Skip to content

Instantly share code, notes, and snippets.

@imtiazziko

imtiazziko/resnet_18-log-with-jitter Secret

Created April 30, 2021 20:45
Show Gist options
  • Save imtiazziko/fb60e4242174bcf5a0961b739c88bda0 to your computer and use it in GitHub Desktop.
Save imtiazziko/fb60e4242174bcf5a0961b739c88bda0 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
resnet_18-log-with-jitter
[2021-04-26 15:14:49 train_lshot.py:38] INFO arch: resnet18
[2021-04-26 15:14:49 train_lshot.py:38] INFO batch_size: 256
[2021-04-26 15:14:49 train_lshot.py:38] INFO beta: -1.0
[2021-04-26 15:14:49 train_lshot.py:38] INFO config: /app/LaplacianShot/configs/mini/softmax/resnet18.config
[2021-04-26 15:14:49 train_lshot.py:38] INFO cutmix_prob: 0
[2021-04-26 15:14:49 train_lshot.py:38] INFO data: /fewshot_xai/fewshot_xai/fewshot_data/data/mini_imagenet
[2021-04-26 15:14:49 train_lshot.py:38] INFO disable_random_resize: False
[2021-04-26 15:14:49 train_lshot.py:38] INFO disable_tqdm: False
[2021-04-26 15:14:49 train_lshot.py:38] INFO disable_train_augment: False
[2021-04-26 15:14:49 train_lshot.py:38] INFO do_meta_train: False
[2021-04-26 15:14:49 train_lshot.py:38] INFO enlarge: True
[2021-04-26 15:14:49 train_lshot.py:38] INFO epochs: 90
[2021-04-26 15:14:49 train_lshot.py:38] INFO eval_fc: False
[2021-04-26 15:14:49 train_lshot.py:38] INFO evaluate: False
[2021-04-26 15:14:49 train_lshot.py:38] INFO jitter: True
[2021-04-26 15:14:49 train_lshot.py:38] INFO knn: 3
[2021-04-26 15:14:49 train_lshot.py:38] INFO label_smooth: 0.1
[2021-04-26 15:14:49 train_lshot.py:38] INFO lmd: 1.0
[2021-04-26 15:14:49 train_lshot.py:38] INFO log_file: /LaplacianShot_protorec.log
[2021-04-26 15:14:49 train_lshot.py:38] INFO lr: 0.1
[2021-04-26 15:14:49 train_lshot.py:38] INFO lr_gamma: 0.1
[2021-04-26 15:14:49 train_lshot.py:38] INFO lr_stepsize: 30
[2021-04-26 15:14:49 train_lshot.py:38] INFO lshot: True
[2021-04-26 15:14:49 train_lshot.py:38] INFO meta_test_iter: 10000
[2021-04-26 15:14:49 train_lshot.py:38] INFO meta_train_iter: 100
[2021-04-26 15:14:49 train_lshot.py:38] INFO meta_train_metric: euclidean
[2021-04-26 15:14:49 train_lshot.py:38] INFO meta_train_query: 15
[2021-04-26 15:14:49 train_lshot.py:38] INFO meta_train_shot: 1
[2021-04-26 15:14:49 train_lshot.py:38] INFO meta_train_way: 30
[2021-04-26 15:14:49 train_lshot.py:38] INFO meta_val_interval: 4
[2021-04-26 15:14:49 train_lshot.py:38] INFO meta_val_iter: 500
[2021-04-26 15:14:49 train_lshot.py:38] INFO meta_val_metric: cosine
[2021-04-26 15:14:49 train_lshot.py:38] INFO meta_val_query: 15
[2021-04-26 15:14:49 train_lshot.py:38] INFO meta_val_shot: 1
[2021-04-26 15:14:49 train_lshot.py:38] INFO meta_val_way: 5
[2021-04-26 15:14:49 train_lshot.py:38] INFO nesterov: False
[2021-04-26 15:14:49 train_lshot.py:38] INFO num_NN: 1
[2021-04-26 15:14:49 train_lshot.py:38] INFO num_classes: 64
[2021-04-26 15:14:49 train_lshot.py:38] INFO optimizer: SGD
[2021-04-26 15:14:49 train_lshot.py:38] INFO plot_converge: False
[2021-04-26 15:14:49 train_lshot.py:38] INFO pretrain: None
[2021-04-26 15:14:49 train_lshot.py:38] INFO print_freq: 10
[2021-04-26 15:14:49 train_lshot.py:38] INFO proto_rect: True
[2021-04-26 15:14:49 train_lshot.py:38] INFO resume:
[2021-04-26 15:14:49 train_lshot.py:38] INFO save_path: /fewshot_xai/fewshot_xai/results/mini/softmax/resnet18-simpleshot
[2021-04-26 15:14:49 train_lshot.py:38] INFO scheduler: multi_step
[2021-04-26 15:14:49 train_lshot.py:38] INFO seed: None
[2021-04-26 15:14:49 train_lshot.py:38] INFO split_dir: /app/LaplacianShot/split/mini/
[2021-04-26 15:14:49 train_lshot.py:38] INFO start_epoch: 0
[2021-04-26 15:14:49 train_lshot.py:38] INFO tune_lmd: True
[2021-04-26 15:14:49 train_lshot.py:38] INFO weight_decay: 0.0001
[2021-04-26 15:14:49 train_lshot.py:38] INFO workers: 40
[2021-04-26 15:14:49 train_lshot.py:46] INFO => creating model 'resnet18'
[2021-04-26 15:14:49 train_lshot.py:49] INFO Number of model parameters: 11201664
[2021-04-26 15:15:13 train_lshot.py:257] INFO Epoch: [0][0/150] Time 22.695 (22.695) Data 21.319 (21.319) Loss 3.5317 (3.5317) Prec@1 2.344 (2.344) Prec@5 10.156 (10.156)
[2021-04-26 15:15:22 train_lshot.py:257] INFO Epoch: [0][10/150] Time 0.905 (2.898) Data 0.000 (1.948) Loss 3.4974 (3.5226) Prec@1 3.125 (2.734) Prec@5 12.109 (11.932)
[2021-04-26 15:15:31 train_lshot.py:257] INFO Epoch: [0][20/150] Time 0.909 (1.950) Data 0.000 (1.021) Loss 3.3619 (3.4505) Prec@1 4.688 (3.888) Prec@5 19.141 (15.216)
[2021-04-26 15:15:40 train_lshot.py:257] INFO Epoch: [0][30/150] Time 0.903 (1.617) Data 0.000 (0.692) Loss 3.1945 (3.3939) Prec@1 9.375 (4.246) Prec@5 28.125 (17.049)
[2021-04-26 15:15:50 train_lshot.py:257] INFO Epoch: [0][40/150] Time 0.923 (1.446) Data 0.001 (0.523) Loss 3.2956 (3.3529) Prec@1 3.516 (4.802) Prec@5 20.312 (18.817)
[2021-04-26 15:15:59 train_lshot.py:257] INFO Epoch: [0][50/150] Time 0.923 (1.344) Data 0.004 (0.421) Loss 3.1224 (3.3141) Prec@1 9.375 (5.484) Prec@5 29.688 (20.527)
[2021-04-26 15:16:08 train_lshot.py:257] INFO Epoch: [0][60/150] Time 0.926 (1.274) Data 0.001 (0.353) Loss 3.0776 (3.2819) Prec@1 10.938 (5.898) Prec@5 30.078 (21.689)
[2021-04-26 15:16:17 train_lshot.py:257] INFO Epoch: [0][70/150] Time 0.916 (1.225) Data 0.000 (0.303) Loss 3.0739 (3.2594) Prec@1 8.984 (6.217) Prec@5 29.688 (22.596)
[2021-04-26 15:16:26 train_lshot.py:257] INFO Epoch: [0][80/150] Time 0.917 (1.187) Data 0.000 (0.266) Loss 3.0877 (3.2357) Prec@1 9.375 (6.549) Prec@5 29.297 (23.423)
[2021-04-26 15:16:36 train_lshot.py:257] INFO Epoch: [0][90/150] Time 0.923 (1.159) Data 0.000 (0.236) Loss 3.0475 (3.2193) Prec@1 10.547 (6.774) Prec@5 29.688 (24.086)
[2021-04-26 15:16:45 train_lshot.py:257] INFO Epoch: [0][100/150] Time 0.923 (1.135) Data 0.000 (0.213) Loss 3.0939 (3.2022) Prec@1 9.375 (7.186) Prec@5 31.641 (24.961)
[2021-04-26 15:16:54 train_lshot.py:257] INFO Epoch: [0][110/150] Time 0.926 (1.117) Data 0.000 (0.194) Loss 3.1073 (3.1835) Prec@1 8.984 (7.506) Prec@5 28.906 (25.739)
[2021-04-26 15:17:03 train_lshot.py:257] INFO Epoch: [0][120/150] Time 0.925 (1.101) Data 0.000 (0.178) Loss 2.9739 (3.1700) Prec@1 10.156 (7.680) Prec@5 35.156 (26.253)
[2021-04-26 15:17:13 train_lshot.py:257] INFO Epoch: [0][130/150] Time 0.931 (1.088) Data 0.000 (0.164) Loss 3.0638 (3.1558) Prec@1 8.984 (8.006) Prec@5 32.031 (26.855)
[2021-04-26 15:17:22 train_lshot.py:257] INFO Epoch: [0][140/150] Time 0.930 (1.076) Data 0.000 (0.153) Loss 2.9936 (3.1438) Prec@1 8.984 (8.198) Prec@5 33.594 (27.294)
[2021-04-26 15:17:44 train_lshot.py:257] INFO Epoch: [1][0/150] Time 12.883 (12.883) Data 11.934 (11.934) Loss 2.8959 (2.8959) Prec@1 9.766 (9.766) Prec@5 37.500 (37.500)
[2021-04-26 15:17:54 train_lshot.py:257] INFO Epoch: [1][10/150] Time 0.934 (2.015) Data 0.000 (1.085) Loss 2.8840 (2.9392) Prec@1 14.062 (11.577) Prec@5 35.547 (35.263)
[2021-04-26 15:18:03 train_lshot.py:257] INFO Epoch: [1][20/150] Time 0.929 (1.498) Data 0.000 (0.569) Loss 2.9677 (2.9578) Prec@1 10.938 (11.365) Prec@5 34.375 (34.319)
[2021-04-26 15:18:12 train_lshot.py:257] INFO Epoch: [1][30/150] Time 0.935 (1.316) Data 0.000 (0.386) Loss 2.8856 (2.9580) Prec@1 14.062 (11.593) Prec@5 40.625 (34.967)
[2021-04-26 15:18:21 train_lshot.py:257] INFO Epoch: [1][40/150] Time 0.929 (1.222) Data 0.000 (0.292) Loss 2.9111 (2.9528) Prec@1 14.844 (11.814) Prec@5 35.547 (35.433)
[2021-04-26 15:18:31 train_lshot.py:257] INFO Epoch: [1][50/150] Time 0.931 (1.165) Data 0.001 (0.235) Loss 2.9389 (2.9490) Prec@1 16.016 (12.071) Prec@5 36.328 (35.424)
[2021-04-26 15:18:40 train_lshot.py:257] INFO Epoch: [1][60/150] Time 0.930 (1.127) Data 0.001 (0.196) Loss 2.9154 (2.9402) Prec@1 13.281 (12.193) Prec@5 39.844 (35.873)
[2021-04-26 15:18:49 train_lshot.py:257] INFO Epoch: [1][70/150] Time 0.935 (1.100) Data 0.000 (0.169) Loss 2.9025 (2.9320) Prec@1 16.406 (12.450) Prec@5 37.109 (36.290)
[2021-04-26 15:18:59 train_lshot.py:257] INFO Epoch: [1][80/150] Time 0.936 (1.080) Data 0.000 (0.148) Loss 2.8846 (2.9194) Prec@1 11.719 (12.799) Prec@5 35.547 (36.719)
[2021-04-26 15:19:08 train_lshot.py:257] INFO Epoch: [1][90/150] Time 0.931 (1.064) Data 0.000 (0.132) Loss 2.9199 (2.9095) Prec@1 12.891 (13.019) Prec@5 35.547 (37.084)
[2021-04-26 15:19:17 train_lshot.py:257] INFO Epoch: [1][100/150] Time 0.938 (1.051) Data 0.000 (0.119) Loss 2.8810 (2.9032) Prec@1 13.281 (13.250) Prec@5 36.328 (37.310)
[2021-04-26 15:19:27 train_lshot.py:257] INFO Epoch: [1][110/150] Time 0.936 (1.041) Data 0.000 (0.108) Loss 2.9012 (2.8943) Prec@1 12.500 (13.471) Prec@5 38.281 (37.736)
[2021-04-26 15:19:36 train_lshot.py:257] INFO Epoch: [1][120/150] Time 0.941 (1.032) Data 0.000 (0.099) Loss 2.9297 (2.8864) Prec@1 8.203 (13.523) Prec@5 37.500 (38.097)
[2021-04-26 15:19:46 train_lshot.py:257] INFO Epoch: [1][130/150] Time 0.926 (1.024) Data 0.000 (0.092) Loss 2.8044 (2.8778) Prec@1 14.844 (13.705) Prec@5 43.750 (38.439)
[2021-04-26 15:19:55 train_lshot.py:257] INFO Epoch: [1][140/150] Time 0.939 (1.018) Data 0.000 (0.085) Loss 2.7716 (2.8677) Prec@1 17.578 (13.946) Prec@5 42.578 (38.783)
[2021-04-26 15:20:17 train_lshot.py:257] INFO Epoch: [2][0/150] Time 12.467 (12.467) Data 11.515 (11.515) Loss 2.7953 (2.7953) Prec@1 14.844 (14.844) Prec@5 41.406 (41.406)
[2021-04-26 15:20:26 train_lshot.py:257] INFO Epoch: [2][10/150] Time 0.938 (1.984) Data 0.000 (1.047) Loss 2.6027 (2.6890) Prec@1 19.922 (17.649) Prec@5 52.734 (46.129)
[2021-04-26 15:20:35 train_lshot.py:257] INFO Epoch: [2][20/150] Time 0.936 (1.484) Data 0.000 (0.549) Loss 2.7475 (2.6996) Prec@1 17.188 (17.634) Prec@5 46.094 (45.833)
[2021-04-26 15:20:45 train_lshot.py:257] INFO Epoch: [2][30/150] Time 0.933 (1.307) Data 0.000 (0.372) Loss 2.7141 (2.6994) Prec@1 18.359 (17.629) Prec@5 44.922 (45.980)
[2021-04-26 15:20:54 train_lshot.py:257] INFO Epoch: [2][40/150] Time 0.935 (1.215) Data 0.000 (0.281) Loss 2.6538 (2.6891) Prec@1 19.141 (18.226) Prec@5 45.312 (46.465)
[2021-04-26 15:21:04 train_lshot.py:257] INFO Epoch: [2][50/150] Time 0.940 (1.161) Data 0.001 (0.226) Loss 2.6049 (2.6850) Prec@1 26.953 (18.673) Prec@5 50.000 (46.684)
[2021-04-26 15:21:13 train_lshot.py:257] INFO Epoch: [2][60/150] Time 0.932 (1.124) Data 0.001 (0.189) Loss 2.6780 (2.6838) Prec@1 20.312 (18.705) Prec@5 44.141 (46.529)
[2021-04-26 15:21:22 train_lshot.py:257] INFO Epoch: [2][70/150] Time 0.934 (1.097) Data 0.000 (0.163) Loss 2.7437 (2.6793) Prec@1 14.453 (18.849) Prec@5 44.531 (46.693)
[2021-04-26 15:21:32 train_lshot.py:257] INFO Epoch: [2][80/150] Time 0.931 (1.077) Data 0.000 (0.143) Loss 2.5569 (2.6691) Prec@1 19.922 (19.097) Prec@5 53.516 (47.111)
[2021-04-26 15:21:41 train_lshot.py:257] INFO Epoch: [2][90/150] Time 0.934 (1.061) Data 0.000 (0.127) Loss 2.5446 (2.6564) Prec@1 19.531 (19.441) Prec@5 54.688 (47.558)
[2021-04-26 15:21:50 train_lshot.py:257] INFO Epoch: [2][100/150] Time 0.933 (1.049) Data 0.000 (0.114) Loss 2.5624 (2.6492) Prec@1 22.266 (19.670) Prec@5 50.781 (47.830)
[2021-04-26 15:22:00 train_lshot.py:257] INFO Epoch: [2][110/150] Time 0.937 (1.038) Data 0.000 (0.104) Loss 2.4764 (2.6413) Prec@1 25.000 (19.936) Prec@5 53.516 (48.107)
[2021-04-26 15:22:09 train_lshot.py:257] INFO Epoch: [2][120/150] Time 0.934 (1.030) Data 0.000 (0.096) Loss 2.5563 (2.6352) Prec@1 23.047 (20.035) Prec@5 50.391 (48.366)
[2021-04-26 15:22:18 train_lshot.py:257] INFO Epoch: [2][130/150] Time 0.938 (1.022) Data 0.000 (0.088) Loss 2.6388 (2.6271) Prec@1 17.188 (20.196) Prec@5 50.391 (48.760)
[2021-04-26 15:22:28 train_lshot.py:257] INFO Epoch: [2][140/150] Time 0.931 (1.016) Data 0.000 (0.082) Loss 2.5499 (2.6228) Prec@1 21.094 (20.332) Prec@5 53.516 (49.061)
[2021-04-26 15:22:54 train_lshot.py:257] INFO Epoch: [3][0/150] Time 16.880 (16.880) Data 15.932 (15.932) Loss 2.4991 (2.4991) Prec@1 21.484 (21.484) Prec@5 53.906 (53.906)
[2021-04-26 15:23:03 train_lshot.py:257] INFO Epoch: [3][10/150] Time 0.924 (2.382) Data 0.000 (1.449) Loss 2.4681 (2.4886) Prec@1 19.141 (22.124) Prec@5 52.344 (53.729)
[2021-04-26 15:23:13 train_lshot.py:257] INFO Epoch: [3][20/150] Time 0.928 (1.691) Data 0.001 (0.759) Loss 2.5205 (2.4671) Prec@1 21.094 (23.084) Prec@5 54.688 (54.948)
[2021-04-26 15:23:22 train_lshot.py:257] INFO Epoch: [3][30/150] Time 0.935 (1.446) Data 0.000 (0.514) Loss 2.4700 (2.4650) Prec@1 26.562 (23.790) Prec@5 54.688 (54.763)
[2021-04-26 15:23:31 train_lshot.py:257] INFO Epoch: [3][40/150] Time 0.937 (1.321) Data 0.002 (0.389) Loss 2.4859 (2.4604) Prec@1 23.438 (24.114) Prec@5 51.172 (54.621)
[2021-04-26 15:23:40 train_lshot.py:257] INFO Epoch: [3][50/150] Time 0.926 (1.244) Data 0.001 (0.313) Loss 2.3872 (2.4527) Prec@1 27.734 (24.272) Prec@5 59.766 (55.017)
[2021-04-26 15:23:50 train_lshot.py:257] INFO Epoch: [3][60/150] Time 0.937 (1.194) Data 0.001 (0.262) Loss 2.3892 (2.4410) Prec@1 30.078 (24.693) Prec@5 58.594 (55.629)
[2021-04-26 15:23:59 train_lshot.py:257] INFO Epoch: [3][70/150] Time 0.940 (1.157) Data 0.002 (0.225) Loss 2.3949 (2.4331) Prec@1 25.391 (24.901) Prec@5 56.250 (55.969)
[2021-04-26 15:24:09 train_lshot.py:257] INFO Epoch: [3][80/150] Time 0.941 (1.130) Data 0.000 (0.197) Loss 2.2588 (2.4273) Prec@1 27.344 (25.029) Prec@5 62.500 (56.245)
[2021-04-26 15:24:18 train_lshot.py:257] INFO Epoch: [3][90/150] Time 0.931 (1.108) Data 0.000 (0.175) Loss 2.4920 (2.4248) Prec@1 22.266 (25.112) Prec@5 58.203 (56.456)
[2021-04-26 15:24:27 train_lshot.py:257] INFO Epoch: [3][100/150] Time 0.933 (1.091) Data 0.000 (0.158) Loss 2.3448 (2.4204) Prec@1 26.172 (25.240) Prec@5 61.719 (56.637)
[2021-04-26 15:24:37 train_lshot.py:257] INFO Epoch: [3][110/150] Time 0.935 (1.077) Data 0.000 (0.144) Loss 2.6373 (2.4185) Prec@1 21.094 (25.204) Prec@5 49.609 (56.746)
[2021-04-26 15:24:46 train_lshot.py:257] INFO Epoch: [3][120/150] Time 0.932 (1.066) Data 0.000 (0.132) Loss 2.3459 (2.4133) Prec@1 23.828 (25.300) Prec@5 60.156 (56.993)
[2021-04-26 15:24:55 train_lshot.py:257] INFO Epoch: [3][130/150] Time 0.931 (1.055) Data 0.000 (0.122) Loss 2.3473 (2.4121) Prec@1 24.609 (25.411) Prec@5 55.078 (56.939)
[2021-04-26 15:25:05 train_lshot.py:257] INFO Epoch: [3][140/150] Time 0.931 (1.047) Data 0.000 (0.113) Loss 2.3274 (2.4045) Prec@1 28.906 (25.670) Prec@5 57.812 (57.236)
[2021-04-26 15:26:14 train_lshot.py:119] INFO Meta Val 3: 0.4276266759634018
[2021-04-26 15:26:31 train_lshot.py:257] INFO Epoch: [4][0/150] Time 14.679 (14.679) Data 13.723 (13.723) Loss 2.2472 (2.2472) Prec@1 29.688 (29.688) Prec@5 61.328 (61.328)
[2021-04-26 15:26:40 train_lshot.py:257] INFO Epoch: [4][10/150] Time 0.927 (2.195) Data 0.000 (1.262) Loss 2.3216 (2.3124) Prec@1 26.953 (27.734) Prec@5 56.250 (59.517)
[2021-04-26 15:26:50 train_lshot.py:257] INFO Epoch: [4][20/150] Time 0.934 (1.596) Data 0.001 (0.661) Loss 2.2077 (2.2864) Prec@1 29.688 (27.939) Prec@5 64.453 (60.956)
[2021-04-26 15:26:59 train_lshot.py:257] INFO Epoch: [4][30/150] Time 0.933 (1.383) Data 0.000 (0.448) Loss 2.2143 (2.2775) Prec@1 27.734 (28.390) Prec@5 62.109 (61.580)
[2021-04-26 15:27:08 train_lshot.py:257] INFO Epoch: [4][40/150] Time 0.938 (1.274) Data 0.000 (0.339) Loss 2.1819 (2.2603) Prec@1 30.469 (29.030) Prec@5 65.625 (61.986)
[2021-04-26 15:27:18 train_lshot.py:257] INFO Epoch: [4][50/150] Time 0.939 (1.208) Data 0.001 (0.273) Loss 2.2598 (2.2560) Prec@1 27.344 (28.960) Prec@5 63.281 (62.171)
[2021-04-26 15:27:27 train_lshot.py:257] INFO Epoch: [4][60/150] Time 0.938 (1.164) Data 0.000 (0.228) Loss 2.2874 (2.2554) Prec@1 31.641 (29.201) Prec@5 59.375 (62.097)
[2021-04-26 15:27:36 train_lshot.py:257] INFO Epoch: [4][70/150] Time 0.941 (1.132) Data 0.000 (0.196) Loss 2.2333 (2.2590) Prec@1 26.953 (29.209) Prec@5 63.281 (61.763)
[2021-04-26 15:27:46 train_lshot.py:257] INFO Epoch: [4][80/150] Time 0.942 (1.108) Data 0.000 (0.172) Loss 2.2253 (2.2559) Prec@1 32.031 (29.432) Prec@5 63.281 (61.863)
[2021-04-26 15:27:55 train_lshot.py:257] INFO Epoch: [4][90/150] Time 0.938 (1.089) Data 0.000 (0.153) Loss 2.2940 (2.2532) Prec@1 28.516 (29.765) Prec@5 58.984 (61.929)
[2021-04-26 15:28:05 train_lshot.py:257] INFO Epoch: [4][100/150] Time 0.943 (1.074) Data 0.000 (0.138) Loss 2.3947 (2.2515) Prec@1 26.172 (29.881) Prec@5 58.984 (61.908)
[2021-04-26 15:28:14 train_lshot.py:257] INFO Epoch: [4][110/150] Time 0.932 (1.062) Data 0.000 (0.125) Loss 2.2376 (2.2475) Prec@1 30.859 (30.036) Prec@5 63.281 (62.064)
[2021-04-26 15:28:23 train_lshot.py:257] INFO Epoch: [4][120/150] Time 0.941 (1.052) Data 0.000 (0.115) Loss 2.2099 (2.2488) Prec@1 31.250 (30.104) Prec@5 64.453 (62.106)
[2021-04-26 15:28:33 train_lshot.py:257] INFO Epoch: [4][130/150] Time 0.935 (1.043) Data 0.000 (0.106) Loss 2.1913 (2.2425) Prec@1 30.859 (30.245) Prec@5 65.234 (62.321)
[2021-04-26 15:28:42 train_lshot.py:257] INFO Epoch: [4][140/150] Time 0.939 (1.036) Data 0.000 (0.099) Loss 2.1028 (2.2352) Prec@1 37.891 (30.544) Prec@5 67.969 (62.522)
[2021-04-26 15:29:04 train_lshot.py:257] INFO Epoch: [5][0/150] Time 12.337 (12.337) Data 11.385 (11.385) Loss 2.1257 (2.1257) Prec@1 28.516 (28.516) Prec@5 65.234 (65.234)
[2021-04-26 15:29:13 train_lshot.py:257] INFO Epoch: [5][10/150] Time 0.927 (1.970) Data 0.000 (1.035) Loss 2.1412 (2.1271) Prec@1 34.766 (33.771) Prec@5 68.359 (65.447)
[2021-04-26 15:29:23 train_lshot.py:257] INFO Epoch: [5][20/150] Time 0.939 (1.477) Data 0.000 (0.542) Loss 2.2400 (2.1075) Prec@1 36.719 (34.896) Prec@5 64.062 (66.388)
[2021-04-26 15:29:32 train_lshot.py:257] INFO Epoch: [5][30/150] Time 0.933 (1.302) Data 0.000 (0.368) Loss 2.0139 (2.1029) Prec@1 39.062 (34.892) Prec@5 64.844 (66.356)
[2021-04-26 15:29:41 train_lshot.py:257] INFO Epoch: [5][40/150] Time 0.936 (1.213) Data 0.001 (0.278) Loss 2.1856 (2.1020) Prec@1 33.594 (34.623) Prec@5 64.062 (66.235)
[2021-04-26 15:29:51 train_lshot.py:257] INFO Epoch: [5][50/150] Time 0.937 (1.159) Data 0.001 (0.224) Loss 2.1831 (2.1084) Prec@1 29.688 (34.260) Prec@5 62.500 (66.115)
[2021-04-26 15:30:00 train_lshot.py:257] INFO Epoch: [5][60/150] Time 0.943 (1.123) Data 0.000 (0.187) Loss 2.1573 (2.1053) Prec@1 33.984 (34.426) Prec@5 64.062 (66.208)
[2021-04-26 15:30:09 train_lshot.py:257] INFO Epoch: [5][70/150] Time 0.936 (1.096) Data 0.000 (0.161) Loss 2.0207 (2.1061) Prec@1 35.547 (34.386) Prec@5 69.141 (66.368)
[2021-04-26 15:30:19 train_lshot.py:257] INFO Epoch: [5][80/150] Time 0.940 (1.076) Data 0.000 (0.141) Loss 2.0434 (2.1072) Prec@1 33.984 (34.389) Prec@5 67.578 (66.291)
[2021-04-26 15:30:28 train_lshot.py:257] INFO Epoch: [5][90/150] Time 0.930 (1.061) Data 0.000 (0.126) Loss 1.9669 (2.1002) Prec@1 36.328 (34.607) Prec@5 70.312 (66.556)
[2021-04-26 15:30:37 train_lshot.py:257] INFO Epoch: [5][100/150] Time 0.936 (1.048) Data 0.000 (0.113) Loss 2.2134 (2.0987) Prec@1 33.203 (34.762) Prec@5 63.672 (66.634)
[2021-04-26 15:30:47 train_lshot.py:257] INFO Epoch: [5][110/150] Time 0.939 (1.038) Data 0.000 (0.103) Loss 1.8900 (2.0961) Prec@1 41.016 (34.737) Prec@5 73.438 (66.681)
[2021-04-26 15:30:56 train_lshot.py:257] INFO Epoch: [5][120/150] Time 0.935 (1.030) Data 0.000 (0.094) Loss 2.0956 (2.0951) Prec@1 32.422 (34.727) Prec@5 65.234 (66.674)
[2021-04-26 15:31:06 train_lshot.py:257] INFO Epoch: [5][130/150] Time 0.940 (1.023) Data 0.000 (0.087) Loss 2.0590 (2.0929) Prec@1 38.672 (34.825) Prec@5 69.141 (66.791)
[2021-04-26 15:31:15 train_lshot.py:257] INFO Epoch: [5][140/150] Time 0.939 (1.017) Data 0.000 (0.081) Loss 1.9951 (2.0894) Prec@1 35.547 (34.918) Prec@5 69.922 (66.883)
[2021-04-26 15:31:36 train_lshot.py:257] INFO Epoch: [6][0/150] Time 12.093 (12.093) Data 11.136 (11.136) Loss 2.0618 (2.0618) Prec@1 37.109 (37.109) Prec@5 66.797 (66.797)
[2021-04-26 15:31:46 train_lshot.py:257] INFO Epoch: [6][10/150] Time 0.964 (1.953) Data 0.000 (1.013) Loss 1.9116 (1.9912) Prec@1 40.234 (39.027) Prec@5 70.312 (69.922)
[2021-04-26 15:31:55 train_lshot.py:257] INFO Epoch: [6][20/150] Time 0.936 (1.470) Data 0.000 (0.531) Loss 1.9016 (2.0122) Prec@1 41.406 (37.723) Prec@5 73.047 (69.048)
[2021-04-26 15:32:05 train_lshot.py:257] INFO Epoch: [6][30/150] Time 0.933 (1.298) Data 0.000 (0.360) Loss 2.1475 (2.0040) Prec@1 34.766 (37.727) Prec@5 62.500 (69.267)
[2021-04-26 15:32:14 train_lshot.py:257] INFO Epoch: [6][40/150] Time 0.944 (1.210) Data 0.000 (0.272) Loss 1.9990 (2.0002) Prec@1 36.719 (37.710) Prec@5 67.969 (69.388)
[2021-04-26 15:32:23 train_lshot.py:257] INFO Epoch: [6][50/150] Time 0.941 (1.158) Data 0.001 (0.219) Loss 2.0131 (2.0001) Prec@1 39.453 (37.745) Prec@5 67.188 (69.225)
[2021-04-26 15:32:33 train_lshot.py:257] INFO Epoch: [6][60/150] Time 0.934 (1.122) Data 0.001 (0.183) Loss 1.9759 (1.9934) Prec@1 35.156 (37.923) Prec@5 66.406 (69.211)
[2021-04-26 15:32:42 train_lshot.py:257] INFO Epoch: [6][70/150] Time 0.945 (1.097) Data 0.002 (0.157) Loss 2.0069 (1.9870) Prec@1 36.719 (37.869) Prec@5 70.703 (69.366)
