 20:13:34 train_lshot.py:257] INFO Epoch: [53][80/150] Time 0.622 (0.729) Data 0.000 (0.107) Loss 0.5181 (0.4646) Prec@1 86.328 (87.606) Prec@5 96.484 (96.687)
[2021-04-26 20:13:40 train_lshot.py:257] INFO Epoch: [53][90/150] Time 0.624 (0.718) Data 0.000 (0.095) Loss 0.4111 (0.4642) Prec@1 87.109 (87.552) Prec@5 98.047 (96.699)
[2021-04-26 20:13:46 train_lshot.py:257] INFO Epoch: [53][100/150] Time 0.619 (0.708) Data 0.000 (0.086) Loss 0.3816 (0.4608) Prec@1 91.016 (87.659) Prec@5 98.438 (96.720)
[2021-04-26 20:13:53 train_lshot.py:257] INFO Epoch: [53][110/150] Time 0.621 (0.700) Data 0.000 (0.078) Loss 0.5661 (0.4600) Prec@1 85.156 (87.651) Prec@5 94.922 (96.745)
[2021-04-26 20:13:59 train_lshot.py:257] INFO Epoch: [53][120/150] Time 0.621 (0.693) Data 0.000 (0.072) Loss 0.5450 (0.4612) Prec@1 85.156 (87.639) Prec@5 96.094 (96.752)
[2021-04-26 20:14:05 train_lshot.py:257] INFO Epoch: [53][130/150] Time 0.621 (0.688) Data 0.000 (0.066) Loss 0.4895 (0.4634) Prec@1 83.594 (87.527) Prec@5 96.875 (96.744)
[2021-04-26 20:14:11 train_lshot.py:257] INFO Epoch: [53][140/150] Time 0.624 (0.683) Data 0.000 (0.062) Loss 0.5051 (0.4638) Prec@1 87.109 (87.539) Prec@5 95.312 (96.717)
[2021-04-26 20:14:27 train_lshot.py:257] INFO Epoch: [54][0/150] Time 10.114 (10.114) Data 9.458 (9.458) Loss 0.4100 (0.4100) Prec@1 90.234 (90.234) Prec@5 96.484 (96.484)
[2021-04-26 20:14:34 train_lshot.py:257] INFO Epoch: [54][10/150] Time 0.623 (1.482) Data 0.000 (0.860) Loss 0.4524 (0.4627) Prec@1 86.719 (87.358) Prec@5 96.484 (96.839)
[2021-04-26 20:14:40 train_lshot.py:257] INFO Epoch: [54][20/150] Time 0.618 (1.072) Data 0.000 (0.451) Loss 0.5171 (0.4520) Prec@1 85.547 (87.593) Prec@5 96.875 (97.042)
[2021-04-26 20:14:46 train_lshot.py:257] INFO Epoch: [54][30/150] Time 0.622 (0.927) Data 0.000 (0.306) Loss 0.4588 (0.4397) Prec@1 87.109 (87.878) Prec@5 96.875 (97.215)
[2021-04-26 20:14:52 train_lshot.py:257] INFO Epoch: [54][40/150] Time 0.625 (0.853) Data 0.001 (0.231) Loss 0.5245 (0.4419) Prec@1 85.938 (87.776) Prec@5 96.094 (97.218)
[2021-04-26 20:14:58 train_lshot.py:257] INFO Epoch: [54][50/150] Time 0.621 (0.808) Data 0.001 (0.186) Loss 0.4413 (0.4425) Prec@1 87.891 (87.699) Prec@5 96.875 (97.174)
[2021-04-26 20:15:05 train_lshot.py:257] INFO Epoch: [54][60/150] Time 0.618 (0.778) Data 0.000 (0.156) Loss 0.4800 (0.4441) Prec@1 86.719 (87.718) Prec@5 96.484 (97.106)
[2021-04-26 20:15:11 train_lshot.py:257] INFO Epoch: [54][70/150] Time 0.863 (0.760) Data 0.238 (0.137) Loss 0.4436 (0.4459) Prec@1 87.109 (87.704) Prec@5 97.266 (97.051)
[2021-04-26 20:15:17 train_lshot.py:257] INFO Epoch: [54][80/150] Time 0.621 (0.744) Data 0.001 (0.120) Loss 0.4989 (0.4481) Prec@1 86.328 (87.669) Prec@5 96.094 (97.044)
[2021-04-26 20:15:24 train_lshot.py:257] INFO Epoch: [54][90/150] Time 0.619 (0.730) Data 0.000 (0.107) Loss 0.5530 (0.4503) Prec@1 85.938 (87.676) Prec@5 95.312 (97.008)
[2021-04-26 20:15:30 train_lshot.py:257] INFO Epoch: [54][100/150] Time 0.618 (0.719) Data 0.000 (0.097) Loss 0.5325 (0.4544) Prec@1 85.938 (87.612) Prec@5 95.312 (96.921)
[2021-04-26 20:15:36 train_lshot.py:257] INFO Epoch: [54][110/150] Time 0.621 (0.711) Data 0.000 (0.088) Loss 0.4369 (0.4530) Prec@1 88.281 (87.683) Prec@5 98.438 (96.963)
[2021-04-26 20:15:42 train_lshot.py:257] INFO Epoch: [54][120/150] Time 0.617 (0.703) Data 0.000 (0.081) Loss 0.5559 (0.4536) Prec@1 85.156 (87.668) Prec@5 96.484 (96.962)
[2021-04-26 20:15:49 train_lshot.py:257] INFO Epoch: [54][130/150] Time 0.621 (0.697) Data 0.000 (0.074) Loss 0.5167 (0.4558) Prec@1 86.328 (87.673) Prec@5 96.094 (96.920)
[2021-04-26 20:15:55 train_lshot.py:257] INFO Epoch: [54][140/150] Time 0.622 (0.691) Data 0.000 (0.069) Loss 0.4337 (0.4524) Prec@1 87.891 (87.763) Prec@5 97.266 (96.964)
[2021-04-26 20:16:10 train_lshot.py:257] INFO Epoch: [55][0/150] Time 8.942 (8.942) Data 8.288 (8.288) Loss 0.4255 (0.4255) Prec@1 89.453 (89.453) Prec@5 96.484 (96.484)
[2021-04-26 20:16:16 train_lshot.py:257] INFO Epoch: [55][10/150] Time 0.618 (1.377) Data 0.000 (0.754) Loss 0.4347 (0.4543) Prec@1 88.672 (88.033) Prec@5 96.875 (96.911)
[2021-04-26 20:16:22 train_lshot.py:257] INFO Epoch: [55][20/150] Time 0.620 (1.017) Data 0.000 (0.395) Loss 0.4203 (0.4493) Prec@1 88.281 (88.244) Prec@5 96.094 (96.838)
[2021-04-26 20:16:28 train_lshot.py:257] INFO Epoch: [55][30/150] Time 0.623 (0.889) Data 0.000 (0.268) Loss 0.3762 (0.4350) Prec@1 89.453 (88.458) Prec@5 97.266 (96.913)
[2021-04-26 20:16:35 train_lshot.py:257] INFO Epoch: [55][40/150] Time 0.618 (0.825) Data 0.000 (0.203) Loss 0.4215 (0.4341) Prec@1 88.672 (88.481) Prec@5 96.484 (97.037)
[2021-04-26 20:16:41 train_lshot.py:257] INFO Epoch: [55][50/150] Time 0.620 (0.785) Data 0.000 (0.163) Loss 0.4460 (0.4410) Prec@1 87.891 (88.197) Prec@5 96.484 (96.929)
[2021-04-26 20:16:47 train_lshot.py:257] INFO Epoch: [55][60/150] Time 0.620 (0.758) Data 0.000 (0.136) Loss 0.4836 (0.4437) Prec@1 87.109 (88.089) Prec@5 96.484 (96.894)
[2021-04-26 20:16:53 train_lshot.py:257] INFO Epoch: [55][70/150] Time 0.630 (0.739) Data 0.003 (0.117) Loss 0.4411 (0.4445) Prec@1 87.891 (88.028) Prec@5 97.266 (96.914)
[2021-04-26 20:16:59 train_lshot.py:257] INFO Epoch: [55][80/150] Time 0.622 (0.725) Data 0.000 (0.103) Loss 0.5760 (0.4497) Prec@1 85.547 (87.997) Prec@5 96.875 (96.822)
[2021-04-26 20:17:06 train_lshot.py:257] INFO Epoch: [55][90/150] Time 0.622 (0.713) Data 0.000 (0.092) Loss 0.5429 (0.4510) Prec@1 83.203 (87.826) Prec@5 96.484 (96.823)
[2021-04-26 20:17:12 train_lshot.py:257] INFO Epoch: [55][100/150] Time 0.619 (0.704) Data 0.000 (0.083) Loss 0.5518 (0.4538) Prec@1 83.984 (87.782) Prec@5 94.922 (96.755)
[2021-04-26 20:17:18 train_lshot.py:257] INFO Epoch: [55][110/150] Time 0.622 (0.697) Data 0.000 (0.075) Loss 0.5779 (0.4562) Prec@1 83.984 (87.672) Prec@5 96.094 (96.727)
[2021-04-26 20:17:24 train_lshot.py:257] INFO Epoch: [55][120/150] Time 0.625 (0.690) Data 0.000 (0.069) Loss 0.4703 (0.4526) Prec@1 84.766 (87.732) Prec@5 96.875 (96.817)
[2021-04-26 20:17:31 train_lshot.py:257] INFO Epoch: [55][130/150] Time 0.618 (0.685) Data 0.000 (0.064) Loss 0.3696 (0.4522) Prec@1 90.625 (87.715) Prec@5 97.266 (96.839)
[2021-04-26 20:17:37 train_lshot.py:257] INFO Epoch: [55][140/150] Time 0.620 (0.680) Data 0.000 (0.059) Loss 0.4605 (0.4573) Prec@1 84.766 (87.544) Prec@5 97.656 (96.822)
[2021-04-26 20:18:23 train_lshot.py:119] INFO Meta Val 55: 0.6308266792297363
[2021-04-26 20:18:34 train_lshot.py:257] INFO Epoch: [56][0/150] Time 9.771 (9.771) Data 9.125 (9.125) Loss 0.4268 (0.4268) Prec@1 86.719 (86.719) Prec@5 96.484 (96.484)
[2021-04-26 20:18:40 train_lshot.py:257] INFO Epoch: [56][10/150] Time 0.615 (1.450) Data 0.000 (0.830) Loss 0.4663 (0.4255) Prec@1 87.500 (88.530) Prec@5 96.875 (97.088)
[2021-04-26 20:18:46 train_lshot.py:257] INFO Epoch: [56][20/150] Time 0.614 (1.054) Data 0.000 (0.435) Loss 0.3416 (0.4293) Prec@1 89.062 (88.132) Prec@5 98.438 (97.173)
[2021-04-26 20:18:52 train_lshot.py:257] INFO Epoch: [56][30/150] Time 0.619 (0.915) Data 0.001 (0.295) Loss 0.4890 (0.4390) Prec@1 86.719 (87.840) Prec@5 95.312 (97.014)
[2021-04-26 20:18:59 train_lshot.py:257] INFO Epoch: [56][40/150] Time 0.632 (0.843) Data 0.001 (0.223) Loss 0.4519 (0.4375) Prec@1 87.891 (87.891) Prec@5 97.266 (97.046)
[2021-04-26 20:19:05 train_lshot.py:257] INFO Epoch: [56][50/150] Time 0.616 (0.800) Data 0.000 (0.180) Loss 0.4817 (0.4409) Prec@1 87.109 (87.845) Prec@5 95.312 (96.967)
[2021-04-26 20:19:11 train_lshot.py:257] INFO Epoch: [56][60/150] Time 0.617 (0.771) Data 0.000 (0.150) Loss 0.4474 (0.4384) Prec@1 89.062 (88.032) Prec@5 96.484 (96.907)
[2021-04-26 20:19:17 train_lshot.py:257] INFO Epoch: [56][70/150] Time 0.617 (0.750) Data 0.001 (0.129) Loss 0.3428 (0.4382) Prec@1 90.625 (88.072) Prec@5 98.828 (96.925)
[2021-04-26 20:19:23 train_lshot.py:257] INFO Epoch: [56][80/150] Time 0.621 (0.734) Data 0.000 (0.113) Loss 0.4517 (0.4411) Prec@1 88.281 (88.093) Prec@5 96.875 (96.904)
[2021-04-26 20:19:30 train_lshot.py:257] INFO Epoch: [56][90/150] Time 0.620 (0.721) Data 0.000 (0.101) Loss 0.3684 (0.4414) Prec@1 92.188 (88.148) Prec@5 97.656 (96.935)
[2021-04-26 20:19:36 train_lshot.py:257] INFO Epoch: [56][100/150] Time 0.618 (0.711) Data 0.000 (0.091) Loss 0.5083 (0.4400) Prec@1 85.547 (88.119) Prec@5 96.484 (96.945)
[2021-04-26 20:19:42 train_lshot.py:257] INFO Epoch: [56][110/150] Time 0.620 (0.703) Data 0.000 (0.083) Loss 0.4598 (0.4406) Prec@1 87.500 (88.123) Prec@5 96.875 (96.942)
[2021-04-26 20:19:48 train_lshot.py:257] INFO Epoch: [56][120/150] Time 0.619 (0.696) Data 0.000 (0.076) Loss 0.3655 (0.4388) Prec@1 92.578 (88.155) Prec@5 97.266 (96.985)
[2021-04-26 20:19:54 train_lshot.py:257] INFO Epoch: [56][130/150] Time 0.621 (0.690) Data 0.000 (0.070) Loss 0.3983 (0.4391) Prec@1 88.281 (88.105) Prec@5 98.828 (97.030)
[2021-04-26 20:20:01 train_lshot.py:257] INFO Epoch: [56][140/150] Time 0.622 (0.685) Data 0.000 (0.065) Loss 0.4823 (0.4413) Prec@1 88.281 (88.071) Prec@5 94.922 (96.989)
[2021-04-26 20:20:16 train_lshot.py:257] INFO Epoch: [57][0/150] Time 9.928 (9.928) Data 9.259 (9.259) Loss 0.3137 (0.3137) Prec@1 92.188 (92.188) Prec@5 98.438 (98.438)
[2021-04-26 20:20:23 train_lshot.py:257] INFO Epoch: [57][10/150] Time 0.617 (1.464) Data 0.001 (0.842) Loss 0.4106 (0.4405) Prec@1 87.891 (87.891) Prec@5 98.438 (97.301)
[2021-04-26 20:20:29 train_lshot.py:257] INFO Epoch: [57][20/150] Time 0.615 (1.064) Data 0.000 (0.441) Loss 0.4735 (0.4390) Prec@1 87.109 (88.039) Prec@5 97.656 (97.173)
[2021-04-26 20:20:35 train_lshot.py:257] INFO Epoch: [57][30/150] Time 0.623 (0.921) Data 0.000 (0.299) Loss 0.3423 (0.4279) Prec@1 90.625 (88.445) Prec@5 98.438 (97.152)
[2021-04-26 20:20:41 train_lshot.py:257] INFO Epoch: [57][40/150] Time 0.622 (0.849) Data 0.001 (0.226) Loss 0.4437 (0.4372) Prec@1 87.891 (88.272) Prec@5 97.266 (96.942)
[2021-04-26 20:20:48 train_lshot.py:257] INFO Epoch: [57][50/150] Time 0.622 (0.804) Data 0.000 (0.182) Loss 0.5062 (0.4394) Prec@1 89.062 (88.320) Prec@5 95.703 (96.944)
[2021-04-26 20:20:54 train_lshot.py:257] INFO Epoch: [57][60/150] Time 0.626 (0.774) Data 0.001 (0.152) Loss 0.4808 (0.4398) Prec@1 86.719 (88.224) Prec@5 97.266 (96.990)
[2021-04-26 20:21:00 train_lshot.py:257] INFO Epoch: [57][70/150] Time 0.624 (0.753) Data 0.002 (0.131) Loss 0.3651 (0.4394) Prec@1 89.062 (88.116) Prec@5 98.047 (96.991)
[2021-04-26 20:21:06 train_lshot.py:257] INFO Epoch: [57][80/150] Time 0.622 (0.736) Data 0.000 (0.115) Loss 0.4311 (0.4381) Prec@1 88.281 (88.175) Prec@5 97.266 (97.010)
[2021-04-26 20:21:12 train_lshot.py:257] INFO Epoch: [57][90/150] Time 0.623 (0.724) Data 0.000 (0.102) Loss 0.4632 (0.4387) Prec@1 87.109 (88.161) Prec@5 97.656 (97.017)
[2021-04-26 20:21:19 train_lshot.py:257] INFO Epoch: [57][100/150] Time 0.625 (0.714) Data 0.000 (0.092) Loss 0.3763 (0.4346) Prec@1 91.016 (88.270) Prec@5 97.266 (97.080)
[2021-04-26 20:21:25 train_lshot.py:257] INFO Epoch: [57][110/150] Time 0.620 (0.705) Data 0.000 (0.084) Loss 0.4797 (0.4369) Prec@1 87.500 (88.172) Prec@5 95.312 (97.051)
[2021-04-26 20:21:31 train_lshot.py:257] INFO Epoch: [57][120/150] Time 0.618 (0.698) Data 0.000 (0.077) Loss 0.4857 (0.4370) Prec@1 85.938 (88.184) Prec@5 97.656 (97.088)
[2021-04-26 20:21:37 train_lshot.py:257] INFO Epoch: [57][130/150] Time 0.618 (0.692) Data 0.000 (0.071) Loss 0.4005 (0.4368) Prec@1 87.891 (88.120) Prec@5 98.438 (97.087)
[2021-04-26 20:21:43 train_lshot.py:257] INFO Epoch: [57][140/150] Time 0.618 (0.687) Data 0.000 (0.066) Loss 0.4423 (0.4359) Prec@1 87.891 (88.146) Prec@5 97.656 (97.091)
[2021-04-26 20:22:00 train_lshot.py:257] INFO Epoch: [58][0/150] Time 10.494 (10.494) Data 9.846 (9.846) Loss 0.3807 (0.3807) Prec@1 87.500 (87.500) Prec@5 97.656 (97.656)
[2021-04-26 20:22:06 train_lshot.py:257] INFO Epoch: [58][10/150] Time 0.629 (1.517) Data 0.000 (0.895) Loss 0.4600 (0.4218) Prec@1 87.109 (88.885) Prec@5 95.703 (97.088)
[2021-04-26 20:22:12 train_lshot.py:257] INFO Epoch: [58][20/150] Time 0.624 (1.089) Data 0.000 (0.469) Loss 0.3094 (0.4193) Prec@1 92.188 (88.672) Prec@5 99.609 (97.228)