[2021-04-26 15:32:52 train_lshot.py:257] INFO Epoch: [6][80/150] Time 0.942 (1.077) Data 0.000 (0.138) Loss 1.9256 (1.9825) Prec@1 44.922 (38.069) Prec@5 72.656 (69.565)
[2021-04-26 15:33:01 train_lshot.py:257] INFO Epoch: [6][90/150] Time 0.939 (1.062) Data 0.000 (0.123) Loss 1.9857 (1.9778) Prec@1 39.453 (38.127) Prec@5 72.656 (69.853)
[2021-04-26 15:33:10 train_lshot.py:257] INFO Epoch: [6][100/150] Time 0.939 (1.050) Data 0.000 (0.111) Loss 1.8663 (1.9753) Prec@1 39.062 (38.188) Prec@5 75.781 (69.903)
[2021-04-26 15:33:20 train_lshot.py:257] INFO Epoch: [6][110/150] Time 0.940 (1.040) Data 0.000 (0.101) Loss 2.0390 (1.9729) Prec@1 38.672 (38.383) Prec@5 66.406 (69.978)
[2021-04-26 15:33:29 train_lshot.py:257] INFO Epoch: [6][120/150] Time 0.946 (1.032) Data 0.000 (0.092) Loss 2.0544 (1.9738) Prec@1 35.938 (38.433) Prec@5 64.062 (69.915)
[2021-04-26 15:33:39 train_lshot.py:257] INFO Epoch: [6][130/150] Time 0.935 (1.025) Data 0.000 (0.085) Loss 1.9749 (1.9676) Prec@1 36.328 (38.559) Prec@5 71.484 (70.202)
[2021-04-26 15:33:48 train_lshot.py:257] INFO Epoch: [6][140/150] Time 0.931 (1.018) Data 0.000 (0.079) Loss 2.0543 (1.9649) Prec@1 36.719 (38.675) Prec@5 67.578 (70.224)
[2021-04-26 15:34:09 train_lshot.py:257] INFO Epoch: [7][0/150] Time 11.756 (11.756) Data 10.805 (10.805) Loss 1.8599 (1.8599) Prec@1 42.578 (42.578) Prec@5 71.875 (71.875)
[2021-04-26 15:34:19 train_lshot.py:257] INFO Epoch: [7][10/150] Time 0.939 (1.931) Data 0.000 (0.995) Loss 1.8787 (1.8880) Prec@1 39.453 (41.300) Prec@5 73.438 (72.727)
[2021-04-26 15:34:28 train_lshot.py:257] INFO Epoch: [7][20/150] Time 0.938 (1.457) Data 0.001 (0.521) Loss 1.9274 (1.8842) Prec@1 37.500 (41.090) Prec@5 70.312 (72.452)
[2021-04-26 15:34:37 train_lshot.py:257] INFO Epoch: [7][30/150] Time 0.934 (1.289) Data 0.000 (0.353) Loss 1.8466 (1.8690) Prec@1 38.281 (41.457) Prec@5 73.438 (72.631)
[2021-04-26 15:34:47 train_lshot.py:257] INFO Epoch: [7][40/150] Time 0.941 (1.204) Data 0.001 (0.267) Loss 1.9508 (1.8645) Prec@1 38.672 (41.463) Prec@5 71.484 (72.618)
[2021-04-26 15:34:56 train_lshot.py:257] INFO Epoch: [7][50/150] Time 0.935 (1.151) Data 0.001 (0.215) Loss 1.8514 (1.8687) Prec@1 42.969 (41.360) Prec@5 73.047 (72.358)
[2021-04-26 15:35:05 train_lshot.py:257] INFO Epoch: [7][60/150] Time 0.933 (1.116) Data 0.000 (0.180) Loss 1.8395 (1.8675) Prec@1 38.281 (41.381) Prec@5 74.609 (72.413)
[2021-04-26 15:35:15 train_lshot.py:257] INFO Epoch: [7][70/150] Time 0.937 (1.091) Data 0.001 (0.155) Loss 1.9162 (1.8625) Prec@1 40.234 (41.494) Prec@5 71.094 (72.700)
[2021-04-26 15:35:24 train_lshot.py:257] INFO Epoch: [7][80/150] Time 0.933 (1.072) Data 0.000 (0.136) Loss 1.8773 (1.8628) Prec@1 41.406 (41.532) Prec@5 75.000 (72.762)
[2021-04-26 15:35:34 train_lshot.py:257] INFO Epoch: [7][90/150] Time 0.937 (1.057) Data 0.000 (0.121) Loss 1.8026 (1.8651) Prec@1 47.266 (41.526) Prec@5 76.172 (72.759)
[2021-04-26 15:35:43 train_lshot.py:257] INFO Epoch: [7][100/150] Time 0.936 (1.045) Data 0.000 (0.109) Loss 1.8001 (1.8624) Prec@1 41.797 (41.615) Prec@5 75.391 (72.819)
[2021-04-26 15:35:52 train_lshot.py:257] INFO Epoch: [7][110/150] Time 0.933 (1.035) Data 0.000 (0.099) Loss 1.7857 (1.8614) Prec@1 48.438 (41.642) Prec@5 73.828 (72.825)
[2021-04-26 15:36:02 train_lshot.py:257] INFO Epoch: [7][120/150] Time 0.938 (1.027) Data 0.000 (0.091) Loss 1.8395 (1.8569) Prec@1 42.578 (41.819) Prec@5 71.094 (72.882)
[2021-04-26 15:36:11 train_lshot.py:257] INFO Epoch: [7][130/150] Time 0.938 (1.020) Data 0.000 (0.084) Loss 1.7725 (1.8559) Prec@1 42.188 (41.904) Prec@5 75.781 (72.928)
[2021-04-26 15:36:20 train_lshot.py:257] INFO Epoch: [7][140/150] Time 0.937 (1.014) Data 0.000 (0.078) Loss 1.7809 (1.8555) Prec@1 43.750 (41.933) Prec@5 75.781 (72.919)
[2021-04-26 15:37:23 train_lshot.py:119] INFO Meta Val 7: 0.4873600106835365
[2021-04-26 15:37:38 train_lshot.py:257] INFO Epoch: [8][0/150] Time 12.762 (12.762) Data 11.789 (11.789) Loss 1.7903 (1.7903) Prec@1 45.312 (45.312) Prec@5 78.516 (78.516)
[2021-04-26 15:37:47 train_lshot.py:257] INFO Epoch: [8][10/150] Time 0.939 (2.009) Data 0.000 (1.072) Loss 1.6288 (1.7635) Prec@1 46.875 (45.597) Prec@5 80.859 (75.639)
[2021-04-26 15:37:57 train_lshot.py:257] INFO Epoch: [8][20/150] Time 0.937 (1.498) Data 0.000 (0.562) Loss 1.7787 (1.7583) Prec@1 41.406 (45.015) Prec@5 76.172 (75.837)
[2021-04-26 15:38:06 train_lshot.py:257] INFO Epoch: [8][30/150] Time 0.936 (1.317) Data 0.000 (0.381) Loss 1.8361 (1.7756) Prec@1 41.406 (44.405) Prec@5 73.047 (75.227)
[2021-04-26 15:38:16 train_lshot.py:257] INFO Epoch: [8][40/150] Time 0.938 (1.225) Data 0.001 (0.288) Loss 1.7063 (1.7713) Prec@1 48.438 (44.674) Prec@5 78.906 (75.143)
[2021-04-26 15:38:25 train_lshot.py:257] INFO Epoch: [8][50/150] Time 0.934 (1.169) Data 0.001 (0.232) Loss 1.8658 (1.7666) Prec@1 41.406 (44.753) Prec@5 72.656 (75.536)
[2021-04-26 15:38:34 train_lshot.py:257] INFO Epoch: [8][60/150] Time 0.940 (1.131) Data 0.000 (0.194) Loss 1.7650 (1.7650) Prec@1 43.750 (44.871) Prec@5 73.828 (75.499)
[2021-04-26 15:38:44 train_lshot.py:257] INFO Epoch: [8][70/150] Time 0.945 (1.104) Data 0.002 (0.167) Loss 1.8070 (1.7672) Prec@1 42.578 (44.515) Prec@5 73.438 (75.506)
[2021-04-26 15:38:53 train_lshot.py:257] INFO Epoch: [8][80/150] Time 0.932 (1.084) Data 0.000 (0.146) Loss 1.7197 (1.7615) Prec@1 44.141 (44.676) Prec@5 74.609 (75.666)
[2021-04-26 15:39:03 train_lshot.py:257] INFO Epoch: [8][90/150] Time 0.940 (1.068) Data 0.000 (0.130) Loss 1.7716 (1.7581) Prec@1 44.922 (44.810) Prec@5 75.000 (75.627)
[2021-04-26 15:39:12 train_lshot.py:257] INFO Epoch: [8][100/150] Time 0.935 (1.055) Data 0.000 (0.117) Loss 1.7543 (1.7555) Prec@1 46.875 (44.903) Prec@5 73.828 (75.712)
[2021-04-26 15:39:21 train_lshot.py:257] INFO Epoch: [8][110/150] Time 0.937 (1.045) Data 0.000 (0.107) Loss 1.9507 (1.7572) Prec@1 38.672 (44.950) Prec@5 68.750 (75.623)
[2021-04-26 15:39:31 train_lshot.py:257] INFO Epoch: [8][120/150] Time 0.941 (1.036) Data 0.000 (0.098) Loss 1.9117 (1.7592) Prec@1 40.625 (44.912) Prec@5 73.047 (75.581)
[2021-04-26 15:39:40 train_lshot.py:257] INFO Epoch: [8][130/150] Time 0.938 (1.029) Data 0.000 (0.090) Loss 1.7360 (1.7595) Prec@1 42.578 (44.922) Prec@5 77.734 (75.543)
[2021-04-26 15:39:50 train_lshot.py:257] INFO Epoch: [8][140/150] Time 0.939 (1.022) Data 0.000 (0.084) Loss 1.6607 (1.7571) Prec@1 48.047 (44.980) Prec@5 78.906 (75.573)
[2021-04-26 15:40:12 train_lshot.py:257] INFO Epoch: [9][0/150] Time 12.719 (12.719) Data 11.763 (11.763) Loss 1.6679 (1.6679) Prec@1 46.094 (46.094) Prec@5 76.953 (76.953)
[2021-04-26 15:40:21 train_lshot.py:257] INFO Epoch: [9][10/150] Time 0.936 (2.007) Data 0.000 (1.070) Loss 1.7324 (1.6889) Prec@1 42.188 (47.195) Prec@5 73.828 (77.557)
[2021-04-26 15:40:31 train_lshot.py:257] INFO Epoch: [9][20/150] Time 0.939 (1.498) Data 0.001 (0.561) Loss 1.7121 (1.6806) Prec@1 44.531 (47.582) Prec@5 73.828 (77.344)
[2021-04-26 15:40:40 train_lshot.py:257] INFO Epoch: [9][30/150] Time 0.941 (1.317) Data 0.001 (0.380) Loss 1.6378 (1.6817) Prec@1 48.047 (47.379) Prec@5 76.562 (77.029)
[2021-04-26 15:40:49 train_lshot.py:257] INFO Epoch: [9][40/150] Time 0.928 (1.223) Data 0.000 (0.287) Loss 1.5782 (1.6790) Prec@1 50.000 (47.542) Prec@5 81.250 (77.229)
[2021-04-26 15:40:59 train_lshot.py:257] INFO Epoch: [9][50/150] Time 0.937 (1.167) Data 0.000 (0.231) Loss 1.7228 (1.6777) Prec@1 45.703 (47.595) Prec@5 75.391 (77.275)
[2021-04-26 15:41:08 train_lshot.py:257] INFO Epoch: [9][60/150] Time 0.942 (1.130) Data 0.000 (0.193) Loss 1.6044 (1.6761) Prec@1 48.047 (47.688) Prec@5 78.906 (77.344)
[2021-04-26 15:41:17 train_lshot.py:257] INFO Epoch: [9][70/150] Time 0.944 (1.103) Data 0.002 (0.166) Loss 1.6545 (1.6763) Prec@1 49.219 (47.794) Prec@5 77.344 (77.168)
[2021-04-26 15:41:27 train_lshot.py:257] INFO Epoch: [9][80/150] Time 0.930 (1.082) Data 0.000 (0.146) Loss 1.6738 (1.6759) Prec@1 46.875 (47.815) Prec@5 76.562 (77.165)
[2021-04-26 15:41:36 train_lshot.py:257] INFO Epoch: [9][90/150] Time 0.937 (1.066) Data 0.000 (0.130) Loss 1.6861 (1.6762) Prec@1 48.047 (47.742) Prec@5 74.219 (77.112)
[2021-04-26 15:41:45 train_lshot.py:257] INFO Epoch: [9][100/150] Time 0.940 (1.053) Data 0.000 (0.117) Loss 1.6136 (1.6749) Prec@1 51.562 (47.765) Prec@5 78.516 (77.197)
[2021-04-26 15:41:55 train_lshot.py:257] INFO Epoch: [9][110/150] Time 0.940 (1.043) Data 0.000 (0.106) Loss 1.7142 (1.6745) Prec@1 48.047 (47.801) Prec@5 77.734 (77.284)
[2021-04-26 15:42:04 train_lshot.py:257] INFO Epoch: [9][120/150] Time 0.939 (1.034) Data 0.000 (0.098) Loss 1.7846 (1.6746) Prec@1 44.531 (47.805) Prec@5 76.562 (77.324)
[2021-04-26 15:42:14 train_lshot.py:257] INFO Epoch: [9][130/150] Time 0.938 (1.027) Data 0.000 (0.090) Loss 1.4890 (1.6691) Prec@1 52.734 (48.032) Prec@5 80.078 (77.415)
[2021-04-26 15:42:23 train_lshot.py:257] INFO Epoch: [9][140/150] Time 0.934 (1.021) Data 0.000 (0.084) Loss 1.4994 (1.6663) Prec@1 51.953 (48.027) Prec@5 85.547 (77.571)
[2021-04-26 15:42:45 train_lshot.py:257] INFO Epoch: [10][0/150] Time 12.866 (12.866) Data 11.890 (11.890) Loss 1.7206 (1.7206) Prec@1 49.609 (49.609) Prec@5 73.047 (73.047)
[2021-04-26 15:42:55 train_lshot.py:257] INFO Epoch: [10][10/150] Time 0.934 (2.019) Data 0.000 (1.081) Loss 1.6122 (1.6534) Prec@1 49.219 (49.680) Prec@5 77.344 (76.420)
[2021-04-26 15:43:04 train_lshot.py:257] INFO Epoch: [10][20/150] Time 0.938 (1.502) Data 0.001 (0.567) Loss 1.6356 (1.6240) Prec@1 47.266 (50.019) Prec@5 80.859 (78.237)
[2021-04-26 15:43:13 train_lshot.py:257] INFO Epoch: [10][30/150] Time 0.934 (1.320) Data 0.000 (0.384) Loss 1.5909 (1.6149) Prec@1 51.953 (50.353) Prec@5 78.516 (78.364)
[2021-04-26 15:43:23 train_lshot.py:257] INFO Epoch: [10][40/150] Time 0.941 (1.227) Data 0.000 (0.290) Loss 1.5153 (1.6015) Prec@1 53.125 (50.648) Prec@5 80.078 (78.611)
[2021-04-26 15:43:32 train_lshot.py:257] INFO Epoch: [10][50/150] Time 0.940 (1.170) Data 0.000 (0.234) Loss 1.5321 (1.5915) Prec@1 53.906 (50.827) Prec@5 81.641 (79.044)
[2021-04-26 15:43:41 train_lshot.py:257] INFO Epoch: [10][60/150] Time 0.939 (1.132) Data 0.000 (0.195) Loss 1.6078 (1.5895) Prec@1 47.266 (50.916) Prec@5 75.781 (78.957)
[2021-04-26 15:43:51 train_lshot.py:257] INFO Epoch: [10][70/150] Time 0.943 (1.105) Data 0.001 (0.168) Loss 1.6183 (1.5871) Prec@1 48.828 (50.831) Prec@5 79.297 (79.099)
[2021-04-26 15:44:00 train_lshot.py:257] INFO Epoch: [10][80/150] Time 0.938 (1.085) Data 0.000 (0.147) Loss 1.5846 (1.5882) Prec@1 50.781 (50.719) Prec@5 80.859 (79.181)
[2021-04-26 15:44:10 train_lshot.py:257] INFO Epoch: [10][90/150] Time 0.942 (1.069) Data 0.000 (0.131) Loss 1.5340 (1.5834) Prec@1 51.172 (50.850) Prec@5 80.078 (79.374)
[2021-04-26 15:44:19 train_lshot.py:257] INFO Epoch: [10][100/150] Time 0.940 (1.056) Data 0.000 (0.118) Loss 1.5653 (1.5797) Prec@1 46.875 (50.948) Prec@5 79.688 (79.428)
[2021-04-26 15:44:28 train_lshot.py:257] INFO Epoch: [10][110/150] Time 0.931 (1.045) Data 0.000 (0.107) Loss 1.6293 (1.5802) Prec@1 50.391 (50.943) Prec@5 77.344 (79.417)
[2021-04-26 15:44:38 train_lshot.py:257] INFO Epoch: [10][120/150] Time 0.937 (1.037) Data 0.000 (0.099) Loss 1.5915 (1.5782) Prec@1 51.562 (51.004) Prec@5 76.562 (79.436)
[2021-04-26 15:44:47 train_lshot.py:257] INFO Epoch: [10][130/150] Time 0.946 (1.029) Data 0.000 (0.091) Loss 1.6356 (1.5780) Prec@1 46.094 (50.948) Prec@5 78.125 (79.467)
[2021-04-26 15:44:57 train_lshot.py:257] INFO Epoch: [10][140/150] Time 0.943 (1.023) Data 0.000 (0.085) Loss 1.5675 (1.5777) Prec@1 53.906 (50.936) Prec@5 77.734 (79.460)
[2021-04-26 15:45:19 train_lshot.py:257] INFO Epoch: [11][0/150] Time 13.179 (13.179) Data 12.210 (12.210) Loss 1.4319 (1.4319) Prec@1 52.344 (52.344) Prec@5 82.812 (82.812)
[2021-04-26 15:45:29 train_lshot.py:257] INFO Epoch: [11][10/150] Time 0.932 (2.073) Data 0.000 (1.135) Loss 1.5690 (1.5150) Prec@1 52.344 (52.805) Prec@5 77.344 (81.214)
[2021-04-26 15:45:38 train_lshot.py:257] INFO Epoch: [11][20/150] Time 0.939 (1.534) Data 0.000 (0.595) Loss 1.5858 (1.5223) Prec@1 51.562 (52.586) Prec@5 76.562 (80.952)
[2021-04-26 15:45:48 train_lshot.py:257] INFO Epoch: [11][30/150] Time 0.946 (1.342) Data 0.000 (0.403) Loss 1.5581 (1.5254) Prec@1 50.391 (52.634) Prec@5 79.297 (80.872)
[2021-04-26 15:45:57 train_lshot.py:257] INFO Epoch: [11][40/150] Time 0.932 (1.243) Data 0.001 (0.305) Loss 1.4748 (1.5144) Prec@1 57.812 (52.849) Prec@5 78.516 (81.021)
[2021-04-26 15:46:06 train_lshot.py:257] INFO Epoch: [11][50/150] Time 0.940 (1.183) Data 0.000 (0.245) Loss 1.4224 (1.5144) Prec@1 57.422 (52.780) Prec@5 85.156 (80.959)
[2021-04-26 15:46:16 train_lshot.py:257] INFO Epoch: [11][60/150] Time 0.943 (1.143) Data 0.000 (0.205) Loss 1.4437 (1.5164) Prec@1 51.953 (52.523) Prec@5 83.984 (80.955)
[2021-04-26 15:46:25 train_lshot.py:257] INFO Epoch: [11][70/150] Time 0.938 (1.114) Data 0.002 (0.176) Loss 1.4932 (1.5130) Prec@1 53.906 (52.503) Prec@5 80.859 (80.997)
[2021-04-26 15:46:35 train_lshot.py:257] INFO Epoch: [11][80/150] Time 0.944 (1.092) Data 0.000 (0.154) Loss 1.6676 (1.5156) Prec@1 50.000 (52.508) Prec@5 74.609 (80.811)
[2021-04-26 15:46:44 train_lshot.py:257] INFO Epoch: [11][90/150] Time 0.938 (1.075) Data 0.000 (0.138) Loss 1.4351 (1.5127) Prec@1 55.469 (52.640) Prec@5 82.031 (80.864)
[2021-04-26 15:46:53 train_lshot.py:257] INFO Epoch: [11][100/150] Time 0.930 (1.062) Data 0.000 (0.124) Loss 1.6852 (1.5150) Prec@1 47.266 (52.526) Prec@5 77.734 (80.817)
[2021-04-26 15:47:03 train_lshot.py:257] INFO Epoch: [11][110/150] Time 0.934 (1.050) Data 0.000 (0.113) Loss 1.6149 (1.5180) Prec@1 48.438 (52.386) Prec@5 81.641 (80.800)
[2021-04-26 15:47:12 train_lshot.py:257] INFO Epoch: [11][120/150] Time 0.941 (1.041) Data 0.000 (0.103) Loss 1.4234 (1.5184) Prec@1 54.688 (52.360) Prec@5 82.812 (80.792)
[2021-04-26 15:47:21 train_lshot.py:257] INFO Epoch: [11][130/150] Time 0.929 (1.033) Data 0.000 (0.096) Loss 1.4170 (1.5207) Prec@1 53.516 (52.308) Prec@5 84.375 (80.755)
[2021-04-26 15:47:31 train_lshot.py:257] INFO Epoch: [11][140/150] Time 0.943 (1.026) Data 0.000 (0.089) Loss 1.5877 (1.5187) Prec@1 50.781 (52.341) Prec@5 80.469 (80.829)
[2021-04-26 15:48:38 train_lshot.py:119] INFO Meta Val 11: 0.5089600127339363
[2021-04-26 15:48:53 train_lshot.py:257] INFO Epoch: [12][0/150] Time 12.904 (12.904) Data 11.944 (11.944) Loss 1.7074 (1.7074) Prec@1 45.312 (45.312) Prec@5 75.000 (75.000)
[2021-04-26 15:49:03 train_lshot.py:257] INFO Epoch: [12][10/150] Time 0.934 (2.022) Data 0.000 (1.086) Loss 1.4884 (1.4860) Prec@1 54.297 (53.906) Prec@5 81.641 (82.102)
[2021-04-26 15:49:12 train_lshot.py:257] INFO Epoch: [12][20/150] Time 0.947 (1.505) Data 0.000 (0.569) Loss 1.4326 (1.4733) Prec@1 53.516 (54.018) Prec@5 83.594 (82.087)
[2021-04-26 15:49:21 train_lshot.py:257] INFO Epoch: [12][30/150] Time 0.931 (1.321) Data 0.000 (0.386) Loss 1.4586 (1.4650) Prec@1 54.688 (54.335) Prec@5 82.812 (82.044)
[2021-04-26 15:49:31 train_lshot.py:257] INFO Epoch: [12][40/150] Time 0.938 (1.227) Data 0.000 (0.292) Loss 1.4613 (1.4702) Prec@1 55.859 (54.021) Prec@5 83.984 (81.822)
[2021-04-26 15:49:40 train_lshot.py:257] INFO Epoch: [12][50/150] Time 0.943 (1.171) Data 0.000 (0.235) Loss 1.4626 (1.4762) Prec@1 57.422 (54.220) Prec@5 82.422 (81.625)
[2021-04-26 15:49:49 train_lshot.py:257] INFO Epoch: [12][60/150] Time 0.940 (1.133) Data 0.000 (0.196) Loss 1.4959 (1.4724) Prec@1 55.859 (54.425) Prec@5 80.078 (81.775)
[2021-04-26 15:49:59 train_lshot.py:257] INFO Epoch: [12][70/150] Time 0.938 (1.105) Data 0.002 (0.169) Loss 1.4121 (1.4717) Prec@1 58.203 (54.544) Prec@5 84.766 (81.839)
[2021-04-26 15:50:08 train_lshot.py:257] INFO Epoch: [12][80/150] Time 0.942 (1.085) Data 0.000 (0.148) Loss 1.4426 (1.4720) Prec@1 53.906 (54.514) Prec@5 84.766 (81.916)
[2021-04-26 15:50:18 train_lshot.py:257] INFO Epoch: [12][90/150] Time 0.944 (1.069) Data 0.000 (0.132) Loss 1.3816 (1.4718) Prec@1 59.375 (54.503) Prec@5 83.984 (81.817)
[2021-04-26 15:50:27 train_lshot.py:257] INFO Epoch: [12][100/150] Time 0.941 (1.057) Data 0.000 (0.119) Loss 1.3550 (1.4671) Prec@1 57.031 (54.672) Prec@5 81.641 (81.815)
[2021-04-26 15:50:36 train_lshot.py:257] INFO Epoch: [12][110/150] Time 0.934 (1.046) Data 0.000 (0.108) Loss 1.3181 (1.4643) Prec@1 59.766 (54.790) Prec@5 83.984 (81.855)
[2021-04-26 15:50:46 train_lshot.py:257] INFO Epoch: [12][120/150] Time 0.936 (1.037) Data 0.000 (0.099) Loss 1.3260 (1.4592) Prec@1 60.156 (54.891) Prec@5 84.766 (81.954)
[2021-04-26 15:50:55 train_lshot.py:257] INFO Epoch: [12][130/150] Time 0.944 (1.030) Data 0.000 (0.092) Loss 1.4976 (1.4591) Prec@1 52.344 (54.881) Prec@5 81.250 (81.927)
[2021-04-26 15:51:05 train_lshot.py:257] INFO Epoch: [12][140/150] Time 0.946 (1.024) Data 0.000 (0.085) Loss 1.4759 (1.4600) Prec@1 55.078 (54.848) Prec@5 82.031 (81.896)
[2021-04-26 15:51:26 train_lshot.py:257] INFO Epoch: [13][0/150] Time 11.347 (11.347) Data 10.375 (10.375) Loss 1.4612 (1.4612) Prec@1 55.469 (55.469) Prec@5 80.859 (80.859)
[2021-04-26 15:51:35 train_lshot.py:257] INFO Epoch: [13][10/150] Time 0.934 (1.883) Data 0.001 (0.944) Loss 1.3073 (1.3870) Prec@1 60.938 (55.646) Prec@5 86.328 (84.162)
[2021-04-26 15:51:44 train_lshot.py:257] INFO Epoch: [13][20/150] Time 0.944 (1.434) Data 0.001 (0.494) Loss 1.4114 (1.3818) Prec@1 55.078 (56.027) Prec@5 81.641 (84.338)
[2021-04-26 15:51:54 train_lshot.py:257] INFO Epoch: [13][30/150] Time 0.941 (1.274) Data 0.000 (0.335) Loss 1.4508 (1.3917) Prec@1 55.469 (56.225) Prec@5 84.375 (84.136)
[2021-04-26 15:52:03 train_lshot.py:257] INFO Epoch: [13][40/150] Time 0.943 (1.193) Data 0.001 (0.254) Loss 1.4074 (1.3894) Prec@1 54.688 (56.479) Prec@5 82.812 (83.765)
[2021-04-26 15:52:12 train_lshot.py:257] INFO Epoch: [13][50/150] Time 0.932 (1.143) Data 0.001 (0.204) Loss 1.3352 (1.3972) Prec@1 55.469 (56.281) Prec@5 85.156 (83.548)
[2021-04-26 15:52:22 train_lshot.py:257] INFO Epoch: [13][60/150] Time 0.946 (1.110) Data 0.001 (0.171) Loss 1.3510 (1.4028) Prec@1 56.641 (55.955) Prec@5 85.938 (83.395)
[2021-04-26 15:52:31 train_lshot.py:257] INFO Epoch: [13][70/150] Time 0.942 (1.086) Data 0.002 (0.147) Loss 1.3455 (1.3970) Prec@1 58.594 (56.206) Prec@5 83.203 (83.654)
[2021-04-26 15:52:41 train_lshot.py:257] INFO Epoch: [13][80/150] Time 0.940 (1.067) Data 0.000 (0.129) Loss 1.4716 (1.3941) Prec@1 52.734 (56.264) Prec@5 81.641 (83.695)
[2021-04-26 15:52:50 train_lshot.py:257] INFO Epoch: [13][90/150] Time 0.941 (1.053) Data 0.000 (0.114) Loss 1.2850 (1.3985) Prec@1 60.547 (56.207) Prec@5 87.891 (83.628)
[2021-04-26 15:52:59 train_lshot.py:257] INFO Epoch: [13][100/150] Time 0.945 (1.042) Data 0.000 (0.103) Loss 1.3564 (1.3970) Prec@1 58.984 (56.381) Prec@5 79.297 (83.601)
[2021-04-26 15:53:09 train_lshot.py:257] INFO Epoch: [13][110/150] Time 0.934 (1.032) Data 0.000 (0.094) Loss 1.4838 (1.3986) Prec@1 53.906 (56.366) Prec@5 82.812 (83.611)
[2021-04-26 15:53:18 train_lshot.py:257] INFO Epoch: [13][120/150] Time 0.941 (1.024) Data 0.000 (0.086) Loss 1.4978 (1.3993) Prec@1 54.688 (56.431) Prec@5 80.469 (83.549)
[2021-04-26 15:53:27 train_lshot.py:257] INFO Epoch: [13][130/150] Time 0.931 (1.018) Data 0.000 (0.080) Loss 1.3062 (1.3994) Prec@1 60.547 (56.414) Prec@5 84.766 (83.436)
[2021-04-26 15:53:37 train_lshot.py:257] INFO Epoch: [13][140/150] Time 0.934 (1.012) Data 0.000 (0.074) Loss 1.4005 (1.3991) Prec@1 57.031 (56.447) Prec@5 83.203 (83.455)
[2021-04-26 15:54:00 train_lshot.py:257] INFO Epoch: [14][0/150] Time 13.436 (13.436) Data 12.488 (12.488) Loss 1.3514 (1.3514) Prec@1 57.031 (57.031) Prec@5 83.203 (83.203)
[2021-04-26 15:54:09 train_lshot.py:257] INFO Epoch: [14][10/150] Time 0.943 (2.070) Data 0.000 (1.136) Loss 1.2822 (1.3220) Prec@1 61.719 (59.730) Prec@5 85.938 (84.055)
[2021-04-26 15:54:18 train_lshot.py:257] INFO Epoch: [14][20/150] Time 0.931 (1.529) Data 0.000 (0.595) Loss 1.3049 (1.3287) Prec@1 59.375 (59.208) Prec@5 85.156 (84.301)
[2021-04-26 15:54:28 train_lshot.py:257] INFO Epoch: [14][30/150] Time 0.942 (1.337) Data 0.001 (0.403) Loss 1.2845 (1.3284) Prec@1 61.719 (59.375) Prec@5 87.109 (84.375)
[2021-04-26 15:54:37 train_lshot.py:257] INFO Epoch: [14][40/150] Time 0.936 (1.240) Data 0.001 (0.305) Loss 1.3117 (1.3362) Prec@1 56.250 (58.775) Prec@5 83.203 (84.061)
[2021-04-26 15:54:47 train_lshot.py:257] INFO Epoch: [14][50/150] Time 0.943 (1.181) Data 0.000 (0.245) Loss 1.4118 (1.3437) Prec@1 55.469 (58.563) Prec@5 85.156 (83.977)
[2021-04-26 15:54:56 train_lshot.py:257] INFO Epoch: [14][60/150] Time 0.934 (1.141) Data 0.000 (0.205) Loss 1.2036 (1.3387) Prec@1 61.328 (58.703) Prec@5 87.500 (84.132)
[2021-04-26 15:55:05 train_lshot.py:257] INFO Epoch: [14][70/150] Time 0.939 (1.112) Data 0.001 (0.176) Loss 1.3606 (1.3332) Prec@1 58.203 (58.764) Prec@5 81.641 (84.265)