[2021-04-26 20:22:19 train_lshot.py:257] INFO Epoch: [58][30/150] Time 0.620 (0.939) Data 0.001 (0.318) Loss 0.4436 (0.4159) Prec@1 88.672 (88.647) Prec@5 97.656 (97.392)
[2021-04-26 20:22:25 train_lshot.py:257] INFO Epoch: [58][40/150] Time 0.621 (0.862) Data 0.001 (0.241) Loss 0.4721 (0.4215) Prec@1 85.938 (88.453) Prec@5 96.875 (97.256)
[2021-04-26 20:22:31 train_lshot.py:257] INFO Epoch: [58][50/150] Time 0.621 (0.815) Data 0.000 (0.194) Loss 0.4060 (0.4217) Prec@1 89.453 (88.366) Prec@5 97.656 (97.266)
[2021-04-26 20:22:37 train_lshot.py:257] INFO Epoch: [58][60/150] Time 0.620 (0.784) Data 0.000 (0.162) Loss 0.3952 (0.4226) Prec@1 89.453 (88.397) Prec@5 96.875 (97.259)
[2021-04-26 20:22:43 train_lshot.py:257] INFO Epoch: [58][70/150] Time 0.620 (0.761) Data 0.001 (0.139) Loss 0.3707 (0.4190) Prec@1 89.062 (88.479) Prec@5 97.656 (97.343)
[2021-04-26 20:22:50 train_lshot.py:257] INFO Epoch: [58][80/150] Time 0.619 (0.744) Data 0.000 (0.122) Loss 0.4261 (0.4242) Prec@1 89.844 (88.392) Prec@5 96.484 (97.232)
[2021-04-26 20:22:56 train_lshot.py:257] INFO Epoch: [58][90/150] Time 0.618 (0.730) Data 0.000 (0.109) Loss 0.3332 (0.4255) Prec@1 90.625 (88.397) Prec@5 98.047 (97.231)
[2021-04-26 20:23:02 train_lshot.py:257] INFO Epoch: [58][100/150] Time 0.617 (0.719) Data 0.000 (0.098) Loss 0.4454 (0.4233) Prec@1 88.672 (88.428) Prec@5 97.656 (97.250)
[2021-04-26 20:23:08 train_lshot.py:257] INFO Epoch: [58][110/150] Time 0.619 (0.710) Data 0.000 (0.089) Loss 0.4816 (0.4196) Prec@1 86.719 (88.499) Prec@5 96.094 (97.301)
[2021-04-26 20:23:14 train_lshot.py:257] INFO Epoch: [58][120/150] Time 0.622 (0.703) Data 0.000 (0.082) Loss 0.4523 (0.4196) Prec@1 89.844 (88.572) Prec@5 98.047 (97.291)
[2021-04-26 20:23:21 train_lshot.py:257] INFO Epoch: [58][130/150] Time 0.620 (0.697) Data 0.000 (0.076) Loss 0.4254 (0.4189) Prec@1 89.453 (88.612) Prec@5 97.266 (97.298)
[2021-04-26 20:23:27 train_lshot.py:257] INFO Epoch: [58][140/150] Time 0.620 (0.691) Data 0.000 (0.070) Loss 0.5273 (0.4206) Prec@1 86.328 (88.542) Prec@5 96.094 (97.266)
[2021-04-26 20:23:43 train_lshot.py:257] INFO Epoch: [59][0/150] Time 9.977 (9.977) Data 9.332 (9.332) Loss 0.3265 (0.3265) Prec@1 91.406 (91.406) Prec@5 98.438 (98.438)
[2021-04-26 20:23:49 train_lshot.py:257] INFO Epoch: [59][10/150] Time 0.620 (1.469) Data 0.000 (0.849) Loss 0.3912 (0.3972) Prec@1 89.453 (89.418) Prec@5 96.875 (97.230)
[2021-04-26 20:23:55 train_lshot.py:257] INFO Epoch: [59][20/150] Time 0.630 (1.066) Data 0.001 (0.445) Loss 0.5053 (0.4030) Prec@1 87.891 (89.044) Prec@5 96.484 (97.247)
[2021-04-26 20:24:01 train_lshot.py:257] INFO Epoch: [59][30/150] Time 0.625 (0.923) Data 0.000 (0.302) Loss 0.3897 (0.4100) Prec@1 91.016 (88.747) Prec@5 97.656 (97.240)
[2021-04-26 20:24:08 train_lshot.py:257] INFO Epoch: [59][40/150] Time 0.627 (0.850) Data 0.001 (0.228) Loss 0.4893 (0.4175) Prec@1 86.328 (88.624) Prec@5 95.312 (97.094)
[2021-04-26 20:24:14 train_lshot.py:257] INFO Epoch: [59][50/150] Time 0.621 (0.805) Data 0.001 (0.184) Loss 0.4591 (0.4186) Prec@1 89.062 (88.542) Prec@5 96.094 (97.128)
[2021-04-26 20:24:20 train_lshot.py:257] INFO Epoch: [59][60/150] Time 0.620 (0.775) Data 0.000 (0.154) Loss 0.3964 (0.4184) Prec@1 88.281 (88.563) Prec@5 97.656 (97.131)
[2021-04-26 20:24:26 train_lshot.py:257] INFO Epoch: [59][70/150] Time 0.629 (0.754) Data 0.001 (0.132) Loss 0.3326 (0.4126) Prec@1 91.406 (88.732) Prec@5 98.828 (97.255)
[2021-04-26 20:24:33 train_lshot.py:257] INFO Epoch: [59][80/150] Time 0.623 (0.737) Data 0.000 (0.116) Loss 0.4515 (0.4103) Prec@1 88.672 (88.845) Prec@5 96.484 (97.323)
[2021-04-26 20:24:39 train_lshot.py:257] INFO Epoch: [59][90/150] Time 0.619 (0.724) Data 0.000 (0.103) Loss 0.3416 (0.4125) Prec@1 88.672 (88.723) Prec@5 100.000 (97.356)
[2021-04-26 20:24:45 train_lshot.py:257] INFO Epoch: [59][100/150] Time 0.624 (0.714) Data 0.000 (0.093) Loss 0.4785 (0.4130) Prec@1 86.719 (88.819) Prec@5 96.484 (97.289)
[2021-04-26 20:24:51 train_lshot.py:257] INFO Epoch: [59][110/150] Time 0.622 (0.706) Data 0.000 (0.085) Loss 0.3709 (0.4150) Prec@1 90.234 (88.799) Prec@5 98.828 (97.248)
[2021-04-26 20:24:57 train_lshot.py:257] INFO Epoch: [59][120/150] Time 0.624 (0.699) Data 0.000 (0.078) Loss 0.4354 (0.4185) Prec@1 87.891 (88.707) Prec@5 97.266 (97.224)
[2021-04-26 20:25:04 train_lshot.py:257] INFO Epoch: [59][130/150] Time 0.626 (0.693) Data 0.000 (0.072) Loss 0.4032 (0.4184) Prec@1 89.062 (88.723) Prec@5 97.656 (97.203)
[2021-04-26 20:25:10 train_lshot.py:257] INFO Epoch: [59][140/150] Time 0.620 (0.688) Data 0.000 (0.067) Loss 0.3916 (0.4209) Prec@1 89.844 (88.630) Prec@5 98.047 (97.194)
[2021-04-26 20:25:54 train_lshot.py:119] INFO Meta Val 59: 0.6240800119638443
[2021-04-26 20:26:04 train_lshot.py:257] INFO Epoch: [60][0/150] Time 9.894 (9.894) Data 9.263 (9.263) Loss 0.5105 (0.5105) Prec@1 88.672 (88.672) Prec@5 96.094 (96.094)
[2021-04-26 20:26:10 train_lshot.py:257] INFO Epoch: [60][10/150] Time 0.617 (1.471) Data 0.000 (0.853) Loss 0.4306 (0.4383) Prec@1 86.328 (88.068) Prec@5 97.656 (97.088)
[2021-04-26 20:26:16 train_lshot.py:257] INFO Epoch: [60][20/150] Time 0.618 (1.067) Data 0.000 (0.447) Loss 0.3801 (0.4225) Prec@1 89.062 (88.542) Prec@5 97.266 (96.931)
[2021-04-26 20:26:22 train_lshot.py:257] INFO Epoch: [60][30/150] Time 0.620 (0.923) Data 0.000 (0.303) Loss 0.3952 (0.4125) Prec@1 88.281 (88.710) Prec@5 97.656 (97.127)
[2021-04-26 20:26:29 train_lshot.py:257] INFO Epoch: [60][40/150] Time 0.619 (0.850) Data 0.000 (0.229) Loss 0.4405 (0.4103) Prec@1 86.719 (88.796) Prec@5 96.875 (97.313)
[2021-04-26 20:26:35 train_lshot.py:257] INFO Epoch: [60][50/150] Time 0.627 (0.806) Data 0.001 (0.185) Loss 0.4061 (0.4117) Prec@1 87.891 (88.764) Prec@5 97.266 (97.273)
[2021-04-26 20:26:41 train_lshot.py:257] INFO Epoch: [60][60/150] Time 0.621 (0.776) Data 0.001 (0.154) Loss 0.6031 (0.4136) Prec@1 82.031 (88.768) Prec@5 94.531 (97.157)
[2021-04-26 20:26:47 train_lshot.py:257] INFO Epoch: [60][70/150] Time 0.618 (0.754) Data 0.001 (0.133) Loss 0.4740 (0.4179) Prec@1 87.500 (88.661) Prec@5 96.484 (97.123)
[2021-04-26 20:26:54 train_lshot.py:257] INFO Epoch: [60][80/150] Time 0.621 (0.737) Data 0.000 (0.116) Loss 0.4633 (0.4193) Prec@1 86.328 (88.590) Prec@5 95.703 (97.140)
[2021-04-26 20:27:00 train_lshot.py:257] INFO Epoch: [60][90/150] Time 0.623 (0.725) Data 0.000 (0.104) Loss 0.4444 (0.4173) Prec@1 89.062 (88.650) Prec@5 96.484 (97.163)
[2021-04-26 20:27:06 train_lshot.py:257] INFO Epoch: [60][100/150] Time 0.620 (0.714) Data 0.000 (0.093) Loss 0.3892 (0.4179) Prec@1 91.406 (88.645) Prec@5 96.875 (97.150)
[2021-04-26 20:27:12 train_lshot.py:257] INFO Epoch: [60][110/150] Time 0.622 (0.706) Data 0.000 (0.085) Loss 0.4030 (0.4162) Prec@1 88.281 (88.658) Prec@5 96.875 (97.157)
[2021-04-26 20:27:18 train_lshot.py:257] INFO Epoch: [60][120/150] Time 0.622 (0.699) Data 0.000 (0.078) Loss 0.5009 (0.4191) Prec@1 83.203 (88.536) Prec@5 98.047 (97.140)
[2021-04-26 20:27:25 train_lshot.py:257] INFO Epoch: [60][130/150] Time 0.619 (0.693) Data 0.000 (0.072) Loss 0.2830 (0.4170) Prec@1 93.359 (88.603) Prec@5 98.438 (97.161)
[2021-04-26 20:27:31 train_lshot.py:257] INFO Epoch: [60][140/150] Time 0.620 (0.688) Data 0.000 (0.067) Loss 0.4240 (0.4154) Prec@1 89.844 (88.691) Prec@5 97.656 (97.185)
[2021-04-26 20:27:47 train_lshot.py:257] INFO Epoch: [61][0/150] Time 10.029 (10.029) Data 9.372 (9.372) Loss 0.3945 (0.3945) Prec@1 88.281 (88.281) Prec@5 96.875 (96.875)
[2021-04-26 20:27:53 train_lshot.py:257] INFO Epoch: [61][10/150] Time 0.620 (1.474) Data 0.000 (0.852) Loss 0.3555 (0.3938) Prec@1 91.016 (89.808) Prec@5 97.656 (97.550)
[2021-04-26 20:27:59 train_lshot.py:257] INFO Epoch: [61][20/150] Time 0.622 (1.068) Data 0.001 (0.447) Loss 0.3093 (0.4073) Prec@1 90.625 (89.156) Prec@5 98.828 (97.452)
[2021-04-26 20:28:05 train_lshot.py:257] INFO Epoch: [61][30/150] Time 0.622 (0.925) Data 0.000 (0.303) Loss 0.3667 (0.4097) Prec@1 90.234 (89.100) Prec@5 98.438 (97.354)
[2021-04-26 20:28:12 train_lshot.py:257] INFO Epoch: [61][40/150] Time 0.621 (0.851) Data 0.001 (0.229) Loss 0.4363 (0.4081) Prec@1 87.109 (89.062) Prec@5 97.266 (97.409)
[2021-04-26 20:28:18 train_lshot.py:257] INFO Epoch: [61][50/150] Time 0.627 (0.806) Data 0.001 (0.184) Loss 0.3814 (0.4142) Prec@1 89.062 (88.871) Prec@5 97.266 (97.419)
[2021-04-26 20:28:24 train_lshot.py:257] INFO Epoch: [61][60/150] Time 0.620 (0.776) Data 0.001 (0.154) Loss 0.4536 (0.4168) Prec@1 85.547 (88.601) Prec@5 97.656 (97.374)
[2021-04-26 20:28:30 train_lshot.py:257] INFO Epoch: [61][70/150] Time 0.623 (0.755) Data 0.001 (0.133) Loss 0.3379 (0.4107) Prec@1 90.234 (88.771) Prec@5 97.656 (97.475)
[2021-04-26 20:28:37 train_lshot.py:257] INFO Epoch: [61][80/150] Time 0.621 (0.739) Data 0.000 (0.116) Loss 0.4079 (0.4155) Prec@1 87.109 (88.653) Prec@5 98.438 (97.430)
[2021-04-26 20:28:43 train_lshot.py:257] INFO Epoch: [61][90/150] Time 0.621 (0.726) Data 0.000 (0.104) Loss 0.5138 (0.4156) Prec@1 85.938 (88.638) Prec@5 96.484 (97.407)
[2021-04-26 20:28:49 train_lshot.py:257] INFO Epoch: [61][100/150] Time 0.620 (0.715) Data 0.000 (0.093) Loss 0.3552 (0.4157) Prec@1 91.406 (88.668) Prec@5 96.484 (97.386)
[2021-04-26 20:28:55 train_lshot.py:257] INFO Epoch: [61][110/150] Time 0.620 (0.707) Data 0.001 (0.085) Loss 0.5130 (0.4162) Prec@1 85.547 (88.707) Prec@5 95.703 (97.332)
[2021-04-26 20:29:01 train_lshot.py:257] INFO Epoch: [61][120/150] Time 0.621 (0.700) Data 0.000 (0.078) Loss 0.4012 (0.4176) Prec@1 87.891 (88.669) Prec@5 97.656 (97.301)
[2021-04-26 20:29:08 train_lshot.py:257] INFO Epoch: [61][130/150] Time 0.620 (0.694) Data 0.000 (0.072) Loss 0.3833 (0.4165) Prec@1 88.281 (88.678) Prec@5 96.484 (97.284)
[2021-04-26 20:29:14 train_lshot.py:257] INFO Epoch: [61][140/150] Time 0.617 (0.689) Data 0.000 (0.067) Loss 0.4020 (0.4172) Prec@1 92.188 (88.647) Prec@5 97.266 (97.249)
[2021-04-26 20:29:30 train_lshot.py:257] INFO Epoch: [62][0/150] Time 9.788 (9.788) Data 9.150 (9.150) Loss 0.4126 (0.4126) Prec@1 89.844 (89.844) Prec@5 98.047 (98.047)
[2021-04-26 20:29:36 train_lshot.py:257] INFO Epoch: [62][10/150] Time 0.620 (1.453) Data 0.000 (0.833) Loss 0.3644 (0.4175) Prec@1 89.453 (88.778) Prec@5 97.656 (97.159)
[2021-04-26 20:29:42 train_lshot.py:257] INFO Epoch: [62][20/150] Time 0.623 (1.058) Data 0.001 (0.436) Loss 0.4261 (0.4189) Prec@1 87.109 (88.504) Prec@5 96.484 (96.949)
[2021-04-26 20:29:48 train_lshot.py:257] INFO Epoch: [62][30/150] Time 0.620 (0.917) Data 0.000 (0.296) Loss 0.3664 (0.4218) Prec@1 90.625 (88.432) Prec@5 98.047 (96.988)
[2021-04-26 20:29:55 train_lshot.py:257] INFO Epoch: [62][40/150] Time 0.622 (0.846) Data 0.000 (0.224) Loss 0.4120 (0.4165) Prec@1 89.844 (88.700) Prec@5 96.094 (97.056)
[2021-04-26 20:30:01 train_lshot.py:257] INFO Epoch: [62][50/150] Time 0.619 (0.802) Data 0.000 (0.180) Loss 0.3639 (0.4173) Prec@1 90.625 (88.748) Prec@5 97.266 (96.975)
[2021-04-26 20:30:07 train_lshot.py:257] INFO Epoch: [62][60/150] Time 0.622 (0.772) Data 0.000 (0.151) Loss 0.3433 (0.4156) Prec@1 89.062 (88.704) Prec@5 98.438 (97.041)
[2021-04-26 20:30:13 train_lshot.py:257] INFO Epoch: [62][70/150] Time 0.761 (0.753) Data 0.142 (0.132) Loss 0.5046 (0.4132) Prec@1 85.547 (88.738) Prec@5 96.484 (97.123)
[2021-04-26 20:30:20 train_lshot.py:257] INFO Epoch: [62][80/150] Time 0.624 (0.739) Data 0.001 (0.115) Loss 0.3367 (0.4150) Prec@1 91.406 (88.643) Prec@5 98.047 (97.111)
[2021-04-26 20:30:26 train_lshot.py:257] INFO Epoch: [62][90/150] Time 0.617 (0.726) Data 0.000 (0.103) Loss 0.4703 (0.4140) Prec@1 88.672 (88.745) Prec@5 97.656 (97.128)
[2021-04-26 20:30:32 train_lshot.py:257] INFO Epoch: [62][100/150] Time 0.619 (0.715) Data 0.000 (0.093) Loss 0.4636 (0.4177) Prec@1 85.547 (88.699) Prec@5 97.266 (97.088)
[2021-04-26 20:30:38 train_lshot.py:257] INFO Epoch: [62][110/150] Time 0.621 (0.707) Data 0.000 (0.084) Loss 0.3716 (0.4177) Prec@1 90.234 (88.707) Prec@5 98.047 (97.090)