[2021-04-26 15:55:15 train_lshot.py:257] INFO Epoch: [14][80/150] Time 0.946 (1.090) Data 0.000 (0.155) Loss 1.3278 (1.3324) Prec@1 55.469 (58.729) Prec@5 85.156 (84.418)
[2021-04-26 15:55:24 train_lshot.py:257] INFO Epoch: [14][90/150] Time 0.937 (1.073) Data 0.000 (0.138) Loss 1.3184 (1.3349) Prec@1 57.422 (58.542) Prec@5 85.547 (84.388)
[2021-04-26 15:55:33 train_lshot.py:257] INFO Epoch: [14][100/150] Time 0.940 (1.060) Data 0.000 (0.124) Loss 1.2688 (1.3371) Prec@1 57.812 (58.373) Prec@5 88.281 (84.468)
[2021-04-26 15:55:43 train_lshot.py:257] INFO Epoch: [14][110/150] Time 0.936 (1.049) Data 0.000 (0.113) Loss 1.3752 (1.3408) Prec@1 57.031 (58.256) Prec@5 84.766 (84.459)
[2021-04-26 15:55:52 train_lshot.py:257] INFO Epoch: [14][120/150] Time 0.937 (1.040) Data 0.000 (0.104) Loss 1.3742 (1.3427) Prec@1 57.031 (58.161) Prec@5 83.203 (84.469)
[2021-04-26 15:56:02 train_lshot.py:257] INFO Epoch: [14][130/150] Time 0.941 (1.033) Data 0.000 (0.096) Loss 1.2509 (1.3403) Prec@1 62.891 (58.230) Prec@5 86.328 (84.578)
[2021-04-26 15:56:11 train_lshot.py:257] INFO Epoch: [14][140/150] Time 0.945 (1.026) Data 0.000 (0.089) Loss 1.3298 (1.3432) Prec@1 60.547 (58.156) Prec@5 83.984 (84.502)
[2021-04-26 15:56:34 train_lshot.py:257] INFO Epoch: [15][0/150] Time 13.804 (13.804) Data 12.832 (12.832) Loss 1.4177 (1.4177) Prec@1 55.859 (55.859) Prec@5 84.375 (84.375)
[2021-04-26 15:56:44 train_lshot.py:257] INFO Epoch: [15][10/150] Time 0.949 (2.108) Data 0.001 (1.167) Loss 1.1367 (1.2396) Prec@1 68.359 (61.825) Prec@5 88.672 (87.180)
[2021-04-26 15:56:53 train_lshot.py:257] INFO Epoch: [15][20/150] Time 0.940 (1.551) Data 0.000 (0.611) Loss 1.2730 (1.2239) Prec@1 63.672 (62.370) Prec@5 85.938 (87.295)
[2021-04-26 15:57:02 train_lshot.py:257] INFO Epoch: [15][30/150] Time 0.945 (1.354) Data 0.000 (0.414) Loss 1.4144 (1.2534) Prec@1 58.594 (61.416) Prec@5 81.250 (86.668)
[2021-04-26 15:57:12 train_lshot.py:257] INFO Epoch: [15][40/150] Time 0.935 (1.253) Data 0.001 (0.313) Loss 1.2221 (1.2632) Prec@1 63.672 (61.014) Prec@5 85.547 (86.357)
[2021-04-26 15:57:21 train_lshot.py:257] INFO Epoch: [15][50/150] Time 0.946 (1.192) Data 0.001 (0.252) Loss 1.2324 (1.2743) Prec@1 59.766 (60.547) Prec@5 87.500 (86.022)
[2021-04-26 15:57:31 train_lshot.py:257] INFO Epoch: [15][60/150] Time 0.936 (1.150) Data 0.000 (0.211) Loss 1.3548 (1.2739) Prec@1 57.031 (60.579) Prec@5 82.812 (86.008)
[2021-04-26 15:57:40 train_lshot.py:257] INFO Epoch: [15][70/150] Time 0.938 (1.121) Data 0.002 (0.181) Loss 1.3689 (1.2820) Prec@1 57.031 (60.415) Prec@5 81.641 (85.717)
[2021-04-26 15:57:49 train_lshot.py:257] INFO Epoch: [15][80/150] Time 0.937 (1.098) Data 0.000 (0.159) Loss 1.3393 (1.2825) Prec@1 60.938 (60.475) Prec@5 84.766 (85.619)
[2021-04-26 15:57:59 train_lshot.py:257] INFO Epoch: [15][90/150] Time 0.938 (1.081) Data 0.000 (0.141) Loss 1.4428 (1.2865) Prec@1 56.250 (60.345) Prec@5 83.984 (85.564)
[2021-04-26 15:58:08 train_lshot.py:257] INFO Epoch: [15][100/150] Time 0.938 (1.067) Data 0.000 (0.127) Loss 1.2824 (1.2883) Prec@1 59.766 (60.191) Prec@5 84.375 (85.493)
[2021-04-26 15:58:18 train_lshot.py:257] INFO Epoch: [15][110/150] Time 0.937 (1.055) Data 0.000 (0.116) Loss 1.3434 (1.2897) Prec@1 56.250 (60.125) Prec@5 88.281 (85.519)
[2021-04-26 15:58:27 train_lshot.py:257] INFO Epoch: [15][120/150] Time 0.935 (1.045) Data 0.000 (0.106) Loss 1.4350 (1.2890) Prec@1 53.906 (60.169) Prec@5 78.516 (85.528)
[2021-04-26 15:58:36 train_lshot.py:257] INFO Epoch: [15][130/150] Time 0.941 (1.037) Data 0.000 (0.098) Loss 1.2583 (1.2919) Prec@1 60.938 (60.064) Prec@5 85.156 (85.463)
[2021-04-26 15:58:46 train_lshot.py:257] INFO Epoch: [15][140/150] Time 0.936 (1.030) Data 0.000 (0.091) Loss 1.3058 (1.2910) Prec@1 59.766 (60.123) Prec@5 86.328 (85.519)
[2021-04-26 15:59:47 train_lshot.py:119] INFO Meta Val 15: 0.545066679418087
[2021-04-26 16:00:01 train_lshot.py:257] INFO Epoch: [16][0/150] Time 12.038 (12.038) Data 11.087 (11.087) Loss 1.2616 (1.2616) Prec@1 59.766 (59.766) Prec@5 84.766 (84.766)
[2021-04-26 16:00:10 train_lshot.py:257] INFO Epoch: [16][10/150] Time 0.933 (1.943) Data 0.000 (1.008) Loss 1.2796 (1.2626) Prec@1 59.766 (61.115) Prec@5 86.328 (85.831)
[2021-04-26 16:00:20 train_lshot.py:257] INFO Epoch: [16][20/150] Time 0.932 (1.463) Data 0.000 (0.528) Loss 1.2530 (1.2918) Prec@1 60.938 (60.268) Prec@5 87.500 (85.026)
[2021-04-26 16:00:29 train_lshot.py:257] INFO Epoch: [16][30/150] Time 0.930 (1.293) Data 0.001 (0.358) Loss 1.2166 (1.2765) Prec@1 63.281 (60.723) Prec@5 87.500 (85.282)
[2021-04-26 16:00:39 train_lshot.py:257] INFO Epoch: [16][40/150] Time 0.937 (1.206) Data 0.000 (0.271) Loss 1.3574 (1.2739) Prec@1 58.594 (60.671) Prec@5 83.203 (85.394)
[2021-04-26 16:00:48 train_lshot.py:257] INFO Epoch: [16][50/150] Time 0.929 (1.153) Data 0.000 (0.218) Loss 1.2717 (1.2744) Prec@1 59.766 (60.761) Prec@5 84.375 (85.409)
[2021-04-26 16:00:57 train_lshot.py:257] INFO Epoch: [16][60/150] Time 0.933 (1.117) Data 0.000 (0.182) Loss 1.1810 (1.2679) Prec@1 62.109 (60.989) Prec@5 87.500 (85.547)
[2021-04-26 16:01:07 train_lshot.py:257] INFO Epoch: [16][70/150] Time 0.946 (1.092) Data 0.000 (0.157) Loss 1.3253 (1.2694) Prec@1 61.719 (60.949) Prec@5 83.984 (85.563)
[2021-04-26 16:01:16 train_lshot.py:257] INFO Epoch: [16][80/150] Time 0.932 (1.073) Data 0.000 (0.137) Loss 1.2835 (1.2735) Prec@1 59.766 (60.913) Prec@5 85.938 (85.431)
[2021-04-26 16:01:25 train_lshot.py:257] INFO Epoch: [16][90/150] Time 0.939 (1.058) Data 0.000 (0.122) Loss 1.4372 (1.2774) Prec@1 55.859 (60.804) Prec@5 80.078 (85.358)
[2021-04-26 16:01:35 train_lshot.py:257] INFO Epoch: [16][100/150] Time 0.936 (1.046) Data 0.000 (0.110) Loss 1.2691 (1.2728) Prec@1 64.453 (60.895) Prec@5 88.281 (85.558)
[2021-04-26 16:01:44 train_lshot.py:257] INFO Epoch: [16][110/150] Time 0.941 (1.036) Data 0.000 (0.100) Loss 1.2197 (1.2698) Prec@1 63.281 (61.011) Prec@5 88.672 (85.638)
[2021-04-26 16:01:54 train_lshot.py:257] INFO Epoch: [16][120/150] Time 0.944 (1.028) Data 0.000 (0.092) Loss 1.1875 (1.2713) Prec@1 63.281 (60.831) Prec@5 85.938 (85.557)
[2021-04-26 16:02:03 train_lshot.py:257] INFO Epoch: [16][130/150] Time 0.940 (1.022) Data 0.000 (0.085) Loss 1.2169 (1.2711) Prec@1 58.594 (60.812) Prec@5 87.109 (85.604)
[2021-04-26 16:02:12 train_lshot.py:257] INFO Epoch: [16][140/150] Time 0.941 (1.016) Data 0.000 (0.079) Loss 1.1233 (1.2691) Prec@1 64.453 (60.865) Prec@5 89.062 (85.641)
[2021-04-26 16:02:34 train_lshot.py:257] INFO Epoch: [17][0/150] Time 11.740 (11.740) Data 10.782 (10.782) Loss 1.1235 (1.1235) Prec@1 64.453 (64.453) Prec@5 89.453 (89.453)
[2021-04-26 16:02:43 train_lshot.py:257] INFO Epoch: [17][10/150] Time 0.940 (1.920) Data 0.000 (0.980) Loss 1.1259 (1.2059) Prec@1 66.016 (63.033) Prec@5 88.672 (86.719)
[2021-04-26 16:02:52 train_lshot.py:257] INFO Epoch: [17][20/150] Time 0.937 (1.456) Data 0.000 (0.514) Loss 1.2184 (1.2224) Prec@1 65.234 (62.630) Prec@5 83.984 (86.496)
[2021-04-26 16:03:02 train_lshot.py:257] INFO Epoch: [17][30/150] Time 0.937 (1.290) Data 0.001 (0.348) Loss 1.1282 (1.2149) Prec@1 62.891 (62.639) Prec@5 87.500 (86.757)
[2021-04-26 16:03:11 train_lshot.py:257] INFO Epoch: [17][40/150] Time 0.940 (1.205) Data 0.001 (0.263) Loss 1.2190 (1.2089) Prec@1 62.109 (62.824) Prec@5 87.500 (86.862)
[2021-04-26 16:03:21 train_lshot.py:257] INFO Epoch: [17][50/150] Time 0.941 (1.152) Data 0.001 (0.212) Loss 1.1996 (1.2148) Prec@1 62.500 (62.615) Prec@5 88.672 (86.895)
[2021-04-26 16:03:30 train_lshot.py:257] INFO Epoch: [17][60/150] Time 0.940 (1.117) Data 0.000 (0.177) Loss 1.2225 (1.2151) Prec@1 61.719 (62.538) Prec@5 87.891 (86.828)
[2021-04-26 16:03:39 train_lshot.py:257] INFO Epoch: [17][70/150] Time 0.938 (1.093) Data 0.000 (0.152) Loss 1.2178 (1.2128) Prec@1 64.062 (62.588) Prec@5 85.156 (86.840)
[2021-04-26 16:03:49 train_lshot.py:257] INFO Epoch: [17][80/150] Time 0.933 (1.074) Data 0.000 (0.134) Loss 1.2547 (1.2191) Prec@1 61.328 (62.418) Prec@5 87.109 (86.671)
[2021-04-26 16:03:58 train_lshot.py:257] INFO Epoch: [17][90/150] Time 0.939 (1.059) Data 0.000 (0.119) Loss 1.1973 (1.2205) Prec@1 62.109 (62.380) Prec@5 89.453 (86.719)
[2021-04-26 16:04:08 train_lshot.py:257] INFO Epoch: [17][100/150] Time 0.940 (1.047) Data 0.000 (0.107) Loss 1.0404 (1.2217) Prec@1 70.312 (62.399) Prec@5 91.406 (86.711)
[2021-04-26 16:04:17 train_lshot.py:257] INFO Epoch: [17][110/150] Time 0.937 (1.037) Data 0.000 (0.098) Loss 1.2836 (1.2250) Prec@1 60.938 (62.324) Prec@5 87.500 (86.691)
[2021-04-26 16:04:26 train_lshot.py:257] INFO Epoch: [17][120/150] Time 0.945 (1.029) Data 0.000 (0.089) Loss 1.4702 (1.2252) Prec@1 53.516 (62.280) Prec@5 83.203 (86.651)
[2021-04-26 16:04:36 train_lshot.py:257] INFO Epoch: [17][130/150] Time 0.941 (1.022) Data 0.000 (0.083) Loss 1.2312 (1.2256) Prec@1 59.375 (62.333) Prec@5 85.938 (86.635)
[2021-04-26 16:04:45 train_lshot.py:257] INFO Epoch: [17][140/150] Time 0.934 (1.016) Data 0.000 (0.077) Loss 1.1910 (1.2220) Prec@1 62.891 (62.411) Prec@5 87.109 (86.719)
[2021-04-26 16:05:09 train_lshot.py:257] INFO Epoch: [18][0/150] Time 14.442 (14.442) Data 13.495 (13.495) Loss 1.1321 (1.1321) Prec@1 66.016 (66.016) Prec@5 86.328 (86.328)
[2021-04-26 16:05:18 train_lshot.py:257] INFO Epoch: [18][10/150] Time 0.935 (2.161) Data 0.000 (1.227) Loss 1.2111 (1.1875) Prec@1 64.062 (64.027) Prec@5 87.500 (87.571)
[2021-04-26 16:05:28 train_lshot.py:257] INFO Epoch: [18][20/150] Time 0.941 (1.578) Data 0.000 (0.643) Loss 1.2200 (1.1856) Prec@1 60.938 (63.821) Prec@5 87.891 (87.835)
[2021-04-26 16:05:37 train_lshot.py:257] INFO Epoch: [18][30/150] Time 0.940 (1.371) Data 0.000 (0.436) Loss 1.2397 (1.1807) Prec@1 59.375 (63.987) Prec@5 91.016 (87.954)
[2021-04-26 16:05:46 train_lshot.py:257] INFO Epoch: [18][40/150] Time 0.942 (1.265) Data 0.001 (0.330) Loss 1.1874 (1.1839) Prec@1 64.062 (63.843) Prec@5 87.500 (87.748)
[2021-04-26 16:05:56 train_lshot.py:257] INFO Epoch: [18][50/150] Time 0.936 (1.200) Data 0.001 (0.265) Loss 1.1914 (1.1839) Prec@1 61.328 (63.779) Prec@5 89.062 (87.883)
[2021-04-26 16:06:05 train_lshot.py:257] INFO Epoch: [18][60/150] Time 0.936 (1.157) Data 0.001 (0.222) Loss 1.0806 (1.1866) Prec@1 69.141 (63.781) Prec@5 90.234 (87.647)
[2021-04-26 16:06:15 train_lshot.py:257] INFO Epoch: [18][70/150] Time 0.935 (1.126) Data 0.002 (0.191) Loss 1.0370 (1.1809) Prec@1 67.578 (63.941) Prec@5 91.406 (87.720)
[2021-04-26 16:06:24 train_lshot.py:257] INFO Epoch: [18][80/150] Time 0.929 (1.102) Data 0.000 (0.167) Loss 1.1841 (1.1806) Prec@1 65.234 (63.976) Prec@5 85.547 (87.645)
[2021-04-26 16:06:33 train_lshot.py:257] INFO Epoch: [18][90/150] Time 0.935 (1.084) Data 0.000 (0.149) Loss 1.1633 (1.1806) Prec@1 62.500 (63.818) Prec@5 88.672 (87.573)
[2021-04-26 16:06:43 train_lshot.py:257] INFO Epoch: [18][100/150] Time 0.932 (1.069) Data 0.000 (0.134) Loss 1.1300 (1.1808) Prec@1 68.750 (63.943) Prec@5 88.672 (87.554)
[2021-04-26 16:06:52 train_lshot.py:257] INFO Epoch: [18][110/150] Time 0.936 (1.057) Data 0.000 (0.122) Loss 1.0697 (1.1815) Prec@1 70.312 (63.876) Prec@5 87.500 (87.525)
[2021-04-26 16:07:01 train_lshot.py:257] INFO Epoch: [18][120/150] Time 0.941 (1.047) Data 0.000 (0.112) Loss 1.0321 (1.1782) Prec@1 69.141 (64.085) Prec@5 90.625 (87.577)
[2021-04-26 16:07:11 train_lshot.py:257] INFO Epoch: [18][130/150] Time 0.938 (1.039) Data 0.000 (0.103) Loss 1.2493 (1.1779) Prec@1 61.719 (64.065) Prec@5 85.547 (87.622)
[2021-04-26 16:07:20 train_lshot.py:257] INFO Epoch: [18][140/150] Time 0.940 (1.032) Data 0.000 (0.096) Loss 1.2224 (1.1781) Prec@1 61.328 (64.029) Prec@5 87.109 (87.580)
[2021-04-26 16:07:43 train_lshot.py:257] INFO Epoch: [19][0/150] Time 13.157 (13.157) Data 12.212 (12.212) Loss 1.0990 (1.0990) Prec@1 64.062 (64.062) Prec@5 89.062 (89.062)
[2021-04-26 16:07:52 train_lshot.py:257] INFO Epoch: [19][10/150] Time 0.937 (2.046) Data 0.000 (1.111) Loss 1.1279 (1.1601) Prec@1 64.453 (64.169) Prec@5 87.109 (88.068)
[2021-04-26 16:08:01 train_lshot.py:257] INFO Epoch: [19][20/150] Time 0.930 (1.519) Data 0.000 (0.582) Loss 1.0740 (1.1333) Prec@1 66.406 (65.160) Prec@5 89.844 (88.635)
[2021-04-26 16:08:11 train_lshot.py:257] INFO Epoch: [19][30/150] Time 0.938 (1.331) Data 0.001 (0.394) Loss 1.2722 (1.1450) Prec@1 63.672 (65.209) Prec@5 84.375 (88.218)
[2021-04-26 16:08:20 train_lshot.py:257] INFO Epoch: [19][40/150] Time 0.945 (1.236) Data 0.001 (0.298) Loss 1.1385 (1.1426) Prec@1 66.016 (65.330) Prec@5 87.891 (88.157)
[2021-04-26 16:08:30 train_lshot.py:257] INFO Epoch: [19][50/150] Time 0.930 (1.177) Data 0.000 (0.240) Loss 1.0883 (1.1394) Prec@1 67.578 (65.510) Prec@5 89.062 (88.182)
[2021-04-26 16:08:39 train_lshot.py:257] INFO Epoch: [19][60/150] Time 0.936 (1.139) Data 0.000 (0.201) Loss 1.1020 (1.1440) Prec@1 66.797 (65.158) Prec@5 88.281 (88.121)
[2021-04-26 16:08:48 train_lshot.py:257] INFO Epoch: [19][70/150] Time 0.941 (1.111) Data 0.000 (0.172) Loss 1.0753 (1.1428) Prec@1 66.797 (65.113) Prec@5 89.844 (88.094)
[2021-04-26 16:08:58 train_lshot.py:257] INFO Epoch: [19][80/150] Time 0.949 (1.090) Data 0.000 (0.151) Loss 1.1819 (1.1460) Prec@1 63.672 (65.080) Prec@5 86.719 (88.011)
[2021-04-26 16:09:07 train_lshot.py:257] INFO Epoch: [19][90/150] Time 0.938 (1.073) Data 0.000 (0.135) Loss 1.1341 (1.1512) Prec@1 60.547 (64.831) Prec@5 89.453 (87.968)
[2021-04-26 16:09:17 train_lshot.py:257] INFO Epoch: [19][100/150] Time 0.940 (1.060) Data 0.000 (0.121) Loss 1.1604 (1.1521) Prec@1 65.234 (64.751) Prec@5 87.500 (87.925)
[2021-04-26 16:09:26 train_lshot.py:257] INFO Epoch: [19][110/150] Time 0.938 (1.049) Data 0.000 (0.110) Loss 1.2352 (1.1540) Prec@1 64.453 (64.721) Prec@5 84.766 (87.898)
[2021-04-26 16:09:35 train_lshot.py:257] INFO Epoch: [19][120/150] Time 0.933 (1.040) Data 0.000 (0.101) Loss 1.2110 (1.1551) Prec@1 64.453 (64.679) Prec@5 86.328 (87.904)
[2021-04-26 16:09:45 train_lshot.py:257] INFO Epoch: [19][130/150] Time 0.936 (1.033) Data 0.000 (0.094) Loss 1.1615 (1.1572) Prec@1 62.109 (64.602) Prec@5 85.547 (87.795)
[2021-04-26 16:09:54 train_lshot.py:257] INFO Epoch: [19][140/150] Time 0.945 (1.026) Data 0.000 (0.087) Loss 1.1287 (1.1533) Prec@1 66.016 (64.705) Prec@5 88.672 (87.891)
[2021-04-26 16:11:00 train_lshot.py:119] INFO Meta Val 19: 0.5763200123906136
[2021-04-26 16:11:14 train_lshot.py:257] INFO Epoch: [20][0/150] Time 11.435 (11.435) Data 10.485 (10.485) Loss 1.0066 (1.0066) Prec@1 71.875 (71.875) Prec@5 89.453 (89.453)
[2021-04-26 16:11:23 train_lshot.py:257] INFO Epoch: [20][10/150] Time 0.934 (1.887) Data 0.000 (0.953) Loss 1.0021 (1.1190) Prec@1 70.703 (66.087) Prec@5 91.797 (89.098)
[2021-04-26 16:11:32 train_lshot.py:257] INFO Epoch: [20][20/150] Time 0.924 (1.433) Data 0.000 (0.500) Loss 1.1337 (1.1098) Prec@1 63.281 (66.146) Prec@5 89.453 (88.858)
[2021-04-26 16:11:42 train_lshot.py:257] INFO Epoch: [20][30/150] Time 0.936 (1.273) Data 0.001 (0.339) Loss 1.0049 (1.1152) Prec@1 70.703 (65.953) Prec@5 93.359 (88.836)
[2021-04-26 16:11:51 train_lshot.py:257] INFO Epoch: [20][40/150] Time 0.933 (1.191) Data 0.000 (0.256) Loss 1.2330 (1.1142) Prec@1 61.328 (66.139) Prec@5 86.328 (88.748)
[2021-04-26 16:12:01 train_lshot.py:257] INFO Epoch: [20][50/150] Time 0.936 (1.141) Data 0.001 (0.206) Loss 0.9970 (1.1181) Prec@1 68.750 (66.138) Prec@5 91.016 (88.565)
[2021-04-26 16:12:10 train_lshot.py:257] INFO Epoch: [20][60/150] Time 0.934 (1.107) Data 0.001 (0.172) Loss 1.0358 (1.1228) Prec@1 66.797 (66.016) Prec@5 91.797 (88.537)
[2021-04-26 16:12:19 train_lshot.py:257] INFO Epoch: [20][70/150] Time 0.936 (1.083) Data 0.000 (0.148) Loss 1.1574 (1.1220) Prec@1 64.062 (65.911) Prec@5 89.844 (88.600)
[2021-04-26 16:12:29 train_lshot.py:257] INFO Epoch: [20][80/150] Time 0.935 (1.065) Data 0.000 (0.130) Loss 1.0198 (1.1201) Prec@1 66.797 (65.943) Prec@5 92.969 (88.710)
[2021-04-26 16:12:38 train_lshot.py:257] INFO Epoch: [20][90/150] Time 0.934 (1.050) Data 0.000 (0.116) Loss 1.0752 (1.1232) Prec@1 65.625 (65.698) Prec@5 91.016 (88.586)
[2021-04-26 16:12:47 train_lshot.py:257] INFO Epoch: [20][100/150] Time 0.940 (1.039) Data 0.000 (0.104) Loss 1.1939 (1.1249) Prec@1 66.016 (65.695) Prec@5 88.672 (88.540)
[2021-04-26 16:12:57 train_lshot.py:257] INFO Epoch: [20][110/150] Time 0.940 (1.030) Data 0.000 (0.095) Loss 1.1781 (1.1253) Prec@1 66.406 (65.657) Prec@5 87.500 (88.510)
[2021-04-26 16:13:06 train_lshot.py:257] INFO Epoch: [20][120/150] Time 0.934 (1.022) Data 0.000 (0.087) Loss 1.0403 (1.1243) Prec@1 67.188 (65.686) Prec@5 89.062 (88.510)
[2021-04-26 16:13:15 train_lshot.py:257] INFO Epoch: [20][130/150] Time 0.943 (1.016) Data 0.000 (0.080) Loss 1.0174 (1.1236) Prec@1 69.141 (65.694) Prec@5 92.578 (88.541)
[2021-04-26 16:13:25 train_lshot.py:257] INFO Epoch: [20][140/150] Time 0.934 (1.010) Data 0.000 (0.075) Loss 1.1398 (1.1223) Prec@1 65.625 (65.752) Prec@5 88.281 (88.511)
[2021-04-26 16:13:49 train_lshot.py:257] INFO Epoch: [21][0/150] Time 15.154 (15.154) Data 14.202 (14.202) Loss 1.0947 (1.0947) Prec@1 66.016 (66.016) Prec@5 90.234 (90.234)
[2021-04-26 16:13:59 train_lshot.py:257] INFO Epoch: [21][10/150] Time 0.941 (2.232) Data 0.001 (1.291) Loss 1.0183 (1.0662) Prec@1 67.969 (68.572) Prec@5 90.625 (89.773)
[2021-04-26 16:14:08 train_lshot.py:257] INFO Epoch: [21][20/150] Time 0.936 (1.615) Data 0.000 (0.677) Loss 0.9781 (1.0655) Prec@1 71.875 (68.248) Prec@5 91.797 (89.732)
[2021-04-26 16:14:18 train_lshot.py:257] INFO Epoch: [21][30/150] Time 0.937 (1.397) Data 0.000 (0.459) Loss 1.1388 (1.0715) Prec@1 66.797 (68.057) Prec@5 86.328 (89.579)
[2021-04-26 16:14:27 train_lshot.py:257] INFO Epoch: [21][40/150] Time 0.941 (1.285) Data 0.001 (0.347) Loss 1.0280 (1.0711) Prec@1 69.531 (67.931) Prec@5 90.625 (89.396)
[2021-04-26 16:14:36 train_lshot.py:257] INFO Epoch: [21][50/150] Time 0.945 (1.217) Data 0.001 (0.279) Loss 1.1956 (1.0693) Prec@1 65.625 (67.969) Prec@5 83.984 (89.377)
[2021-04-26 16:14:46 train_lshot.py:257] INFO Epoch: [21][60/150] Time 0.943 (1.172) Data 0.001 (0.233) Loss 0.9393 (1.0636) Prec@1 71.094 (68.084) Prec@5 92.969 (89.549)
[2021-04-26 16:14:55 train_lshot.py:257] INFO Epoch: [21][70/150] Time 0.941 (1.139) Data 0.000 (0.201) Loss 1.1139 (1.0691) Prec@1 67.188 (67.771) Prec@5 87.500 (89.360)
[2021-04-26 16:15:05 train_lshot.py:257] INFO Epoch: [21][80/150] Time 0.942 (1.115) Data 0.000 (0.176) Loss 1.0835 (1.0727) Prec@1 68.359 (67.665) Prec@5 89.453 (89.304)
[2021-04-26 16:15:14 train_lshot.py:257] INFO Epoch: [21][90/150] Time 0.929 (1.095) Data 0.000 (0.157) Loss 0.9899 (1.0733) Prec@1 70.312 (67.630) Prec@5 90.625 (89.273)
[2021-04-26 16:15:23 train_lshot.py:257] INFO Epoch: [21][100/150] Time 0.935 (1.080) Data 0.000 (0.141) Loss 1.1517 (1.0732) Prec@1 65.625 (67.675) Prec@5 88.672 (89.256)
[2021-04-26 16:15:33 train_lshot.py:257] INFO Epoch: [21][110/150] Time 0.942 (1.067) Data 0.000 (0.128) Loss 1.2095 (1.0812) Prec@1 60.938 (67.254) Prec@5 85.156 (89.105)
[2021-04-26 16:15:42 train_lshot.py:257] INFO Epoch: [21][120/150] Time 0.934 (1.057) Data 0.000 (0.118) Loss 1.1389 (1.0847) Prec@1 60.547 (67.023) Prec@5 88.672 (89.040)
[2021-04-26 16:15:52 train_lshot.py:257] INFO Epoch: [21][130/150] Time 0.940 (1.048) Data 0.000 (0.109) Loss 1.2286 (1.0892) Prec@1 59.375 (66.857) Prec@5 86.719 (88.937)
[2021-04-26 16:16:01 train_lshot.py:257] INFO Epoch: [21][140/150] Time 0.936 (1.040) Data 0.000 (0.101) Loss 1.1004 (1.0908) Prec@1 64.453 (66.794) Prec@5 88.672 (88.921)
[2021-04-26 16:16:23 train_lshot.py:257] INFO Epoch: [22][0/150] Time 12.818 (12.818) Data 11.869 (11.869) Loss 1.1136 (1.1136) Prec@1 67.188 (67.188) Prec@5 88.672 (88.672)
[2021-04-26 16:16:33 train_lshot.py:257] INFO Epoch: [22][10/150] Time 0.946 (2.017) Data 0.001 (1.079) Loss 1.0825 (1.0736) Prec@1 69.531 (67.791) Prec@5 87.500 (88.778)
[2021-04-26 16:16:42 train_lshot.py:257] INFO Epoch: [22][20/150] Time 0.931 (1.502) Data 0.000 (0.566) Loss 1.2219 (1.0801) Prec@1 60.547 (67.094) Prec@5 86.719 (89.118)
[2021-04-26 16:16:51 train_lshot.py:257] INFO Epoch: [22][30/150] Time 0.933 (1.320) Data 0.000 (0.383) Loss 1.2389 (1.0948) Prec@1 60.938 (66.419) Prec@5 87.500 (88.962)
[2021-04-26 16:17:01 train_lshot.py:257] INFO Epoch: [22][40/150] Time 0.938 (1.226) Data 0.000 (0.290) Loss 1.0879 (1.0879) Prec@1 67.188 (66.530) Prec@5 90.234 (89.263)
[2021-04-26 16:17:10 train_lshot.py:257] INFO Epoch: [22][50/150] Time 0.941 (1.170) Data 0.001 (0.233) Loss 1.0208 (1.0864) Prec@1 67.969 (66.483) Prec@5 90.625 (89.285)
[2021-04-26 16:17:19 train_lshot.py:257] INFO Epoch: [22][60/150] Time 0.935 (1.132) Data 0.000 (0.195) Loss 0.9563 (1.0790) Prec@1 69.531 (66.778) Prec@5 93.359 (89.479)
[2021-04-26 16:17:29 train_lshot.py:257] INFO Epoch: [22][70/150] Time 0.935 (1.104) Data 0.001 (0.168) Loss 0.9739 (1.0683) Prec@1 67.188 (67.083) Prec@5 92.188 (89.679)