[2021-04-26 20:30:45 train_lshot.py:257] INFO Epoch: [62][120/150] Time 0.621 (0.700) Data 0.000 (0.077) Loss 0.4467 (0.4184) Prec@1 87.891 (88.665) Prec@5 96.875 (97.095)
[2021-04-26 20:30:51 train_lshot.py:257] INFO Epoch: [62][130/150] Time 0.625 (0.694) Data 0.000 (0.071) Loss 0.3655 (0.4185) Prec@1 91.016 (88.657) Prec@5 98.047 (97.120)
[2021-04-26 20:30:57 train_lshot.py:257] INFO Epoch: [62][140/150] Time 0.620 (0.689) Data 0.000 (0.066) Loss 0.4301 (0.4177) Prec@1 87.891 (88.683) Prec@5 97.266 (97.146)
[2021-04-26 20:31:13 train_lshot.py:257] INFO Epoch: [63][0/150] Time 9.925 (9.925) Data 9.287 (9.287) Loss 0.4542 (0.4542) Prec@1 86.328 (86.328) Prec@5 96.875 (96.875)
[2021-04-26 20:31:19 train_lshot.py:257] INFO Epoch: [63][10/150] Time 0.620 (1.465) Data 0.000 (0.845) Loss 0.3975 (0.4238) Prec@1 87.109 (88.281) Prec@5 98.438 (97.159)
[2021-04-26 20:31:25 train_lshot.py:257] INFO Epoch: [63][20/150] Time 0.623 (1.064) Data 0.001 (0.443) Loss 0.4494 (0.4154) Prec@1 86.719 (88.411) Prec@5 98.828 (97.396)
[2021-04-26 20:31:32 train_lshot.py:257] INFO Epoch: [63][30/150] Time 0.622 (0.921) Data 0.001 (0.300) Loss 0.4308 (0.4174) Prec@1 88.672 (88.420) Prec@5 96.875 (97.228)
[2021-04-26 20:31:38 train_lshot.py:257] INFO Epoch: [63][40/150] Time 0.620 (0.849) Data 0.000 (0.227) Loss 0.4502 (0.4205) Prec@1 88.672 (88.453) Prec@5 96.875 (97.142)
[2021-04-26 20:31:44 train_lshot.py:257] INFO Epoch: [63][50/150] Time 0.628 (0.805) Data 0.001 (0.183) Loss 0.3382 (0.4143) Prec@1 90.625 (88.725) Prec@5 97.266 (97.143)
[2021-04-26 20:31:50 train_lshot.py:257] INFO Epoch: [63][60/150] Time 0.628 (0.775) Data 0.001 (0.153) Loss 0.4528 (0.4146) Prec@1 86.719 (88.736) Prec@5 96.094 (97.170)
[2021-04-26 20:31:57 train_lshot.py:257] INFO Epoch: [63][70/150] Time 0.621 (0.753) Data 0.001 (0.131) Loss 0.4783 (0.4122) Prec@1 85.938 (88.776) Prec@5 96.094 (97.216)
[2021-04-26 20:32:03 train_lshot.py:257] INFO Epoch: [63][80/150] Time 0.620 (0.737) Data 0.001 (0.115) Loss 0.2949 (0.4099) Prec@1 91.797 (88.903) Prec@5 99.609 (97.246)
[2021-04-26 20:32:09 train_lshot.py:257] INFO Epoch: [63][90/150] Time 0.621 (0.724) Data 0.000 (0.103) Loss 0.4640 (0.4140) Prec@1 87.891 (88.766) Prec@5 97.656 (97.223)
[2021-04-26 20:32:15 train_lshot.py:257] INFO Epoch: [63][100/150] Time 0.619 (0.714) Data 0.000 (0.092) Loss 0.4306 (0.4123) Prec@1 89.453 (88.800) Prec@5 97.266 (97.235)
[2021-04-26 20:32:21 train_lshot.py:257] INFO Epoch: [63][110/150] Time 0.620 (0.706) Data 0.000 (0.084) Loss 0.4814 (0.4116) Prec@1 86.719 (88.799) Prec@5 96.094 (97.287)
[2021-04-26 20:32:28 train_lshot.py:257] INFO Epoch: [63][120/150] Time 0.622 (0.699) Data 0.000 (0.077) Loss 0.5128 (0.4139) Prec@1 85.938 (88.753) Prec@5 95.703 (97.266)
[2021-04-26 20:32:34 train_lshot.py:257] INFO Epoch: [63][130/150] Time 0.617 (0.693) Data 0.000 (0.071) Loss 0.3607 (0.4135) Prec@1 91.797 (88.809) Prec@5 97.266 (97.251)
[2021-04-26 20:32:40 train_lshot.py:257] INFO Epoch: [63][140/150] Time 0.620 (0.688) Data 0.000 (0.066) Loss 0.4570 (0.4126) Prec@1 85.938 (88.830) Prec@5 97.266 (97.263)
[2021-04-26 20:33:33 train_lshot.py:119] INFO Meta Val 63: 0.6275200147032738
[2021-04-26 20:33:44 train_lshot.py:257] INFO Epoch: [64][0/150] Time 10.552 (10.552) Data 9.909 (9.909) Loss 0.4415 (0.4415) Prec@1 89.062 (89.062) Prec@5 95.703 (95.703)
[2021-04-26 20:33:50 train_lshot.py:257] INFO Epoch: [64][10/150] Time 0.617 (1.521) Data 0.000 (0.901) Loss 0.4676 (0.4049) Prec@1 90.234 (89.844) Prec@5 96.094 (97.337)
[2021-04-26 20:33:56 train_lshot.py:257] INFO Epoch: [64][20/150] Time 0.619 (1.092) Data 0.000 (0.472) Loss 0.3817 (0.4001) Prec@1 91.016 (89.974) Prec@5 97.656 (97.284)
[2021-04-26 20:34:02 train_lshot.py:257] INFO Epoch: [64][30/150] Time 0.636 (0.941) Data 0.001 (0.320) Loss 0.3847 (0.3966) Prec@1 90.234 (89.907) Prec@5 97.656 (97.203)
[2021-04-26 20:34:08 train_lshot.py:257] INFO Epoch: [64][40/150] Time 0.622 (0.863) Data 0.001 (0.242) Loss 0.4336 (0.3963) Prec@1 85.938 (89.720) Prec@5 98.438 (97.275)
[2021-04-26 20:34:15 train_lshot.py:257] INFO Epoch: [64][50/150] Time 0.623 (0.815) Data 0.000 (0.195) Loss 0.2915 (0.3912) Prec@1 91.016 (89.668) Prec@5 99.219 (97.327)
[2021-04-26 20:34:21 train_lshot.py:257] INFO Epoch: [64][60/150] Time 0.632 (0.784) Data 0.001 (0.163) Loss 0.3719 (0.3873) Prec@1 87.109 (89.671) Prec@5 97.656 (97.374)
[2021-04-26 20:34:27 train_lshot.py:257] INFO Epoch: [64][70/150] Time 0.622 (0.762) Data 0.001 (0.140) Loss 0.4957 (0.3956) Prec@1 85.156 (89.393) Prec@5 94.922 (97.310)
[2021-04-26 20:34:33 train_lshot.py:257] INFO Epoch: [64][80/150] Time 0.622 (0.744) Data 0.000 (0.123) Loss 0.4731 (0.3965) Prec@1 87.500 (89.342) Prec@5 95.703 (97.328)
[2021-04-26 20:34:40 train_lshot.py:257] INFO Epoch: [64][90/150] Time 0.625 (0.731) Data 0.000 (0.109) Loss 0.3131 (0.3950) Prec@1 91.406 (89.410) Prec@5 98.047 (97.326)
[2021-04-26 20:34:46 train_lshot.py:257] INFO Epoch: [64][100/150] Time 0.620 (0.720) Data 0.000 (0.099) Loss 0.3596 (0.3934) Prec@1 91.016 (89.472) Prec@5 98.047 (97.331)
[2021-04-26 20:34:52 train_lshot.py:257] INFO Epoch: [64][110/150] Time 0.618 (0.711) Data 0.000 (0.090) Loss 0.2872 (0.3929) Prec@1 92.578 (89.481) Prec@5 98.828 (97.347)
[2021-04-26 20:34:58 train_lshot.py:257] INFO Epoch: [64][120/150] Time 0.623 (0.703) Data 0.000 (0.082) Loss 0.4126 (0.3959) Prec@1 87.500 (89.340) Prec@5 96.875 (97.324)
[2021-04-26 20:35:04 train_lshot.py:257] INFO Epoch: [64][130/150] Time 0.624 (0.697) Data 0.000 (0.076) Loss 0.4321 (0.3980) Prec@1 87.500 (89.247) Prec@5 97.656 (97.298)
[2021-04-26 20:35:11 train_lshot.py:257] INFO Epoch: [64][140/150] Time 0.621 (0.692) Data 0.000 (0.071) Loss 0.4906 (0.3977) Prec@1 87.500 (89.268) Prec@5 96.484 (97.296)
[2021-04-26 20:35:26 train_lshot.py:257] INFO Epoch: [65][0/150] Time 9.870 (9.870) Data 9.212 (9.212) Loss 0.3970 (0.3970) Prec@1 90.625 (90.625) Prec@5 96.875 (96.875)
[2021-04-26 20:35:33 train_lshot.py:257] INFO Epoch: [65][10/150] Time 0.621 (1.460) Data 0.000 (0.838) Loss 0.4137 (0.3926) Prec@1 90.234 (89.631) Prec@5 96.875 (97.656)
[2021-04-26 20:35:39 train_lshot.py:257] INFO Epoch: [65][20/150] Time 0.619 (1.062) Data 0.000 (0.439) Loss 0.2961 (0.3798) Prec@1 93.359 (90.067) Prec@5 98.047 (97.712)
[2021-04-26 20:35:45 train_lshot.py:257] INFO Epoch: [65][30/150] Time 0.620 (0.920) Data 0.000 (0.298) Loss 0.3171 (0.3791) Prec@1 91.406 (89.995) Prec@5 99.219 (97.770)
[2021-04-26 20:35:51 train_lshot.py:257] INFO Epoch: [65][40/150] Time 0.624 (0.848) Data 0.001 (0.225) Loss 0.4277 (0.3822) Prec@1 89.453 (89.825) Prec@5 96.875 (97.742)
[2021-04-26 20:35:58 train_lshot.py:257] INFO Epoch: [65][50/150] Time 0.630 (0.804) Data 0.001 (0.181) Loss 0.3886 (0.3848) Prec@1 91.797 (89.828) Prec@5 98.438 (97.641)
[2021-04-26 20:36:04 train_lshot.py:257] INFO Epoch: [65][60/150] Time 0.626 (0.774) Data 0.000 (0.152) Loss 0.3017 (0.3893) Prec@1 92.188 (89.735) Prec@5 98.438 (97.515)
[2021-04-26 20:36:10 train_lshot.py:257] INFO Epoch: [65][70/150] Time 0.624 (0.753) Data 0.001 (0.130) Loss 0.3208 (0.3868) Prec@1 89.062 (89.827) Prec@5 98.047 (97.568)
[2021-04-26 20:36:16 train_lshot.py:257] INFO Epoch: [65][80/150] Time 0.622 (0.737) Data 0.000 (0.114) Loss 0.4070 (0.3856) Prec@1 90.234 (89.906) Prec@5 98.047 (97.478)
[2021-04-26 20:36:22 train_lshot.py:257] INFO Epoch: [65][90/150] Time 0.622 (0.724) Data 0.000 (0.102) Loss 0.4787 (0.3855) Prec@1 87.500 (89.891) Prec@5 96.094 (97.493)
[2021-04-26 20:36:29 train_lshot.py:257] INFO Epoch: [65][100/150] Time 0.619 (0.714) Data 0.000 (0.092) Loss 0.4170 (0.3878) Prec@1 89.453 (89.759) Prec@5 96.094 (97.447)
[2021-04-26 20:36:35 train_lshot.py:257] INFO Epoch: [65][110/150] Time 0.622 (0.705) Data 0.000 (0.084) Loss 0.4402 (0.3880) Prec@1 88.281 (89.763) Prec@5 98.047 (97.428)
[2021-04-26 20:36:41 train_lshot.py:257] INFO Epoch: [65][120/150] Time 0.619 (0.698) Data 0.000 (0.077) Loss 0.5093 (0.3917) Prec@1 87.109 (89.647) Prec@5 97.266 (97.372)
[2021-04-26 20:36:47 train_lshot.py:257] INFO Epoch: [65][130/150] Time 0.619 (0.692) Data 0.000 (0.071) Loss 0.4226 (0.3924) Prec@1 88.281 (89.629) Prec@5 96.875 (97.361)
[2021-04-26 20:36:53 train_lshot.py:257] INFO Epoch: [65][140/150] Time 0.621 (0.687) Data 0.000 (0.066) Loss 0.3266 (0.3940) Prec@1 89.844 (89.594) Prec@5 98.438 (97.329)
[2021-04-26 20:37:10 train_lshot.py:257] INFO Epoch: [66][0/150] Time 10.583 (10.583) Data 9.926 (9.926) Loss 0.3799 (0.3799) Prec@1 90.625 (90.625) Prec@5 98.438 (98.438)
[2021-04-26 20:37:16 train_lshot.py:257] INFO Epoch: [66][10/150] Time 0.616 (1.525) Data 0.000 (0.903) Loss 0.3977 (0.4040) Prec@1 89.844 (88.743) Prec@5 96.875 (97.337)
[2021-04-26 20:37:22 train_lshot.py:257] INFO Epoch: [66][20/150] Time 0.621 (1.095) Data 0.001 (0.474) Loss 0.4980 (0.3997) Prec@1 86.328 (89.062) Prec@5 95.312 (97.228)
[2021-04-26 20:37:29 train_lshot.py:257] INFO Epoch: [66][30/150] Time 0.618 (0.943) Data 0.000 (0.321) Loss 0.4577 (0.3974) Prec@1 85.938 (89.138) Prec@5 97.266 (97.341)
[2021-04-26 20:37:35 train_lshot.py:257] INFO Epoch: [66][40/150] Time 0.620 (0.865) Data 0.001 (0.243) Loss 0.3947 (0.3939) Prec@1 88.281 (89.205) Prec@5 97.656 (97.437)
[2021-04-26 20:37:41 train_lshot.py:257] INFO Epoch: [66][50/150] Time 0.622 (0.817) Data 0.001 (0.195) Loss 0.4675 (0.3975) Prec@1 86.328 (89.147) Prec@5 95.703 (97.411)
[2021-04-26 20:37:47 train_lshot.py:257] INFO Epoch: [66][60/150] Time 0.629 (0.785) Data 0.001 (0.163) Loss 0.3499 (0.3986) Prec@1 89.844 (89.255) Prec@5 98.438 (97.407)
[2021-04-26 20:37:54 train_lshot.py:257] INFO Epoch: [66][70/150] Time 0.621 (0.763) Data 0.001 (0.141) Loss 0.3718 (0.4017) Prec@1 90.234 (89.173) Prec@5 96.875 (97.343)
[2021-04-26 20:38:00 train_lshot.py:257] INFO Epoch: [66][80/150] Time 0.624 (0.745) Data 0.000 (0.123) Loss 0.4521 (0.4030) Prec@1 89.062 (89.217) Prec@5 96.484 (97.314)
[2021-04-26 20:38:06 train_lshot.py:257] INFO Epoch: [66][90/150] Time 0.622 (0.731) Data 0.000 (0.110) Loss 0.3531 (0.4035) Prec@1 90.234 (89.226) Prec@5 97.266 (97.296)
[2021-04-26 20:38:12 train_lshot.py:257] INFO Epoch: [66][100/150] Time 0.618 (0.720) Data 0.000 (0.099) Loss 0.4027 (0.4047) Prec@1 89.062 (89.171) Prec@5 97.656 (97.277)
[2021-04-26 20:38:18 train_lshot.py:257] INFO Epoch: [66][110/150] Time 0.624 (0.711) Data 0.000 (0.090) Loss 0.3982 (0.4020) Prec@1 89.453 (89.221) Prec@5 97.266 (97.301)
[2021-04-26 20:38:25 train_lshot.py:257] INFO Epoch: [66][120/150] Time 0.622 (0.704) Data 0.000 (0.083) Loss 0.3830 (0.4026) Prec@1 91.406 (89.240) Prec@5 96.484 (97.282)
[2021-04-26 20:38:31 train_lshot.py:257] INFO Epoch: [66][130/150] Time 0.619 (0.697) Data 0.000 (0.076) Loss 0.3701 (0.4023) Prec@1 91.406 (89.235) Prec@5 98.047 (97.286)
[2021-04-26 20:38:37 train_lshot.py:257] INFO Epoch: [66][140/150] Time 0.620 (0.692) Data 0.000 (0.071) Loss 0.4493 (0.4034) Prec@1 88.281 (89.231) Prec@5 96.484 (97.291)
[2021-04-26 20:38:53 train_lshot.py:257] INFO Epoch: [67][0/150] Time 9.837 (9.837) Data 9.200 (9.200) Loss 0.3936 (0.3936) Prec@1 90.625 (90.625) Prec@5 97.266 (97.266)
[2021-04-26 20:38:59 train_lshot.py:257] INFO Epoch: [67][10/150] Time 0.621 (1.457) Data 0.000 (0.837) Loss 0.3689 (0.3703) Prec@1 89.062 (90.696) Prec@5 98.047 (97.621)
[2021-04-26 20:39:05 train_lshot.py:257] INFO Epoch: [67][20/150] Time 0.621 (1.059) Data 0.001 (0.439) Loss 0.3884 (0.3809) Prec@1 91.016 (90.011) Prec@5 97.656 (97.452)
[2021-04-26 20:39:12 train_lshot.py:257] INFO Epoch: [67][30/150] Time 0.626 (0.919) Data 0.001 (0.297) Loss 0.3171 (0.4017) Prec@1 90.234 (89.390) Prec@5 98.828 (97.253)
[2021-04-26 20:39:18 train_lshot.py:257] INFO Epoch: [67][40/150] Time 0.620 (0.847) Data 0.001 (0.225) Loss 0.3616 (0.4021) Prec@1 91.797 (89.377) Prec@5 97.266 (97.199)
[2021-04-26 20:39:24 train_lshot.py:257] INFO Epoch: [67][50/150] Time 0.621 (0.803) Data 0.000 (0.181) Loss 0.3297 (0.3976) Prec@1 92.578 (89.415) Prec@5 96.484 (97.250)
[2021-04-26 20:39:30 train_lshot.py:257] INFO Epoch: [67][60/150] Time 0.628 (0.774) Data 0.001 (0.151) Loss 0.2706 (0.3936) Prec@1 92.188 (89.466) Prec@5 98.828 (97.336)