[2021-04-26 16:17:38 train_lshot.py:257] INFO Epoch: [22][80/150] Time 0.937 (1.084) Data 0.000 (0.147) Loss 1.1614 (1.0667) Prec@1 66.797 (67.168) Prec@5 88.281 (89.714)
[2021-04-26 16:17:47 train_lshot.py:257] INFO Epoch: [22][90/150] Time 0.927 (1.067) Data 0.000 (0.131) Loss 1.0121 (1.0653) Prec@1 69.922 (67.355) Prec@5 91.797 (89.689)
[2021-04-26 16:17:57 train_lshot.py:257] INFO Epoch: [22][100/150] Time 0.946 (1.054) Data 0.000 (0.118) Loss 1.1046 (1.0648) Prec@1 68.750 (67.400) Prec@5 87.891 (89.643)
[2021-04-26 16:18:06 train_lshot.py:257] INFO Epoch: [22][110/150] Time 0.932 (1.044) Data 0.000 (0.107) Loss 1.0923 (1.0655) Prec@1 66.797 (67.367) Prec@5 87.109 (89.615)
[2021-04-26 16:18:16 train_lshot.py:257] INFO Epoch: [22][120/150] Time 0.935 (1.035) Data 0.000 (0.098) Loss 1.0045 (1.0655) Prec@1 68.750 (67.349) Prec@5 91.406 (89.579)
[2021-04-26 16:18:25 train_lshot.py:257] INFO Epoch: [22][130/150] Time 0.943 (1.027) Data 0.000 (0.091) Loss 0.9704 (1.0629) Prec@1 70.312 (67.453) Prec@5 89.844 (89.602)
[2021-04-26 16:18:34 train_lshot.py:257] INFO Epoch: [22][140/150] Time 0.933 (1.021) Data 0.000 (0.085) Loss 1.0442 (1.0618) Prec@1 66.797 (67.445) Prec@5 91.016 (89.625)
[2021-04-26 16:18:55 train_lshot.py:257] INFO Epoch: [23][0/150] Time 11.759 (11.759) Data 10.811 (10.811) Loss 1.0549 (1.0549) Prec@1 64.844 (64.844) Prec@5 91.016 (91.016)
[2021-04-26 16:19:05 train_lshot.py:257] INFO Epoch: [23][10/150] Time 0.926 (1.919) Data 0.000 (0.983) Loss 0.9742 (0.9938) Prec@1 71.094 (70.810) Prec@5 91.406 (91.406)
[2021-04-26 16:19:14 train_lshot.py:257] INFO Epoch: [23][20/150] Time 0.938 (1.451) Data 0.000 (0.515) Loss 0.9825 (1.0233) Prec@1 67.578 (69.457) Prec@5 91.016 (90.662)
[2021-04-26 16:19:23 train_lshot.py:257] INFO Epoch: [23][30/150] Time 0.942 (1.285) Data 0.001 (0.349) Loss 1.1325 (1.0295) Prec@1 66.797 (69.216) Prec@5 87.891 (90.474)
[2021-04-26 16:19:33 train_lshot.py:257] INFO Epoch: [23][40/150] Time 0.936 (1.200) Data 0.000 (0.264) Loss 0.9949 (1.0278) Prec@1 71.094 (69.103) Prec@5 91.797 (90.387)
[2021-04-26 16:19:42 train_lshot.py:257] INFO Epoch: [23][50/150] Time 0.941 (1.148) Data 0.001 (0.212) Loss 1.2308 (1.0275) Prec@1 65.234 (69.133) Prec@5 83.984 (90.250)
[2021-04-26 16:19:52 train_lshot.py:257] INFO Epoch: [23][60/150] Time 0.941 (1.114) Data 0.001 (0.178) Loss 1.0573 (1.0286) Prec@1 65.625 (69.109) Prec@5 87.500 (90.126)
[2021-04-26 16:20:01 train_lshot.py:257] INFO Epoch: [23][70/150] Time 0.941 (1.090) Data 0.002 (0.153) Loss 1.0167 (1.0348) Prec@1 69.922 (68.844) Prec@5 91.406 (89.976)
[2021-04-26 16:20:10 train_lshot.py:257] INFO Epoch: [23][80/150] Time 0.940 (1.071) Data 0.000 (0.134) Loss 0.9775 (1.0359) Prec@1 72.266 (68.991) Prec@5 89.062 (89.931)
[2021-04-26 16:20:20 train_lshot.py:257] INFO Epoch: [23][90/150] Time 0.944 (1.056) Data 0.000 (0.119) Loss 0.9118 (1.0380) Prec@1 73.438 (68.840) Prec@5 92.969 (89.942)
[2021-04-26 16:20:29 train_lshot.py:257] INFO Epoch: [23][100/150] Time 0.933 (1.045) Data 0.000 (0.107) Loss 1.0083 (1.0374) Prec@1 69.922 (68.851) Prec@5 90.625 (89.910)
[2021-04-26 16:20:39 train_lshot.py:257] INFO Epoch: [23][110/150] Time 0.932 (1.035) Data 0.000 (0.098) Loss 1.0042 (1.0360) Prec@1 69.531 (68.799) Prec@5 90.625 (89.932)
[2021-04-26 16:20:48 train_lshot.py:257] INFO Epoch: [23][120/150] Time 0.940 (1.027) Data 0.000 (0.090) Loss 0.9425 (1.0368) Prec@1 71.094 (68.760) Prec@5 90.625 (89.902)
[2021-04-26 16:20:57 train_lshot.py:257] INFO Epoch: [23][130/150] Time 0.939 (1.020) Data 0.000 (0.083) Loss 1.0709 (1.0358) Prec@1 67.188 (68.783) Prec@5 88.281 (89.903)
[2021-04-26 16:21:07 train_lshot.py:257] INFO Epoch: [23][140/150] Time 0.945 (1.015) Data 0.000 (0.077) Loss 1.1169 (1.0347) Prec@1 67.188 (68.811) Prec@5 89.453 (89.921)
[2021-04-26 16:22:15 train_lshot.py:119] INFO Meta Val 23: 0.5748266803622246
[2021-04-26 16:22:28 train_lshot.py:257] INFO Epoch: [24][0/150] Time 11.998 (11.998) Data 11.042 (11.042) Loss 1.0701 (1.0701) Prec@1 69.141 (69.141) Prec@5 87.891 (87.891)
[2021-04-26 16:22:38 train_lshot.py:257] INFO Epoch: [24][10/150] Time 0.933 (1.940) Data 0.000 (1.004) Loss 0.9302 (1.0247) Prec@1 72.656 (69.638) Prec@5 91.406 (90.128)
[2021-04-26 16:22:47 train_lshot.py:257] INFO Epoch: [24][20/150] Time 0.941 (1.462) Data 0.000 (0.526) Loss 0.9218 (1.0076) Prec@1 73.828 (70.126) Prec@5 92.578 (90.420)
[2021-04-26 16:22:56 train_lshot.py:257] INFO Epoch: [24][30/150] Time 0.937 (1.292) Data 0.000 (0.357) Loss 0.9608 (1.0097) Prec@1 69.922 (69.846) Prec@5 93.359 (90.575)
[2021-04-26 16:23:06 train_lshot.py:257] INFO Epoch: [24][40/150] Time 0.935 (1.205) Data 0.001 (0.270) Loss 1.0453 (1.0136) Prec@1 67.578 (69.579) Prec@5 89.453 (90.463)
[2021-04-26 16:23:15 train_lshot.py:257] INFO Epoch: [24][50/150] Time 0.933 (1.152) Data 0.001 (0.217) Loss 0.9885 (1.0156) Prec@1 71.875 (69.531) Prec@5 89.844 (90.265)
[2021-04-26 16:23:24 train_lshot.py:257] INFO Epoch: [24][60/150] Time 0.929 (1.117) Data 0.000 (0.182) Loss 1.0324 (1.0170) Prec@1 69.531 (69.679) Prec@5 89.453 (90.222)
[2021-04-26 16:23:34 train_lshot.py:257] INFO Epoch: [24][70/150] Time 0.933 (1.091) Data 0.000 (0.156) Loss 1.0761 (1.0194) Prec@1 66.406 (69.625) Prec@5 88.281 (90.152)
[2021-04-26 16:23:43 train_lshot.py:257] INFO Epoch: [24][80/150] Time 0.934 (1.072) Data 0.000 (0.137) Loss 0.9902 (1.0208) Prec@1 72.266 (69.647) Prec@5 91.797 (90.186)
[2021-04-26 16:23:53 train_lshot.py:257] INFO Epoch: [24][90/150] Time 0.934 (1.057) Data 0.000 (0.122) Loss 1.0265 (1.0238) Prec@1 65.234 (69.420) Prec@5 89.453 (90.123)
[2021-04-26 16:24:02 train_lshot.py:257] INFO Epoch: [24][100/150] Time 0.939 (1.045) Data 0.000 (0.110) Loss 1.0376 (1.0238) Prec@1 65.625 (69.346) Prec@5 91.406 (90.157)
[2021-04-26 16:24:11 train_lshot.py:257] INFO Epoch: [24][110/150] Time 0.929 (1.035) Data 0.000 (0.100) Loss 0.9535 (1.0229) Prec@1 70.703 (69.310) Prec@5 91.797 (90.143)
[2021-04-26 16:24:21 train_lshot.py:257] INFO Epoch: [24][120/150] Time 0.930 (1.027) Data 0.000 (0.092) Loss 1.1187 (1.0250) Prec@1 67.578 (69.237) Prec@5 86.328 (90.076)
[2021-04-26 16:24:30 train_lshot.py:257] INFO Epoch: [24][130/150] Time 0.938 (1.020) Data 0.000 (0.085) Loss 1.0908 (1.0267) Prec@1 65.625 (69.221) Prec@5 89.453 (90.091)
[2021-04-26 16:24:39 train_lshot.py:257] INFO Epoch: [24][140/150] Time 0.935 (1.014) Data 0.000 (0.079) Loss 1.0537 (1.0268) Prec@1 68.359 (69.185) Prec@5 91.406 (90.143)
[2021-04-26 16:25:01 train_lshot.py:257] INFO Epoch: [25][0/150] Time 12.435 (12.435) Data 11.479 (11.479) Loss 1.0603 (1.0603) Prec@1 68.750 (68.750) Prec@5 88.281 (88.281)
[2021-04-26 16:25:10 train_lshot.py:257] INFO Epoch: [25][10/150] Time 0.937 (1.981) Data 0.000 (1.044) Loss 0.9532 (0.9775) Prec@1 69.922 (70.810) Prec@5 91.016 (90.518)
[2021-04-26 16:25:20 train_lshot.py:257] INFO Epoch: [25][20/150] Time 0.935 (1.483) Data 0.000 (0.547) Loss 0.9252 (0.9726) Prec@1 73.828 (70.722) Prec@5 89.844 (90.681)
[2021-04-26 16:25:29 train_lshot.py:257] INFO Epoch: [25][30/150] Time 0.934 (1.306) Data 0.001 (0.371) Loss 1.1286 (0.9833) Prec@1 66.406 (70.413) Prec@5 88.672 (90.499)
[2021-04-26 16:25:39 train_lshot.py:257] INFO Epoch: [25][40/150] Time 0.934 (1.216) Data 0.000 (0.280) Loss 0.9418 (0.9846) Prec@1 73.438 (70.598) Prec@5 91.797 (90.511)
[2021-04-26 16:25:48 train_lshot.py:257] INFO Epoch: [25][50/150] Time 0.941 (1.162) Data 0.001 (0.226) Loss 1.0305 (0.9787) Prec@1 71.484 (70.795) Prec@5 88.281 (90.579)
[2021-04-26 16:25:57 train_lshot.py:257] INFO Epoch: [25][60/150] Time 0.934 (1.125) Data 0.000 (0.189) Loss 1.0694 (0.9841) Prec@1 65.234 (70.530) Prec@5 89.453 (90.599)
[2021-04-26 16:26:07 train_lshot.py:257] INFO Epoch: [25][70/150] Time 0.941 (1.099) Data 0.001 (0.162) Loss 1.1028 (0.9847) Prec@1 67.969 (70.318) Prec@5 88.672 (90.675)
[2021-04-26 16:26:16 train_lshot.py:257] INFO Epoch: [25][80/150] Time 0.940 (1.079) Data 0.000 (0.142) Loss 1.0269 (0.9867) Prec@1 71.875 (70.317) Prec@5 91.406 (90.620)
[2021-04-26 16:26:26 train_lshot.py:257] INFO Epoch: [25][90/150] Time 0.950 (1.064) Data 0.000 (0.127) Loss 0.9282 (0.9853) Prec@1 72.266 (70.514) Prec@5 91.797 (90.702)
[2021-04-26 16:26:35 train_lshot.py:257] INFO Epoch: [25][100/150] Time 0.943 (1.052) Data 0.000 (0.114) Loss 1.2030 (0.9914) Prec@1 64.453 (70.432) Prec@5 88.281 (90.579)
[2021-04-26 16:26:44 train_lshot.py:257] INFO Epoch: [25][110/150] Time 0.938 (1.042) Data 0.000 (0.104) Loss 0.9220 (0.9864) Prec@1 70.703 (70.566) Prec@5 91.406 (90.678)
[2021-04-26 16:26:54 train_lshot.py:257] INFO Epoch: [25][120/150] Time 0.943 (1.033) Data 0.000 (0.095) Loss 0.9139 (0.9897) Prec@1 73.438 (70.480) Prec@5 91.797 (90.589)
[2021-04-26 16:27:03 train_lshot.py:257] INFO Epoch: [25][130/150] Time 0.936 (1.026) Data 0.000 (0.088) Loss 0.9446 (0.9883) Prec@1 70.703 (70.465) Prec@5 93.750 (90.649)
[2021-04-26 16:27:12 train_lshot.py:257] INFO Epoch: [25][140/150] Time 0.937 (1.020) Data 0.000 (0.082) Loss 0.9996 (0.9893) Prec@1 69.531 (70.318) Prec@5 91.016 (90.631)
[2021-04-26 16:27:37 train_lshot.py:257] INFO Epoch: [26][0/150] Time 15.334 (15.334) Data 14.381 (14.381) Loss 0.9956 (0.9956) Prec@1 69.531 (69.531) Prec@5 90.625 (90.625)
[2021-04-26 16:27:47 train_lshot.py:257] INFO Epoch: [26][10/150] Time 0.947 (2.246) Data 0.000 (1.308) Loss 0.8977 (0.9679) Prec@1 75.391 (71.484) Prec@5 90.625 (90.909)
[2021-04-26 16:27:56 train_lshot.py:257] INFO Epoch: [26][20/150] Time 0.936 (1.624) Data 0.000 (0.685) Loss 1.0358 (0.9692) Prec@1 71.094 (71.540) Prec@5 89.844 (90.941)
[2021-04-26 16:28:05 train_lshot.py:257] INFO Epoch: [26][30/150] Time 0.937 (1.402) Data 0.000 (0.464) Loss 1.0646 (0.9673) Prec@1 70.703 (71.711) Prec@5 87.891 (91.091)
[2021-04-26 16:28:15 train_lshot.py:257] INFO Epoch: [26][40/150] Time 0.936 (1.288) Data 0.002 (0.351) Loss 1.1343 (0.9771) Prec@1 66.016 (71.322) Prec@5 88.672 (91.082)
[2021-04-26 16:28:24 train_lshot.py:257] INFO Epoch: [26][50/150] Time 0.939 (1.220) Data 0.000 (0.282) Loss 0.9546 (0.9770) Prec@1 72.266 (71.339) Prec@5 89.062 (90.977)
[2021-04-26 16:28:33 train_lshot.py:257] INFO Epoch: [26][60/150] Time 0.937 (1.174) Data 0.000 (0.236) Loss 0.9738 (0.9753) Prec@1 71.484 (71.331) Prec@5 92.188 (90.907)
[2021-04-26 16:28:43 train_lshot.py:257] INFO Epoch: [26][70/150] Time 0.937 (1.140) Data 0.001 (0.203) Loss 0.9513 (0.9785) Prec@1 69.141 (71.105) Prec@5 91.016 (90.785)
[2021-04-26 16:28:52 train_lshot.py:257] INFO Epoch: [26][80/150] Time 0.930 (1.115) Data 0.000 (0.178) Loss 0.9298 (0.9783) Prec@1 72.266 (70.968) Prec@5 92.969 (90.828)
[2021-04-26 16:29:02 train_lshot.py:257] INFO Epoch: [26][90/150] Time 0.931 (1.095) Data 0.000 (0.158) Loss 1.0633 (0.9766) Prec@1 67.188 (71.059) Prec@5 89.453 (90.853)
[2021-04-26 16:29:11 train_lshot.py:257] INFO Epoch: [26][100/150] Time 0.932 (1.079) Data 0.000 (0.143) Loss 0.9889 (0.9763) Prec@1 71.094 (70.993) Prec@5 91.406 (90.842)
[2021-04-26 16:29:20 train_lshot.py:257] INFO Epoch: [26][110/150] Time 0.938 (1.067) Data 0.000 (0.130) Loss 0.9892 (0.9779) Prec@1 72.656 (70.851) Prec@5 88.281 (90.833)
[2021-04-26 16:29:30 train_lshot.py:257] INFO Epoch: [26][120/150] Time 0.936 (1.056) Data 0.000 (0.119) Loss 0.9103 (0.9784) Prec@1 74.609 (70.858) Prec@5 93.750 (90.893)
[2021-04-26 16:29:39 train_lshot.py:257] INFO Epoch: [26][130/150] Time 0.938 (1.047) Data 0.000 (0.110) Loss 0.9537 (0.9807) Prec@1 69.141 (70.766) Prec@5 89.844 (90.807)
[2021-04-26 16:29:48 train_lshot.py:257] INFO Epoch: [26][140/150] Time 0.941 (1.039) Data 0.000 (0.102) Loss 0.9943 (0.9813) Prec@1 70.312 (70.759) Prec@5 90.625 (90.800)
[2021-04-26 16:30:11 train_lshot.py:257] INFO Epoch: [27][0/150] Time 13.587 (13.587) Data 12.641 (12.641) Loss 0.8570 (0.8570) Prec@1 74.609 (74.609) Prec@5 93.750 (93.750)
[2021-04-26 16:30:21 train_lshot.py:257] INFO Epoch: [27][10/150] Time 0.938 (2.086) Data 0.000 (1.149) Loss 0.9672 (0.9323) Prec@1 71.484 (72.798) Prec@5 91.797 (91.690)
[2021-04-26 16:30:30 train_lshot.py:257] INFO Epoch: [27][20/150] Time 0.943 (1.539) Data 0.001 (0.602) Loss 1.0060 (0.9372) Prec@1 70.312 (72.228) Prec@5 91.406 (91.574)
[2021-04-26 16:30:39 train_lshot.py:257] INFO Epoch: [27][30/150] Time 0.927 (1.343) Data 0.001 (0.408) Loss 1.0265 (0.9442) Prec@1 69.531 (72.014) Prec@5 91.016 (91.394)
[2021-04-26 16:30:49 train_lshot.py:257] INFO Epoch: [27][40/150] Time 0.933 (1.244) Data 0.000 (0.309) Loss 0.9190 (0.9436) Prec@1 71.484 (71.951) Prec@5 91.797 (91.454)
[2021-04-26 16:30:58 train_lshot.py:257] INFO Epoch: [27][50/150] Time 0.937 (1.184) Data 0.000 (0.248) Loss 0.9473 (0.9399) Prec@1 70.312 (71.998) Prec@5 91.797 (91.521)
[2021-04-26 16:31:08 train_lshot.py:257] INFO Epoch: [27][60/150] Time 0.935 (1.143) Data 0.000 (0.208) Loss 1.0761 (0.9466) Prec@1 66.797 (71.753) Prec@5 89.844 (91.451)
[2021-04-26 16:31:17 train_lshot.py:257] INFO Epoch: [27][70/150] Time 0.939 (1.114) Data 0.002 (0.179) Loss 0.8188 (0.9461) Prec@1 76.562 (71.721) Prec@5 94.531 (91.467)
[2021-04-26 16:31:26 train_lshot.py:257] INFO Epoch: [27][80/150] Time 0.931 (1.093) Data 0.000 (0.157) Loss 1.0068 (0.9509) Prec@1 70.703 (71.634) Prec@5 92.188 (91.310)
[2021-04-26 16:31:36 train_lshot.py:257] INFO Epoch: [27][90/150] Time 0.929 (1.075) Data 0.000 (0.139) Loss 0.8728 (0.9519) Prec@1 73.438 (71.519) Prec@5 92.188 (91.355)
[2021-04-26 16:31:45 train_lshot.py:257] INFO Epoch: [27][100/150] Time 0.936 (1.061) Data 0.000 (0.126) Loss 0.8860 (0.9490) Prec@1 71.094 (71.573) Prec@5 91.797 (91.433)
[2021-04-26 16:31:54 train_lshot.py:257] INFO Epoch: [27][110/150] Time 0.936 (1.050) Data 0.000 (0.114) Loss 0.9215 (0.9503) Prec@1 73.828 (71.590) Prec@5 93.359 (91.463)
[2021-04-26 16:32:04 train_lshot.py:257] INFO Epoch: [27][120/150] Time 0.944 (1.041) Data 0.000 (0.105) Loss 0.9435 (0.9518) Prec@1 71.484 (71.497) Prec@5 89.844 (91.380)
[2021-04-26 16:32:13 train_lshot.py:257] INFO Epoch: [27][130/150] Time 0.946 (1.033) Data 0.000 (0.097) Loss 1.0611 (0.9551) Prec@1 70.312 (71.389) Prec@5 89.844 (91.296)
[2021-04-26 16:32:23 train_lshot.py:257] INFO Epoch: [27][140/150] Time 0.937 (1.027) Data 0.000 (0.090) Loss 0.8608 (0.9556) Prec@1 73.828 (71.374) Prec@5 91.797 (91.271)
[2021-04-26 16:33:31 train_lshot.py:119] INFO Meta Val 27: 0.5774933454394341
[2021-04-26 16:33:46 train_lshot.py:257] INFO Epoch: [28][0/150] Time 12.911 (12.911) Data 11.958 (11.958) Loss 0.8909 (0.8909) Prec@1 69.922 (69.922) Prec@5 93.359 (93.359)
[2021-04-26 16:33:56 train_lshot.py:257] INFO Epoch: [28][10/150] Time 0.927 (2.023) Data 0.000 (1.087) Loss 0.8250 (0.9045) Prec@1 74.609 (73.295) Prec@5 92.969 (92.010)
[2021-04-26 16:34:05 train_lshot.py:257] INFO Epoch: [28][20/150] Time 0.935 (1.505) Data 0.001 (0.570) Loss 0.8988 (0.9045) Prec@1 74.609 (72.693) Prec@5 94.141 (92.485)
[2021-04-26 16:34:15 train_lshot.py:257] INFO Epoch: [28][30/150] Time 0.938 (1.322) Data 0.001 (0.386) Loss 0.8395 (0.8974) Prec@1 78.125 (73.009) Prec@5 92.969 (92.591)
[2021-04-26 16:34:24 train_lshot.py:257] INFO Epoch: [28][40/150] Time 0.943 (1.228) Data 0.001 (0.292) Loss 0.9175 (0.9076) Prec@1 73.828 (72.961) Prec@5 92.188 (92.426)
[2021-04-26 16:34:33 train_lshot.py:257] INFO Epoch: [28][50/150] Time 0.933 (1.171) Data 0.000 (0.235) Loss 1.0050 (0.9179) Prec@1 69.141 (72.679) Prec@5 88.672 (92.142)
[2021-04-26 16:34:43 train_lshot.py:257] INFO Epoch: [28][60/150] Time 0.941 (1.132) Data 0.000 (0.197) Loss 0.9823 (0.9215) Prec@1 72.266 (72.605) Prec@5 89.844 (91.970)
[2021-04-26 16:34:52 train_lshot.py:257] INFO Epoch: [28][70/150] Time 0.943 (1.105) Data 0.000 (0.169) Loss 0.9212 (0.9244) Prec@1 75.781 (72.563) Prec@5 90.234 (91.879)
[2021-04-26 16:35:01 train_lshot.py:257] INFO Epoch: [28][80/150] Time 0.935 (1.084) Data 0.000 (0.148) Loss 0.8492 (0.9218) Prec@1 77.344 (72.796) Prec@5 94.531 (91.889)
[2021-04-26 16:35:11 train_lshot.py:257] INFO Epoch: [28][90/150] Time 0.933 (1.068) Data 0.000 (0.132) Loss 0.8557 (0.9195) Prec@1 75.000 (72.879) Prec@5 92.969 (91.887)
[2021-04-26 16:35:20 train_lshot.py:257] INFO Epoch: [28][100/150] Time 0.935 (1.055) Data 0.000 (0.119) Loss 0.9913 (0.9214) Prec@1 69.922 (72.823) Prec@5 90.625 (91.828)
[2021-04-26 16:35:29 train_lshot.py:257] INFO Epoch: [28][110/150] Time 0.931 (1.044) Data 0.000 (0.108) Loss 0.9897 (0.9228) Prec@1 69.141 (72.741) Prec@5 92.188 (91.836)
[2021-04-26 16:35:39 train_lshot.py:257] INFO Epoch: [28][120/150] Time 0.939 (1.035) Data 0.000 (0.099) Loss 0.9937 (0.9227) Prec@1 72.266 (72.785) Prec@5 90.625 (91.826)
[2021-04-26 16:35:48 train_lshot.py:257] INFO Epoch: [28][130/150] Time 0.939 (1.028) Data 0.000 (0.092) Loss 1.0221 (0.9260) Prec@1 67.578 (72.713) Prec@5 90.234 (91.707)
[2021-04-26 16:35:58 train_lshot.py:257] INFO Epoch: [28][140/150] Time 0.926 (1.021) Data 0.000 (0.085) Loss 1.0312 (0.9273) Prec@1 66.406 (72.598) Prec@5 91.016 (91.714)
[2021-04-26 16:36:19 train_lshot.py:257] INFO Epoch: [29][0/150] Time 11.995 (11.995) Data 10.975 (10.975) Loss 0.9188 (0.9188) Prec@1 71.094 (71.094) Prec@5 92.969 (92.969)
[2021-04-26 16:36:28 train_lshot.py:257] INFO Epoch: [29][10/150] Time 0.925 (1.940) Data 0.000 (0.999) Loss 0.8503 (0.9045) Prec@1 77.734 (74.325) Prec@5 92.188 (91.761)
[2021-04-26 16:36:38 train_lshot.py:257] INFO Epoch: [29][20/150] Time 0.931 (1.462) Data 0.000 (0.524) Loss 0.9183 (0.8960) Prec@1 69.922 (73.642) Prec@5 92.188 (92.001)
[2021-04-26 16:36:47 train_lshot.py:257] INFO Epoch: [29][30/150] Time 0.932 (1.292) Data 0.000 (0.355) Loss 0.9774 (0.9017) Prec@1 67.188 (73.135) Prec@5 92.188 (91.784)
[2021-04-26 16:36:56 train_lshot.py:257] INFO Epoch: [29][40/150] Time 0.932 (1.205) Data 0.000 (0.269) Loss 0.9125 (0.8987) Prec@1 72.266 (73.285) Prec@5 92.969 (91.987)
[2021-04-26 16:37:06 train_lshot.py:257] INFO Epoch: [29][50/150] Time 0.943 (1.153) Data 0.000 (0.216) Loss 1.0466 (0.9040) Prec@1 72.656 (73.323) Prec@5 90.625 (91.942)
[2021-04-26 16:37:15 train_lshot.py:257] INFO Epoch: [29][60/150] Time 0.946 (1.117) Data 0.000 (0.181) Loss 0.8060 (0.9007) Prec@1 74.219 (73.252) Prec@5 96.484 (92.091)
[2021-04-26 16:37:24 train_lshot.py:257] INFO Epoch: [29][70/150] Time 0.937 (1.092) Data 0.002 (0.155) Loss 0.8692 (0.9043) Prec@1 75.781 (73.074) Prec@5 91.797 (92.028)
[2021-04-26 16:37:34 train_lshot.py:257] INFO Epoch: [29][80/150] Time 0.933 (1.073) Data 0.000 (0.136) Loss 0.9341 (0.9027) Prec@1 73.828 (73.124) Prec@5 91.016 (92.009)
[2021-04-26 16:37:43 train_lshot.py:257] INFO Epoch: [29][90/150] Time 0.945 (1.058) Data 0.000 (0.121) Loss 0.8955 (0.9026) Prec@1 71.484 (73.150) Prec@5 91.797 (91.956)
[2021-04-26 16:37:53 train_lshot.py:257] INFO Epoch: [29][100/150] Time 0.928 (1.046) Data 0.000 (0.109) Loss 0.8607 (0.9051) Prec@1 75.391 (73.089) Prec@5 92.969 (91.901)
[2021-04-26 16:38:02 train_lshot.py:257] INFO Epoch: [29][110/150] Time 0.933 (1.036) Data 0.000 (0.099) Loss 0.8476 (0.9083) Prec@1 75.781 (73.047) Prec@5 91.406 (91.807)
[2021-04-26 16:38:11 train_lshot.py:257] INFO Epoch: [29][120/150] Time 0.938 (1.028) Data 0.000 (0.091) Loss 0.9198 (0.9085) Prec@1 69.531 (73.079) Prec@5 91.797 (91.832)
[2021-04-26 16:38:21 train_lshot.py:257] INFO Epoch: [29][130/150] Time 0.945 (1.021) Data 0.000 (0.084) Loss 0.8470 (0.9087) Prec@1 75.000 (72.954) Prec@5 92.969 (91.874)
[2021-04-26 16:38:30 train_lshot.py:257] INFO Epoch: [29][140/150] Time 0.940 (1.015) Data 0.000 (0.078) Loss 0.9373 (0.9094) Prec@1 70.312 (72.947) Prec@5 90.234 (91.863)
[2021-04-26 16:38:52 train_lshot.py:257] INFO Epoch: [30][0/150] Time 12.934 (12.934) Data 11.964 (11.964) Loss 0.8136 (0.8136) Prec@1 73.438 (73.438) Prec@5 95.312 (95.312)
[2021-04-26 16:39:02 train_lshot.py:257] INFO Epoch: [30][10/150] Time 0.930 (2.028) Data 0.000 (1.088) Loss 0.8330 (0.8785) Prec@1 75.391 (73.047) Prec@5 94.141 (93.075)
[2021-04-26 16:39:11 train_lshot.py:257] INFO Epoch: [30][20/150] Time 0.937 (1.509) Data 0.000 (0.570) Loss 0.9617 (0.8853) Prec@1 70.703 (73.624) Prec@5 90.234 (92.076)
[2021-04-26 16:39:21 train_lshot.py:257] INFO Epoch: [30][30/150] Time 0.942 (1.325) Data 0.001 (0.386) Loss 0.8605 (0.8941) Prec@1 74.219 (73.412) Prec@5 92.188 (91.860)
[2021-04-26 16:39:30 train_lshot.py:257] INFO Epoch: [30][40/150] Time 0.937 (1.230) Data 0.000 (0.292) Loss 0.7628 (0.8835) Prec@1 78.516 (73.828) Prec@5 94.531 (92.149)
[2021-04-26 16:39:39 train_lshot.py:257] INFO Epoch: [30][50/150] Time 0.936 (1.173) Data 0.000 (0.235) Loss 0.9303 (0.8908) Prec@1 71.094 (73.606) Prec@5 91.406 (91.950)
[2021-04-26 16:39:49 train_lshot.py:257] INFO Epoch: [30][60/150] Time 0.934 (1.135) Data 0.001 (0.197) Loss 0.9184 (0.8905) Prec@1 70.703 (73.431) Prec@5 90.625 (92.002)
[2021-04-26 16:39:58 train_lshot.py:257] INFO Epoch: [30][70/150] Time 0.933 (1.107) Data 0.002 (0.169) Loss 0.8112 (0.8891) Prec@1 75.391 (73.581) Prec@5 94.531 (92.072)
[2021-04-26 16:40:07 train_lshot.py:257] INFO Epoch: [30][80/150] Time 0.944 (1.086) Data 0.000 (0.148) Loss 0.8055 (0.8893) Prec@1 74.609 (73.568) Prec@5 96.094 (92.091)
[2021-04-26 16:40:17 train_lshot.py:257] INFO Epoch: [30][90/150] Time 0.938 (1.070) Data 0.000 (0.132) Loss 0.9582 (0.8935) Prec@1 73.047 (73.425) Prec@5 91.016 (92.037)
[2021-04-26 16:40:26 train_lshot.py:257] INFO Epoch: [30][100/150] Time 0.932 (1.057) Data 0.000 (0.119) Loss 1.0658 (0.8982) Prec@1 64.844 (73.267) Prec@5 88.672 (91.975)
[2021-04-26 16:40:36 train_lshot.py:257] INFO Epoch: [30][110/150] Time 0.934 (1.046) Data 0.000 (0.108) Loss 0.8490 (0.8982) Prec@1 75.391 (73.247) Prec@5 92.578 (91.994)
[2021-04-26 16:40:45 train_lshot.py:257] INFO Epoch: [30][120/150] Time 0.938 (1.037) Data 0.000 (0.099) Loss 0.9196 (0.8972) Prec@1 72.656 (73.325) Prec@5 91.797 (91.987)
[2021-04-26 16:40:54 train_lshot.py:257] INFO Epoch: [30][130/150] Time 0.939 (1.030) Data 0.000 (0.092) Loss 0.8146 (0.8971) Prec@1 76.953 (73.348) Prec@5 93.359 (91.982)
[2021-04-26 16:41:04 train_lshot.py:257] INFO Epoch: [30][140/150] Time 0.937 (1.023) Data 0.000 (0.085) Loss 0.9217 (0.8976) Prec@1 75.000 (73.299) Prec@5 91.797 (92.005)
[2021-04-26 16:41:27 train_lshot.py:257] INFO Epoch: [31][0/150] Time 13.554 (13.554) Data 12.536 (12.536) Loss 0.8320 (0.8320) Prec@1 73.438 (73.438) Prec@5 93.359 (93.359)
[2021-04-26 16:41:36 train_lshot.py:257] INFO Epoch: [31][10/150] Time 0.933 (2.082) Data 0.000 (1.140) Loss 0.8355 (0.8542) Prec@1 74.609 (75.178) Prec@5 91.797 (92.365)
[2021-04-26 16:41:45 train_lshot.py:257] INFO Epoch: [31][20/150] Time 0.942 (1.537) Data 0.001 (0.597) Loss 0.8227 (0.8467) Prec@1 73.438 (75.279) Prec@5 93.359 (92.727)
[2021-04-26 16:41:55 train_lshot.py:257] INFO Epoch: [31][30/150] Time 0.932 (1.342) Data 0.001 (0.405) Loss 0.8804 (0.8475) Prec@1 75.000 (75.252) Prec@5 91.797 (92.855)
[2021-04-26 16:42:04 train_lshot.py:257] INFO Epoch: [31][40/150] Time 0.932 (1.243) Data 0.000 (0.306) Loss 0.8612 (0.8574) Prec@1 73.047 (74.638) Prec@5 92.969 (92.759)
[2021-04-26 16:42:13 train_lshot.py:257] INFO Epoch: [31][50/150] Time 0.934 (1.183) Data 0.001 (0.246) Loss 0.8828 (0.8623) Prec@1 74.609 (74.487) Prec@5 91.016 (92.609)
[2021-04-26 16:42:23 train_lshot.py:257] INFO Epoch: [31][60/150] Time 0.929 (1.142) Data 0.001 (0.206) Loss 0.7837 (0.8705) Prec@1 78.516 (74.257) Prec@5 92.188 (92.463)
[2021-04-26 16:42:32 train_lshot.py:257] INFO Epoch: [31][70/150] Time 0.929 (1.113) Data 0.000 (0.177) Loss 0.8707 (0.8673) Prec@1 69.922 (74.263) Prec@5 94.531 (92.562)
[2021-04-26 16:42:42 train_lshot.py:257] INFO Epoch: [31][80/150] Time 0.930 (1.091) Data 0.000 (0.155) Loss 0.9465 (0.8708) Prec@1 70.312 (74.180) Prec@5 91.797 (92.491)
[2021-04-26 16:42:51 train_lshot.py:257] INFO Epoch: [31][90/150] Time 0.934 (1.074) Data 0.000 (0.138) Loss 0.9750 (0.8765) Prec@1 69.141 (74.013) Prec@5 89.844 (92.329)
[2021-04-26 16:43:00 train_lshot.py:257] INFO Epoch: [31][100/150] Time 0.936 (1.060) Data 0.000 (0.125) Loss 0.9021 (0.8793) Prec@1 76.172 (73.940) Prec@5 91.016 (92.338)
[2021-04-26 16:43:10 train_lshot.py:257] INFO Epoch: [31][110/150] Time 0.931 (1.049) Data 0.000 (0.113) Loss 0.9316 (0.8847) Prec@1 73.047 (73.796) Prec@5 92.188 (92.230)
[2021-04-26 16:43:19 train_lshot.py:257] INFO Epoch: [31][120/150] Time 0.936 (1.039) Data 0.000 (0.104) Loss 0.9055 (0.8838) Prec@1 71.875 (73.789) Prec@5 89.453 (92.210)
[2021-04-26 16:43:28 train_lshot.py:257] INFO Epoch: [31][130/150] Time 0.939 (1.032) Data 0.000 (0.096) Loss 0.7917 (0.8820) Prec@1 77.734 (73.828) Prec@5 93.750 (92.256)
[2021-04-26 16:43:38 train_lshot.py:257] INFO Epoch: [31][140/150] Time 0.932 (1.025) Data 0.000 (0.089) Loss 0.8579 (0.8846) Prec@1 76.172 (73.795) Prec@5 92.578 (92.160)
[2021-04-26 16:44:45 train_lshot.py:119] INFO Meta Val 31: 0.5865333466529846
[2021-04-26 16:45:03 train_lshot.py:257] INFO Epoch: [32][0/150] Time 15.299 (15.299) Data 14.347 (14.347) Loss 0.8861 (0.8861) Prec@1 75.781 (75.781) Prec@5 92.188 (92.188)
[2021-04-26 16:45:12 train_lshot.py:257] INFO Epoch: [32][10/150] Time 0.929 (2.239) Data 0.000 (1.305) Loss 0.7888 (0.8354) Prec@1 77.734 (75.710) Prec@5 94.141 (93.430)
[2021-04-26 16:45:22 train_lshot.py:257] INFO Epoch: [32][20/150] Time 0.930 (1.618) Data 0.000 (0.684) Loss 0.9117 (0.8485) Prec@1 72.656 (75.112) Prec@5 90.625 (92.969)
[2021-04-26 16:45:31 train_lshot.py:257] INFO Epoch: [32][30/150] Time 0.927 (1.398) Data 0.001 (0.463) Loss 1.0074 (0.8544) Prec@1 68.359 (74.773) Prec@5 91.016 (92.666)
[2021-04-26 16:45:40 train_lshot.py:257] INFO Epoch: [32][40/150] Time 0.937 (1.286) Data 0.001 (0.350) Loss 0.8492 (0.8465) Prec@1 76.562 (75.067) Prec@5 91.016 (92.759)
[2021-04-26 16:45:50 train_lshot.py:257] INFO Epoch: [32][50/150] Time 0.937 (1.217) Data 0.000 (0.282) Loss 0.7145 (0.8416) Prec@1 79.297 (75.138) Prec@5 95.312 (92.823)
[2021-04-26 16:45:59 train_lshot.py:257] INFO Epoch: [32][60/150] Time 0.935 (1.171) Data 0.000 (0.236) Loss 0.8351 (0.8465) Prec@1 76.172 (75.019) Prec@5 91.797 (92.706)
[2021-04-26 16:46:08 train_lshot.py:257] INFO Epoch: [32][70/150] Time 0.939 (1.139) Data 0.000 (0.203) Loss 0.8127 (0.8465) Prec@1 74.609 (75.094) Prec@5 93.750 (92.738)
[2021-04-26 16:46:18 train_lshot.py:257] INFO Epoch: [32][80/150] Time 0.929 (1.114) Data 0.000 (0.178) Loss 0.8723 (0.8502) Prec@1 73.438 (75.005) Prec@5 91.797 (92.689)
[2021-04-26 16:46:27 train_lshot.py:257] INFO Epoch: [32][90/150] Time 0.937 (1.094) Data 0.000 (0.158) Loss 0.6811 (0.8510) Prec@1 81.641 (74.901) Prec@5 95.312 (92.728)
[2021-04-26 16:46:37 train_lshot.py:257] INFO Epoch: [32][100/150] Time 0.933 (1.079) Data 0.000 (0.142) Loss 0.9329 (0.8546) Prec@1 75.000 (74.818) Prec@5 89.062 (92.644)
[2021-04-26 16:46:46 train_lshot.py:257] INFO Epoch: [32][110/150] Time 0.928 (1.066) Data 0.000 (0.130) Loss 0.9614 (0.8580) Prec@1 70.312 (74.733) Prec@5 91.406 (92.641)
[2021-04-26 16:46:55 train_lshot.py:257] INFO Epoch: [32][120/150] Time 0.931 (1.055) Data 0.000 (0.119) Loss 0.8618 (0.8568) Prec@1 71.875 (74.703) Prec@5 91.406 (92.669)
[2021-04-26 16:47:05 train_lshot.py:257] INFO Epoch: [32][130/150] Time 0.937 (1.046) Data 0.000 (0.110) Loss 0.8555 (0.8574) Prec@1 73.438 (74.666) Prec@5 93.750 (92.641)
[2021-04-26 16:47:14 train_lshot.py:257] INFO Epoch: [32][140/150] Time 0.935 (1.039) Data 0.000 (0.102) Loss 0.8592 (0.8583) Prec@1 73.828 (74.659) Prec@5 93.359 (92.628)
[2021-04-26 16:47:37 train_lshot.py:257] INFO Epoch: [33][0/150] Time 12.944 (12.944) Data 11.991 (11.991) Loss 0.9679 (0.9679) Prec@1 71.484 (71.484) Prec@5 89.844 (89.844)
[2021-04-26 16:47:46 train_lshot.py:257] INFO Epoch: [33][10/150] Time 0.970 (2.031) Data 0.000 (1.090) Loss 0.7814 (0.8491) Prec@1 76.562 (75.923) Prec@5 94.141 (92.649)
[2021-04-26 16:47:55 train_lshot.py:257] INFO Epoch: [33][20/150] Time 0.937 (1.510) Data 0.000 (0.571) Loss 0.8311 (0.8320) Prec@1 76.562 (76.079) Prec@5 93.750 (92.932)
[2021-04-26 16:48:05 train_lshot.py:257] INFO Epoch: [33][30/150] Time 0.940 (1.325) Data 0.000 (0.387) Loss 0.7720 (0.8287) Prec@1 80.859 (76.134) Prec@5 94.141 (92.981)
[2021-04-26 16:48:14 train_lshot.py:257] INFO Epoch: [33][40/150] Time 0.935 (1.230) Data 0.000 (0.293) Loss 0.8554 (0.8314) Prec@1 73.047 (75.819) Prec@5 91.016 (92.864)
[2021-04-26 16:48:23 train_lshot.py:257] INFO Epoch: [33][50/150] Time 0.925 (1.172) Data 0.000 (0.236) Loss 0.9175 (0.8354) Prec@1 71.875 (75.597) Prec@5 91.797 (92.785)
[2021-04-26 16:48:33 train_lshot.py:257] INFO Epoch: [33][60/150] Time 0.928 (1.133) Data 0.000 (0.197) Loss 0.7475 (0.8337) Prec@1 80.469 (75.679) Prec@5 94.922 (92.777)
[2021-04-26 16:48:42 train_lshot.py:257] INFO Epoch: [33][70/150] Time 0.933 (1.105) Data 0.000 (0.169) Loss 0.9418 (0.8347) Prec@1 70.703 (75.671) Prec@5 93.359 (92.820)
[2021-04-26 16:48:51 train_lshot.py:257] INFO Epoch: [33][80/150] Time 0.927 (1.083) Data 0.000 (0.149) Loss 0.8812 (0.8345) Prec@1 72.656 (75.699) Prec@5 92.188 (92.848)
[2021-04-26 16:49:01 train_lshot.py:257] INFO Epoch: [33][90/150] Time 0.937 (1.067) Data 0.000 (0.132) Loss 0.7667 (0.8370) Prec@1 78.906 (75.644) Prec@5 93.359 (92.831)
[2021-04-26 16:49:10 train_lshot.py:257] INFO Epoch: [33][100/150] Time 0.933 (1.054) Data 0.000 (0.119) Loss 0.8497 (0.8393) Prec@1 74.609 (75.545) Prec@5 93.750 (92.818)
[2021-04-26 16:49:19 train_lshot.py:257] INFO Epoch: [33][110/150] Time 0.930 (1.043) Data 0.000 (0.108) Loss 0.7723 (0.8396) Prec@1 80.078 (75.521) Prec@5 94.922 (92.860)
[2021-04-26 16:49:29 train_lshot.py:257] INFO Epoch: [33][120/150] Time 0.929 (1.034) Data 0.000 (0.099) Loss 0.8909 (0.8416) Prec@1 74.609 (75.397) Prec@5 93.359 (92.853)
[2021-04-26 16:49:38 train_lshot.py:257] INFO Epoch: [33][130/150] Time 0.934 (1.027) Data 0.000 (0.092) Loss 0.8935 (0.8437) Prec@1 73.438 (75.391) Prec@5 91.016 (92.781)
[2021-04-26 16:49:47 train_lshot.py:257] INFO Epoch: [33][140/150] Time 0.946 (1.020) Data 0.000 (0.085) Loss 0.9271 (0.8457) Prec@1 75.391 (75.341) Prec@5 89.453 (92.730)
[2021-04-26 16:50:10 train_lshot.py:257] INFO Epoch: [34][0/150] Time 13.502 (13.502) Data 12.550 (12.550) Loss 0.7483 (0.7483) Prec@1 79.688 (79.688) Prec@5 94.141 (94.141)
[2021-04-26 16:50:20 train_lshot.py:257] INFO Epoch: [34][10/150] Time 0.935 (2.077) Data 0.000 (1.141) Loss 0.7913 (0.8281) Prec@1 73.828 (76.101) Prec@5 93.359 (92.720)
[2021-04-26 16:50:29 train_lshot.py:257] INFO Epoch: [34][20/150] Time 0.940 (1.533) Data 0.001 (0.598) Loss 0.7448 (0.8100) Prec@1 80.078 (76.395) Prec@5 93.359 (93.211)
[2021-04-26 16:50:38 train_lshot.py:257] INFO Epoch: [34][30/150] Time 0.937 (1.340) Data 0.000 (0.405) Loss 0.8292 (0.8060) Prec@1 75.000 (76.462) Prec@5 93.359 (93.397)
[2021-04-26 16:50:48 train_lshot.py:257] INFO Epoch: [34][40/150] Time 0.936 (1.242) Data 0.000 (0.307) Loss 0.8523 (0.8157) Prec@1 75.000 (76.134) Prec@5 91.406 (93.197)
[2021-04-26 16:50:57 train_lshot.py:257] INFO Epoch: [34][50/150] Time 0.945 (1.182) Data 0.001 (0.247) Loss 0.9080 (0.8205) Prec@1 71.484 (76.072) Prec@5 92.188 (93.260)
[2021-04-26 16:51:06 train_lshot.py:257] INFO Epoch: [34][60/150] Time 0.933 (1.142) Data 0.000 (0.206) Loss 0.9125 (0.8279) Prec@1 73.047 (75.724) Prec@5 94.141 (93.231)
[2021-04-26 16:51:16 train_lshot.py:257] INFO Epoch: [34][70/150] Time 0.932 (1.113) Data 0.000 (0.177) Loss 0.8906 (0.8278) Prec@1 75.391 (75.787) Prec@5 91.797 (93.211)
[2021-04-26 16:51:25 train_lshot.py:257] INFO Epoch: [34][80/150] Time 0.932 (1.091) Data 0.000 (0.155) Loss 0.9729 (0.8301) Prec@1 69.531 (75.704) Prec@5 89.453 (93.128)
[2021-04-26 16:51:35 train_lshot.py:257] INFO Epoch: [34][90/150] Time 0.937 (1.074) Data 0.000 (0.138) Loss 0.8538 (0.8315) Prec@1 76.172 (75.665) Prec@5 91.406 (93.063)
[2021-04-26 16:51:44 train_lshot.py:257] INFO Epoch: [34][100/150] Time 0.937 (1.060) Data 0.000 (0.125) Loss 0.7856 (0.8307) Prec@1 74.609 (75.638) Prec@5 93.750 (93.069)
[2021-04-26 16:51:53 train_lshot.py:257] INFO Epoch: [34][110/150] Time 0.933 (1.049) Data 0.000 (0.113) Loss 0.9153 (0.8322) Prec@1 73.438 (75.577) Prec@5 91.016 (93.036)
[2021-04-26 16:52:03 train_lshot.py:257] INFO Epoch: [34][120/150] Time 0.943 (1.040) Data 0.000 (0.104) Loss 0.7150 (0.8298) Prec@1 81.641 (75.636) Prec@5 94.141 (93.088)
[2021-04-26 16:52:12 train_lshot.py:257] INFO Epoch: [34][130/150] Time 0.939 (1.032) Data 0.000 (0.096) Loss 0.9163 (0.8315) Prec@1 73.438 (75.581) Prec@5 91.016 (93.061)
[2021-04-26 16:52:21 train_lshot.py:257] INFO Epoch: [34][140/150] Time 0.948 (1.026) Data 0.000 (0.089) Loss 0.8311 (0.8340) Prec@1 76.562 (75.504) Prec@5 92.969 (92.977)
[2021-04-26 16:52:44 train_lshot.py:257] INFO Epoch: [35][0/150] Time 12.883 (12.883) Data 11.931 (11.931) Loss 0.7625 (0.7625) Prec@1 78.125 (78.125) Prec@5 94.141 (94.141)
[2021-04-26 16:52:53 train_lshot.py:257] INFO Epoch: [35][10/150] Time 0.945 (2.023) Data 0.000 (1.085) Loss 0.7761 (0.8021) Prec@1 80.469 (76.953) Prec@5 96.094 (93.999)
[2021-04-26 16:53:02 train_lshot.py:257] INFO Epoch: [35][20/150] Time 0.936 (1.504) Data 0.001 (0.568) Loss 0.8339 (0.8032) Prec@1 75.781 (76.711) Prec@5 93.359 (93.880)
[2021-04-26 16:53:12 train_lshot.py:257] INFO Epoch: [35][30/150] Time 0.935 (1.321) Data 0.001 (0.385) Loss 0.7971 (0.8015) Prec@1 76.562 (76.890) Prec@5 93.359 (93.725)
[2021-04-26 16:53:21 train_lshot.py:257] INFO Epoch: [35][40/150] Time 0.935 (1.227) Data 0.000 (0.291) Loss 0.6826 (0.8081) Prec@1 80.859 (76.686) Prec@5 94.922 (93.578)
[2021-04-26 16:53:31 train_lshot.py:257] INFO Epoch: [35][50/150] Time 0.937 (1.170) Data 0.000 (0.234) Loss 0.9229 (0.8102) Prec@1 73.047 (76.723) Prec@5 91.406 (93.620)
[2021-04-26 16:53:40 train_lshot.py:257] INFO Epoch: [35][60/150] Time 0.940 (1.131) Data 0.000 (0.196) Loss 0.8152 (0.8126) Prec@1 76.562 (76.511) Prec@5 93.750 (93.545)
[2021-04-26 16:53:49 train_lshot.py:257] INFO Epoch: [35][70/150] Time 0.937 (1.104) Data 0.000 (0.168) Loss 0.8099 (0.8132) Prec@1 76.562 (76.408) Prec@5 93.750 (93.535)
[2021-04-26 16:53:59 train_lshot.py:257] INFO Epoch: [35][80/150] Time 0.934 (1.083) Data 0.000 (0.148) Loss 0.7639 (0.8095) Prec@1 80.078 (76.562) Prec@5 92.188 (93.586)
[2021-04-26 16:54:08 train_lshot.py:257] INFO Epoch: [35][90/150] Time 0.945 (1.066) Data 0.000 (0.131) Loss 0.8333 (0.8124) Prec@1 79.297 (76.554) Prec@5 92.969 (93.540)
[2021-04-26 16:54:17 train_lshot.py:257] INFO Epoch: [35][100/150] Time 0.935 (1.053) Data 0.000 (0.118) Loss 0.8838 (0.8130) Prec@1 75.391 (76.559) Prec@5 92.578 (93.541)
[2021-04-26 16:54:27 train_lshot.py:257] INFO Epoch: [35][110/150] Time 0.933 (1.043) Data 0.000 (0.108) Loss 0.6770 (0.8160) Prec@1 83.203 (76.464) Prec@5 94.922 (93.486)
[2021-04-26 16:54:36 train_lshot.py:257] INFO Epoch: [35][120/150] Time 0.937 (1.034) Data 0.000 (0.099) Loss 0.8743 (0.8182) Prec@1 75.000 (76.291) Prec@5 89.844 (93.430)
[2021-04-26 16:54:45 train_lshot.py:257] INFO Epoch: [35][130/150] Time 0.926 (1.026) Data 0.000 (0.091) Loss 0.8355 (0.8181) Prec@1 75.000 (76.249) Prec@5 90.234 (93.431)
[2021-04-26 16:54:55 train_lshot.py:257] INFO Epoch: [35][140/150] Time 0.932 (1.019) Data 0.000 (0.085) Loss 0.8006 (0.8200) Prec@1 76.562 (76.205) Prec@5 93.359 (93.398)
[2021-04-26 16:56:01 train_lshot.py:119] INFO Meta Val 35: 0.5849866806864739
[2021-04-26 16:56:15 train_lshot.py:257] INFO Epoch: [36][0/150] Time 13.380 (13.380) Data 12.418 (12.418) Loss 0.7776 (0.7776) Prec@1 75.781 (75.781) Prec@5 94.922 (94.922)
[2021-04-26 16:56:25 train_lshot.py:257] INFO Epoch: [36][10/150] Time 0.932 (2.063) Data 0.000 (1.129) Loss 0.7737 (0.8196) Prec@1 79.688 (77.628) Prec@5 93.359 (92.649)
[2021-04-26 16:56:34 train_lshot.py:257] INFO Epoch: [36][20/150] Time 0.940 (1.525) Data 0.001 (0.592) Loss 0.7561 (0.7956) Prec@1 78.516 (77.772) Prec@5 94.922 (93.266)
[2021-04-26 16:56:43 train_lshot.py:257] INFO Epoch: [36][30/150] Time 0.930 (1.334) Data 0.000 (0.401) Loss 0.7847 (0.7946) Prec@1 78.516 (77.608) Prec@5 92.969 (93.296)
[2021-04-26 16:56:53 train_lshot.py:257] INFO Epoch: [36][40/150] Time 0.946 (1.237) Data 0.002 (0.303) Loss 0.9229 (0.8008) Prec@1 73.438 (77.268) Prec@5 90.625 (93.169)
[2021-04-26 16:57:02 train_lshot.py:257] INFO Epoch: [36][50/150] Time 0.932 (1.178) Data 0.000 (0.244) Loss 0.8437 (0.8047) Prec@1 77.344 (77.114) Prec@5 90.625 (93.153)
[2021-04-26 16:57:11 train_lshot.py:257] INFO Epoch: [36][60/150] Time 0.939 (1.138) Data 0.000 (0.204) Loss 0.7624 (0.7998) Prec@1 77.344 (77.062) Prec@5 93.359 (93.315)
[2021-04-26 16:57:21 train_lshot.py:257] INFO Epoch: [36][70/150] Time 0.942 (1.110) Data 0.002 (0.175) Loss 0.8240 (0.8017) Prec@1 75.000 (76.860) Prec@5 94.922 (93.304)
[2021-04-26 16:57:30 train_lshot.py:257] INFO Epoch: [36][80/150] Time 0.935 (1.089) Data 0.000 (0.154) Loss 0.8767 (0.8029) Prec@1 74.609 (76.794) Prec@5 89.844 (93.268)
[2021-04-26 16:57:40 train_lshot.py:257] INFO Epoch: [36][90/150] Time 0.935 (1.072) Data 0.000 (0.137) Loss 0.8753 (0.8039) Prec@1 74.219 (76.794) Prec@5 92.578 (93.329)
[2021-04-26 16:57:49 train_lshot.py:257] INFO Epoch: [36][100/150] Time 0.940 (1.059) Data 0.000 (0.123) Loss 0.8784 (0.8046) Prec@1 75.781 (76.822) Prec@5 91.406 (93.259)
[2021-04-26 16:57:58 train_lshot.py:257] INFO Epoch: [36][110/150] Time 0.934 (1.048) Data 0.000 (0.112) Loss 0.8101 (0.8065) Prec@1 77.734 (76.696) Prec@5 92.969 (93.226)
[2021-04-26 16:58:08 train_lshot.py:257] INFO Epoch: [36][120/150] Time 0.936 (1.039) Data 0.000 (0.103) Loss 0.7762 (0.8063) Prec@1 78.906 (76.766) Prec@5 94.531 (93.195)
[2021-04-26 16:58:17 train_lshot.py:257] INFO Epoch: [36][130/150] Time 0.932 (1.031) Data 0.000 (0.095) Loss 0.9172 (0.8073) Prec@1 73.047 (76.676) Prec@5 92.969 (93.216)
[2021-04-26 16:58:27 train_lshot.py:257] INFO Epoch: [36][140/150] Time 0.938 (1.025) Data 0.000 (0.088) Loss 0.8952 (0.8110) Prec@1 74.219 (76.565) Prec@5 92.188 (93.152)
[2021-04-26 16:58:48 train_lshot.py:257] INFO Epoch: [37][0/150] Time 11.834 (11.834) Data 10.881 (10.881) Loss 0.7334 (0.7334) Prec@1 78.516 (78.516) Prec@5 93.359 (93.359)
[2021-04-26 16:58:57 train_lshot.py:257] INFO Epoch: [37][10/150] Time 0.939 (1.931) Data 0.000 (0.990) Loss 0.7613 (0.7462) Prec@1 78.906 (79.119) Prec@5 93.750 (94.105)
[2021-04-26 16:59:07 train_lshot.py:257] INFO Epoch: [37][20/150] Time 0.937 (1.457) Data 0.001 (0.519) Loss 0.7058 (0.7539) Prec@1 80.469 (78.367) Prec@5 94.922 (94.345)
[2021-04-26 16:59:16 train_lshot.py:257] INFO Epoch: [37][30/150] Time 0.941 (1.289) Data 0.001 (0.351) Loss 0.8081 (0.7561) Prec@1 75.000 (78.238) Prec@5 92.969 (94.367)
[2021-04-26 16:59:25 train_lshot.py:257] INFO Epoch: [37][40/150] Time 0.932 (1.202) Data 0.000 (0.266) Loss 0.6781 (0.7613) Prec@1 80.469 (78.039) Prec@5 96.094 (94.350)
[2021-04-26 16:59:35 train_lshot.py:257] INFO Epoch: [37][50/150] Time 0.931 (1.149) Data 0.000 (0.214) Loss 0.8254 (0.7677) Prec@1 73.828 (77.658) Prec@5 94.141 (94.256)
[2021-04-26 16:59:44 train_lshot.py:257] INFO Epoch: [37][60/150] Time 0.936 (1.114) Data 0.000 (0.179) Loss 0.8538 (0.7659) Prec@1 75.000 (77.837) Prec@5 92.969 (94.230)
[2021-04-26 16:59:53 train_lshot.py:257] INFO Epoch: [37][70/150] Time 0.938 (1.089) Data 0.002 (0.154) Loss 0.8187 (0.7712) Prec@1 77.344 (77.641) Prec@5 93.750 (94.146)
[2021-04-26 17:00:03 train_lshot.py:257] INFO Epoch: [37][80/150] Time 0.933 (1.070) Data 0.000 (0.135) Loss 0.7265 (0.7715) Prec@1 79.688 (77.681) Prec@5 93.359 (94.078)
[2021-04-26 17:00:12 train_lshot.py:257] INFO Epoch: [37][90/150] Time 0.936 (1.055) Data 0.000 (0.120) Loss 0.7155 (0.7752) Prec@1 80.469 (77.511) Prec@5 92.969 (93.960)
[2021-04-26 17:00:21 train_lshot.py:257] INFO Epoch: [37][100/150] Time 0.940 (1.043) Data 0.000 (0.108) Loss 0.7399 (0.7742) Prec@1 78.906 (77.576) Prec@5 95.703 (94.032)
[2021-04-26 17:00:31 train_lshot.py:257] INFO Epoch: [37][110/150] Time 0.936 (1.033) Data 0.000 (0.098) Loss 0.8065 (0.7802) Prec@1 78.516 (77.390) Prec@5 94.141 (93.884)
[2021-04-26 17:00:40 train_lshot.py:257] INFO Epoch: [37][120/150] Time 0.928 (1.025) Data 0.000 (0.090) Loss 0.8357 (0.7834) Prec@1 77.344 (77.353) Prec@5 90.234 (93.776)
[2021-04-26 17:00:49 train_lshot.py:257] INFO Epoch: [37][130/150] Time 0.934 (1.018) Data 0.000 (0.083) Loss 0.8706 (0.7857) Prec@1 71.094 (77.242) Prec@5 90.234 (93.723)
[2021-04-26 17:00:59 train_lshot.py:257] INFO Epoch: [37][140/150] Time 0.935 (1.012) Data 0.000 (0.078) Loss 0.7730 (0.7877) Prec@1 77.344 (77.189) Prec@5 94.531 (93.675)
[2021-04-26 17:01:20 train_lshot.py:257] INFO Epoch: [38][0/150] Time 11.843 (11.843) Data 10.894 (10.894) Loss 0.7562 (0.7562) Prec@1 82.031 (82.031) Prec@5 92.188 (92.188)
[2021-04-26 17:01:29 train_lshot.py:257] INFO Epoch: [38][10/150] Time 0.925 (1.922) Data 0.000 (0.991) Loss 0.8457 (0.7658) Prec@1 74.219 (78.445) Prec@5 93.359 (93.395)
[2021-04-26 17:01:39 train_lshot.py:257] INFO Epoch: [38][20/150] Time 0.935 (1.452) Data 0.000 (0.519) Loss 0.8695 (0.7595) Prec@1 75.391 (78.478) Prec@5 92.578 (93.787)
[2021-04-26 17:01:48 train_lshot.py:257] INFO Epoch: [38][30/150] Time 0.928 (1.285) Data 0.000 (0.352) Loss 0.7377 (0.7596) Prec@1 79.688 (78.478) Prec@5 95.703 (94.027)
[2021-04-26 17:01:57 train_lshot.py:257] INFO Epoch: [38][40/150] Time 0.940 (1.199) Data 0.000 (0.266) Loss 0.8096 (0.7693) Prec@1 74.219 (77.973) Prec@5 93.359 (93.969)
[2021-04-26 17:02:07 train_lshot.py:257] INFO Epoch: [38][50/150] Time 0.928 (1.147) Data 0.001 (0.214) Loss 0.8532 (0.7765) Prec@1 73.047 (77.757) Prec@5 94.531 (93.804)
[2021-04-26 17:02:16 train_lshot.py:257] INFO Epoch: [38][60/150] Time 0.940 (1.113) Data 0.000 (0.179) Loss 0.8042 (0.7758) Prec@1 74.609 (77.805) Prec@5 95.312 (93.897)
[2021-04-26 17:02:25 train_lshot.py:257] INFO Epoch: [38][70/150] Time 0.940 (1.089) Data 0.002 (0.154) Loss 0.7349 (0.7761) Prec@1 82.812 (77.844) Prec@5 93.359 (93.866)