[2021-04-26 20:39:36 train_lshot.py:257] INFO Epoch: [67][70/150] Time 0.634 (0.753) Data 0.002 (0.130) Loss 0.3882 (0.3909) Prec@1 89.453 (89.563) Prec@5 97.266 (97.381)
[2021-04-26 20:39:43 train_lshot.py:257] INFO Epoch: [67][80/150] Time 0.625 (0.736) Data 0.000 (0.114) Loss 0.4136 (0.3906) Prec@1 88.281 (89.564) Prec@5 98.438 (97.401)
[2021-04-26 20:39:49 train_lshot.py:257] INFO Epoch: [67][90/150] Time 0.619 (0.724) Data 0.000 (0.102) Loss 0.3675 (0.3915) Prec@1 89.844 (89.556) Prec@5 98.438 (97.386)
[2021-04-26 20:39:55 train_lshot.py:257] INFO Epoch: [67][100/150] Time 0.620 (0.713) Data 0.000 (0.092) Loss 0.4471 (0.3911) Prec@1 87.109 (89.546) Prec@5 96.484 (97.389)
[2021-04-26 20:40:01 train_lshot.py:257] INFO Epoch: [67][110/150] Time 0.617 (0.705) Data 0.000 (0.083) Loss 0.4894 (0.3925) Prec@1 85.938 (89.492) Prec@5 98.047 (97.403)
[2021-04-26 20:40:07 train_lshot.py:257] INFO Epoch: [67][120/150] Time 0.621 (0.698) Data 0.000 (0.076) Loss 0.4307 (0.3920) Prec@1 87.891 (89.447) Prec@5 96.875 (97.437)
[2021-04-26 20:40:14 train_lshot.py:257] INFO Epoch: [67][130/150] Time 0.622 (0.692) Data 0.000 (0.071) Loss 0.3481 (0.3937) Prec@1 89.062 (89.358) Prec@5 98.828 (97.427)
[2021-04-26 20:40:20 train_lshot.py:257] INFO Epoch: [67][140/150] Time 0.621 (0.687) Data 0.000 (0.066) Loss 0.2499 (0.3930) Prec@1 94.922 (89.398) Prec@5 98.438 (97.440)
[2021-04-26 20:41:14 train_lshot.py:119] INFO Meta Val 67: 0.6211200138926506
[2021-04-26 20:41:26 train_lshot.py:257] INFO Epoch: [68][0/150] Time 11.109 (11.109) Data 10.456 (10.456) Loss 0.3092 (0.3092) Prec@1 91.406 (91.406) Prec@5 98.438 (98.438)
[2021-04-26 20:41:32 train_lshot.py:257] INFO Epoch: [68][10/150] Time 0.615 (1.572) Data 0.001 (0.951) Loss 0.4134 (0.3412) Prec@1 86.328 (90.554) Prec@5 99.219 (98.260)
[2021-04-26 20:41:38 train_lshot.py:257] INFO Epoch: [68][20/150] Time 0.617 (1.119) Data 0.000 (0.499) Loss 0.2923 (0.3521) Prec@1 92.969 (90.383) Prec@5 98.438 (98.103)
[2021-04-26 20:41:44 train_lshot.py:257] INFO Epoch: [68][30/150] Time 0.618 (0.959) Data 0.000 (0.338) Loss 0.4633 (0.3752) Prec@1 88.281 (89.793) Prec@5 97.266 (97.744)
[2021-04-26 20:41:50 train_lshot.py:257] INFO Epoch: [68][40/150] Time 0.621 (0.877) Data 0.001 (0.256) Loss 0.3741 (0.3744) Prec@1 89.453 (89.796) Prec@5 97.266 (97.618)
[2021-04-26 20:41:57 train_lshot.py:257] INFO Epoch: [68][50/150] Time 0.630 (0.827) Data 0.001 (0.206) Loss 0.3053 (0.3770) Prec@1 92.578 (89.767) Prec@5 97.656 (97.610)
[2021-04-26 20:42:03 train_lshot.py:257] INFO Epoch: [68][60/150] Time 0.621 (0.794) Data 0.001 (0.172) Loss 0.3126 (0.3776) Prec@1 91.797 (89.703) Prec@5 98.438 (97.592)
[2021-04-26 20:42:09 train_lshot.py:257] INFO Epoch: [68][70/150] Time 0.625 (0.770) Data 0.002 (0.148) Loss 0.3856 (0.3798) Prec@1 88.672 (89.668) Prec@5 97.656 (97.513)
[2021-04-26 20:42:15 train_lshot.py:257] INFO Epoch: [68][80/150] Time 0.621 (0.752) Data 0.001 (0.130) Loss 0.3056 (0.3808) Prec@1 92.578 (89.685) Prec@5 98.047 (97.478)
[2021-04-26 20:42:22 train_lshot.py:257] INFO Epoch: [68][90/150] Time 0.620 (0.737) Data 0.000 (0.116) Loss 0.4357 (0.3828) Prec@1 89.453 (89.676) Prec@5 96.484 (97.416)
[2021-04-26 20:42:28 train_lshot.py:257] INFO Epoch: [68][100/150] Time 0.621 (0.726) Data 0.000 (0.104) Loss 0.4168 (0.3799) Prec@1 89.062 (89.751) Prec@5 96.875 (97.451)
[2021-04-26 20:42:34 train_lshot.py:257] INFO Epoch: [68][110/150] Time 0.620 (0.716) Data 0.000 (0.095) Loss 0.5307 (0.3805) Prec@1 88.281 (89.745) Prec@5 95.312 (97.442)
[2021-04-26 20:42:40 train_lshot.py:257] INFO Epoch: [68][120/150] Time 0.628 (0.708) Data 0.000 (0.087) Loss 0.3969 (0.3804) Prec@1 89.062 (89.676) Prec@5 97.266 (97.466)
[2021-04-26 20:42:46 train_lshot.py:257] INFO Epoch: [68][130/150] Time 0.625 (0.702) Data 0.000 (0.080) Loss 0.3873 (0.3803) Prec@1 89.844 (89.713) Prec@5 98.047 (97.471)
[2021-04-26 20:42:53 train_lshot.py:257] INFO Epoch: [68][140/150] Time 0.624 (0.696) Data 0.000 (0.075) Loss 0.4401 (0.3823) Prec@1 90.234 (89.689) Prec@5 96.484 (97.446)
[2021-04-26 20:43:08 train_lshot.py:257] INFO Epoch: [69][0/150] Time 9.416 (9.416) Data 8.771 (8.771) Loss 0.4655 (0.4655) Prec@1 87.500 (87.500) Prec@5 94.141 (94.141)
[2021-04-26 20:43:14 train_lshot.py:257] INFO Epoch: [69][10/150] Time 0.616 (1.421) Data 0.000 (0.799) Loss 0.4815 (0.4016) Prec@1 86.328 (89.489) Prec@5 96.875 (96.982)
[2021-04-26 20:43:21 train_lshot.py:257] INFO Epoch: [69][20/150] Time 0.625 (1.041) Data 0.001 (0.419) Loss 0.4069 (0.3889) Prec@1 87.109 (89.342) Prec@5 97.266 (97.210)
[2021-04-26 20:43:27 train_lshot.py:257] INFO Epoch: [69][30/150] Time 0.626 (0.906) Data 0.000 (0.284) Loss 0.2389 (0.3843) Prec@1 93.750 (89.592) Prec@5 98.828 (97.278)
[2021-04-26 20:43:33 train_lshot.py:257] INFO Epoch: [69][40/150] Time 0.627 (0.837) Data 0.001 (0.215) Loss 0.4015 (0.3833) Prec@1 90.625 (89.644) Prec@5 96.875 (97.294)
[2021-04-26 20:43:39 train_lshot.py:257] INFO Epoch: [69][50/150] Time 0.621 (0.795) Data 0.000 (0.173) Loss 0.4649 (0.3839) Prec@1 89.453 (89.606) Prec@5 95.703 (97.342)
[2021-04-26 20:43:45 train_lshot.py:257] INFO Epoch: [69][60/150] Time 0.621 (0.767) Data 0.000 (0.145) Loss 0.3796 (0.3852) Prec@1 87.500 (89.556) Prec@5 96.875 (97.323)
[2021-04-26 20:43:52 train_lshot.py:257] INFO Epoch: [69][70/150] Time 0.621 (0.747) Data 0.001 (0.124) Loss 0.4989 (0.3850) Prec@1 86.328 (89.563) Prec@5 96.094 (97.310)
[2021-04-26 20:43:58 train_lshot.py:257] INFO Epoch: [69][80/150] Time 0.620 (0.731) Data 0.000 (0.109) Loss 0.2724 (0.3837) Prec@1 93.359 (89.574) Prec@5 98.828 (97.372)
[2021-04-26 20:44:04 train_lshot.py:257] INFO Epoch: [69][90/150] Time 0.624 (0.719) Data 0.000 (0.097) Loss 0.2465 (0.3795) Prec@1 93.359 (89.736) Prec@5 99.609 (97.463)
[2021-04-26 20:44:10 train_lshot.py:257] INFO Epoch: [69][100/150] Time 0.622 (0.710) Data 0.000 (0.087) Loss 0.3368 (0.3768) Prec@1 92.969 (89.840) Prec@5 97.656 (97.486)
[2021-04-26 20:44:17 train_lshot.py:257] INFO Epoch: [69][110/150] Time 0.618 (0.702) Data 0.000 (0.080) Loss 0.4156 (0.3753) Prec@1 87.891 (89.858) Prec@5 96.094 (97.487)
[2021-04-26 20:44:23 train_lshot.py:257] INFO Epoch: [69][120/150] Time 0.620 (0.695) Data 0.000 (0.073) Loss 0.3138 (0.3777) Prec@1 90.625 (89.815) Prec@5 98.438 (97.514)
[2021-04-26 20:44:29 train_lshot.py:257] INFO Epoch: [69][130/150] Time 0.622 (0.690) Data 0.000 (0.067) Loss 0.4004 (0.3805) Prec@1 88.672 (89.748) Prec@5 97.266 (97.468)
[2021-04-26 20:44:35 train_lshot.py:257] INFO Epoch: [69][140/150] Time 0.617 (0.685) Data 0.000 (0.063) Loss 0.3390 (0.3790) Prec@1 90.625 (89.797) Prec@5 98.438 (97.496)
[2021-04-26 20:44:51 train_lshot.py:257] INFO Epoch: [70][0/150] Time 9.911 (9.911) Data 9.260 (9.260) Loss 0.5049 (0.5049) Prec@1 87.500 (87.500) Prec@5 94.531 (94.531)
[2021-04-26 20:44:57 train_lshot.py:257] INFO Epoch: [70][10/150] Time 0.617 (1.463) Data 0.000 (0.842) Loss 0.4319 (0.3698) Prec@1 89.453 (90.661) Prec@5 95.703 (97.479)
[2021-04-26 20:45:04 train_lshot.py:257] INFO Epoch: [70][20/150] Time 0.621 (1.062) Data 0.001 (0.441) Loss 0.2740 (0.3567) Prec@1 92.578 (90.644) Prec@5 99.609 (97.638)
[2021-04-26 20:45:10 train_lshot.py:257] INFO Epoch: [70][30/150] Time 0.623 (0.921) Data 0.000 (0.299) Loss 0.4165 (0.3619) Prec@1 91.016 (90.449) Prec@5 97.266 (97.719)
[2021-04-26 20:45:16 train_lshot.py:257] INFO Epoch: [70][40/150] Time 0.628 (0.848) Data 0.001 (0.226) Loss 0.3424 (0.3653) Prec@1 91.406 (90.387) Prec@5 98.438 (97.694)
[2021-04-26 20:45:22 train_lshot.py:257] INFO Epoch: [70][50/150] Time 0.620 (0.804) Data 0.000 (0.182) Loss 0.4253 (0.3731) Prec@1 89.844 (90.242) Prec@5 96.875 (97.618)
[2021-04-26 20:45:29 train_lshot.py:257] INFO Epoch: [70][60/150] Time 0.625 (0.775) Data 0.001 (0.152) Loss 0.3604 (0.3726) Prec@1 90.625 (90.132) Prec@5 97.656 (97.618)
[2021-04-26 20:45:35 train_lshot.py:257] INFO Epoch: [70][70/150] Time 0.623 (0.753) Data 0.001 (0.131) Loss 0.3144 (0.3739) Prec@1 90.234 (90.119) Prec@5 98.438 (97.563)
[2021-04-26 20:45:41 train_lshot.py:257] INFO Epoch: [70][80/150] Time 0.619 (0.737) Data 0.000 (0.115) Loss 0.3300 (0.3746) Prec@1 91.797 (90.099) Prec@5 98.047 (97.565)
[2021-04-26 20:45:47 train_lshot.py:257] INFO Epoch: [70][90/150] Time 0.620 (0.724) Data 0.000 (0.102) Loss 0.3898 (0.3698) Prec@1 89.844 (90.217) Prec@5 97.266 (97.626)
[2021-04-26 20:45:53 train_lshot.py:257] INFO Epoch: [70][100/150] Time 0.622 (0.714) Data 0.000 (0.092) Loss 0.3925 (0.3701) Prec@1 89.062 (90.200) Prec@5 97.656 (97.598)
[2021-04-26 20:46:00 train_lshot.py:257] INFO Epoch: [70][110/150] Time 0.620 (0.706) Data 0.000 (0.084) Loss 0.3175 (0.3717) Prec@1 91.016 (90.129) Prec@5 98.438 (97.579)
[2021-04-26 20:46:06 train_lshot.py:257] INFO Epoch: [70][120/150] Time 0.620 (0.699) Data 0.000 (0.077) Loss 0.3851 (0.3704) Prec@1 90.625 (90.183) Prec@5 98.047 (97.614)
[2021-04-26 20:46:12 train_lshot.py:257] INFO Epoch: [70][130/150] Time 0.621 (0.693) Data 0.000 (0.071) Loss 0.4110 (0.3707) Prec@1 88.672 (90.216) Prec@5 97.266 (97.594)
[2021-04-26 20:46:18 train_lshot.py:257] INFO Epoch: [70][140/150] Time 0.624 (0.688) Data 0.000 (0.066) Loss 0.3728 (0.3715) Prec@1 87.500 (90.198) Prec@5 97.266 (97.559)
[2021-04-26 20:46:34 train_lshot.py:257] INFO Epoch: [71][0/150] Time 9.525 (9.525) Data 8.872 (8.872) Loss 0.4290 (0.4290) Prec@1 87.891 (87.891) Prec@5 96.875 (96.875)
[2021-04-26 20:46:40 train_lshot.py:257] INFO Epoch: [71][10/150] Time 0.625 (1.431) Data 0.000 (0.807) Loss 0.4209 (0.4094) Prec@1 89.453 (89.276) Prec@5 96.875 (97.124)
[2021-04-26 20:46:46 train_lshot.py:257] INFO Epoch: [71][20/150] Time 0.627 (1.046) Data 0.001 (0.423) Loss 0.4138 (0.3904) Prec@1 89.453 (89.993) Prec@5 97.656 (97.396)
[2021-04-26 20:46:53 train_lshot.py:257] INFO Epoch: [71][30/150] Time 0.623 (0.910) Data 0.000 (0.287) Loss 0.4433 (0.3879) Prec@1 87.109 (89.932) Prec@5 95.312 (97.354)
[2021-04-26 20:46:59 train_lshot.py:257] INFO Epoch: [71][40/150] Time 0.629 (0.841) Data 0.001 (0.217) Loss 0.3122 (0.3827) Prec@1 90.234 (90.053) Prec@5 99.219 (97.447)
[2021-04-26 20:47:05 train_lshot.py:257] INFO Epoch: [71][50/150] Time 0.621 (0.798) Data 0.001 (0.175) Loss 0.3797 (0.3757) Prec@1 89.453 (90.112) Prec@5 97.266 (97.541)
[2021-04-26 20:47:11 train_lshot.py:257] INFO Epoch: [71][60/150] Time 0.624 (0.769) Data 0.000 (0.146) Loss 0.4997 (0.3709) Prec@1 87.500 (90.266) Prec@5 94.531 (97.579)
[2021-04-26 20:47:17 train_lshot.py:257] INFO Epoch: [71][70/150] Time 0.625 (0.749) Data 0.001 (0.126) Loss 0.3484 (0.3684) Prec@1 91.016 (90.267) Prec@5 97.266 (97.574)
[2021-04-26 20:47:24 train_lshot.py:257] INFO Epoch: [71][80/150] Time 0.621 (0.733) Data 0.000 (0.110) Loss 0.3399 (0.3676) Prec@1 90.234 (90.268) Prec@5 98.047 (97.594)
[2021-04-26 20:47:30 train_lshot.py:257] INFO Epoch: [71][90/150] Time 0.624 (0.721) Data 0.000 (0.098) Loss 0.2797 (0.3693) Prec@1 93.750 (90.269) Prec@5 98.438 (97.618)
[2021-04-26 20:47:36 train_lshot.py:257] INFO Epoch: [71][100/150] Time 0.620 (0.711) Data 0.000 (0.088) Loss 0.3067 (0.3665) Prec@1 93.750 (90.350) Prec@5 97.266 (97.614)
[2021-04-26 20:47:42 train_lshot.py:257] INFO Epoch: [71][110/150] Time 0.620 (0.703) Data 0.000 (0.080) Loss 0.3485 (0.3649) Prec@1 91.406 (90.421) Prec@5 97.656 (97.607)
[2021-04-26 20:47:49 train_lshot.py:257] INFO Epoch: [71][120/150] Time 0.625 (0.696) Data 0.000 (0.074) Loss 0.2880 (0.3648) Prec@1 92.969 (90.405) Prec@5 97.266 (97.582)
[2021-04-26 20:47:55 train_lshot.py:257] INFO Epoch: [71][130/150] Time 0.624 (0.691) Data 0.000 (0.068) Loss 0.3582 (0.3656) Prec@1 92.578 (90.392) Prec@5 97.656 (97.600)
[2021-04-26 20:48:01 train_lshot.py:257] INFO Epoch: [71][140/150] Time 0.626 (0.686) Data 0.000 (0.063) Loss 0.2761 (0.3646) Prec@1 91.797 (90.401) Prec@5 97.656 (97.593)
[2021-04-26 20:48:54 train_lshot.py:119] INFO Meta Val 71: 0.6208800141215325
[2021-04-26 20:49:05 train_lshot.py:257] INFO Epoch: [72][0/150] Time 10.047 (10.047) Data 9.385 (9.385) Loss 0.3486 (0.3486) Prec@1 89.453 (89.453) Prec@5 97.656 (97.656)