[2021-04-26 17:02:35 train_lshot.py:257] INFO Epoch: [38][80/150] Time 0.941 (1.070) Data 0.000 (0.135) Loss 0.8256 (0.7815) Prec@1 75.000 (77.652) Prec@5 94.141 (93.851)
[2021-04-26 17:02:44 train_lshot.py:257] INFO Epoch: [38][90/150] Time 0.927 (1.055) Data 0.000 (0.120) Loss 0.8336 (0.7826) Prec@1 74.219 (77.627) Prec@5 93.359 (93.759)
[2021-04-26 17:02:53 train_lshot.py:257] INFO Epoch: [38][100/150] Time 0.938 (1.044) Data 0.000 (0.108) Loss 0.7671 (0.7839) Prec@1 80.078 (77.495) Prec@5 94.531 (93.793)
[2021-04-26 17:03:03 train_lshot.py:257] INFO Epoch: [38][110/150] Time 0.930 (1.034) Data 0.000 (0.099) Loss 0.8122 (0.7853) Prec@1 76.562 (77.470) Prec@5 91.797 (93.736)
[2021-04-26 17:03:12 train_lshot.py:257] INFO Epoch: [38][120/150] Time 0.934 (1.026) Data 0.000 (0.090) Loss 0.7959 (0.7859) Prec@1 74.219 (77.415) Prec@5 95.703 (93.760)
[2021-04-26 17:03:22 train_lshot.py:257] INFO Epoch: [38][130/150] Time 0.939 (1.019) Data 0.000 (0.083) Loss 0.8857 (0.7891) Prec@1 75.000 (77.281) Prec@5 91.406 (93.726)
[2021-04-26 17:03:31 train_lshot.py:257] INFO Epoch: [38][140/150] Time 0.937 (1.013) Data 0.000 (0.078) Loss 0.7031 (0.7883) Prec@1 79.297 (77.280) Prec@5 96.094 (93.725)
[2021-04-26 17:03:53 train_lshot.py:257] INFO Epoch: [39][0/150] Time 12.556 (12.556) Data 11.593 (11.593) Loss 0.7277 (0.7277) Prec@1 76.172 (76.172) Prec@5 95.703 (95.703)
[2021-04-26 17:04:02 train_lshot.py:257] INFO Epoch: [39][10/150] Time 0.956 (1.994) Data 0.000 (1.054) Loss 0.8151 (0.7396) Prec@1 76.172 (78.267) Prec@5 91.406 (94.815)
[2021-04-26 17:04:12 train_lshot.py:257] INFO Epoch: [39][20/150] Time 0.931 (1.491) Data 0.000 (0.552) Loss 0.7373 (0.7351) Prec@1 78.906 (78.367) Prec@5 96.094 (94.773)
[2021-04-26 17:04:21 train_lshot.py:257] INFO Epoch: [39][30/150] Time 0.935 (1.312) Data 0.000 (0.374) Loss 0.8081 (0.7414) Prec@1 75.781 (78.314) Prec@5 93.359 (94.695)
[2021-04-26 17:04:30 train_lshot.py:257] INFO Epoch: [39][40/150] Time 0.935 (1.220) Data 0.000 (0.283) Loss 0.7943 (0.7446) Prec@1 76.172 (78.249) Prec@5 93.359 (94.588)
[2021-04-26 17:04:40 train_lshot.py:257] INFO Epoch: [39][50/150] Time 0.944 (1.164) Data 0.000 (0.228) Loss 0.7748 (0.7512) Prec@1 78.125 (77.987) Prec@5 92.969 (94.409)
[2021-04-26 17:04:49 train_lshot.py:257] INFO Epoch: [39][60/150] Time 0.941 (1.127) Data 0.001 (0.191) Loss 0.8211 (0.7546) Prec@1 77.344 (77.997) Prec@5 93.359 (94.390)
[2021-04-26 17:04:59 train_lshot.py:257] INFO Epoch: [39][70/150] Time 0.938 (1.100) Data 0.003 (0.164) Loss 0.7536 (0.7615) Prec@1 76.562 (77.800) Prec@5 95.312 (94.284)
[2021-04-26 17:05:08 train_lshot.py:257] INFO Epoch: [39][80/150] Time 0.940 (1.080) Data 0.000 (0.144) Loss 0.7654 (0.7613) Prec@1 78.125 (77.734) Prec@5 94.922 (94.353)
[2021-04-26 17:05:17 train_lshot.py:257] INFO Epoch: [39][90/150] Time 0.932 (1.064) Data 0.000 (0.128) Loss 0.7520 (0.7646) Prec@1 78.125 (77.739) Prec@5 94.922 (94.248)
[2021-04-26 17:05:27 train_lshot.py:257] INFO Epoch: [39][100/150] Time 0.935 (1.051) Data 0.000 (0.115) Loss 0.9021 (0.7670) Prec@1 76.172 (77.742) Prec@5 89.844 (94.164)
[2021-04-26 17:05:36 train_lshot.py:257] INFO Epoch: [39][110/150] Time 0.930 (1.041) Data 0.000 (0.105) Loss 0.7768 (0.7676) Prec@1 75.391 (77.727) Prec@5 96.094 (94.165)
[2021-04-26 17:05:45 train_lshot.py:257] INFO Epoch: [39][120/150] Time 0.943 (1.032) Data 0.000 (0.096) Loss 0.8080 (0.7722) Prec@1 78.125 (77.579) Prec@5 91.797 (94.070)
[2021-04-26 17:05:55 train_lshot.py:257] INFO Epoch: [39][130/150] Time 0.938 (1.025) Data 0.000 (0.089) Loss 0.8722 (0.7734) Prec@1 74.609 (77.576) Prec@5 91.797 (94.063)
[2021-04-26 17:06:04 train_lshot.py:257] INFO Epoch: [39][140/150] Time 0.938 (1.019) Data 0.000 (0.083) Loss 0.7490 (0.7745) Prec@1 78.516 (77.590) Prec@5 95.703 (94.044)
[2021-04-26 17:07:10 train_lshot.py:119] INFO Meta Val 39: 0.5986933458447457
[2021-04-26 17:07:25 train_lshot.py:257] INFO Epoch: [40][0/150] Time 11.834 (11.834) Data 10.884 (10.884) Loss 0.7913 (0.7913) Prec@1 75.000 (75.000) Prec@5 91.797 (91.797)
[2021-04-26 17:07:34 train_lshot.py:257] INFO Epoch: [40][10/150] Time 0.932 (1.922) Data 0.000 (0.990) Loss 0.6747 (0.7502) Prec@1 78.516 (78.018) Prec@5 96.875 (94.638)
[2021-04-26 17:07:43 train_lshot.py:257] INFO Epoch: [40][20/150] Time 0.928 (1.450) Data 0.000 (0.519) Loss 0.7799 (0.7611) Prec@1 75.391 (77.623) Prec@5 95.703 (94.327)
[2021-04-26 17:07:53 train_lshot.py:257] INFO Epoch: [40][30/150] Time 0.930 (1.283) Data 0.000 (0.352) Loss 0.7227 (0.7587) Prec@1 79.688 (77.760) Prec@5 95.312 (94.330)
[2021-04-26 17:08:02 train_lshot.py:257] INFO Epoch: [40][40/150] Time 0.924 (1.198) Data 0.001 (0.266) Loss 0.6906 (0.7545) Prec@1 82.812 (78.163) Prec@5 96.484 (94.264)
[2021-04-26 17:08:11 train_lshot.py:257] INFO Epoch: [40][50/150] Time 0.937 (1.146) Data 0.000 (0.214) Loss 0.7622 (0.7531) Prec@1 80.078 (78.309) Prec@5 94.531 (94.294)
[2021-04-26 17:08:21 train_lshot.py:257] INFO Epoch: [40][60/150] Time 0.933 (1.112) Data 0.000 (0.179) Loss 0.7147 (0.7536) Prec@1 81.250 (78.381) Prec@5 94.922 (94.275)
[2021-04-26 17:08:30 train_lshot.py:257] INFO Epoch: [40][70/150] Time 0.934 (1.087) Data 0.000 (0.154) Loss 0.6927 (0.7525) Prec@1 82.422 (78.510) Prec@5 94.922 (94.229)
[2021-04-26 17:08:39 train_lshot.py:257] INFO Epoch: [40][80/150] Time 0.939 (1.068) Data 0.000 (0.135) Loss 0.7594 (0.7503) Prec@1 76.562 (78.583) Prec@5 94.922 (94.295)
[2021-04-26 17:08:49 train_lshot.py:257] INFO Epoch: [40][90/150] Time 0.933 (1.054) Data 0.000 (0.120) Loss 0.7518 (0.7514) Prec@1 78.906 (78.541) Prec@5 96.094 (94.351)
[2021-04-26 17:08:58 train_lshot.py:257] INFO Epoch: [40][100/150] Time 0.930 (1.042) Data 0.000 (0.108) Loss 0.8753 (0.7523) Prec@1 75.781 (78.450) Prec@5 91.797 (94.315)
[2021-04-26 17:09:08 train_lshot.py:257] INFO Epoch: [40][110/150] Time 0.935 (1.033) Data 0.000 (0.098) Loss 0.7769 (0.7523) Prec@1 75.781 (78.428) Prec@5 94.922 (94.355)
[2021-04-26 17:09:17 train_lshot.py:257] INFO Epoch: [40][120/150] Time 0.935 (1.025) Data 0.000 (0.090) Loss 0.7753 (0.7516) Prec@1 76.953 (78.441) Prec@5 95.312 (94.380)
[2021-04-26 17:09:26 train_lshot.py:257] INFO Epoch: [40][130/150] Time 0.940 (1.018) Data 0.000 (0.083) Loss 0.7483 (0.7515) Prec@1 78.906 (78.471) Prec@5 94.531 (94.373)
[2021-04-26 17:09:36 train_lshot.py:257] INFO Epoch: [40][140/150] Time 0.936 (1.012) Data 0.000 (0.078) Loss 0.8770 (0.7538) Prec@1 73.438 (78.396) Prec@5 91.016 (94.329)
[2021-04-26 17:10:00 train_lshot.py:257] INFO Epoch: [41][0/150] Time 14.714 (14.714) Data 13.760 (13.760) Loss 0.6164 (0.6164) Prec@1 82.812 (82.812) Prec@5 97.266 (97.266)
[2021-04-26 17:10:09 train_lshot.py:257] INFO Epoch: [41][10/150] Time 0.938 (2.188) Data 0.000 (1.251) Loss 0.7274 (0.7255) Prec@1 78.125 (79.368) Prec@5 95.312 (94.531)
[2021-04-26 17:10:19 train_lshot.py:257] INFO Epoch: [41][20/150] Time 0.931 (1.594) Data 0.000 (0.656) Loss 0.7558 (0.7238) Prec@1 78.125 (79.334) Prec@5 94.922 (94.475)
[2021-04-26 17:10:28 train_lshot.py:257] INFO Epoch: [41][30/150] Time 0.936 (1.381) Data 0.000 (0.444) Loss 0.7373 (0.7184) Prec@1 76.953 (79.637) Prec@5 95.312 (94.758)
[2021-04-26 17:10:37 train_lshot.py:257] INFO Epoch: [41][40/150] Time 0.937 (1.273) Data 0.000 (0.336) Loss 0.7183 (0.7226) Prec@1 79.297 (79.459) Prec@5 93.359 (94.493)
[2021-04-26 17:10:47 train_lshot.py:257] INFO Epoch: [41][50/150] Time 0.931 (1.207) Data 0.000 (0.270) Loss 0.8485 (0.7315) Prec@1 72.656 (79.312) Prec@5 93.750 (94.363)
[2021-04-26 17:10:56 train_lshot.py:257] INFO Epoch: [41][60/150] Time 0.944 (1.163) Data 0.001 (0.226) Loss 0.6563 (0.7369) Prec@1 81.641 (79.098) Prec@5 96.875 (94.217)
[2021-04-26 17:11:05 train_lshot.py:257] INFO Epoch: [41][70/150] Time 0.943 (1.131) Data 0.001 (0.194) Loss 0.7168 (0.7385) Prec@1 78.125 (78.917) Prec@5 92.969 (94.251)
[2021-04-26 17:11:15 train_lshot.py:257] INFO Epoch: [41][80/150] Time 0.936 (1.107) Data 0.000 (0.170) Loss 0.7820 (0.7418) Prec@1 75.391 (78.839) Prec@5 92.578 (94.203)
[2021-04-26 17:11:24 train_lshot.py:257] INFO Epoch: [41][90/150] Time 0.935 (1.088) Data 0.000 (0.152) Loss 0.6807 (0.7473) Prec@1 81.641 (78.627) Prec@5 93.750 (94.196)
[2021-04-26 17:11:34 train_lshot.py:257] INFO Epoch: [41][100/150] Time 0.935 (1.073) Data 0.000 (0.137) Loss 0.7515 (0.7479) Prec@1 78.906 (78.585) Prec@5 95.703 (94.168)
[2021-04-26 17:11:43 train_lshot.py:257] INFO Epoch: [41][110/150] Time 0.931 (1.061) Data 0.000 (0.124) Loss 0.8153 (0.7528) Prec@1 78.906 (78.421) Prec@5 91.797 (94.056)
[2021-04-26 17:11:52 train_lshot.py:257] INFO Epoch: [41][120/150] Time 0.943 (1.050) Data 0.000 (0.114) Loss 0.7927 (0.7527) Prec@1 76.562 (78.380) Prec@5 94.531 (94.089)
[2021-04-26 17:12:02 train_lshot.py:257] INFO Epoch: [41][130/150] Time 0.928 (1.042) Data 0.000 (0.105) Loss 0.7756 (0.7518) Prec@1 75.391 (78.417) Prec@5 95.312 (94.120)
[2021-04-26 17:12:11 train_lshot.py:257] INFO Epoch: [41][140/150] Time 0.935 (1.034) Data 0.000 (0.098) Loss 0.8134 (0.7517) Prec@1 76.172 (78.408) Prec@5 91.406 (94.105)
[2021-04-26 17:12:31 train_lshot.py:257] INFO Epoch: [42][0/150] Time 10.560 (10.560) Data 9.606 (9.606) Loss 0.7352 (0.7352) Prec@1 80.078 (80.078) Prec@5 95.703 (95.703)
[2021-04-26 17:12:40 train_lshot.py:257] INFO Epoch: [42][10/150] Time 0.933 (1.810) Data 0.000 (0.874) Loss 0.7736 (0.7234) Prec@1 74.219 (78.977) Prec@5 94.141 (94.780)
[2021-04-26 17:12:50 train_lshot.py:257] INFO Epoch: [42][20/150] Time 0.936 (1.394) Data 0.001 (0.458) Loss 0.6990 (0.7243) Prec@1 80.469 (79.129) Prec@5 96.875 (94.810)
[2021-04-26 17:12:59 train_lshot.py:257] INFO Epoch: [42][30/150] Time 0.934 (1.245) Data 0.000 (0.310) Loss 0.7873 (0.7267) Prec@1 78.125 (79.183) Prec@5 92.969 (94.632)
[2021-04-26 17:13:08 train_lshot.py:257] INFO Epoch: [42][40/150] Time 0.936 (1.169) Data 0.000 (0.235) Loss 0.6473 (0.7190) Prec@1 80.469 (79.516) Prec@5 96.484 (94.693)
[2021-04-26 17:13:18 train_lshot.py:257] INFO Epoch: [42][50/150] Time 0.936 (1.123) Data 0.000 (0.189) Loss 0.8570 (0.7232) Prec@1 73.047 (79.251) Prec@5 94.531 (94.608)
[2021-04-26 17:13:27 train_lshot.py:257] INFO Epoch: [42][60/150] Time 0.936 (1.092) Data 0.000 (0.158) Loss 0.6931 (0.7224) Prec@1 79.297 (79.303) Prec@5 95.312 (94.589)
[2021-04-26 17:13:36 train_lshot.py:257] INFO Epoch: [42][70/150] Time 0.933 (1.070) Data 0.001 (0.136) Loss 0.8435 (0.7278) Prec@1 74.609 (79.115) Prec@5 89.453 (94.454)
[2021-04-26 17:13:46 train_lshot.py:257] INFO Epoch: [42][80/150] Time 0.939 (1.054) Data 0.000 (0.119) Loss 0.8354 (0.7282) Prec@1 76.172 (79.118) Prec@5 94.531 (94.488)
[2021-04-26 17:13:55 train_lshot.py:257] INFO Epoch: [42][90/150] Time 0.933 (1.041) Data 0.000 (0.106) Loss 0.7517 (0.7289) Prec@1 76.562 (79.056) Prec@5 95.312 (94.583)
[2021-04-26 17:14:04 train_lshot.py:257] INFO Epoch: [42][100/150] Time 0.936 (1.030) Data 0.000 (0.096) Loss 0.7284 (0.7279) Prec@1 78.906 (79.123) Prec@5 92.969 (94.570)
[2021-04-26 17:14:14 train_lshot.py:257] INFO Epoch: [42][110/150] Time 0.930 (1.022) Data 0.000 (0.087) Loss 0.7266 (0.7282) Prec@1 80.078 (79.131) Prec@5 92.188 (94.524)
[2021-04-26 17:14:23 train_lshot.py:257] INFO Epoch: [42][120/150] Time 0.927 (1.015) Data 0.000 (0.080) Loss 0.7888 (0.7329) Prec@1 78.125 (78.948) Prec@5 93.750 (94.444)
[2021-04-26 17:14:33 train_lshot.py:257] INFO Epoch: [42][130/150] Time 0.940 (1.009) Data 0.000 (0.074) Loss 0.7777 (0.7343) Prec@1 77.734 (78.909) Prec@5 93.750 (94.418)
[2021-04-26 17:14:42 train_lshot.py:257] INFO Epoch: [42][140/150] Time 0.932 (1.004) Data 0.000 (0.068) Loss 0.7244 (0.7358) Prec@1 79.688 (78.895) Prec@5 92.969 (94.398)
[2021-04-26 17:15:06 train_lshot.py:257] INFO Epoch: [43][0/150] Time 14.249 (14.249) Data 13.288 (13.288) Loss 0.6852 (0.6852) Prec@1 82.812 (82.812) Prec@5 94.141 (94.141)
[2021-04-26 17:15:15 train_lshot.py:257] INFO Epoch: [43][10/150] Time 0.934 (2.147) Data 0.000 (1.208) Loss 0.6394 (0.7061) Prec@1 83.203 (80.291) Prec@5 96.875 (95.277)
[2021-04-26 17:15:24 train_lshot.py:257] INFO Epoch: [43][20/150] Time 0.939 (1.572) Data 0.001 (0.633) Loss 0.6817 (0.7206) Prec@1 81.250 (79.836) Prec@5 94.531 (94.847)
[2021-04-26 17:15:34 train_lshot.py:257] INFO Epoch: [43][30/150] Time 0.941 (1.367) Data 0.000 (0.429) Loss 0.6802 (0.7155) Prec@1 78.906 (79.851) Prec@5 94.531 (94.846)
[2021-04-26 17:15:43 train_lshot.py:257] INFO Epoch: [43][40/150] Time 0.932 (1.262) Data 0.000 (0.325) Loss 0.6110 (0.7169) Prec@1 84.766 (79.821) Prec@5 96.484 (94.731)
[2021-04-26 17:15:52 train_lshot.py:257] INFO Epoch: [43][50/150] Time 0.934 (1.198) Data 0.000 (0.261) Loss 0.8201 (0.7131) Prec@1 78.516 (79.933) Prec@5 91.797 (94.723)
[2021-04-26 17:16:02 train_lshot.py:257] INFO Epoch: [43][60/150] Time 0.938 (1.155) Data 0.000 (0.218) Loss 0.7832 (0.7120) Prec@1 79.688 (80.033) Prec@5 93.750 (94.730)
[2021-04-26 17:16:11 train_lshot.py:257] INFO Epoch: [43][70/150] Time 0.940 (1.125) Data 0.002 (0.188) Loss 0.7758 (0.7134) Prec@1 77.344 (80.001) Prec@5 92.188 (94.685)
[2021-04-26 17:16:21 train_lshot.py:257] INFO Epoch: [43][80/150] Time 0.934 (1.102) Data 0.000 (0.165) Loss 0.6796 (0.7189) Prec@1 81.250 (79.808) Prec@5 94.531 (94.608)
[2021-04-26 17:16:30 train_lshot.py:257] INFO Epoch: [43][90/150] Time 0.945 (1.084) Data 0.000 (0.146) Loss 0.6731 (0.7211) Prec@1 80.078 (79.700) Prec@5 96.094 (94.566)
[2021-04-26 17:16:39 train_lshot.py:257] INFO Epoch: [43][100/150] Time 0.938 (1.069) Data 0.000 (0.132) Loss 0.8398 (0.7266) Prec@1 72.266 (79.486) Prec@5 93.750 (94.469)
[2021-04-26 17:16:49 train_lshot.py:257] INFO Epoch: [43][110/150] Time 0.933 (1.057) Data 0.000 (0.120) Loss 0.7326 (0.7284) Prec@1 80.469 (79.427) Prec@5 94.141 (94.426)
[2021-04-26 17:16:58 train_lshot.py:257] INFO Epoch: [43][120/150] Time 0.931 (1.047) Data 0.000 (0.110) Loss 0.6815 (0.7305) Prec@1 83.203 (79.342) Prec@5 93.750 (94.357)
[2021-04-26 17:17:07 train_lshot.py:257] INFO Epoch: [43][130/150] Time 0.939 (1.039) Data 0.000 (0.102) Loss 0.7903 (0.7322) Prec@1 76.172 (79.252) Prec@5 92.188 (94.352)
[2021-04-26 17:17:17 train_lshot.py:257] INFO Epoch: [43][140/150] Time 0.935 (1.032) Data 0.000 (0.095) Loss 0.7544 (0.7350) Prec@1 79.297 (79.183) Prec@5 95.312 (94.321)
[2021-04-26 17:18:28 train_lshot.py:119] INFO Meta Val 43: 0.5969333450198173
[2021-04-26 17:18:41 train_lshot.py:257] INFO Epoch: [44][0/150] Time 11.569 (11.569) Data 10.610 (10.610) Loss 0.6404 (0.6404) Prec@1 83.984 (83.984) Prec@5 95.703 (95.703)
[2021-04-26 17:18:50 train_lshot.py:257] INFO Epoch: [44][10/150] Time 0.930 (1.899) Data 0.000 (0.965) Loss 0.6037 (0.7108) Prec@1 84.766 (79.084) Prec@5 94.531 (94.780)
[2021-04-26 17:18:59 train_lshot.py:257] INFO Epoch: [44][20/150] Time 0.937 (1.441) Data 0.001 (0.506) Loss 0.7385 (0.6986) Prec@1 80.859 (79.818) Prec@5 92.969 (94.885)
[2021-04-26 17:19:09 train_lshot.py:257] INFO Epoch: [44][30/150] Time 0.926 (1.276) Data 0.000 (0.343) Loss 0.7440 (0.6958) Prec@1 79.297 (80.179) Prec@5 92.969 (94.834)
[2021-04-26 17:19:18 train_lshot.py:257] INFO Epoch: [44][40/150] Time 0.938 (1.193) Data 0.000 (0.259) Loss 0.7082 (0.6914) Prec@1 80.859 (80.450) Prec@5 94.922 (95.017)
[2021-04-26 17:19:27 train_lshot.py:257] INFO Epoch: [44][50/150] Time 0.938 (1.143) Data 0.001 (0.208) Loss 0.8043 (0.7018) Prec@1 75.000 (79.986) Prec@5 92.969 (94.761)
[2021-04-26 17:19:37 train_lshot.py:257] INFO Epoch: [44][60/150] Time 0.933 (1.109) Data 0.000 (0.174) Loss 0.7984 (0.6996) Prec@1 76.953 (80.117) Prec@5 94.141 (94.864)
[2021-04-26 17:19:46 train_lshot.py:257] INFO Epoch: [44][70/150] Time 0.936 (1.084) Data 0.000 (0.150) Loss 0.6855 (0.7022) Prec@1 82.422 (80.161) Prec@5 94.531 (94.735)
[2021-04-26 17:19:56 train_lshot.py:257] INFO Epoch: [44][80/150] Time 0.938 (1.066) Data 0.000 (0.131) Loss 0.7645 (0.7037) Prec@1 77.344 (80.073) Prec@5 93.359 (94.768)
[2021-04-26 17:20:05 train_lshot.py:257] INFO Epoch: [44][90/150] Time 0.940 (1.052) Data 0.000 (0.117) Loss 0.7517 (0.7073) Prec@1 78.906 (79.975) Prec@5 93.750 (94.707)
[2021-04-26 17:20:14 train_lshot.py:257] INFO Epoch: [44][100/150] Time 0.941 (1.040) Data 0.000 (0.105) Loss 0.6574 (0.7111) Prec@1 82.422 (79.889) Prec@5 95.703 (94.636)
[2021-04-26 17:20:24 train_lshot.py:257] INFO Epoch: [44][110/150] Time 0.936 (1.031) Data 0.000 (0.096) Loss 0.7217 (0.7129) Prec@1 81.641 (79.867) Prec@5 95.703 (94.591)
[2021-04-26 17:20:33 train_lshot.py:257] INFO Epoch: [44][120/150] Time 0.943 (1.023) Data 0.000 (0.088) Loss 0.8070 (0.7150) Prec@1 77.734 (79.794) Prec@5 91.797 (94.541)
[2021-04-26 17:20:42 train_lshot.py:257] INFO Epoch: [44][130/150] Time 0.938 (1.017) Data 0.000 (0.081) Loss 0.7040 (0.7177) Prec@1 81.250 (79.723) Prec@5 94.141 (94.457)
[2021-04-26 17:20:52 train_lshot.py:257] INFO Epoch: [44][140/150] Time 0.936 (1.011) Data 0.000 (0.076) Loss 0.6300 (0.7157) Prec@1 82.812 (79.845) Prec@5 95.312 (94.473)
[2021-04-26 17:21:15 train_lshot.py:257] INFO Epoch: [45][0/150] Time 13.722 (13.722) Data 12.774 (12.774) Loss 0.6430 (0.6430) Prec@1 82.031 (82.031) Prec@5 95.312 (95.312)
[2021-04-26 17:21:24 train_lshot.py:257] INFO Epoch: [45][10/150] Time 0.939 (2.098) Data 0.000 (1.162) Loss 0.7428 (0.7049) Prec@1 79.688 (80.504) Prec@5 93.359 (95.135)
[2021-04-26 17:21:34 train_lshot.py:257] INFO Epoch: [45][20/150] Time 0.942 (1.546) Data 0.001 (0.609) Loss 0.6261 (0.6995) Prec@1 82.812 (80.599) Prec@5 95.703 (94.996)
[2021-04-26 17:21:43 train_lshot.py:257] INFO Epoch: [45][30/150] Time 0.941 (1.350) Data 0.001 (0.413) Loss 0.6231 (0.6974) Prec@1 81.641 (80.507) Prec@5 98.438 (95.060)
[2021-04-26 17:21:52 train_lshot.py:257] INFO Epoch: [45][40/150] Time 0.940 (1.249) Data 0.002 (0.312) Loss 0.6942 (0.6953) Prec@1 80.078 (80.431) Prec@5 95.312 (95.112)
[2021-04-26 17:22:02 train_lshot.py:257] INFO Epoch: [45][50/150] Time 0.938 (1.188) Data 0.001 (0.251) Loss 0.6107 (0.6876) Prec@1 83.594 (80.821) Prec@5 95.312 (95.113)
[2021-04-26 17:22:11 train_lshot.py:257] INFO Epoch: [45][60/150] Time 0.932 (1.147) Data 0.001 (0.210) Loss 0.6989 (0.6832) Prec@1 83.203 (81.083) Prec@5 94.531 (95.114)
[2021-04-26 17:22:21 train_lshot.py:257] INFO Epoch: [45][70/150] Time 0.933 (1.118) Data 0.000 (0.180) Loss 0.6301 (0.6893) Prec@1 82.422 (80.942) Prec@5 97.266 (95.032)
[2021-04-26 17:22:30 train_lshot.py:257] INFO Epoch: [45][80/150] Time 0.934 (1.095) Data 0.000 (0.158) Loss 0.7873 (0.6927) Prec@1 77.344 (80.816) Prec@5 93.359 (94.970)
[2021-04-26 17:22:39 train_lshot.py:257] INFO Epoch: [45][90/150] Time 0.935 (1.078) Data 0.000 (0.141) Loss 0.6967 (0.6946) Prec@1 79.297 (80.662) Prec@5 95.312 (94.956)
[2021-04-26 17:22:49 train_lshot.py:257] INFO Epoch: [45][100/150] Time 0.930 (1.064) Data 0.000 (0.127) Loss 0.7607 (0.6974) Prec@1 81.250 (80.596) Prec@5 93.359 (94.933)
[2021-04-26 17:22:58 train_lshot.py:257] INFO Epoch: [45][110/150] Time 0.938 (1.053) Data 0.000 (0.115) Loss 0.7226 (0.6992) Prec@1 77.344 (80.476) Prec@5 93.750 (94.869)
[2021-04-26 17:23:07 train_lshot.py:257] INFO Epoch: [45][120/150] Time 0.941 (1.043) Data 0.000 (0.106) Loss 0.6612 (0.7013) Prec@1 80.859 (80.369) Prec@5 96.875 (94.867)
[2021-04-26 17:23:17 train_lshot.py:257] INFO Epoch: [45][130/150] Time 0.939 (1.035) Data 0.000 (0.098) Loss 0.7346 (0.7039) Prec@1 81.250 (80.254) Prec@5 94.141 (94.859)
[2021-04-26 17:23:26 train_lshot.py:257] INFO Epoch: [45][140/150] Time 0.937 (1.028) Data 0.000 (0.091) Loss 0.7328 (0.7062) Prec@1 78.906 (80.075) Prec@5 95.312 (94.886)
[2021-04-26 17:23:49 train_lshot.py:257] INFO Epoch: [46][0/150] Time 13.858 (13.858) Data 12.894 (12.894) Loss 0.7382 (0.7382) Prec@1 80.469 (80.469) Prec@5 93.359 (93.359)
[2021-04-26 17:23:59 train_lshot.py:257] INFO Epoch: [46][10/150] Time 0.933 (2.108) Data 0.001 (1.173) Loss 0.6952 (0.6564) Prec@1 77.344 (81.712) Prec@5 95.312 (95.490)
[2021-04-26 17:24:08 train_lshot.py:257] INFO Epoch: [46][20/150] Time 0.937 (1.550) Data 0.000 (0.614) Loss 0.6213 (0.6532) Prec@1 83.203 (82.236) Prec@5 94.922 (95.312)
[2021-04-26 17:24:17 train_lshot.py:257] INFO Epoch: [46][30/150] Time 0.936 (1.351) Data 0.001 (0.416) Loss 0.6652 (0.6466) Prec@1 82.422 (82.497) Prec@5 93.750 (95.300)
[2021-04-26 17:24:27 train_lshot.py:257] INFO Epoch: [46][40/150] Time 0.932 (1.251) Data 0.000 (0.315) Loss 0.6188 (0.6388) Prec@1 85.156 (82.784) Prec@5 93.359 (95.370)
[2021-04-26 17:24:36 train_lshot.py:257] INFO Epoch: [46][50/150] Time 0.933 (1.188) Data 0.000 (0.253) Loss 0.6183 (0.6265) Prec@1 83.203 (83.257) Prec@5 94.531 (95.458)
[2021-04-26 17:24:46 train_lshot.py:257] INFO Epoch: [46][60/150] Time 0.936 (1.147) Data 0.001 (0.212) Loss 0.5553 (0.6192) Prec@1 85.156 (83.395) Prec@5 96.875 (95.588)
[2021-04-26 17:24:55 train_lshot.py:257] INFO Epoch: [46][70/150] Time 0.939 (1.118) Data 0.000 (0.182) Loss 0.6234 (0.6129) Prec@1 81.641 (83.550) Prec@5 96.094 (95.703)