[2021-04-26 20:49:11 train_lshot.py:257] INFO Epoch: [72][10/150] Time 0.618 (1.518) Data 0.000 (0.896) Loss 0.3990 (0.3716) Prec@1 90.234 (89.915) Prec@5 97.266 (97.869)
[2021-04-26 20:49:17 train_lshot.py:257] INFO Epoch: [72][20/150] Time 0.619 (1.092) Data 0.000 (0.469) Loss 0.3319 (0.3718) Prec@1 90.625 (89.881) Prec@5 97.656 (97.824)
[2021-04-26 20:49:24 train_lshot.py:257] INFO Epoch: [72][30/150] Time 0.620 (0.940) Data 0.000 (0.318) Loss 0.4215 (0.3711) Prec@1 88.281 (89.844) Prec@5 98.047 (97.833)
[2021-04-26 20:49:30 train_lshot.py:257] INFO Epoch: [72][40/150] Time 0.624 (0.863) Data 0.002 (0.241) Loss 0.3082 (0.3649) Prec@1 90.625 (89.949) Prec@5 97.656 (97.818)
[2021-04-26 20:49:36 train_lshot.py:257] INFO Epoch: [72][50/150] Time 0.624 (0.816) Data 0.000 (0.194) Loss 0.3619 (0.3615) Prec@1 91.406 (90.242) Prec@5 98.438 (97.917)
[2021-04-26 20:49:42 train_lshot.py:257] INFO Epoch: [72][60/150] Time 0.622 (0.784) Data 0.000 (0.162) Loss 0.5040 (0.3707) Prec@1 84.766 (89.914) Prec@5 97.266 (97.778)
[2021-04-26 20:49:49 train_lshot.py:257] INFO Epoch: [72][70/150] Time 0.621 (0.762) Data 0.001 (0.139) Loss 0.3627 (0.3713) Prec@1 90.625 (89.921) Prec@5 96.875 (97.722)
[2021-04-26 20:49:55 train_lshot.py:257] INFO Epoch: [72][80/150] Time 0.625 (0.744) Data 0.000 (0.122) Loss 0.3822 (0.3722) Prec@1 88.281 (89.945) Prec@5 98.047 (97.685)
[2021-04-26 20:50:01 train_lshot.py:257] INFO Epoch: [72][90/150] Time 0.622 (0.731) Data 0.000 (0.109) Loss 0.3114 (0.3724) Prec@1 91.797 (89.968) Prec@5 98.438 (97.643)
[2021-04-26 20:50:07 train_lshot.py:257] INFO Epoch: [72][100/150] Time 0.620 (0.720) Data 0.000 (0.098) Loss 0.3619 (0.3700) Prec@1 89.844 (90.018) Prec@5 97.656 (97.652)
[2021-04-26 20:50:13 train_lshot.py:257] INFO Epoch: [72][110/150] Time 0.621 (0.711) Data 0.000 (0.089) Loss 0.2911 (0.3699) Prec@1 92.578 (90.009) Prec@5 98.047 (97.656)
[2021-04-26 20:50:20 train_lshot.py:257] INFO Epoch: [72][120/150] Time 0.622 (0.704) Data 0.000 (0.082) Loss 0.3569 (0.3714) Prec@1 90.625 (89.976) Prec@5 96.875 (97.637)
[2021-04-26 20:50:26 train_lshot.py:257] INFO Epoch: [72][130/150] Time 0.621 (0.697) Data 0.000 (0.076) Loss 0.3580 (0.3693) Prec@1 90.234 (90.061) Prec@5 99.219 (97.665)
[2021-04-26 20:50:32 train_lshot.py:257] INFO Epoch: [72][140/150] Time 0.623 (0.692) Data 0.000 (0.070) Loss 0.4167 (0.3702) Prec@1 89.453 (90.024) Prec@5 96.094 (97.648)
[2021-04-26 20:50:48 train_lshot.py:257] INFO Epoch: [73][0/150] Time 9.726 (9.726) Data 9.075 (9.075) Loss 0.3562 (0.3562) Prec@1 90.625 (90.625) Prec@5 96.484 (96.484)
[2021-04-26 20:50:54 train_lshot.py:257] INFO Epoch: [73][10/150] Time 0.618 (1.446) Data 0.000 (0.826) Loss 0.4062 (0.3972) Prec@1 89.453 (89.808) Prec@5 95.703 (96.911)
[2021-04-26 20:51:00 train_lshot.py:257] INFO Epoch: [73][20/150] Time 0.637 (1.057) Data 0.001 (0.434) Loss 0.3025 (0.3847) Prec@1 92.188 (89.900) Prec@5 97.656 (97.210)
[2021-04-26 20:51:07 train_lshot.py:257] INFO Epoch: [73][30/150] Time 0.626 (0.916) Data 0.000 (0.294) Loss 0.4857 (0.3883) Prec@1 85.547 (89.630) Prec@5 97.266 (97.366)
[2021-04-26 20:51:13 train_lshot.py:257] INFO Epoch: [73][40/150] Time 0.625 (0.845) Data 0.001 (0.223) Loss 0.4136 (0.3827) Prec@1 87.891 (89.739) Prec@5 98.047 (97.437)
[2021-04-26 20:51:19 train_lshot.py:257] INFO Epoch: [73][50/150] Time 0.621 (0.801) Data 0.000 (0.179) Loss 0.3404 (0.3736) Prec@1 91.797 (90.005) Prec@5 97.266 (97.465)
[2021-04-26 20:51:25 train_lshot.py:257] INFO Epoch: [73][60/150] Time 0.618 (0.772) Data 0.000 (0.150) Loss 0.3669 (0.3724) Prec@1 89.062 (89.959) Prec@5 98.047 (97.503)
[2021-04-26 20:51:31 train_lshot.py:257] INFO Epoch: [73][70/150] Time 0.625 (0.751) Data 0.002 (0.129) Loss 0.3430 (0.3734) Prec@1 91.797 (89.992) Prec@5 98.047 (97.475)
[2021-04-26 20:51:38 train_lshot.py:257] INFO Epoch: [73][80/150] Time 0.620 (0.735) Data 0.000 (0.113) Loss 0.3664 (0.3759) Prec@1 89.844 (89.984) Prec@5 96.875 (97.463)
[2021-04-26 20:51:44 train_lshot.py:257] INFO Epoch: [73][90/150] Time 0.620 (0.723) Data 0.000 (0.101) Loss 0.2972 (0.3755) Prec@1 93.359 (90.020) Prec@5 98.047 (97.485)
[2021-04-26 20:51:50 train_lshot.py:257] INFO Epoch: [73][100/150] Time 0.620 (0.712) Data 0.000 (0.091) Loss 0.4593 (0.3760) Prec@1 88.281 (90.010) Prec@5 96.094 (97.478)
[2021-04-26 20:51:56 train_lshot.py:257] INFO Epoch: [73][110/150] Time 0.622 (0.704) Data 0.000 (0.083) Loss 0.3183 (0.3748) Prec@1 91.016 (90.044) Prec@5 98.047 (97.473)
[2021-04-26 20:52:02 train_lshot.py:257] INFO Epoch: [73][120/150] Time 0.620 (0.697) Data 0.000 (0.076) Loss 0.3686 (0.3732) Prec@1 89.844 (90.125) Prec@5 97.266 (97.475)
[2021-04-26 20:52:09 train_lshot.py:257] INFO Epoch: [73][130/150] Time 0.623 (0.692) Data 0.000 (0.070) Loss 0.3743 (0.3719) Prec@1 89.062 (90.130) Prec@5 96.875 (97.489)
[2021-04-26 20:52:15 train_lshot.py:257] INFO Epoch: [73][140/150] Time 0.616 (0.687) Data 0.000 (0.065) Loss 0.3384 (0.3704) Prec@1 88.281 (90.126) Prec@5 98.828 (97.487)
[2021-04-26 20:52:30 train_lshot.py:257] INFO Epoch: [74][0/150] Time 9.399 (9.399) Data 8.740 (8.740) Loss 0.4792 (0.4792) Prec@1 87.109 (87.109) Prec@5 97.656 (97.656)
[2021-04-26 20:52:37 train_lshot.py:257] INFO Epoch: [74][10/150] Time 0.621 (1.415) Data 0.001 (0.795) Loss 0.3091 (0.3460) Prec@1 91.797 (90.518) Prec@5 98.047 (97.763)
[2021-04-26 20:52:43 train_lshot.py:257] INFO Epoch: [74][20/150] Time 0.625 (1.037) Data 0.001 (0.417) Loss 0.3523 (0.3647) Prec@1 89.062 (90.216) Prec@5 98.438 (97.600)
[2021-04-26 20:52:49 train_lshot.py:257] INFO Epoch: [74][30/150] Time 0.618 (0.903) Data 0.000 (0.283) Loss 0.3462 (0.3609) Prec@1 91.797 (90.272) Prec@5 97.656 (97.669)
[2021-04-26 20:52:55 train_lshot.py:257] INFO Epoch: [74][40/150] Time 0.626 (0.835) Data 0.001 (0.214) Loss 0.4293 (0.3647) Prec@1 87.891 (90.320) Prec@5 96.484 (97.656)
[2021-04-26 20:53:01 train_lshot.py:257] INFO Epoch: [74][50/150] Time 0.621 (0.793) Data 0.000 (0.172) Loss 0.3219 (0.3636) Prec@1 91.406 (90.311) Prec@5 98.828 (97.725)
[2021-04-26 20:53:08 train_lshot.py:257] INFO Epoch: [74][60/150] Time 0.620 (0.766) Data 0.001 (0.144) Loss 0.4325 (0.3664) Prec@1 90.234 (90.241) Prec@5 96.484 (97.637)
[2021-04-26 20:53:14 train_lshot.py:257] INFO Epoch: [74][70/150] Time 0.629 (0.746) Data 0.002 (0.124) Loss 0.3260 (0.3727) Prec@1 90.625 (90.075) Prec@5 98.047 (97.552)
[2021-04-26 20:53:20 train_lshot.py:257] INFO Epoch: [74][80/150] Time 0.620 (0.730) Data 0.000 (0.108) Loss 0.4618 (0.3705) Prec@1 87.500 (90.186) Prec@5 96.875 (97.560)
[2021-04-26 20:53:26 train_lshot.py:257] INFO Epoch: [74][90/150] Time 0.624 (0.718) Data 0.000 (0.097) Loss 0.3434 (0.3723) Prec@1 92.188 (90.127) Prec@5 96.875 (97.545)
[2021-04-26 20:53:33 train_lshot.py:257] INFO Epoch: [74][100/150] Time 0.623 (0.709) Data 0.001 (0.087) Loss 0.4562 (0.3723) Prec@1 89.453 (90.114) Prec@5 96.094 (97.563)
[2021-04-26 20:53:39 train_lshot.py:257] INFO Epoch: [74][110/150] Time 0.617 (0.701) Data 0.000 (0.079) Loss 0.4365 (0.3724) Prec@1 89.453 (90.051) Prec@5 97.266 (97.607)
[2021-04-26 20:53:45 train_lshot.py:257] INFO Epoch: [74][120/150] Time 0.620 (0.694) Data 0.000 (0.073) Loss 0.4207 (0.3728) Prec@1 88.281 (89.989) Prec@5 97.266 (97.611)
[2021-04-26 20:53:51 train_lshot.py:257] INFO Epoch: [74][130/150] Time 0.622 (0.688) Data 0.000 (0.067) Loss 0.3610 (0.3763) Prec@1 89.453 (89.868) Prec@5 97.266 (97.555)
[2021-04-26 20:53:57 train_lshot.py:257] INFO Epoch: [74][140/150] Time 0.621 (0.684) Data 0.000 (0.062) Loss 0.4627 (0.3769) Prec@1 86.719 (89.871) Prec@5 96.484 (97.526)
[2021-04-26 20:54:13 train_lshot.py:257] INFO Epoch: [75][0/150] Time 9.628 (9.628) Data 8.983 (8.983) Loss 0.4095 (0.4095) Prec@1 90.234 (90.234) Prec@5 96.484 (96.484)
[2021-04-26 20:54:19 train_lshot.py:257] INFO Epoch: [75][10/150] Time 0.621 (1.447) Data 0.000 (0.827) Loss 0.2906 (0.3610) Prec@1 93.359 (91.229) Prec@5 98.828 (97.621)
[2021-04-26 20:54:25 train_lshot.py:257] INFO Epoch: [75][20/150] Time 0.620 (1.054) Data 0.000 (0.433) Loss 0.3195 (0.3613) Prec@1 91.016 (90.699) Prec@5 98.047 (97.545)
[2021-04-26 20:54:32 train_lshot.py:257] INFO Epoch: [75][30/150] Time 0.619 (0.916) Data 0.000 (0.294) Loss 0.3504 (0.3578) Prec@1 91.406 (90.776) Prec@5 98.438 (97.707)
[2021-04-26 20:54:38 train_lshot.py:257] INFO Epoch: [75][40/150] Time 0.630 (0.845) Data 0.001 (0.222) Loss 0.4292 (0.3584) Prec@1 89.062 (90.558) Prec@5 95.312 (97.647)
[2021-04-26 20:54:44 train_lshot.py:257] INFO Epoch: [75][50/150] Time 0.623 (0.802) Data 0.000 (0.179) Loss 0.3835 (0.3614) Prec@1 88.672 (90.456) Prec@5 98.438 (97.672)
[2021-04-26 20:54:50 train_lshot.py:257] INFO Epoch: [75][60/150] Time 0.622 (0.773) Data 0.000 (0.150) Loss 0.3650 (0.3651) Prec@1 91.406 (90.394) Prec@5 97.266 (97.599)
[2021-04-26 20:54:57 train_lshot.py:257] INFO Epoch: [75][70/150] Time 0.623 (0.752) Data 0.001 (0.129) Loss 0.3973 (0.3670) Prec@1 88.672 (90.317) Prec@5 97.656 (97.623)
[2021-04-26 20:55:03 train_lshot.py:257] INFO Epoch: [75][80/150] Time 0.619 (0.736) Data 0.000 (0.113) Loss 0.3219 (0.3645) Prec@1 89.844 (90.254) Prec@5 98.438 (97.700)
[2021-04-26 20:55:09 train_lshot.py:257] INFO Epoch: [75][90/150] Time 0.621 (0.723) Data 0.000 (0.100) Loss 0.3578 (0.3673) Prec@1 90.625 (90.114) Prec@5 98.438 (97.708)
[2021-04-26 20:55:15 train_lshot.py:257] INFO Epoch: [75][100/150] Time 0.622 (0.713) Data 0.000 (0.090) Loss 0.3929 (0.3669) Prec@1 88.672 (90.126) Prec@5 97.656 (97.726)
[2021-04-26 20:55:22 train_lshot.py:257] INFO Epoch: [75][110/150] Time 0.623 (0.705) Data 0.000 (0.082) Loss 0.3791 (0.3663) Prec@1 90.234 (90.192) Prec@5 96.875 (97.730)
[2021-04-26 20:55:28 train_lshot.py:257] INFO Epoch: [75][120/150] Time 0.622 (0.698) Data 0.000 (0.076) Loss 0.2835 (0.3642) Prec@1 93.750 (90.283) Prec@5 98.438 (97.718)
[2021-04-26 20:55:34 train_lshot.py:257] INFO Epoch: [75][130/150] Time 0.620 (0.692) Data 0.000 (0.070) Loss 0.2966 (0.3637) Prec@1 92.188 (90.261) Prec@5 98.047 (97.737)
[2021-04-26 20:55:40 train_lshot.py:257] INFO Epoch: [75][140/150] Time 0.620 (0.687) Data 0.000 (0.065) Loss 0.3567 (0.3642) Prec@1 91.797 (90.234) Prec@5 96.875 (97.737)
[2021-04-26 20:56:26 train_lshot.py:119] INFO Meta Val 75: 0.6281066805124282
[2021-04-26 20:56:37 train_lshot.py:257] INFO Epoch: [76][0/150] Time 10.231 (10.231) Data 9.578 (9.578) Loss 0.4216 (0.4216) Prec@1 88.672 (88.672) Prec@5 96.875 (96.875)
[2021-04-26 20:56:43 train_lshot.py:257] INFO Epoch: [76][10/150] Time 0.618 (1.493) Data 0.000 (0.871) Loss 0.3933 (0.3557) Prec@1 89.844 (90.661) Prec@5 96.875 (97.585)
[2021-04-26 20:56:49 train_lshot.py:257] INFO Epoch: [76][20/150] Time 0.620 (1.079) Data 0.000 (0.457) Loss 0.4527 (0.3685) Prec@1 87.891 (90.011) Prec@5 96.094 (97.433)
[2021-04-26 20:56:55 train_lshot.py:257] INFO Epoch: [76][30/150] Time 0.624 (0.932) Data 0.001 (0.310) Loss 0.3466 (0.3722) Prec@1 91.797 (90.033) Prec@5 97.266 (97.480)
[2021-04-26 20:57:01 train_lshot.py:257] INFO Epoch: [76][40/150] Time 0.620 (0.857) Data 0.001 (0.234) Loss 0.3913 (0.3767) Prec@1 89.844 (89.987) Prec@5 96.875 (97.447)
[2021-04-26 20:57:08 train_lshot.py:257] INFO Epoch: [76][50/150] Time 0.624 (0.811) Data 0.001 (0.188) Loss 0.3948 (0.3720) Prec@1 89.844 (90.066) Prec@5 96.875 (97.549)
[2021-04-26 20:57:14 train_lshot.py:257] INFO Epoch: [76][60/150] Time 0.634 (0.780) Data 0.001 (0.158) Loss 0.4458 (0.3718) Prec@1 88.672 (90.081) Prec@5 97.266 (97.490)
[2021-04-26 20:57:20 train_lshot.py:257] INFO Epoch: [76][70/150] Time 0.625 (0.758) Data 0.002 (0.136) Loss 0.3216 (0.3704) Prec@1 91.406 (90.163) Prec@5 97.656 (97.486)
[2021-04-26 20:57:26 train_lshot.py:257] INFO Epoch: [76][80/150] Time 0.621 (0.741) Data 0.000 (0.119) Loss 0.3580 (0.3695) Prec@1 89.844 (90.186) Prec@5 98.828 (97.497)
[2021-04-26 20:57:33 train_lshot.py:257] INFO Epoch: [76][90/150] Time 0.620 (0.728) Data 0.000 (0.106) Loss 0.3032 (0.3656) Prec@1 91.016 (90.256) Prec@5 98.828 (97.536)
[2021-04-26 20:57:39 train_lshot.py:257] INFO Epoch: [76][100/150] Time 0.620 (0.717) Data 0.000 (0.095) Loss 0.4276 (0.3635) Prec@1 89.453 (90.331) Prec@5 96.875 (97.583)