[2021-04-26 17:25:04 train_lshot.py:257] INFO Epoch: [46][80/150] Time 0.934 (1.095) Data 0.000 (0.160) Loss 0.5467 (0.6055) Prec@1 85.547 (83.902) Prec@5 97.266 (95.800)
[2021-04-26 17:25:14 train_lshot.py:257] INFO Epoch: [46][90/150] Time 0.937 (1.077) Data 0.000 (0.142) Loss 0.4767 (0.5989) Prec@1 88.672 (84.117) Prec@5 97.656 (95.866)
[2021-04-26 17:25:23 train_lshot.py:257] INFO Epoch: [46][100/150] Time 0.941 (1.064) Data 0.000 (0.128) Loss 0.6318 (0.5933) Prec@1 79.688 (84.305) Prec@5 98.047 (95.955)
[2021-04-26 17:25:32 train_lshot.py:257] INFO Epoch: [46][110/150] Time 0.943 (1.052) Data 0.000 (0.117) Loss 0.6052 (0.5919) Prec@1 81.641 (84.336) Prec@5 96.875 (95.999)
[2021-04-26 17:25:42 train_lshot.py:257] INFO Epoch: [46][120/150] Time 0.932 (1.043) Data 0.000 (0.107) Loss 0.5190 (0.5895) Prec@1 87.109 (84.465) Prec@5 95.703 (96.029)
[2021-04-26 17:25:51 train_lshot.py:257] INFO Epoch: [46][130/150] Time 0.939 (1.034) Data 0.000 (0.099) Loss 0.5480 (0.5866) Prec@1 84.766 (84.566) Prec@5 95.312 (96.052)
[2021-04-26 17:26:00 train_lshot.py:257] INFO Epoch: [46][140/150] Time 0.943 (1.028) Data 0.000 (0.092) Loss 0.5066 (0.5856) Prec@1 87.109 (84.594) Prec@5 98.047 (96.063)
[2021-04-26 17:26:24 train_lshot.py:257] INFO Epoch: [47][0/150] Time 14.112 (14.112) Data 13.157 (13.157) Loss 0.5540 (0.5540) Prec@1 83.984 (83.984) Prec@5 98.438 (98.438)
[2021-04-26 17:26:33 train_lshot.py:257] INFO Epoch: [47][10/150] Time 0.960 (2.145) Data 0.000 (1.210) Loss 0.4868 (0.5530) Prec@1 86.719 (86.257) Prec@5 97.656 (96.058)
[2021-04-26 17:26:43 train_lshot.py:257] INFO Epoch: [47][20/150] Time 0.929 (1.568) Data 0.000 (0.634) Loss 0.5231 (0.5416) Prec@1 87.500 (86.365) Prec@5 95.312 (96.298)
[2021-04-26 17:26:52 train_lshot.py:257] INFO Epoch: [47][30/150] Time 0.939 (1.364) Data 0.000 (0.429) Loss 0.5334 (0.5420) Prec@1 87.891 (86.290) Prec@5 96.484 (96.295)
[2021-04-26 17:27:02 train_lshot.py:257] INFO Epoch: [47][40/150] Time 0.938 (1.260) Data 0.001 (0.325) Loss 0.4963 (0.5385) Prec@1 87.109 (86.614) Prec@5 98.047 (96.370)
[2021-04-26 17:27:11 train_lshot.py:257] INFO Epoch: [47][50/150] Time 0.937 (1.197) Data 0.001 (0.261) Loss 0.4900 (0.5366) Prec@1 87.891 (86.619) Prec@5 97.656 (96.423)
[2021-04-26 17:27:20 train_lshot.py:257] INFO Epoch: [47][60/150] Time 0.944 (1.154) Data 0.000 (0.219) Loss 0.5807 (0.5355) Prec@1 84.766 (86.668) Prec@5 96.094 (96.446)
[2021-04-26 17:27:30 train_lshot.py:257] INFO Epoch: [47][70/150] Time 0.934 (1.124) Data 0.000 (0.188) Loss 0.5588 (0.5386) Prec@1 85.938 (86.559) Prec@5 96.094 (96.418)
[2021-04-26 17:27:39 train_lshot.py:257] INFO Epoch: [47][80/150] Time 0.946 (1.101) Data 0.000 (0.165) Loss 0.5566 (0.5406) Prec@1 83.984 (86.434) Prec@5 94.531 (96.393)
[2021-04-26 17:27:48 train_lshot.py:257] INFO Epoch: [47][90/150] Time 0.935 (1.083) Data 0.000 (0.147) Loss 0.5310 (0.5382) Prec@1 86.328 (86.543) Prec@5 96.875 (96.416)
[2021-04-26 17:27:58 train_lshot.py:257] INFO Epoch: [47][100/150] Time 0.934 (1.069) Data 0.000 (0.132) Loss 0.5902 (0.5371) Prec@1 83.594 (86.618) Prec@5 94.141 (96.430)
[2021-04-26 17:28:07 train_lshot.py:257] INFO Epoch: [47][110/150] Time 0.929 (1.057) Data 0.000 (0.120) Loss 0.6218 (0.5397) Prec@1 83.984 (86.469) Prec@5 94.141 (96.453)
[2021-04-26 17:28:17 train_lshot.py:257] INFO Epoch: [47][120/150] Time 0.948 (1.047) Data 0.000 (0.110) Loss 0.5491 (0.5380) Prec@1 83.984 (86.467) Prec@5 97.266 (96.481)
[2021-04-26 17:28:26 train_lshot.py:257] INFO Epoch: [47][130/150] Time 0.939 (1.039) Data 0.000 (0.102) Loss 0.6018 (0.5375) Prec@1 83.984 (86.465) Prec@5 94.922 (96.458)
[2021-04-26 17:28:35 train_lshot.py:257] INFO Epoch: [47][140/150] Time 0.937 (1.032) Data 0.000 (0.095) Loss 0.5055 (0.5361) Prec@1 87.891 (86.528) Prec@5 96.875 (96.468)
[2021-04-26 17:29:37 train_lshot.py:119] INFO Meta Val 47: 0.6233333464860916
[2021-04-26 17:29:53 train_lshot.py:257] INFO Epoch: [48][0/150] Time 12.903 (12.903) Data 11.961 (11.961) Loss 0.5340 (0.5340) Prec@1 87.891 (87.891) Prec@5 95.312 (95.312)
[2021-04-26 17:30:02 train_lshot.py:257] INFO Epoch: [48][10/150] Time 0.934 (2.022) Data 0.000 (1.088) Loss 0.4979 (0.5045) Prec@1 87.500 (88.246) Prec@5 96.875 (96.520)
[2021-04-26 17:30:11 train_lshot.py:257] INFO Epoch: [48][20/150] Time 0.927 (1.502) Data 0.000 (0.570) Loss 0.5806 (0.5237) Prec@1 85.156 (87.258) Prec@5 94.531 (96.503)
[2021-04-26 17:30:21 train_lshot.py:257] INFO Epoch: [48][30/150] Time 0.939 (1.319) Data 0.000 (0.386) Loss 0.5885 (0.5333) Prec@1 85.547 (86.744) Prec@5 95.312 (96.434)
[2021-04-26 17:30:30 train_lshot.py:257] INFO Epoch: [48][40/150] Time 0.927 (1.225) Data 0.000 (0.292) Loss 0.5151 (0.5318) Prec@1 87.891 (86.681) Prec@5 95.703 (96.456)
[2021-04-26 17:30:39 train_lshot.py:257] INFO Epoch: [48][50/150] Time 0.930 (1.168) Data 0.000 (0.235) Loss 0.4527 (0.5297) Prec@1 89.844 (86.757) Prec@5 98.438 (96.523)
[2021-04-26 17:30:49 train_lshot.py:257] INFO Epoch: [48][60/150] Time 0.940 (1.130) Data 0.001 (0.197) Loss 0.5171 (0.5334) Prec@1 85.938 (86.565) Prec@5 98.438 (96.408)
[2021-04-26 17:30:58 train_lshot.py:257] INFO Epoch: [48][70/150] Time 0.936 (1.102) Data 0.002 (0.169) Loss 0.5681 (0.5324) Prec@1 84.766 (86.499) Prec@5 95.703 (96.440)
[2021-04-26 17:31:07 train_lshot.py:257] INFO Epoch: [48][80/150] Time 0.928 (1.081) Data 0.000 (0.148) Loss 0.4708 (0.5315) Prec@1 88.281 (86.531) Prec@5 97.266 (96.427)
[2021-04-26 17:31:17 train_lshot.py:257] INFO Epoch: [48][90/150] Time 0.934 (1.065) Data 0.000 (0.132) Loss 0.5006 (0.5304) Prec@1 89.062 (86.680) Prec@5 98.438 (96.489)
[2021-04-26 17:31:26 train_lshot.py:257] INFO Epoch: [48][100/150] Time 0.937 (1.053) Data 0.000 (0.119) Loss 0.5390 (0.5297) Prec@1 87.109 (86.676) Prec@5 96.875 (96.531)
[2021-04-26 17:31:35 train_lshot.py:257] INFO Epoch: [48][110/150] Time 0.941 (1.042) Data 0.000 (0.108) Loss 0.4876 (0.5284) Prec@1 88.672 (86.680) Prec@5 95.703 (96.569)
[2021-04-26 17:31:45 train_lshot.py:257] INFO Epoch: [48][120/150] Time 0.936 (1.033) Data 0.000 (0.099) Loss 0.4735 (0.5278) Prec@1 87.500 (86.622) Prec@5 98.047 (96.588)
[2021-04-26 17:31:54 train_lshot.py:257] INFO Epoch: [48][130/150] Time 0.932 (1.026) Data 0.000 (0.092) Loss 0.5428 (0.5265) Prec@1 84.375 (86.695) Prec@5 96.484 (96.613)
[2021-04-26 17:32:03 train_lshot.py:257] INFO Epoch: [48][140/150] Time 0.936 (1.019) Data 0.000 (0.085) Loss 0.4802 (0.5231) Prec@1 87.891 (86.807) Prec@5 97.656 (96.673)
[2021-04-26 17:32:27 train_lshot.py:257] INFO Epoch: [49][0/150] Time 14.026 (14.026) Data 13.065 (13.065) Loss 0.5413 (0.5413) Prec@1 85.547 (85.547) Prec@5 96.484 (96.484)
[2021-04-26 17:32:36 train_lshot.py:257] INFO Epoch: [49][10/150] Time 0.933 (2.124) Data 0.000 (1.188) Loss 0.5302 (0.5052) Prec@1 86.328 (87.713) Prec@5 95.703 (96.875)
[2021-04-26 17:32:46 train_lshot.py:257] INFO Epoch: [49][20/150] Time 0.937 (1.558) Data 0.000 (0.622) Loss 0.4510 (0.4934) Prec@1 89.453 (88.114) Prec@5 96.484 (96.987)
[2021-04-26 17:32:55 train_lshot.py:257] INFO Epoch: [49][30/150] Time 0.938 (1.357) Data 0.000 (0.422) Loss 0.4764 (0.4874) Prec@1 87.109 (88.269) Prec@5 97.656 (97.152)
[2021-04-26 17:33:04 train_lshot.py:257] INFO Epoch: [49][40/150] Time 0.947 (1.255) Data 0.001 (0.319) Loss 0.5656 (0.4932) Prec@1 82.422 (87.967) Prec@5 96.875 (97.027)
[2021-04-26 17:33:14 train_lshot.py:257] INFO Epoch: [49][50/150] Time 0.944 (1.193) Data 0.001 (0.257) Loss 0.4604 (0.4964) Prec@1 89.844 (87.783) Prec@5 96.875 (96.959)
[2021-04-26 17:33:23 train_lshot.py:257] INFO Epoch: [49][60/150] Time 0.938 (1.151) Data 0.000 (0.215) Loss 0.5295 (0.4997) Prec@1 88.672 (87.590) Prec@5 97.656 (96.984)
[2021-04-26 17:33:32 train_lshot.py:257] INFO Epoch: [49][70/150] Time 0.945 (1.121) Data 0.000 (0.184) Loss 0.5604 (0.5021) Prec@1 85.156 (87.506) Prec@5 95.703 (96.903)
[2021-04-26 17:33:42 train_lshot.py:257] INFO Epoch: [49][80/150] Time 0.933 (1.099) Data 0.000 (0.162) Loss 0.5623 (0.5028) Prec@1 83.984 (87.476) Prec@5 96.484 (96.870)
[2021-04-26 17:33:51 train_lshot.py:257] INFO Epoch: [49][90/150] Time 0.938 (1.081) Data 0.000 (0.144) Loss 0.5841 (0.5032) Prec@1 85.547 (87.431) Prec@5 94.922 (96.828)
[2021-04-26 17:34:01 train_lshot.py:257] INFO Epoch: [49][100/150] Time 0.940 (1.067) Data 0.000 (0.130) Loss 0.5696 (0.5046) Prec@1 85.156 (87.434) Prec@5 95.703 (96.802)
[2021-04-26 17:34:10 train_lshot.py:257] INFO Epoch: [49][110/150] Time 0.936 (1.056) Data 0.000 (0.118) Loss 0.5358 (0.5051) Prec@1 84.766 (87.405) Prec@5 98.438 (96.829)
[2021-04-26 17:34:19 train_lshot.py:257] INFO Epoch: [49][120/150] Time 0.930 (1.046) Data 0.000 (0.108) Loss 0.5718 (0.5073) Prec@1 85.547 (87.342) Prec@5 95.703 (96.814)
[2021-04-26 17:34:29 train_lshot.py:257] INFO Epoch: [49][130/150] Time 0.939 (1.038) Data 0.000 (0.100) Loss 0.4639 (0.5065) Prec@1 87.891 (87.425) Prec@5 98.047 (96.851)
[2021-04-26 17:34:38 train_lshot.py:257] INFO Epoch: [49][140/150] Time 0.937 (1.031) Data 0.000 (0.093) Loss 0.4345 (0.5059) Prec@1 90.234 (87.414) Prec@5 97.656 (96.856)
[2021-04-26 17:35:01 train_lshot.py:257] INFO Epoch: [50][0/150] Time 12.964 (12.964) Data 12.000 (12.000) Loss 0.4299 (0.4299) Prec@1 89.453 (89.453) Prec@5 98.828 (98.828)
[2021-04-26 17:35:10 train_lshot.py:257] INFO Epoch: [50][10/150] Time 0.938 (2.027) Data 0.000 (1.091) Loss 0.4854 (0.4935) Prec@1 86.719 (87.926) Prec@5 97.266 (97.337)
[2021-04-26 17:35:19 train_lshot.py:257] INFO Epoch: [50][20/150] Time 0.939 (1.508) Data 0.000 (0.572) Loss 0.5088 (0.4998) Prec@1 89.844 (88.132) Prec@5 95.312 (96.987)
[2021-04-26 17:35:29 train_lshot.py:257] INFO Epoch: [50][30/150] Time 0.936 (1.324) Data 0.001 (0.388) Loss 0.5796 (0.5046) Prec@1 84.375 (87.777) Prec@5 94.922 (96.913)
[2021-04-26 17:35:38 train_lshot.py:257] INFO Epoch: [50][40/150] Time 0.931 (1.229) Data 0.000 (0.293) Loss 0.5201 (0.4960) Prec@1 87.109 (88.119) Prec@5 97.656 (97.027)
[2021-04-26 17:35:47 train_lshot.py:257] INFO Epoch: [50][50/150] Time 0.940 (1.172) Data 0.001 (0.236) Loss 0.5195 (0.4966) Prec@1 87.109 (87.998) Prec@5 96.875 (97.013)
[2021-04-26 17:35:57 train_lshot.py:257] INFO Epoch: [50][60/150] Time 0.934 (1.133) Data 0.001 (0.197) Loss 0.4809 (0.4983) Prec@1 88.281 (87.846) Prec@5 96.875 (96.958)
[2021-04-26 17:36:06 train_lshot.py:257] INFO Epoch: [50][70/150] Time 0.942 (1.105) Data 0.002 (0.170) Loss 0.5001 (0.4971) Prec@1 85.547 (87.781) Prec@5 97.266 (96.991)
[2021-04-26 17:36:15 train_lshot.py:257] INFO Epoch: [50][80/150] Time 0.940 (1.084) Data 0.000 (0.149) Loss 0.4663 (0.4956) Prec@1 88.672 (87.862) Prec@5 96.875 (97.010)
[2021-04-26 17:36:25 train_lshot.py:257] INFO Epoch: [50][90/150] Time 0.937 (1.068) Data 0.000 (0.132) Loss 0.3655 (0.4951) Prec@1 92.188 (87.835) Prec@5 99.219 (96.999)
[2021-04-26 17:36:34 train_lshot.py:257] INFO Epoch: [50][100/150] Time 0.934 (1.055) Data 0.000 (0.119) Loss 0.5464 (0.4950) Prec@1 86.328 (87.864) Prec@5 95.703 (97.010)
[2021-04-26 17:36:44 train_lshot.py:257] INFO Epoch: [50][110/150] Time 0.943 (1.044) Data 0.000 (0.109) Loss 0.5062 (0.4959) Prec@1 88.281 (87.848) Prec@5 98.047 (97.023)
[2021-04-26 17:36:53 train_lshot.py:257] INFO Epoch: [50][120/150] Time 0.936 (1.035) Data 0.000 (0.100) Loss 0.4493 (0.4949) Prec@1 89.453 (87.878) Prec@5 96.484 (97.043)
[2021-04-26 17:37:02 train_lshot.py:257] INFO Epoch: [50][130/150] Time 0.942 (1.027) Data 0.000 (0.092) Loss 0.4546 (0.4929) Prec@1 89.453 (88.007) Prec@5 98.047 (97.081)
[2021-04-26 17:37:12 train_lshot.py:257] INFO Epoch: [50][140/150] Time 0.934 (1.021) Data 0.000 (0.085) Loss 0.4634 (0.4944) Prec@1 88.281 (87.913) Prec@5 98.438 (97.055)
[2021-04-26 17:37:32 train_lshot.py:257] INFO Epoch: [51][0/150] Time 11.437 (11.437) Data 10.458 (10.458) Loss 0.4697 (0.4697) Prec@1 89.062 (89.062) Prec@5 98.047 (98.047)
[2021-04-26 17:37:42 train_lshot.py:257] INFO Epoch: [51][10/150] Time 0.941 (1.891) Data 0.000 (0.951) Loss 0.5084 (0.5077) Prec@1 89.453 (87.642) Prec@5 95.703 (96.626)
[2021-04-26 17:37:51 train_lshot.py:257] INFO Epoch: [51][20/150] Time 0.937 (1.437) Data 0.000 (0.498) Loss 0.4175 (0.5009) Prec@1 92.578 (87.891) Prec@5 98.438 (96.689)
[2021-04-26 17:38:01 train_lshot.py:257] INFO Epoch: [51][30/150] Time 0.931 (1.275) Data 0.000 (0.338) Loss 0.4811 (0.4982) Prec@1 88.281 (87.853) Prec@5 96.484 (96.825)
[2021-04-26 17:38:10 train_lshot.py:257] INFO Epoch: [51][40/150] Time 0.941 (1.192) Data 0.001 (0.256) Loss 0.4319 (0.4911) Prec@1 90.234 (88.081) Prec@5 98.047 (97.027)
[2021-04-26 17:38:19 train_lshot.py:257] INFO Epoch: [51][50/150] Time 0.926 (1.142) Data 0.001 (0.206) Loss 0.4905 (0.4918) Prec@1 87.500 (88.028) Prec@5 96.094 (96.975)
[2021-04-26 17:38:29 train_lshot.py:257] INFO Epoch: [51][60/150] Time 0.944 (1.108) Data 0.000 (0.172) Loss 0.5519 (0.4917) Prec@1 87.500 (88.108) Prec@5 96.094 (96.958)
[2021-04-26 17:38:38 train_lshot.py:257] INFO Epoch: [51][70/150] Time 0.939 (1.084) Data 0.000 (0.148) Loss 0.5175 (0.4924) Prec@1 84.766 (88.056) Prec@5 96.875 (96.969)
[2021-04-26 17:38:47 train_lshot.py:257] INFO Epoch: [51][80/150] Time 0.935 (1.066) Data 0.000 (0.130) Loss 0.5175 (0.4951) Prec@1 86.328 (87.915) Prec@5 96.484 (96.938)
[2021-04-26 17:38:57 train_lshot.py:257] INFO Epoch: [51][90/150] Time 0.936 (1.052) Data 0.000 (0.115) Loss 0.4711 (0.4909) Prec@1 89.062 (88.041) Prec@5 97.656 (97.047)
[2021-04-26 17:39:06 train_lshot.py:257] INFO Epoch: [51][100/150] Time 0.930 (1.040) Data 0.000 (0.104) Loss 0.4301 (0.4911) Prec@1 90.234 (87.995) Prec@5 98.047 (97.030)
[2021-04-26 17:39:15 train_lshot.py:257] INFO Epoch: [51][110/150] Time 0.936 (1.031) Data 0.000 (0.095) Loss 0.4047 (0.4900) Prec@1 91.016 (88.010) Prec@5 97.656 (97.051)
[2021-04-26 17:39:25 train_lshot.py:257] INFO Epoch: [51][120/150] Time 0.934 (1.023) Data 0.000 (0.087) Loss 0.4423 (0.4885) Prec@1 91.016 (88.078) Prec@5 97.656 (97.069)
[2021-04-26 17:39:34 train_lshot.py:257] INFO Epoch: [51][130/150] Time 0.947 (1.017) Data 0.000 (0.080) Loss 0.4859 (0.4878) Prec@1 87.500 (88.147) Prec@5 98.438 (97.093)
[2021-04-26 17:39:44 train_lshot.py:257] INFO Epoch: [51][140/150] Time 0.942 (1.011) Data 0.000 (0.074) Loss 0.5884 (0.4893) Prec@1 83.984 (88.143) Prec@5 96.094 (97.077)
[2021-04-26 17:40:49 train_lshot.py:119] INFO Meta Val 51: 0.6200000132918357
[2021-04-26 17:41:01 train_lshot.py:257] INFO Epoch: [52][0/150] Time 10.735 (10.735) Data 9.755 (9.755) Loss 0.4653 (0.4653) Prec@1 88.281 (88.281) Prec@5 96.484 (96.484)
[2021-04-26 17:41:11 train_lshot.py:257] INFO Epoch: [52][10/150] Time 0.940 (1.873) Data 0.000 (0.933) Loss 0.5099 (0.4774) Prec@1 85.156 (88.601) Prec@5 97.266 (97.656)
[2021-04-26 17:41:20 train_lshot.py:257] INFO Epoch: [52][20/150] Time 0.944 (1.428) Data 0.001 (0.489) Loss 0.4497 (0.4836) Prec@1 88.672 (88.151) Prec@5 96.875 (97.284)
[2021-04-26 17:41:29 train_lshot.py:257] INFO Epoch: [52][30/150] Time 0.936 (1.269) Data 0.000 (0.331) Loss 0.5750 (0.4867) Prec@1 84.375 (88.029) Prec@5 96.094 (97.140)
[2021-04-26 17:41:39 train_lshot.py:257] INFO Epoch: [52][40/150] Time 0.936 (1.188) Data 0.000 (0.251) Loss 0.5440 (0.4906) Prec@1 87.500 (87.976) Prec@5 95.312 (97.027)
[2021-04-26 17:41:48 train_lshot.py:257] INFO Epoch: [52][50/150] Time 0.946 (1.138) Data 0.000 (0.202) Loss 0.4391 (0.4876) Prec@1 88.281 (88.036) Prec@5 98.047 (97.097)
[2021-04-26 17:41:57 train_lshot.py:257] INFO Epoch: [52][60/150] Time 0.936 (1.106) Data 0.000 (0.169) Loss 0.4011 (0.4855) Prec@1 89.062 (88.147) Prec@5 98.047 (97.106)
[2021-04-26 17:42:07 train_lshot.py:257] INFO Epoch: [52][70/150] Time 0.947 (1.082) Data 0.002 (0.145) Loss 0.5370 (0.4848) Prec@1 87.891 (88.237) Prec@5 94.922 (97.090)
[2021-04-26 17:42:16 train_lshot.py:257] INFO Epoch: [52][80/150] Time 0.935 (1.064) Data 0.000 (0.127) Loss 0.5034 (0.4845) Prec@1 87.891 (88.247) Prec@5 97.266 (97.111)
[2021-04-26 17:42:25 train_lshot.py:257] INFO Epoch: [52][90/150] Time 0.934 (1.049) Data 0.000 (0.113) Loss 0.5218 (0.4846) Prec@1 85.547 (88.178) Prec@5 96.875 (97.158)
[2021-04-26 17:42:35 train_lshot.py:257] INFO Epoch: [52][100/150] Time 0.928 (1.038) Data 0.000 (0.102) Loss 0.4860 (0.4866) Prec@1 87.891 (88.057) Prec@5 96.875 (97.103)
[2021-04-26 17:42:44 train_lshot.py:257] INFO Epoch: [52][110/150] Time 0.931 (1.029) Data 0.000 (0.093) Loss 0.4355 (0.4884) Prec@1 91.406 (88.035) Prec@5 97.656 (97.072)
[2021-04-26 17:42:53 train_lshot.py:257] INFO Epoch: [52][120/150] Time 0.931 (1.021) Data 0.000 (0.085) Loss 0.5313 (0.4904) Prec@1 86.719 (87.991) Prec@5 95.703 (97.011)
[2021-04-26 17:43:03 train_lshot.py:257] INFO Epoch: [52][130/150] Time 0.934 (1.014) Data 0.000 (0.079) Loss 0.5582 (0.4913) Prec@1 83.594 (87.926) Prec@5 96.094 (96.991)
[2021-04-26 17:43:12 train_lshot.py:257] INFO Epoch: [52][140/150] Time 0.931 (1.009) Data 0.000 (0.073) Loss 0.4866 (0.4894) Prec@1 87.500 (87.971) Prec@5 97.656 (97.066)
[2021-04-26 17:43:34 train_lshot.py:257] INFO Epoch: [53][0/150] Time 11.973 (11.973) Data 11.024 (11.024) Loss 0.4225 (0.4225) Prec@1 91.406 (91.406) Prec@5 98.438 (98.438)
[2021-04-26 17:43:43 train_lshot.py:257] INFO Epoch: [53][10/150] Time 0.939 (1.937) Data 0.000 (1.003) Loss 0.5740 (0.4795) Prec@1 84.375 (88.423) Prec@5 94.531 (96.839)
[2021-04-26 17:43:52 train_lshot.py:257] INFO Epoch: [53][20/150] Time 0.932 (1.460) Data 0.001 (0.525) Loss 0.4370 (0.4792) Prec@1 91.016 (88.207) Prec@5 98.828 (97.284)
[2021-04-26 17:44:02 train_lshot.py:257] INFO Epoch: [53][30/150] Time 0.937 (1.291) Data 0.000 (0.356) Loss 0.5174 (0.4866) Prec@1 87.891 (87.966) Prec@5 96.484 (97.051)
[2021-04-26 17:44:11 train_lshot.py:257] INFO Epoch: [53][40/150] Time 0.938 (1.204) Data 0.000 (0.269) Loss 0.5918 (0.4903) Prec@1 82.031 (87.900) Prec@5 94.531 (97.066)
[2021-04-26 17:44:20 train_lshot.py:257] INFO Epoch: [53][50/150] Time 0.934 (1.152) Data 0.000 (0.217) Loss 0.5093 (0.4866) Prec@1 85.938 (87.975) Prec@5 96.484 (97.143)
[2021-04-26 17:44:30 train_lshot.py:257] INFO Epoch: [53][60/150] Time 0.940 (1.117) Data 0.000 (0.181) Loss 0.4359 (0.4893) Prec@1 91.016 (87.897) Prec@5 97.266 (97.041)
[2021-04-26 17:44:39 train_lshot.py:257] INFO Epoch: [53][70/150] Time 0.939 (1.091) Data 0.000 (0.156) Loss 0.4744 (0.4893) Prec@1 90.625 (87.968) Prec@5 98.438 (97.057)
[2021-04-26 17:44:48 train_lshot.py:257] INFO Epoch: [53][80/150] Time 0.934 (1.072) Data 0.000 (0.137) Loss 0.5657 (0.4882) Prec@1 84.766 (87.982) Prec@5 94.141 (97.029)
[2021-04-26 17:44:58 train_lshot.py:257] INFO Epoch: [53][90/150] Time 0.940 (1.057) Data 0.000 (0.122) Loss 0.4688 (0.4885) Prec@1 89.453 (87.989) Prec@5 97.656 (97.017)
[2021-04-26 17:45:07 train_lshot.py:257] INFO Epoch: [53][100/150] Time 0.940 (1.045) Data 0.000 (0.110) Loss 0.4482 (0.4876) Prec@1 89.453 (88.038) Prec@5 96.484 (97.006)
[2021-04-26 17:45:17 train_lshot.py:257] INFO Epoch: [53][110/150] Time 0.930 (1.036) Data 0.000 (0.100) Loss 0.4106 (0.4843) Prec@1 89.844 (88.218) Prec@5 97.656 (97.065)
[2021-04-26 17:45:26 train_lshot.py:257] INFO Epoch: [53][120/150] Time 0.940 (1.028) Data 0.000 (0.091) Loss 0.4907 (0.4842) Prec@1 86.719 (88.175) Prec@5 96.484 (97.056)
[2021-04-26 17:45:35 train_lshot.py:257] INFO Epoch: [53][130/150] Time 0.938 (1.021) Data 0.000 (0.084) Loss 0.4899 (0.4849) Prec@1 87.500 (88.213) Prec@5 96.875 (97.036)
[2021-04-26 17:45:45 train_lshot.py:257] INFO Epoch: [53][140/150] Time 0.941 (1.015) Data 0.000 (0.079) Loss 0.4226 (0.4836) Prec@1 90.625 (88.248) Prec@5 97.656 (97.052)
[2021-04-26 17:46:07 train_lshot.py:257] INFO Epoch: [54][0/150] Time 12.905 (12.905) Data 11.946 (11.946) Loss 0.3809 (0.3809) Prec@1 93.359 (93.359) Prec@5 98.438 (98.438)
[2021-04-26 17:46:16 train_lshot.py:257] INFO Epoch: [54][10/150] Time 0.951 (2.024) Data 0.001 (1.086) Loss 0.4503 (0.4722) Prec@1 90.234 (88.636) Prec@5 97.266 (96.982)
[2021-04-26 17:46:26 train_lshot.py:257] INFO Epoch: [54][20/150] Time 0.944 (1.507) Data 0.001 (0.569) Loss 0.4420 (0.4679) Prec@1 91.016 (88.783) Prec@5 98.828 (97.266)
[2021-04-26 17:46:35 train_lshot.py:257] INFO Epoch: [54][30/150] Time 0.948 (1.323) Data 0.001 (0.386) Loss 0.4623 (0.4678) Prec@1 89.453 (88.697) Prec@5 96.875 (97.341)
[2021-04-26 17:46:45 train_lshot.py:257] INFO Epoch: [54][40/150] Time 0.938 (1.229) Data 0.001 (0.292) Loss 0.5205 (0.4711) Prec@1 87.109 (88.653) Prec@5 96.094 (97.170)
[2021-04-26 17:46:54 train_lshot.py:257] INFO Epoch: [54][50/150] Time 0.940 (1.172) Data 0.001 (0.235) Loss 0.4808 (0.4719) Prec@1 89.453 (88.588) Prec@5 97.266 (97.181)
[2021-04-26 17:47:03 train_lshot.py:257] INFO Epoch: [54][60/150] Time 0.939 (1.134) Data 0.001 (0.196) Loss 0.4150 (0.4698) Prec@1 91.016 (88.717) Prec@5 97.266 (97.182)
[2021-04-26 17:47:13 train_lshot.py:257] INFO Epoch: [54][70/150] Time 0.943 (1.107) Data 0.002 (0.169) Loss 0.3792 (0.4691) Prec@1 93.359 (88.859) Prec@5 98.828 (97.189)