[2021-04-26 20:57:45 train_lshot.py:257] INFO Epoch: [76][110/150] Time 0.622 (0.709) Data 0.000 (0.087) Loss 0.3360 (0.3672) Prec@1 89.453 (90.220) Prec@5 98.438 (97.537)
[2021-04-26 20:57:51 train_lshot.py:257] INFO Epoch: [76][120/150] Time 0.622 (0.701) Data 0.000 (0.080) Loss 0.4765 (0.3682) Prec@1 85.156 (90.205) Prec@5 98.047 (97.527)
[2021-04-26 20:57:57 train_lshot.py:257] INFO Epoch: [76][130/150] Time 0.625 (0.695) Data 0.000 (0.074) Loss 0.3058 (0.3669) Prec@1 92.188 (90.252) Prec@5 98.438 (97.552)
[2021-04-26 20:58:04 train_lshot.py:257] INFO Epoch: [76][140/150] Time 0.623 (0.690) Data 0.000 (0.068) Loss 0.3464 (0.3665) Prec@1 91.797 (90.257) Prec@5 96.484 (97.568)
[2021-04-26 20:58:20 train_lshot.py:257] INFO Epoch: [77][0/150] Time 10.800 (10.800) Data 10.150 (10.150) Loss 0.3212 (0.3212) Prec@1 91.797 (91.797) Prec@5 97.656 (97.656)
[2021-04-26 20:58:27 train_lshot.py:257] INFO Epoch: [77][10/150] Time 0.623 (1.546) Data 0.002 (0.923) Loss 0.4103 (0.3487) Prec@1 87.891 (90.554) Prec@5 97.656 (97.869)
[2021-04-26 20:58:33 train_lshot.py:257] INFO Epoch: [77][20/150] Time 0.632 (1.106) Data 0.001 (0.484) Loss 0.2954 (0.3388) Prec@1 92.578 (90.848) Prec@5 98.047 (97.972)
[2021-04-26 20:58:39 train_lshot.py:257] INFO Epoch: [77][30/150] Time 0.617 (0.950) Data 0.000 (0.328) Loss 0.3749 (0.3396) Prec@1 87.500 (90.701) Prec@5 98.438 (98.022)
[2021-04-26 20:58:45 train_lshot.py:257] INFO Epoch: [77][40/150] Time 0.629 (0.871) Data 0.002 (0.248) Loss 0.3533 (0.3450) Prec@1 90.234 (90.482) Prec@5 98.047 (97.847)
[2021-04-26 20:58:52 train_lshot.py:257] INFO Epoch: [77][50/150] Time 0.622 (0.822) Data 0.001 (0.200) Loss 0.4168 (0.3498) Prec@1 89.844 (90.533) Prec@5 96.484 (97.741)
[2021-04-26 20:58:58 train_lshot.py:257] INFO Epoch: [77][60/150] Time 0.622 (0.790) Data 0.000 (0.167) Loss 0.3291 (0.3562) Prec@1 88.281 (90.260) Prec@5 98.438 (97.669)
[2021-04-26 20:59:04 train_lshot.py:257] INFO Epoch: [77][70/150] Time 0.623 (0.766) Data 0.001 (0.144) Loss 0.3315 (0.3607) Prec@1 90.625 (90.207) Prec@5 98.047 (97.651)
[2021-04-26 20:59:10 train_lshot.py:257] INFO Epoch: [77][80/150] Time 0.623 (0.749) Data 0.001 (0.126) Loss 0.3498 (0.3604) Prec@1 88.672 (90.205) Prec@5 97.656 (97.651)
[2021-04-26 20:59:17 train_lshot.py:257] INFO Epoch: [77][90/150] Time 0.619 (0.735) Data 0.000 (0.112) Loss 0.4313 (0.3613) Prec@1 89.453 (90.256) Prec@5 96.875 (97.656)
[2021-04-26 20:59:23 train_lshot.py:257] INFO Epoch: [77][100/150] Time 0.620 (0.724) Data 0.000 (0.101) Loss 0.3953 (0.3626) Prec@1 88.281 (90.223) Prec@5 97.656 (97.625)
[2021-04-26 20:59:29 train_lshot.py:257] INFO Epoch: [77][110/150] Time 0.622 (0.714) Data 0.000 (0.092) Loss 0.3890 (0.3604) Prec@1 87.500 (90.245) Prec@5 98.438 (97.663)
[2021-04-26 20:59:35 train_lshot.py:257] INFO Epoch: [77][120/150] Time 0.621 (0.707) Data 0.000 (0.084) Loss 0.4024 (0.3608) Prec@1 90.234 (90.270) Prec@5 98.047 (97.666)
[2021-04-26 20:59:41 train_lshot.py:257] INFO Epoch: [77][130/150] Time 0.618 (0.700) Data 0.000 (0.078) Loss 0.3774 (0.3595) Prec@1 89.453 (90.318) Prec@5 98.047 (97.683)
[2021-04-26 20:59:48 train_lshot.py:257] INFO Epoch: [77][140/150] Time 0.621 (0.695) Data 0.000 (0.072) Loss 0.3123 (0.3602) Prec@1 93.359 (90.290) Prec@5 98.828 (97.687)
[2021-04-26 21:00:04 train_lshot.py:257] INFO Epoch: [78][0/150] Time 9.891 (9.891) Data 9.253 (9.253) Loss 0.3724 (0.3724) Prec@1 89.062 (89.062) Prec@5 98.047 (98.047)
[2021-04-26 21:00:10 train_lshot.py:257] INFO Epoch: [78][10/150] Time 0.618 (1.462) Data 0.000 (0.842) Loss 0.3810 (0.3631) Prec@1 92.578 (90.412) Prec@5 98.047 (97.869)
[2021-04-26 21:00:16 train_lshot.py:257] INFO Epoch: [78][20/150] Time 0.630 (1.062) Data 0.001 (0.441) Loss 0.4717 (0.3519) Prec@1 85.547 (90.718) Prec@5 96.484 (98.028)
[2021-04-26 21:00:22 train_lshot.py:257] INFO Epoch: [78][30/150] Time 0.623 (0.920) Data 0.000 (0.299) Loss 0.4259 (0.3608) Prec@1 89.062 (90.486) Prec@5 98.828 (97.870)
[2021-04-26 21:00:28 train_lshot.py:257] INFO Epoch: [78][40/150] Time 0.622 (0.848) Data 0.001 (0.226) Loss 0.3907 (0.3613) Prec@1 89.453 (90.482) Prec@5 97.656 (97.761)
[2021-04-26 21:00:35 train_lshot.py:257] INFO Epoch: [78][50/150] Time 0.621 (0.804) Data 0.000 (0.182) Loss 0.3058 (0.3616) Prec@1 91.797 (90.418) Prec@5 97.656 (97.771)
[2021-04-26 21:00:41 train_lshot.py:257] INFO Epoch: [78][60/150] Time 0.630 (0.775) Data 0.001 (0.152) Loss 0.2999 (0.3622) Prec@1 92.578 (90.407) Prec@5 98.438 (97.733)
[2021-04-26 21:00:47 train_lshot.py:257] INFO Epoch: [78][70/150] Time 0.621 (0.753) Data 0.001 (0.131) Loss 0.3799 (0.3613) Prec@1 89.453 (90.388) Prec@5 97.266 (97.700)
[2021-04-26 21:00:53 train_lshot.py:257] INFO Epoch: [78][80/150] Time 0.620 (0.737) Data 0.000 (0.115) Loss 0.4471 (0.3633) Prec@1 87.109 (90.316) Prec@5 96.094 (97.676)
[2021-04-26 21:01:00 train_lshot.py:257] INFO Epoch: [78][90/150] Time 0.619 (0.724) Data 0.000 (0.102) Loss 0.3447 (0.3622) Prec@1 90.625 (90.355) Prec@5 97.656 (97.635)
[2021-04-26 21:01:06 train_lshot.py:257] INFO Epoch: [78][100/150] Time 0.624 (0.714) Data 0.000 (0.092) Loss 0.3381 (0.3606) Prec@1 90.234 (90.401) Prec@5 98.828 (97.656)
[2021-04-26 21:01:12 train_lshot.py:257] INFO Epoch: [78][110/150] Time 0.618 (0.706) Data 0.000 (0.084) Loss 0.4255 (0.3608) Prec@1 90.625 (90.438) Prec@5 95.312 (97.653)
[2021-04-26 21:01:18 train_lshot.py:257] INFO Epoch: [78][120/150] Time 0.622 (0.699) Data 0.000 (0.077) Loss 0.3506 (0.3613) Prec@1 90.625 (90.402) Prec@5 97.266 (97.672)
[2021-04-26 21:01:24 train_lshot.py:257] INFO Epoch: [78][130/150] Time 0.621 (0.693) Data 0.000 (0.071) Loss 0.3259 (0.3629) Prec@1 92.578 (90.327) Prec@5 97.266 (97.650)
[2021-04-26 21:01:31 train_lshot.py:257] INFO Epoch: [78][140/150] Time 0.620 (0.688) Data 0.000 (0.066) Loss 0.4520 (0.3633) Prec@1 88.281 (90.331) Prec@5 96.094 (97.667)
[2021-04-26 21:01:48 train_lshot.py:257] INFO Epoch: [79][0/150] Time 10.972 (10.972) Data 10.322 (10.322) Loss 0.3710 (0.3710) Prec@1 91.406 (91.406) Prec@5 97.266 (97.266)
[2021-04-26 21:01:54 train_lshot.py:257] INFO Epoch: [79][10/150] Time 0.624 (1.561) Data 0.000 (0.939) Loss 0.3539 (0.3725) Prec@1 91.406 (90.163) Prec@5 98.047 (97.550)
[2021-04-26 21:02:00 train_lshot.py:257] INFO Epoch: [79][20/150] Time 0.624 (1.114) Data 0.000 (0.492) Loss 0.3150 (0.3528) Prec@1 89.844 (90.532) Prec@5 99.609 (97.898)
[2021-04-26 21:02:06 train_lshot.py:257] INFO Epoch: [79][30/150] Time 0.630 (0.956) Data 0.001 (0.334) Loss 0.4785 (0.3635) Prec@1 85.938 (90.108) Prec@5 96.484 (97.795)
[2021-04-26 21:02:12 train_lshot.py:257] INFO Epoch: [79][40/150] Time 0.622 (0.875) Data 0.001 (0.252) Loss 0.4141 (0.3723) Prec@1 89.844 (89.977) Prec@5 96.484 (97.618)
[2021-04-26 21:02:19 train_lshot.py:257] INFO Epoch: [79][50/150] Time 0.623 (0.826) Data 0.000 (0.203) Loss 0.2637 (0.3751) Prec@1 93.750 (89.890) Prec@5 99.219 (97.541)
[2021-04-26 21:02:25 train_lshot.py:257] INFO Epoch: [79][60/150] Time 0.623 (0.792) Data 0.000 (0.170) Loss 0.3758 (0.3754) Prec@1 89.844 (89.863) Prec@5 98.047 (97.515)
[2021-04-26 21:02:31 train_lshot.py:257] INFO Epoch: [79][70/150] Time 0.625 (0.769) Data 0.001 (0.146) Loss 0.4069 (0.3729) Prec@1 88.672 (90.014) Prec@5 98.047 (97.530)
[2021-04-26 21:02:37 train_lshot.py:257] INFO Epoch: [79][80/150] Time 0.619 (0.750) Data 0.001 (0.128) Loss 0.4686 (0.3747) Prec@1 90.234 (89.979) Prec@5 95.703 (97.478)
[2021-04-26 21:02:44 train_lshot.py:257] INFO Epoch: [79][90/150] Time 0.620 (0.736) Data 0.000 (0.114) Loss 0.2490 (0.3716) Prec@1 94.531 (90.071) Prec@5 98.828 (97.536)
[2021-04-26 21:02:50 train_lshot.py:257] INFO Epoch: [79][100/150] Time 0.621 (0.725) Data 0.000 (0.103) Loss 0.3183 (0.3712) Prec@1 91.797 (90.107) Prec@5 97.266 (97.513)
[2021-04-26 21:02:56 train_lshot.py:257] INFO Epoch: [79][110/150] Time 0.621 (0.716) Data 0.000 (0.093) Loss 0.4036 (0.3714) Prec@1 89.062 (90.108) Prec@5 97.656 (97.537)
[2021-04-26 21:03:02 train_lshot.py:257] INFO Epoch: [79][120/150] Time 0.621 (0.708) Data 0.000 (0.086) Loss 0.3885 (0.3710) Prec@1 89.844 (90.134) Prec@5 97.656 (97.566)
[2021-04-26 21:03:08 train_lshot.py:257] INFO Epoch: [79][130/150] Time 0.622 (0.701) Data 0.000 (0.079) Loss 0.3185 (0.3725) Prec@1 91.406 (90.100) Prec@5 98.438 (97.537)
[2021-04-26 21:03:15 train_lshot.py:257] INFO Epoch: [79][140/150] Time 0.622 (0.696) Data 0.000 (0.074) Loss 0.2435 (0.3708) Prec@1 93.359 (90.118) Prec@5 99.609 (97.565)
[2021-04-26 21:04:02 train_lshot.py:119] INFO Meta Val 79: 0.6281600125432014
[2021-04-26 21:04:12 train_lshot.py:257] INFO Epoch: [80][0/150] Time 10.648 (10.648) Data 10.007 (10.007) Loss 0.3939 (0.3939) Prec@1 91.406 (91.406) Prec@5 96.094 (96.094)
[2021-04-26 21:04:19 train_lshot.py:257] INFO Epoch: [80][10/150] Time 0.618 (1.531) Data 0.000 (0.910) Loss 0.4148 (0.3730) Prec@1 88.672 (89.986) Prec@5 98.047 (98.082)
[2021-04-26 21:04:25 train_lshot.py:257] INFO Epoch: [80][20/150] Time 0.619 (1.097) Data 0.000 (0.477) Loss 0.2651 (0.3720) Prec@1 91.016 (90.011) Prec@5 99.219 (97.619)
[2021-04-26 21:04:31 train_lshot.py:257] INFO Epoch: [80][30/150] Time 0.620 (0.943) Data 0.001 (0.323) Loss 0.3501 (0.3718) Prec@1 91.797 (90.108) Prec@5 97.266 (97.581)
[2021-04-26 21:04:37 train_lshot.py:257] INFO Epoch: [80][40/150] Time 0.622 (0.865) Data 0.000 (0.245) Loss 0.3873 (0.3766) Prec@1 88.672 (89.949) Prec@5 98.438 (97.523)
[2021-04-26 21:04:44 train_lshot.py:257] INFO Epoch: [80][50/150] Time 0.623 (0.818) Data 0.000 (0.197) Loss 0.4595 (0.3758) Prec@1 84.766 (89.982) Prec@5 98.047 (97.557)
[2021-04-26 21:04:50 train_lshot.py:257] INFO Epoch: [80][60/150] Time 0.630 (0.786) Data 0.001 (0.165) Loss 0.3179 (0.3715) Prec@1 90.625 (90.177) Prec@5 98.438 (97.618)
[2021-04-26 21:04:56 train_lshot.py:257] INFO Epoch: [80][70/150] Time 0.631 (0.763) Data 0.002 (0.142) Loss 0.3937 (0.3696) Prec@1 89.844 (90.245) Prec@5 96.875 (97.585)
[2021-04-26 21:05:02 train_lshot.py:257] INFO Epoch: [80][80/150] Time 0.625 (0.746) Data 0.000 (0.124) Loss 0.4593 (0.3701) Prec@1 87.891 (90.205) Prec@5 95.703 (97.536)
[2021-04-26 21:05:08 train_lshot.py:257] INFO Epoch: [80][90/150] Time 0.622 (0.732) Data 0.000 (0.111) Loss 0.3141 (0.3694) Prec@1 91.016 (90.191) Prec@5 97.266 (97.515)
[2021-04-26 21:05:15 train_lshot.py:257] INFO Epoch: [80][100/150] Time 0.622 (0.721) Data 0.000 (0.100) Loss 0.3152 (0.3680) Prec@1 91.016 (90.219) Prec@5 98.047 (97.490)
[2021-04-26 21:05:21 train_lshot.py:257] INFO Epoch: [80][110/150] Time 0.621 (0.712) Data 0.000 (0.091) Loss 0.3519 (0.3674) Prec@1 89.062 (90.224) Prec@5 96.484 (97.484)
[2021-04-26 21:05:27 train_lshot.py:257] INFO Epoch: [80][120/150] Time 0.626 (0.704) Data 0.000 (0.083) Loss 0.3443 (0.3672) Prec@1 89.844 (90.257) Prec@5 97.656 (97.505)
[2021-04-26 21:05:33 train_lshot.py:257] INFO Epoch: [80][130/150] Time 0.619 (0.698) Data 0.000 (0.077) Loss 0.3556 (0.3696) Prec@1 89.062 (90.184) Prec@5 98.438 (97.492)
[2021-04-26 21:05:40 train_lshot.py:257] INFO Epoch: [80][140/150] Time 0.623 (0.693) Data 0.000 (0.071) Loss 0.3815 (0.3680) Prec@1 89.844 (90.232) Prec@5 98.828 (97.540)
[2021-04-26 21:05:55 train_lshot.py:257] INFO Epoch: [81][0/150] Time 9.503 (9.503) Data 8.841 (8.841) Loss 0.3220 (0.3220) Prec@1 91.797 (91.797) Prec@5 97.656 (97.656)
[2021-04-26 21:06:01 train_lshot.py:257] INFO Epoch: [81][10/150] Time 0.622 (1.445) Data 0.001 (0.821) Loss 0.3115 (0.3225) Prec@1 92.578 (90.874) Prec@5 98.828 (98.295)
[2021-04-26 21:06:08 train_lshot.py:257] INFO Epoch: [81][20/150] Time 0.619 (1.053) Data 0.000 (0.430) Loss 0.3909 (0.3494) Prec@1 90.625 (90.253) Prec@5 96.875 (97.731)
[2021-04-26 21:06:14 train_lshot.py:257] INFO Epoch: [81][30/150] Time 0.620 (0.915) Data 0.001 (0.292) Loss 0.4294 (0.3448) Prec@1 88.281 (90.486) Prec@5 96.875 (97.807)
[2021-04-26 21:06:20 train_lshot.py:257] INFO Epoch: [81][40/150] Time 0.623 (0.843) Data 0.000 (0.221) Loss 0.4435 (0.3505) Prec@1 88.281 (90.520) Prec@5 96.094 (97.713)
[2021-04-26 21:06:26 train_lshot.py:257] INFO Epoch: [81][50/150] Time 0.623 (0.800) Data 0.000 (0.178) Loss 0.3537 (0.3511) Prec@1 91.406 (90.472) Prec@5 97.266 (97.702)
[2021-04-26 21:06:33 train_lshot.py:257] INFO Epoch: [81][60/150] Time 0.623 (0.771) Data 0.000 (0.149) Loss 0.3525 (0.3534) Prec@1 91.016 (90.375) Prec@5 97.266 (97.688)
[2021-04-26 21:06:39 train_lshot.py:257] INFO Epoch: [81][70/150] Time 0.622 (0.750) Data 0.001 (0.128) Loss 0.2614 (0.3532) Prec@1 93.750 (90.416) Prec@5 98.047 (97.689)
[2021-04-26 21:06:45 train_lshot.py:257] INFO Epoch: [81][80/150] Time 0.619 (0.734) Data 0.000 (0.112) Loss 0.3349 (0.3542) Prec@1 91.016 (90.360) Prec@5 98.438 (97.704)
[2021-04-26 21:06:51 train_lshot.py:257] INFO Epoch: [81][90/150] Time 0.622 (0.722) Data 0.000 (0.100) Loss 0.3240 (0.3535) Prec@1 89.844 (90.380) Prec@5 98.438 (97.729)
[2021-04-26 21:06:57 train_lshot.py:257] INFO Epoch: [81][100/150] Time 0.625 (0.712) Data 0.000 (0.090) Loss 0.3324 (0.3538) Prec@1 91.016 (90.374) Prec@5 98.438 (97.749)
[2021-04-26 21:07:04 train_lshot.py:257] INFO Epoch: [81][110/150] Time 0.623 (0.704) Data 0.000 (0.082) Loss 0.2726 (0.3566) Prec@1 92.969 (90.329) Prec@5 98.047 (97.681)
[2021-04-26 21:07:10 train_lshot.py:257] INFO Epoch: [81][120/150] Time 0.625 (0.697) Data 0.000 (0.075) Loss 0.3790 (0.3579) Prec@1 90.234 (90.318) Prec@5 97.266 (97.672)
[2021-04-26 21:07:16 train_lshot.py:257] INFO Epoch: [81][130/150] Time 0.624 (0.691) Data 0.000 (0.069) Loss 0.3203 (0.3598) Prec@1 91.797 (90.252) Prec@5 99.219 (97.638)
[2021-04-26 21:07:22 train_lshot.py:257] INFO Epoch: [81][140/150] Time 0.624 (0.686) Data 0.000 (0.064) Loss 0.4062 (0.3613) Prec@1 89.844 (90.215) Prec@5 96.875 (97.617)
[2021-04-26 21:07:38 train_lshot.py:257] INFO Epoch: [82][0/150] Time 10.099 (10.099) Data 9.444 (9.444) Loss 0.3683 (0.3683) Prec@1 87.891 (87.891) Prec@5 98.828 (98.828)
[2021-04-26 21:07:45 train_lshot.py:257] INFO Epoch: [82][10/150] Time 0.622 (1.481) Data 0.000 (0.859) Loss 0.2947 (0.3552) Prec@1 91.797 (90.341) Prec@5 99.219 (98.047)
[2021-04-26 21:07:51 train_lshot.py:257] INFO Epoch: [82][20/150] Time 0.624 (1.072) Data 0.001 (0.450) Loss 0.3065 (0.3531) Prec@1 92.578 (90.272) Prec@5 98.828 (98.028)
[2021-04-26 21:07:57 train_lshot.py:257] INFO Epoch: [82][30/150] Time 0.620 (0.927) Data 0.000 (0.305) Loss 0.3496 (0.3520) Prec@1 90.234 (90.335) Prec@5 98.438 (98.022)
[2021-04-26 21:08:03 train_lshot.py:257] INFO Epoch: [82][40/150] Time 0.620 (0.853) Data 0.001 (0.231) Loss 0.3903 (0.3548) Prec@1 90.625 (90.292) Prec@5 96.875 (97.885)
[2021-04-26 21:08:09 train_lshot.py:257] INFO Epoch: [82][50/150] Time 0.621 (0.808) Data 0.000 (0.186) Loss 0.3926 (0.3581) Prec@1 89.062 (90.135) Prec@5 98.047 (97.878)
[2021-04-26 21:08:16 train_lshot.py:257] INFO Epoch: [82][60/150] Time 0.620 (0.777) Data 0.000 (0.155) Loss 0.3582 (0.3590) Prec@1 89.453 (90.158) Prec@5 98.047 (97.861)
[2021-04-26 21:08:22 train_lshot.py:257] INFO Epoch: [82][70/150] Time 0.619 (0.756) Data 0.002 (0.134) Loss 0.2909 (0.3565) Prec@1 92.578 (90.251) Prec@5 98.047 (97.898)
[2021-04-26 21:08:28 train_lshot.py:257] INFO Epoch: [82][80/150] Time 0.619 (0.739) Data 0.000 (0.117) Loss 0.2648 (0.3559) Prec@1 92.969 (90.287) Prec@5 99.609 (97.844)
[2021-04-26 21:08:34 train_lshot.py:257] INFO Epoch: [82][90/150] Time 0.620 (0.726) Data 0.000 (0.104) Loss 0.2801 (0.3544) Prec@1 92.578 (90.359) Prec@5 99.609 (97.879)
[2021-04-26 21:08:41 train_lshot.py:257] INFO Epoch: [82][100/150] Time 0.619 (0.716) Data 0.000 (0.094) Loss 0.2752 (0.3533) Prec@1 94.141 (90.393) Prec@5 98.047 (97.888)
[2021-04-26 21:08:47 train_lshot.py:257] INFO Epoch: [82][110/150] Time 0.620 (0.707) Data 0.000 (0.086) Loss 0.3396 (0.3541) Prec@1 90.625 (90.379) Prec@5 98.047 (97.871)
[2021-04-26 21:08:53 train_lshot.py:257] INFO Epoch: [82][120/150] Time 0.623 (0.700) Data 0.000 (0.079) Loss 0.3518 (0.3580) Prec@1 90.625 (90.270) Prec@5 98.438 (97.814)
[2021-04-26 21:08:59 train_lshot.py:257] INFO Epoch: [82][130/150] Time 0.622 (0.694) Data 0.000 (0.073) Loss 0.2960 (0.3608) Prec@1 92.578 (90.193) Prec@5 98.438 (97.767)
[2021-04-26 21:09:05 train_lshot.py:257] INFO Epoch: [82][140/150] Time 0.624 (0.689) Data 0.000 (0.067) Loss 0.4886 (0.3602) Prec@1 87.500 (90.245) Prec@5 96.484 (97.753)
[2021-04-26 21:09:21 train_lshot.py:257] INFO Epoch: [83][0/150] Time 9.313 (9.313) Data 8.641 (8.641) Loss 0.3362 (0.3362) Prec@1 91.406 (91.406) Prec@5 99.219 (99.219)
[2021-04-26 21:09:27 train_lshot.py:257] INFO Epoch: [83][10/150] Time 0.616 (1.409) Data 0.000 (0.786) Loss 0.4380 (0.3538) Prec@1 90.234 (90.838) Prec@5 96.484 (97.763)
[2021-04-26 21:09:33 train_lshot.py:257] INFO Epoch: [83][20/150] Time 0.621 (1.034) Data 0.000 (0.412) Loss 0.3168 (0.3662) Prec@1 93.359 (90.848) Prec@5 98.438 (97.489)
[2021-04-26 21:09:39 train_lshot.py:257] INFO Epoch: [83][30/150] Time 0.621 (0.901) Data 0.000 (0.279) Loss 0.3629 (0.3713) Prec@1 88.281 (90.650) Prec@5 98.047 (97.442)
[2021-04-26 21:09:46 train_lshot.py:257] INFO Epoch: [83][40/150] Time 0.618 (0.834) Data 0.001 (0.211) Loss 0.3515 (0.3676) Prec@1 91.016 (90.520) Prec@5 97.656 (97.485)
[2021-04-26 21:09:52 train_lshot.py:257] INFO Epoch: [83][50/150] Time 0.622 (0.793) Data 0.000 (0.170) Loss 0.4672 (0.3686) Prec@1 86.328 (90.395) Prec@5 96.875 (97.480)
[2021-04-26 21:09:58 train_lshot.py:257] INFO Epoch: [83][60/150] Time 0.620 (0.764) Data 0.001 (0.142) Loss 0.3825 (0.3665) Prec@1 89.453 (90.369) Prec@5 96.484 (97.541)
[2021-04-26 21:10:04 train_lshot.py:257] INFO Epoch: [83][70/150] Time 0.621 (0.744) Data 0.001 (0.122) Loss 0.3574 (0.3645) Prec@1 89.062 (90.306) Prec@5 98.047 (97.557)
[2021-04-26 21:10:11 train_lshot.py:257] INFO Epoch: [83][80/150] Time 0.624 (0.732) Data 0.000 (0.107) Loss 0.3769 (0.3628) Prec@1 90.234 (90.350) Prec@5 97.266 (97.545)
[2021-04-26 21:10:17 train_lshot.py:257] INFO Epoch: [83][90/150] Time 0.624 (0.720) Data 0.000 (0.095) Loss 0.3795 (0.3628) Prec@1 88.672 (90.389) Prec@5 97.266 (97.540)
[2021-04-26 21:10:23 train_lshot.py:257] INFO Epoch: [83][100/150] Time 0.620 (0.710) Data 0.000 (0.086) Loss 0.3506 (0.3624) Prec@1 90.234 (90.428) Prec@5 98.047 (97.560)
[2021-04-26 21:10:29 train_lshot.py:257] INFO Epoch: [83][110/150] Time 0.621 (0.702) Data 0.000 (0.078) Loss 0.4213 (0.3622) Prec@1 89.062 (90.470) Prec@5 98.047 (97.561)
[2021-04-26 21:10:36 train_lshot.py:257] INFO Epoch: [83][120/150] Time 0.619 (0.695) Data 0.000 (0.072) Loss 0.3464 (0.3636) Prec@1 91.016 (90.393) Prec@5 97.266 (97.569)
[2021-04-26 21:10:42 train_lshot.py:257] INFO Epoch: [83][130/150] Time 0.625 (0.689) Data 0.000 (0.066) Loss 0.3300 (0.3633) Prec@1 91.016 (90.380) Prec@5 97.656 (97.555)
[2021-04-26 21:10:48 train_lshot.py:257] INFO Epoch: [83][140/150] Time 0.619 (0.684) Data 0.000 (0.062) Loss 0.3806 (0.3623) Prec@1 90.625 (90.398) Prec@5 96.484 (97.590)
[2021-04-26 21:11:35 train_lshot.py:119] INFO Meta Val 83: 0.6212800130844116
[2021-04-26 21:11:46 train_lshot.py:257] INFO Epoch: [84][0/150] Time 10.282 (10.282) Data 9.637 (9.637) Loss 0.3711 (0.3711) Prec@1 90.234 (90.234) Prec@5 97.266 (97.266)
[2021-04-26 21:11:52 train_lshot.py:257] INFO Epoch: [84][10/150] Time 0.619 (1.498) Data 0.000 (0.877) Loss 0.3605 (0.3816) Prec@1 91.406 (89.595) Prec@5 96.484 (97.443)
[2021-04-26 21:11:58 train_lshot.py:257] INFO Epoch: [84][20/150] Time 0.623 (1.080) Data 0.000 (0.460) Loss 0.3190 (0.3609) Prec@1 93.359 (90.662) Prec@5 98.047 (97.545)
[2021-04-26 21:12:05 train_lshot.py:257] INFO Epoch: [84][30/150] Time 0.623 (0.932) Data 0.000 (0.311) Loss 0.3125 (0.3624) Prec@1 91.797 (90.814) Prec@5 98.438 (97.631)
[2021-04-26 21:12:11 train_lshot.py:257] INFO Epoch: [84][40/150] Time 0.621 (0.857) Data 0.001 (0.236) Loss 0.4160 (0.3638) Prec@1 89.453 (90.673) Prec@5 95.703 (97.609)
[2021-04-26 21:12:17 train_lshot.py:257] INFO Epoch: [84][50/150] Time 0.620 (0.811) Data 0.000 (0.190) Loss 0.3476 (0.3611) Prec@1 91.406 (90.755) Prec@5 96.875 (97.603)
[2021-04-26 21:12:23 train_lshot.py:257] INFO Epoch: [84][60/150] Time 0.625 (0.780) Data 0.001 (0.159) Loss 0.3800 (0.3660) Prec@1 88.672 (90.638) Prec@5 98.828 (97.496)
[2021-04-26 21:12:29 train_lshot.py:257] INFO Epoch: [84][70/150] Time 0.631 (0.758) Data 0.002 (0.136) Loss 0.2996 (0.3602) Prec@1 93.359 (90.790) Prec@5 97.266 (97.535)
[2021-04-26 21:12:36 train_lshot.py:257] INFO Epoch: [84][80/150] Time 0.622 (0.741) Data 0.000 (0.120) Loss 0.3722 (0.3594) Prec@1 89.844 (90.746) Prec@5 97.656 (97.565)
[2021-04-26 21:12:42 train_lshot.py:257] INFO Epoch: [84][90/150] Time 0.619 (0.728) Data 0.000 (0.106) Loss 0.4083 (0.3582) Prec@1 89.453 (90.775) Prec@5 96.875 (97.588)
[2021-04-26 21:12:48 train_lshot.py:257] INFO Epoch: [84][100/150] Time 0.622 (0.717) Data 0.000 (0.096) Loss 0.4427 (0.3606) Prec@1 87.500 (90.598) Prec@5 96.875 (97.579)
[2021-04-26 21:12:54 train_lshot.py:257] INFO Epoch: [84][110/150] Time 0.621 (0.709) Data 0.000 (0.087) Loss 0.3733 (0.3615) Prec@1 90.234 (90.597) Prec@5 97.656 (97.579)
[2021-04-26 21:13:01 train_lshot.py:257] INFO Epoch: [84][120/150] Time 0.622 (0.701) Data 0.000 (0.080) Loss 0.3577 (0.3606) Prec@1 90.625 (90.615) Prec@5 98.047 (97.624)
[2021-04-26 21:13:07 train_lshot.py:257] INFO Epoch: [84][130/150] Time 0.622 (0.695) Data 0.000 (0.074) Loss 0.4067 (0.3595) Prec@1 90.234 (90.604) Prec@5 96.484 (97.647)
[2021-04-26 21:13:13 train_lshot.py:257] INFO Epoch: [84][140/150] Time 0.621 (0.690) Data 0.000 (0.069) Loss 0.2869 (0.3572) Prec@1 92.188 (90.672) Prec@5 98.438 (97.687)
[2021-04-26 21:13:29 train_lshot.py:257] INFO Epoch: [85][0/150] Time 9.828 (9.828) Data 9.176 (9.176) Loss 0.3053 (0.3053) Prec@1 93.359 (93.359) Prec@5 98.438 (98.438)
[2021-04-26 21:13:35 train_lshot.py:257] INFO Epoch: [85][10/150] Time 0.620 (1.456) Data 0.000 (0.835) Loss 0.4092 (0.3580) Prec@1 90.625 (90.589) Prec@5 97.266 (97.443)
[2021-04-26 21:13:41 train_lshot.py:257] INFO Epoch: [85][20/150] Time 0.622 (1.060) Data 0.000 (0.438) Loss 0.3402 (0.3474) Prec@1 90.625 (90.885) Prec@5 98.047 (97.712)
[2021-04-26 21:13:47 train_lshot.py:257] INFO Epoch: [85][30/150] Time 0.620 (0.918) Data 0.000 (0.297) Loss 0.4189 (0.3472) Prec@1 89.062 (90.877) Prec@5 96.094 (97.694)
[2021-04-26 21:13:54 train_lshot.py:257] INFO Epoch: [85][40/150] Time 0.635 (0.847) Data 0.001 (0.225) Loss 0.4180 (0.3550) Prec@1 88.672 (90.568) Prec@5 97.266 (97.685)
[2021-04-26 21:14:00 train_lshot.py:257] INFO Epoch: [85][50/150] Time 0.624 (0.803) Data 0.001 (0.181) Loss 0.3766 (0.3592) Prec@1 89.062 (90.479) Prec@5 98.047 (97.664)
[2021-04-26 21:14:06 train_lshot.py:257] INFO Epoch: [85][60/150] Time 0.620 (0.773) Data 0.001 (0.151) Loss 0.3142 (0.3572) Prec@1 91.016 (90.523) Prec@5 98.047 (97.707)
[2021-04-26 21:14:12 train_lshot.py:257] INFO Epoch: [85][70/150] Time 0.621 (0.752) Data 0.001 (0.130) Loss 0.4492 (0.3636) Prec@1 88.281 (90.388) Prec@5 96.484 (97.629)
[2021-04-26 21:14:19 train_lshot.py:257] INFO Epoch: [85][80/150] Time 0.620 (0.736) Data 0.000 (0.114) Loss 0.3505 (0.3637) Prec@1 91.797 (90.403) Prec@5 96.875 (97.637)
[2021-04-26 21:14:25 train_lshot.py:257] INFO Epoch: [85][90/150] Time 0.622 (0.723) Data 0.000 (0.101) Loss 0.3645 (0.3625) Prec@1 92.188 (90.428) Prec@5 97.266 (97.673)
[2021-04-26 21:14:31 train_lshot.py:257] INFO Epoch: [85][100/150] Time 0.624 (0.713) Data 0.000 (0.091) Loss 0.3399 (0.3579) Prec@1 91.016 (90.513) Prec@5 98.047 (97.734)
[2021-04-26 21:14:37 train_lshot.py:257] INFO Epoch: [85][110/150] Time 0.622 (0.705) Data 0.000 (0.083) Loss 0.4326 (0.3574) Prec@1 87.109 (90.495) Prec@5 95.312 (97.727)
[2021-04-26 21:14:43 train_lshot.py:257] INFO Epoch: [85][120/150] Time 0.625 (0.698) Data 0.000 (0.076) Loss 0.4114 (0.3603) Prec@1 88.672 (90.389) Prec@5 97.266 (97.695)
[2021-04-26 21:14:50 train_lshot.py:257] INFO Epoch: [85][130/150] Time 0.622 (0.692) Data 0.000 (0.071) Loss 0.4291 (0.3624) Prec@1 90.234 (90.342) Prec@5 96.875 (97.650)
[2021-04-26 21:14:56 train_lshot.py:257] INFO Epoch: [85][140/150] Time 0.619 (0.687) Data 0.000 (0.066) Loss 0.3988 (0.3635) Prec@1 90.234 (90.317) Prec@5 97.266 (97.631)