[2021-04-26 17:47:22 train_lshot.py:257] INFO Epoch: [54][80/150] Time 0.941 (1.086) Data 0.000 (0.148) Loss 0.4607 (0.4688) Prec@1 88.281 (88.826) Prec@5 98.047 (97.237)
[2021-04-26 17:47:31 train_lshot.py:257] INFO Epoch: [54][90/150] Time 0.933 (1.069) Data 0.000 (0.132) Loss 0.4427 (0.4686) Prec@1 90.234 (88.835) Prec@5 97.266 (97.266)
[2021-04-26 17:47:41 train_lshot.py:257] INFO Epoch: [54][100/150] Time 0.939 (1.056) Data 0.000 (0.119) Loss 0.4362 (0.4704) Prec@1 91.016 (88.780) Prec@5 98.438 (97.258)
[2021-04-26 17:47:50 train_lshot.py:257] INFO Epoch: [54][110/150] Time 0.934 (1.046) Data 0.000 (0.108) Loss 0.5401 (0.4716) Prec@1 84.375 (88.689) Prec@5 94.922 (97.220)
[2021-04-26 17:48:00 train_lshot.py:257] INFO Epoch: [54][120/150] Time 0.942 (1.037) Data 0.000 (0.099) Loss 0.4481 (0.4706) Prec@1 89.844 (88.720) Prec@5 98.047 (97.246)
[2021-04-26 17:48:09 train_lshot.py:257] INFO Epoch: [54][130/150] Time 0.933 (1.029) Data 0.000 (0.092) Loss 0.4783 (0.4709) Prec@1 90.234 (88.737) Prec@5 96.094 (97.221)
[2021-04-26 17:48:18 train_lshot.py:257] INFO Epoch: [54][140/150] Time 0.938 (1.022) Data 0.000 (0.085) Loss 0.5111 (0.4721) Prec@1 85.547 (88.683) Prec@5 96.484 (97.205)
[2021-04-26 17:48:39 train_lshot.py:257] INFO Epoch: [55][0/150] Time 11.487 (11.487) Data 10.531 (10.531) Loss 0.4186 (0.4186) Prec@1 90.234 (90.234) Prec@5 98.047 (98.047)
[2021-04-26 17:48:49 train_lshot.py:257] INFO Epoch: [55][10/150] Time 0.941 (1.924) Data 0.000 (0.987) Loss 0.4004 (0.4542) Prec@1 89.062 (89.134) Prec@5 98.438 (97.053)
[2021-04-26 17:48:58 train_lshot.py:257] INFO Epoch: [55][20/150] Time 0.935 (1.452) Data 0.001 (0.517) Loss 0.5700 (0.4644) Prec@1 82.812 (88.672) Prec@5 97.656 (97.135)
[2021-04-26 17:49:08 train_lshot.py:257] INFO Epoch: [55][30/150] Time 0.937 (1.286) Data 0.001 (0.351) Loss 0.4119 (0.4599) Prec@1 90.625 (89.062) Prec@5 97.266 (97.253)
[2021-04-26 17:49:17 train_lshot.py:257] INFO Epoch: [55][40/150] Time 0.931 (1.200) Data 0.001 (0.265) Loss 0.5165 (0.4676) Prec@1 87.500 (88.777) Prec@5 94.922 (97.075)
[2021-04-26 17:49:26 train_lshot.py:257] INFO Epoch: [55][50/150] Time 0.940 (1.149) Data 0.000 (0.213) Loss 0.4886 (0.4703) Prec@1 84.766 (88.526) Prec@5 97.266 (97.120)
[2021-04-26 17:49:36 train_lshot.py:257] INFO Epoch: [55][60/150] Time 0.941 (1.114) Data 0.000 (0.179) Loss 0.4822 (0.4708) Prec@1 87.891 (88.563) Prec@5 98.438 (97.125)
[2021-04-26 17:49:45 train_lshot.py:257] INFO Epoch: [55][70/150] Time 0.933 (1.089) Data 0.000 (0.153) Loss 0.5233 (0.4718) Prec@1 85.938 (88.507) Prec@5 96.484 (97.128)
[2021-04-26 17:49:54 train_lshot.py:257] INFO Epoch: [55][80/150] Time 0.937 (1.070) Data 0.000 (0.135) Loss 0.4857 (0.4711) Prec@1 89.453 (88.522) Prec@5 97.656 (97.174)
[2021-04-26 17:50:04 train_lshot.py:257] INFO Epoch: [55][90/150] Time 0.938 (1.055) Data 0.000 (0.120) Loss 0.4306 (0.4676) Prec@1 91.406 (88.693) Prec@5 96.094 (97.206)
[2021-04-26 17:50:13 train_lshot.py:257] INFO Epoch: [55][100/150] Time 0.939 (1.043) Data 0.000 (0.108) Loss 0.3760 (0.4670) Prec@1 91.016 (88.718) Prec@5 99.219 (97.235)
[2021-04-26 17:50:22 train_lshot.py:257] INFO Epoch: [55][110/150] Time 0.937 (1.033) Data 0.000 (0.098) Loss 0.4456 (0.4664) Prec@1 90.234 (88.721) Prec@5 96.875 (97.213)
[2021-04-26 17:50:32 train_lshot.py:257] INFO Epoch: [55][120/150] Time 0.931 (1.025) Data 0.000 (0.090) Loss 0.4374 (0.4654) Prec@1 89.844 (88.765) Prec@5 98.438 (97.211)
[2021-04-26 17:50:41 train_lshot.py:257] INFO Epoch: [55][130/150] Time 0.942 (1.018) Data 0.000 (0.083) Loss 0.3890 (0.4666) Prec@1 90.625 (88.684) Prec@5 98.438 (97.209)
[2021-04-26 17:50:51 train_lshot.py:257] INFO Epoch: [55][140/150] Time 0.940 (1.013) Data 0.000 (0.077) Loss 0.4536 (0.4685) Prec@1 88.672 (88.628) Prec@5 98.438 (97.171)
[2021-04-26 17:51:55 train_lshot.py:119] INFO Meta Val 55: 0.6250400131940842
[2021-04-26 17:52:11 train_lshot.py:257] INFO Epoch: [56][0/150] Time 13.600 (13.600) Data 12.650 (12.650) Loss 0.4547 (0.4547) Prec@1 87.109 (87.109) Prec@5 97.266 (97.266)
[2021-04-26 17:52:20 train_lshot.py:257] INFO Epoch: [56][10/150] Time 0.934 (2.087) Data 0.000 (1.150) Loss 0.4740 (0.4652) Prec@1 89.062 (89.098) Prec@5 96.875 (97.159)
[2021-04-26 17:52:29 train_lshot.py:257] INFO Epoch: [56][20/150] Time 0.936 (1.540) Data 0.000 (0.603) Loss 0.4947 (0.4725) Prec@1 86.328 (88.969) Prec@5 96.875 (97.061)
[2021-04-26 17:52:39 train_lshot.py:257] INFO Epoch: [56][30/150] Time 0.930 (1.346) Data 0.000 (0.409) Loss 0.4664 (0.4761) Prec@1 88.281 (88.836) Prec@5 97.266 (96.900)
[2021-04-26 17:52:48 train_lshot.py:257] INFO Epoch: [56][40/150] Time 0.941 (1.246) Data 0.001 (0.309) Loss 0.4264 (0.4787) Prec@1 89.453 (88.510) Prec@5 98.047 (96.875)
[2021-04-26 17:52:57 train_lshot.py:257] INFO Epoch: [56][50/150] Time 0.941 (1.186) Data 0.001 (0.249) Loss 0.4842 (0.4730) Prec@1 89.844 (88.687) Prec@5 98.047 (97.021)
[2021-04-26 17:53:07 train_lshot.py:257] INFO Epoch: [56][60/150] Time 0.944 (1.145) Data 0.001 (0.208) Loss 0.4629 (0.4728) Prec@1 89.844 (88.723) Prec@5 97.656 (97.048)
[2021-04-26 17:53:16 train_lshot.py:257] INFO Epoch: [56][70/150] Time 0.944 (1.116) Data 0.000 (0.179) Loss 0.4766 (0.4699) Prec@1 89.062 (88.815) Prec@5 96.875 (97.079)
[2021-04-26 17:53:26 train_lshot.py:257] INFO Epoch: [56][80/150] Time 0.936 (1.094) Data 0.000 (0.157) Loss 0.4580 (0.4691) Prec@1 89.062 (88.807) Prec@5 97.656 (97.116)
[2021-04-26 17:53:35 train_lshot.py:257] INFO Epoch: [56][90/150] Time 0.932 (1.077) Data 0.000 (0.139) Loss 0.4219 (0.4679) Prec@1 91.016 (88.852) Prec@5 96.484 (97.167)
[2021-04-26 17:53:44 train_lshot.py:257] INFO Epoch: [56][100/150] Time 0.937 (1.063) Data 0.000 (0.126) Loss 0.5328 (0.4674) Prec@1 85.938 (88.823) Prec@5 94.922 (97.146)
[2021-04-26 17:53:54 train_lshot.py:257] INFO Epoch: [56][110/150] Time 0.935 (1.051) Data 0.000 (0.114) Loss 0.4546 (0.4684) Prec@1 89.453 (88.735) Prec@5 98.047 (97.132)
[2021-04-26 17:54:03 train_lshot.py:257] INFO Epoch: [56][120/150] Time 0.941 (1.042) Data 0.000 (0.105) Loss 0.5264 (0.4703) Prec@1 88.672 (88.627) Prec@5 96.875 (97.107)
[2021-04-26 17:54:12 train_lshot.py:257] INFO Epoch: [56][130/150] Time 0.943 (1.034) Data 0.000 (0.097) Loss 0.4646 (0.4725) Prec@1 87.109 (88.565) Prec@5 98.828 (97.114)
[2021-04-26 17:54:22 train_lshot.py:257] INFO Epoch: [56][140/150] Time 0.934 (1.027) Data 0.000 (0.090) Loss 0.4302 (0.4718) Prec@1 90.625 (88.594) Prec@5 98.047 (97.152)
[2021-04-26 17:54:45 train_lshot.py:257] INFO Epoch: [57][0/150] Time 13.618 (13.618) Data 12.670 (12.670) Loss 0.3682 (0.3682) Prec@1 93.359 (93.359) Prec@5 98.047 (98.047)
[2021-04-26 17:54:54 train_lshot.py:257] INFO Epoch: [57][10/150] Time 0.940 (2.088) Data 0.000 (1.152) Loss 0.3835 (0.4542) Prec@1 91.016 (89.382) Prec@5 97.266 (97.479)
[2021-04-26 17:55:04 train_lshot.py:257] INFO Epoch: [57][20/150] Time 0.942 (1.539) Data 0.000 (0.604) Loss 0.5624 (0.4611) Prec@1 85.156 (89.174) Prec@5 95.312 (97.247)
[2021-04-26 17:55:13 train_lshot.py:257] INFO Epoch: [57][30/150] Time 0.941 (1.344) Data 0.001 (0.409) Loss 0.5054 (0.4654) Prec@1 87.500 (89.189) Prec@5 95.703 (97.064)
[2021-04-26 17:55:22 train_lshot.py:257] INFO Epoch: [57][40/150] Time 0.934 (1.244) Data 0.002 (0.310) Loss 0.4034 (0.4647) Prec@1 89.844 (89.129) Prec@5 97.656 (97.094)
[2021-04-26 17:55:32 train_lshot.py:257] INFO Epoch: [57][50/150] Time 0.947 (1.184) Data 0.000 (0.249) Loss 0.5133 (0.4628) Prec@1 86.328 (89.070) Prec@5 96.484 (97.197)
[2021-04-26 17:55:41 train_lshot.py:257] INFO Epoch: [57][60/150] Time 0.943 (1.143) Data 0.000 (0.208) Loss 0.4875 (0.4661) Prec@1 88.281 (88.954) Prec@5 97.266 (97.182)
[2021-04-26 17:55:50 train_lshot.py:257] INFO Epoch: [57][70/150] Time 0.938 (1.114) Data 0.002 (0.179) Loss 0.4350 (0.4604) Prec@1 90.625 (89.118) Prec@5 97.656 (97.266)
[2021-04-26 17:56:00 train_lshot.py:257] INFO Epoch: [57][80/150] Time 0.939 (1.092) Data 0.000 (0.157) Loss 0.4466 (0.4594) Prec@1 88.672 (89.149) Prec@5 98.047 (97.299)
[2021-04-26 17:56:09 train_lshot.py:257] INFO Epoch: [57][90/150] Time 0.931 (1.075) Data 0.000 (0.140) Loss 0.4169 (0.4589) Prec@1 89.453 (89.097) Prec@5 98.047 (97.334)
[2021-04-26 17:56:18 train_lshot.py:257] INFO Epoch: [57][100/150] Time 0.943 (1.061) Data 0.000 (0.126) Loss 0.5153 (0.4637) Prec@1 86.719 (88.981) Prec@5 96.484 (97.239)
[2021-04-26 17:56:28 train_lshot.py:257] INFO Epoch: [57][110/150] Time 0.928 (1.049) Data 0.000 (0.115) Loss 0.5058 (0.4624) Prec@1 89.062 (89.066) Prec@5 97.656 (97.259)
[2021-04-26 17:56:37 train_lshot.py:257] INFO Epoch: [57][120/150] Time 0.936 (1.040) Data 0.000 (0.105) Loss 0.4149 (0.4617) Prec@1 91.016 (89.040) Prec@5 98.438 (97.285)
[2021-04-26 17:56:46 train_lshot.py:257] INFO Epoch: [57][130/150] Time 0.940 (1.032) Data 0.000 (0.097) Loss 0.4227 (0.4609) Prec@1 90.625 (89.092) Prec@5 97.266 (97.310)
[2021-04-26 17:56:56 train_lshot.py:257] INFO Epoch: [57][140/150] Time 0.930 (1.025) Data 0.000 (0.090) Loss 0.4638 (0.4622) Prec@1 89.844 (89.049) Prec@5 97.656 (97.279)
[2021-04-26 17:57:17 train_lshot.py:257] INFO Epoch: [58][0/150] Time 12.125 (12.125) Data 11.177 (11.177) Loss 0.4264 (0.4264) Prec@1 90.234 (90.234) Prec@5 97.266 (97.266)
[2021-04-26 17:57:27 train_lshot.py:257] INFO Epoch: [58][10/150] Time 0.949 (1.957) Data 0.000 (1.021) Loss 0.4861 (0.4679) Prec@1 89.453 (89.098) Prec@5 96.875 (96.768)
[2021-04-26 17:57:36 train_lshot.py:257] INFO Epoch: [58][20/150] Time 0.935 (1.471) Data 0.000 (0.535) Loss 0.5213 (0.4666) Prec@1 86.328 (88.783) Prec@5 95.312 (97.135)
[2021-04-26 17:57:45 train_lshot.py:257] INFO Epoch: [58][30/150] Time 0.944 (1.299) Data 0.000 (0.362) Loss 0.4243 (0.4603) Prec@1 89.453 (89.100) Prec@5 96.484 (97.152)
[2021-04-26 17:57:55 train_lshot.py:257] INFO Epoch: [58][40/150] Time 0.941 (1.211) Data 0.000 (0.274) Loss 0.4778 (0.4558) Prec@1 88.281 (89.186) Prec@5 97.656 (97.275)
[2021-04-26 17:58:04 train_lshot.py:257] INFO Epoch: [58][50/150] Time 0.941 (1.158) Data 0.000 (0.221) Loss 0.4246 (0.4601) Prec@1 88.672 (89.177) Prec@5 97.266 (97.128)
[2021-04-26 17:58:14 train_lshot.py:257] INFO Epoch: [58][60/150] Time 0.940 (1.122) Data 0.000 (0.185) Loss 0.4710 (0.4596) Prec@1 86.328 (89.159) Prec@5 98.047 (97.170)
[2021-04-26 17:58:23 train_lshot.py:257] INFO Epoch: [58][70/150] Time 0.941 (1.096) Data 0.002 (0.159) Loss 0.3719 (0.4585) Prec@1 91.406 (89.239) Prec@5 98.047 (97.189)
[2021-04-26 17:58:32 train_lshot.py:257] INFO Epoch: [58][80/150] Time 0.937 (1.076) Data 0.000 (0.139) Loss 0.4610 (0.4586) Prec@1 88.672 (89.217) Prec@5 97.266 (97.208)
[2021-04-26 17:58:42 train_lshot.py:257] INFO Epoch: [58][90/150] Time 0.936 (1.061) Data 0.000 (0.124) Loss 0.4874 (0.4609) Prec@1 88.281 (89.118) Prec@5 96.484 (97.145)
[2021-04-26 17:58:51 train_lshot.py:257] INFO Epoch: [58][100/150] Time 0.942 (1.049) Data 0.000 (0.112) Loss 0.4799 (0.4633) Prec@1 88.672 (89.012) Prec@5 97.656 (97.111)
[2021-04-26 17:59:01 train_lshot.py:257] INFO Epoch: [58][110/150] Time 0.941 (1.039) Data 0.000 (0.102) Loss 0.4865 (0.4626) Prec@1 88.672 (89.038) Prec@5 98.047 (97.132)
[2021-04-26 17:59:10 train_lshot.py:257] INFO Epoch: [58][120/150] Time 0.935 (1.031) Data 0.000 (0.093) Loss 0.5142 (0.4631) Prec@1 87.891 (88.991) Prec@5 96.484 (97.143)
[2021-04-26 17:59:19 train_lshot.py:257] INFO Epoch: [58][130/150] Time 0.935 (1.024) Data 0.000 (0.086) Loss 0.4863 (0.4623) Prec@1 87.500 (89.021) Prec@5 96.094 (97.140)
[2021-04-26 17:59:29 train_lshot.py:257] INFO Epoch: [58][140/150] Time 0.939 (1.018) Data 0.000 (0.080) Loss 0.4214 (0.4617) Prec@1 88.672 (89.043) Prec@5 98.047 (97.177)
[2021-04-26 17:59:50 train_lshot.py:257] INFO Epoch: [59][0/150] Time 11.712 (11.712) Data 10.746 (10.746) Loss 0.5201 (0.5201) Prec@1 88.281 (88.281) Prec@5 96.094 (96.094)
[2021-04-26 17:59:59 train_lshot.py:257] INFO Epoch: [59][10/150] Time 0.933 (1.913) Data 0.000 (0.977) Loss 0.3597 (0.4514) Prec@1 93.359 (89.879) Prec@5 98.828 (97.337)
[2021-04-26 18:00:08 train_lshot.py:257] INFO Epoch: [59][20/150] Time 0.938 (1.447) Data 0.001 (0.512) Loss 0.4686 (0.4522) Prec@1 89.062 (89.490) Prec@5 97.266 (97.266)
[2021-04-26 18:00:18 train_lshot.py:257] INFO Epoch: [59][30/150] Time 0.934 (1.281) Data 0.001 (0.347) Loss 0.4335 (0.4492) Prec@1 89.453 (89.428) Prec@5 98.047 (97.379)
[2021-04-26 18:00:27 train_lshot.py:257] INFO Epoch: [59][40/150] Time 0.933 (1.197) Data 0.000 (0.263) Loss 0.4733 (0.4513) Prec@1 89.062 (89.301) Prec@5 98.438 (97.361)
[2021-04-26 18:00:37 train_lshot.py:257] INFO Epoch: [59][50/150] Time 0.931 (1.145) Data 0.000 (0.211) Loss 0.4672 (0.4476) Prec@1 88.672 (89.430) Prec@5 97.656 (97.411)
[2021-04-26 18:00:46 train_lshot.py:257] INFO Epoch: [59][60/150] Time 0.933 (1.111) Data 0.001 (0.177) Loss 0.4939 (0.4452) Prec@1 88.281 (89.556) Prec@5 94.922 (97.413)
[2021-04-26 18:00:55 train_lshot.py:257] INFO Epoch: [59][70/150] Time 0.940 (1.086) Data 0.002 (0.152) Loss 0.5343 (0.4451) Prec@1 85.547 (89.613) Prec@5 97.656 (97.469)
[2021-04-26 18:01:05 train_lshot.py:257] INFO Epoch: [59][80/150] Time 0.935 (1.067) Data 0.000 (0.133) Loss 0.4246 (0.4463) Prec@1 89.844 (89.497) Prec@5 96.875 (97.439)
[2021-04-26 18:01:14 train_lshot.py:257] INFO Epoch: [59][90/150] Time 0.939 (1.052) Data 0.000 (0.119) Loss 0.3531 (0.4459) Prec@1 92.578 (89.509) Prec@5 99.609 (97.489)
[2021-04-26 18:01:23 train_lshot.py:257] INFO Epoch: [59][100/150] Time 0.938 (1.041) Data 0.000 (0.107) Loss 0.4922 (0.4457) Prec@1 89.062 (89.527) Prec@5 95.703 (97.455)
[2021-04-26 18:01:33 train_lshot.py:257] INFO Epoch: [59][110/150] Time 0.937 (1.031) Data 0.000 (0.097) Loss 0.4447 (0.4481) Prec@1 88.672 (89.450) Prec@5 96.875 (97.420)
[2021-04-26 18:01:42 train_lshot.py:257] INFO Epoch: [59][120/150] Time 0.929 (1.023) Data 0.000 (0.089) Loss 0.4864 (0.4494) Prec@1 87.891 (89.456) Prec@5 98.047 (97.421)
[2021-04-26 18:01:51 train_lshot.py:257] INFO Epoch: [59][130/150] Time 0.931 (1.016) Data 0.000 (0.082) Loss 0.4280 (0.4499) Prec@1 91.016 (89.438) Prec@5 97.266 (97.403)
[2021-04-26 18:02:01 train_lshot.py:257] INFO Epoch: [59][140/150] Time 0.931 (1.010) Data 0.000 (0.077) Loss 0.4886 (0.4513) Prec@1 87.109 (89.364) Prec@5 97.266 (97.410)
[2021-04-26 18:03:07 train_lshot.py:119] INFO Meta Val 59: 0.6128000133037567
[2021-04-26 18:03:22 train_lshot.py:257] INFO Epoch: [60][0/150] Time 14.037 (14.037) Data 13.081 (13.081) Loss 0.4967 (0.4967) Prec@1 86.328 (86.328) Prec@5 96.875 (96.875)
[2021-04-26 18:03:31 train_lshot.py:257] INFO Epoch: [60][10/150] Time 0.939 (2.123) Data 0.000 (1.189) Loss 0.5058 (0.4555) Prec@1 87.109 (88.885) Prec@5 96.484 (97.053)
[2021-04-26 18:03:40 train_lshot.py:257] INFO Epoch: [60][20/150] Time 0.927 (1.556) Data 0.001 (0.623) Loss 0.5261 (0.4462) Prec@1 88.281 (89.304) Prec@5 94.922 (97.377)
[2021-04-26 18:03:50 train_lshot.py:257] INFO Epoch: [60][30/150] Time 0.931 (1.356) Data 0.000 (0.422) Loss 0.4330 (0.4420) Prec@1 90.625 (89.516) Prec@5 96.484 (97.392)
[2021-04-26 18:03:59 train_lshot.py:257] INFO Epoch: [60][40/150] Time 0.935 (1.253) Data 0.001 (0.319) Loss 0.4239 (0.4357) Prec@1 89.453 (89.872) Prec@5 98.438 (97.570)
[2021-04-26 18:04:08 train_lshot.py:257] INFO Epoch: [60][50/150] Time 0.935 (1.190) Data 0.000 (0.257) Loss 0.4272 (0.4357) Prec@1 90.625 (89.759) Prec@5 96.875 (97.557)
[2021-04-26 18:04:18 train_lshot.py:257] INFO Epoch: [60][60/150] Time 0.938 (1.149) Data 0.000 (0.215) Loss 0.4727 (0.4397) Prec@1 89.453 (89.728) Prec@5 97.656 (97.560)
[2021-04-26 18:04:27 train_lshot.py:257] INFO Epoch: [60][70/150] Time 0.935 (1.119) Data 0.000 (0.185) Loss 0.4985 (0.4430) Prec@1 86.328 (89.629) Prec@5 96.875 (97.464)
[2021-04-26 18:04:36 train_lshot.py:257] INFO Epoch: [60][80/150] Time 0.943 (1.097) Data 0.000 (0.162) Loss 0.4033 (0.4440) Prec@1 90.625 (89.559) Prec@5 96.094 (97.459)
[2021-04-26 18:04:46 train_lshot.py:257] INFO Epoch: [60][90/150] Time 0.931 (1.079) Data 0.000 (0.144) Loss 0.4472 (0.4458) Prec@1 88.672 (89.414) Prec@5 96.875 (97.416)
[2021-04-26 18:04:55 train_lshot.py:257] INFO Epoch: [60][100/150] Time 0.939 (1.065) Data 0.000 (0.130) Loss 0.4487 (0.4482) Prec@1 90.234 (89.356) Prec@5 97.656 (97.362)
[2021-04-26 18:05:05 train_lshot.py:257] INFO Epoch: [60][110/150] Time 0.935 (1.053) Data 0.000 (0.118) Loss 0.4540 (0.4505) Prec@1 90.234 (89.309) Prec@5 96.875 (97.357)
[2021-04-26 18:05:14 train_lshot.py:257] INFO Epoch: [60][120/150] Time 0.928 (1.044) Data 0.000 (0.108) Loss 0.4950 (0.4508) Prec@1 88.672 (89.337) Prec@5 95.312 (97.362)
[2021-04-26 18:05:23 train_lshot.py:257] INFO Epoch: [60][130/150] Time 0.941 (1.036) Data 0.000 (0.100) Loss 0.4060 (0.4500) Prec@1 91.406 (89.408) Prec@5 98.438 (97.364)
[2021-04-26 18:05:33 train_lshot.py:257] INFO Epoch: [60][140/150] Time 0.936 (1.029) Data 0.000 (0.093) Loss 0.4835 (0.4503) Prec@1 86.719 (89.362) Prec@5 97.656 (97.382)
[2021-04-26 18:05:55 train_lshot.py:257] INFO Epoch: [61][0/150] Time 12.600 (12.600) Data 11.614 (11.614) Loss 0.4736 (0.4736) Prec@1 89.844 (89.844) Prec@5 97.656 (97.656)
[2021-04-26 18:06:04 train_lshot.py:257] INFO Epoch: [61][10/150] Time 0.940 (1.996) Data 0.000 (1.056) Loss 0.4338 (0.4388) Prec@1 91.797 (90.057) Prec@5 98.438 (97.692)
[2021-04-26 18:06:13 train_lshot.py:257] INFO Epoch: [61][20/150] Time 0.936 (1.492) Data 0.000 (0.553) Loss 0.4925 (0.4460) Prec@1 87.109 (89.360) Prec@5 96.484 (97.638)
[2021-04-26 18:06:23 train_lshot.py:257] INFO Epoch: [61][30/150] Time 0.937 (1.313) Data 0.000 (0.375) Loss 0.4105 (0.4453) Prec@1 90.625 (89.415) Prec@5 99.609 (97.644)
[2021-04-26 18:06:32 train_lshot.py:257] INFO Epoch: [61][40/150] Time 0.935 (1.221) Data 0.001 (0.284) Loss 0.4437 (0.4432) Prec@1 91.406 (89.520) Prec@5 97.656 (97.618)
[2021-04-26 18:06:42 train_lshot.py:257] INFO Epoch: [61][50/150] Time 0.938 (1.164) Data 0.000 (0.228) Loss 0.4591 (0.4405) Prec@1 89.453 (89.599) Prec@5 95.703 (97.572)
[2021-04-26 18:06:51 train_lshot.py:257] INFO Epoch: [61][60/150] Time 0.931 (1.127) Data 0.000 (0.191) Loss 0.5295 (0.4423) Prec@1 87.109 (89.620) Prec@5 96.875 (97.547)
[2021-04-26 18:07:00 train_lshot.py:257] INFO Epoch: [61][70/150] Time 0.937 (1.100) Data 0.000 (0.164) Loss 0.4035 (0.4408) Prec@1 89.844 (89.629) Prec@5 97.656 (97.590)
[2021-04-26 18:07:10 train_lshot.py:257] INFO Epoch: [61][80/150] Time 0.931 (1.079) Data 0.000 (0.144) Loss 0.4319 (0.4412) Prec@1 90.234 (89.675) Prec@5 98.438 (97.589)
[2021-04-26 18:07:19 train_lshot.py:257] INFO Epoch: [61][90/150] Time 0.929 (1.064) Data 0.000 (0.128) Loss 0.4318 (0.4423) Prec@1 89.453 (89.668) Prec@5 96.875 (97.536)
[2021-04-26 18:07:28 train_lshot.py:257] INFO Epoch: [61][100/150] Time 0.925 (1.050) Data 0.000 (0.115) Loss 0.4622 (0.4440) Prec@1 88.281 (89.608) Prec@5 95.312 (97.471)
[2021-04-26 18:07:38 train_lshot.py:257] INFO Epoch: [61][110/150] Time 0.933 (1.040) Data 0.000 (0.105) Loss 0.5072 (0.4439) Prec@1 88.672 (89.636) Prec@5 96.875 (97.480)
[2021-04-26 18:07:47 train_lshot.py:257] INFO Epoch: [61][120/150] Time 0.937 (1.031) Data 0.000 (0.096) Loss 0.4807 (0.4457) Prec@1 87.500 (89.585) Prec@5 97.266 (97.463)
[2021-04-26 18:07:56 train_lshot.py:257] INFO Epoch: [61][130/150] Time 0.930 (1.024) Data 0.000 (0.089) Loss 0.4599 (0.4452) Prec@1 88.281 (89.605) Prec@5 97.266 (97.465)
[2021-04-26 18:08:06 train_lshot.py:257] INFO Epoch: [61][140/150] Time 0.938 (1.017) Data 0.000 (0.083) Loss 0.4991 (0.4466) Prec@1 88.281 (89.520) Prec@5 96.484 (97.437)
[2021-04-26 18:08:31 train_lshot.py:257] INFO Epoch: [62][0/150] Time 16.358 (16.358) Data 15.406 (15.406) Loss 0.4102 (0.4102) Prec@1 89.453 (89.453) Prec@5 97.656 (97.656)
[2021-04-26 18:08:41 train_lshot.py:257] INFO Epoch: [62][10/150] Time 0.925 (2.333) Data 0.000 (1.401) Loss 0.5088 (0.4388) Prec@1 86.719 (89.560) Prec@5 96.094 (97.301)
[2021-04-26 18:08:50 train_lshot.py:257] INFO Epoch: [62][20/150] Time 0.932 (1.666) Data 0.000 (0.734) Loss 0.5245 (0.4387) Prec@1 86.719 (89.528) Prec@5 95.703 (97.377)
[2021-04-26 18:08:59 train_lshot.py:257] INFO Epoch: [62][30/150] Time 0.928 (1.429) Data 0.000 (0.497) Loss 0.3970 (0.4382) Prec@1 91.406 (89.617) Prec@5 97.656 (97.366)
[2021-04-26 18:09:09 train_lshot.py:257] INFO Epoch: [62][40/150] Time 0.934 (1.309) Data 0.000 (0.376) Loss 0.5706 (0.4362) Prec@1 85.547 (89.701) Prec@5 95.312 (97.428)
[2021-04-26 18:09:18 train_lshot.py:257] INFO Epoch: [62][50/150] Time 0.936 (1.235) Data 0.001 (0.303) Loss 0.4493 (0.4402) Prec@1 89.062 (89.514) Prec@5 95.703 (97.358)
[2021-04-26 18:09:27 train_lshot.py:257] INFO Epoch: [62][60/150] Time 0.939 (1.186) Data 0.000 (0.253) Loss 0.4925 (0.4420) Prec@1 86.328 (89.556) Prec@5 96.484 (97.349)
[2021-04-26 18:09:37 train_lshot.py:257] INFO Epoch: [62][70/150] Time 0.932 (1.151) Data 0.000 (0.218) Loss 0.4521 (0.4441) Prec@1 91.016 (89.486) Prec@5