[2021-04-26 21:15:13 train_lshot.py:257] INFO Epoch: [86][0/150] Time 10.602 (10.602) Data 9.946 (9.946) Loss 0.3681 (0.3681) Prec@1 90.234 (90.234) Prec@5 97.656 (97.656)
[2021-04-26 21:15:19 train_lshot.py:257] INFO Epoch: [86][10/150] Time 0.621 (1.538) Data 0.000 (0.915) Loss 0.3093 (0.3456) Prec@1 91.016 (91.264) Prec@5 97.656 (97.656)
[2021-04-26 21:15:25 train_lshot.py:257] INFO Epoch: [86][20/150] Time 0.622 (1.102) Data 0.000 (0.479) Loss 0.2788 (0.3550) Prec@1 92.969 (90.885) Prec@5 98.438 (97.526)
[2021-04-26 21:15:31 train_lshot.py:257] INFO Epoch: [86][30/150] Time 0.620 (0.947) Data 0.000 (0.325) Loss 0.2568 (0.3556) Prec@1 91.797 (90.776) Prec@5 98.828 (97.543)
[2021-04-26 21:15:38 train_lshot.py:257] INFO Epoch: [86][40/150] Time 0.623 (0.868) Data 0.000 (0.246) Loss 0.3203 (0.3529) Prec@1 91.016 (90.825) Prec@5 96.875 (97.580)
[2021-04-26 21:15:44 train_lshot.py:257] INFO Epoch: [86][50/150] Time 0.626 (0.820) Data 0.001 (0.198) Loss 0.4899 (0.3591) Prec@1 87.500 (90.541) Prec@5 95.312 (97.557)
[2021-04-26 21:15:50 train_lshot.py:257] INFO Epoch: [86][60/150] Time 0.622 (0.788) Data 0.000 (0.165) Loss 0.3651 (0.3589) Prec@1 92.188 (90.497) Prec@5 97.266 (97.611)
[2021-04-26 21:15:56 train_lshot.py:257] INFO Epoch: [86][70/150] Time 0.623 (0.765) Data 0.001 (0.142) Loss 0.3577 (0.3563) Prec@1 90.625 (90.614) Prec@5 98.438 (97.618)
[2021-04-26 21:16:02 train_lshot.py:257] INFO Epoch: [86][80/150] Time 0.618 (0.747) Data 0.000 (0.125) Loss 0.2650 (0.3531) Prec@1 92.578 (90.620) Prec@5 99.609 (97.690)
[2021-04-26 21:16:09 train_lshot.py:257] INFO Epoch: [86][90/150] Time 0.622 (0.733) Data 0.000 (0.111) Loss 0.4481 (0.3553) Prec@1 87.891 (90.595) Prec@5 96.875 (97.678)
[2021-04-26 21:16:15 train_lshot.py:257] INFO Epoch: [86][100/150] Time 0.620 (0.722) Data 0.000 (0.100) Loss 0.4550 (0.3593) Prec@1 86.719 (90.447) Prec@5 96.875 (97.664)
[2021-04-26 21:16:21 train_lshot.py:257] INFO Epoch: [86][110/150] Time 0.617 (0.713) Data 0.000 (0.091) Loss 0.3359 (0.3594) Prec@1 91.797 (90.449) Prec@5 98.438 (97.670)
[2021-04-26 21:16:27 train_lshot.py:257] INFO Epoch: [86][120/150] Time 0.622 (0.705) Data 0.000 (0.084) Loss 0.2858 (0.3599) Prec@1 91.016 (90.399) Prec@5 99.219 (97.695)
[2021-04-26 21:16:34 train_lshot.py:257] INFO Epoch: [86][130/150] Time 0.618 (0.699) Data 0.000 (0.077) Loss 0.3546 (0.3602) Prec@1 90.234 (90.363) Prec@5 97.656 (97.677)
[2021-04-26 21:16:40 train_lshot.py:257] INFO Epoch: [86][140/150] Time 0.620 (0.693) Data 0.000 (0.072) Loss 0.3007 (0.3559) Prec@1 91.406 (90.473) Prec@5 98.438 (97.759)
[2021-04-26 21:16:56 train_lshot.py:257] INFO Epoch: [87][0/150] Time 10.002 (10.002) Data 9.352 (9.352) Loss 0.3349 (0.3349) Prec@1 89.062 (89.062) Prec@5 98.047 (98.047)
[2021-04-26 21:17:02 train_lshot.py:257] INFO Epoch: [87][10/150] Time 0.619 (1.473) Data 0.000 (0.851) Loss 0.4054 (0.3848) Prec@1 91.016 (89.915) Prec@5 95.703 (97.124)
[2021-04-26 21:17:08 train_lshot.py:257] INFO Epoch: [87][20/150] Time 0.626 (1.068) Data 0.001 (0.446) Loss 0.2565 (0.3795) Prec@1 94.141 (90.272) Prec@5 98.438 (97.266)
[2021-04-26 21:17:14 train_lshot.py:257] INFO Epoch: [87][30/150] Time 0.622 (0.924) Data 0.000 (0.302) Loss 0.3349 (0.3749) Prec@1 91.406 (90.247) Prec@5 98.828 (97.417)
[2021-04-26 21:17:21 train_lshot.py:257] INFO Epoch: [87][40/150] Time 0.622 (0.851) Data 0.001 (0.229) Loss 0.3396 (0.3758) Prec@1 91.797 (90.044) Prec@5 97.656 (97.494)
[2021-04-26 21:17:27 train_lshot.py:257] INFO Epoch: [87][50/150] Time 0.620 (0.806) Data 0.000 (0.184) Loss 0.2931 (0.3723) Prec@1 92.969 (90.196) Prec@5 98.047 (97.541)
[2021-04-26 21:17:33 train_lshot.py:257] INFO Epoch: [87][60/150] Time 0.619 (0.776) Data 0.001 (0.154) Loss 0.3229 (0.3721) Prec@1 91.406 (90.241) Prec@5 98.828 (97.503)
[2021-04-26 21:17:39 train_lshot.py:257] INFO Epoch: [87][70/150] Time 0.632 (0.755) Data 0.002 (0.132) Loss 0.3336 (0.3698) Prec@1 91.406 (90.185) Prec@5 98.438 (97.590)
[2021-04-26 21:17:46 train_lshot.py:257] INFO Epoch: [87][80/150] Time 0.619 (0.739) Data 0.000 (0.116) Loss 0.3800 (0.3697) Prec@1 91.406 (90.210) Prec@5 97.266 (97.579)
[2021-04-26 21:17:52 train_lshot.py:257] INFO Epoch: [87][90/150] Time 0.619 (0.726) Data 0.000 (0.103) Loss 0.2805 (0.3672) Prec@1 92.969 (90.303) Prec@5 98.438 (97.618)
[2021-04-26 21:17:58 train_lshot.py:257] INFO Epoch: [87][100/150] Time 0.623 (0.715) Data 0.000 (0.093) Loss 0.2964 (0.3668) Prec@1 93.359 (90.300) Prec@5 97.656 (97.575)
[2021-04-26 21:18:04 train_lshot.py:257] INFO Epoch: [87][110/150] Time 0.622 (0.707) Data 0.000 (0.085) Loss 0.3890 (0.3661) Prec@1 90.234 (90.322) Prec@5 96.484 (97.579)
[2021-04-26 21:18:10 train_lshot.py:257] INFO Epoch: [87][120/150] Time 0.621 (0.700) Data 0.000 (0.078) Loss 0.2805 (0.3651) Prec@1 94.141 (90.351) Prec@5 98.438 (97.605)
[2021-04-26 21:18:17 train_lshot.py:257] INFO Epoch: [87][130/150] Time 0.620 (0.694) Data 0.000 (0.072) Loss 0.2965 (0.3647) Prec@1 90.625 (90.318) Prec@5 98.047 (97.623)
[2021-04-26 21:18:23 train_lshot.py:257] INFO Epoch: [87][140/150] Time 0.618 (0.689) Data 0.000 (0.067) Loss 0.4880 (0.3645) Prec@1 86.719 (90.312) Prec@5 95.312 (97.623)
[2021-04-26 21:19:08 train_lshot.py:119] INFO Meta Val 87: 0.6138666788637638
[2021-04-26 21:19:19 train_lshot.py:257] INFO Epoch: [88][0/150] Time 10.478 (10.478) Data 9.823 (9.823) Loss 0.3496 (0.3496) Prec@1 91.016 (91.016) Prec@5 98.438 (98.438)
[2021-04-26 21:19:25 train_lshot.py:257] INFO Epoch: [88][10/150] Time 0.616 (1.514) Data 0.000 (0.893) Loss 0.3466 (0.3377) Prec@1 89.844 (90.732) Prec@5 97.266 (98.082)
[2021-04-26 21:19:31 train_lshot.py:257] INFO Epoch: [88][20/150] Time 0.619 (1.089) Data 0.000 (0.468) Loss 0.3560 (0.3401) Prec@1 89.844 (90.681) Prec@5 98.047 (98.028)
[2021-04-26 21:19:37 train_lshot.py:257] INFO Epoch: [88][30/150] Time 0.628 (0.939) Data 0.001 (0.317) Loss 0.2744 (0.3426) Prec@1 93.359 (90.776) Prec@5 99.219 (98.047)
[2021-04-26 21:19:43 train_lshot.py:257] INFO Epoch: [88][40/150] Time 0.622 (0.862) Data 0.000 (0.240) Loss 0.3704 (0.3461) Prec@1 91.797 (90.739) Prec@5 97.656 (97.990)
[2021-04-26 21:19:50 train_lshot.py:257] INFO Epoch: [88][50/150] Time 0.632 (0.815) Data 0.001 (0.193) Loss 0.4359 (0.3489) Prec@1 89.062 (90.633) Prec@5 95.312 (97.917)
[2021-04-26 21:19:56 train_lshot.py:257] INFO Epoch: [88][60/150] Time 0.625 (0.784) Data 0.001 (0.162) Loss 0.3695 (0.3558) Prec@1 89.844 (90.426) Prec@5 97.656 (97.772)
[2021-04-26 21:20:02 train_lshot.py:257] INFO Epoch: [88][70/150] Time 0.623 (0.761) Data 0.001 (0.139) Loss 0.3913 (0.3539) Prec@1 87.891 (90.443) Prec@5 97.656 (97.777)
[2021-04-26 21:20:08 train_lshot.py:257] INFO Epoch: [88][80/150] Time 0.620 (0.744) Data 0.000 (0.122) Loss 0.4608 (0.3547) Prec@1 88.281 (90.394) Prec@5 96.484 (97.772)
[2021-04-26 21:20:15 train_lshot.py:257] INFO Epoch: [88][90/150] Time 0.621 (0.731) Data 0.000 (0.108) Loss 0.2981 (0.3553) Prec@1 91.406 (90.337) Prec@5 98.047 (97.734)
[2021-04-26 21:20:21 train_lshot.py:257] INFO Epoch: [88][100/150] Time 0.625 (0.720) Data 0.000 (0.098) Loss 0.3478 (0.3574) Prec@1 89.844 (90.319) Prec@5 95.703 (97.641)
[2021-04-26 21:20:27 train_lshot.py:257] INFO Epoch: [88][110/150] Time 0.623 (0.711) Data 0.000 (0.089) Loss 0.3463 (0.3564) Prec@1 89.062 (90.368) Prec@5 97.266 (97.625)
[2021-04-26 21:20:33 train_lshot.py:257] INFO Epoch: [88][120/150] Time 0.622 (0.704) Data 0.000 (0.082) Loss 0.4138 (0.3552) Prec@1 89.453 (90.364) Prec@5 96.875 (97.647)
[2021-04-26 21:20:40 train_lshot.py:257] INFO Epoch: [88][130/150] Time 0.620 (0.699) Data 0.000 (0.075) Loss 0.3917 (0.3575) Prec@1 89.453 (90.351) Prec@5 96.875 (97.591)
[2021-04-26 21:20:46 train_lshot.py:257] INFO Epoch: [88][140/150] Time 0.622 (0.693) Data 0.000 (0.070) Loss 0.4439 (0.3591) Prec@1 88.672 (90.315) Prec@5 96.875 (97.581)
[2021-04-26 21:21:01 train_lshot.py:257] INFO Epoch: [89][0/150] Time 9.159 (9.159) Data 8.497 (8.497) Loss 0.3042 (0.3042) Prec@1 91.016 (91.016) Prec@5 98.047 (98.047)
[2021-04-26 21:21:07 train_lshot.py:257] INFO Epoch: [89][10/150] Time 0.621 (1.398) Data 0.000 (0.773) Loss 0.3845 (0.3422) Prec@1 89.062 (90.661) Prec@5 96.875 (97.798)
[2021-04-26 21:21:13 train_lshot.py:257] INFO Epoch: [89][20/150] Time 0.622 (1.028) Data 0.001 (0.405) Loss 0.3711 (0.3538) Prec@1 88.672 (90.383) Prec@5 97.656 (97.675)
[2021-04-26 21:21:20 train_lshot.py:257] INFO Epoch: [89][30/150] Time 0.621 (0.898) Data 0.000 (0.275) Loss 0.3202 (0.3593) Prec@1 93.359 (90.474) Prec@5 97.656 (97.631)
[2021-04-26 21:21:26 train_lshot.py:257] INFO Epoch: [89][40/150] Time 0.625 (0.831) Data 0.001 (0.208) Loss 0.3471 (0.3619) Prec@1 90.234 (90.482) Prec@5 98.047 (97.532)
[2021-04-26 21:21:32 train_lshot.py:257] INFO Epoch: [89][50/150] Time 0.631 (0.791) Data 0.001 (0.167) Loss 0.3473 (0.3669) Prec@1 91.016 (90.395) Prec@5 98.047 (97.472)
[2021-04-26 21:21:38 train_lshot.py:257] INFO Epoch: [89][60/150] Time 0.621 (0.763) Data 0.000 (0.140) Loss 0.4608 (0.3676) Prec@1 87.891 (90.337) Prec@5 95.703 (97.451)
[2021-04-26 21:21:45 train_lshot.py:257] INFO Epoch: [89][70/150] Time 0.628 (0.744) Data 0.002 (0.120) Loss 0.3729 (0.3664) Prec@1 89.453 (90.328) Prec@5 98.438 (97.519)
[2021-04-26 21:21:51 train_lshot.py:257] INFO Epoch: [89][80/150] Time 0.621 (0.729) Data 0.001 (0.106) Loss 0.4172 (0.3674) Prec@1 87.500 (90.312) Prec@5 97.266 (97.507)
[2021-04-26 21:21:57 train_lshot.py:257] INFO Epoch: [89][90/150] Time 0.620 (0.717) Data 0.000 (0.094) Loss 0.3634 (0.3637) Prec@1 92.188 (90.423) Prec@5 96.875 (97.532)
[2021-04-26 21:22:03 train_lshot.py:257] INFO Epoch: [89][100/150] Time 0.621 (0.707) Data 0.000 (0.085) Loss 0.4232 (0.3646) Prec@1 87.891 (90.401) Prec@5 96.484 (97.505)
[2021-04-26 21:22:09 train_lshot.py:257] INFO Epoch: [89][110/150] Time 0.622 (0.700) Data 0.000 (0.077) Loss 0.3394 (0.3620) Prec@1 92.188 (90.502) Prec@5 97.656 (97.530)
[2021-04-26 21:22:16 train_lshot.py:257] INFO Epoch: [89][120/150] Time 0.621 (0.693) Data 0.000 (0.071) Loss 0.2966 (0.3641) Prec@1 91.797 (90.473) Prec@5 98.438 (97.472)
[2021-04-26 21:22:22 train_lshot.py:257] INFO Epoch: [89][130/150] Time 0.624 (0.688) Data 0.000 (0.065) Loss 0.4505 (0.3644) Prec@1 85.156 (90.419) Prec@5 96.875 (97.462)
[2021-04-26 21:22:28 train_lshot.py:257] INFO Epoch: [89][140/150] Time 0.623 (0.683) Data 0.000 (0.061) Loss 0.3153 (0.3630) Prec@1 91.797 (90.439) Prec@5 99.219 (97.487)
[2021-04-26 21:23:35 train_lshot.py:570] INFO validation lmd=0.10: Best
feature CL2N
GVP 1Shot 0.7264(0.0088)
GVP_5Shot 0.8240(0.0061))
[2021-04-26 21:23:40 train_lshot.py:570] INFO validation lmd=0.30: Best
feature CL2N
GVP 1Shot 0.7283(0.0091)
GVP_5Shot 0.8259(0.0064))
[2021-04-26 21:23:45 train_lshot.py:570] INFO validation lmd=0.50: Best
feature CL2N
GVP 1Shot 0.7355(0.0092)
GVP_5Shot 0.8198(0.0063))
[2021-04-26 21:23:51 train_lshot.py:570] INFO validation lmd=0.70: Best
feature CL2N
GVP 1Shot 0.7406(0.0091)
GVP_5Shot 0.8128(0.0062))
[2021-04-26 21:23:57 train_lshot.py:570] INFO validation lmd=0.80: Best
feature CL2N
GVP 1Shot 0.7367(0.0087)
GVP_5Shot 0.8071(0.0065))
[2021-04-26 21:24:03 train_lshot.py:570] INFO validation lmd=1.00: Best
feature CL2N
GVP 1Shot 0.7233(0.0084)
GVP_5Shot 0.8023(0.0061))
[2021-04-26 21:24:09 train_lshot.py:570] INFO validation lmd=1.20: Best
feature CL2N
GVP 1Shot 0.7154(0.0083)
GVP_5Shot 0.7722(0.0069))
[2021-04-26 21:24:15 train_lshot.py:570] INFO validation lmd=1.50: Best
feature CL2N
GVP 1Shot 0.6813(0.0086)
GVP_5Shot 0.7339(0.0084))
[2021-04-26 21:24:15 train_lshot.py:580] INFO Best lambda on validation:
0.70 with 1 shot acc 0.7406
0.30 with 5 shot acc 0.8259
[2021-04-26 21:24:15 train_lshot.py:707] INFO Proto-rectification = True in Evaluation
[2021-04-26 21:25:17 train_lshot.py:713] INFO Run with lambda 0.7 for 1 shot
[2021-04-26 21:27:40 train_lshot.py:717] INFO Run with lambda 0.3 for 5 shot
[2021-04-26 21:30:00 train_lshot.py:724] INFO Meta Test: LAST
feature UN L2N CL2N
GVP 1Shot 0.6501(0.0020) 0.6741(0.0020) 0.7223(0.0020)
GVP_5Shot 0.7435(0.0019) 0.7625(0.0018) 0.8234(0.0014)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment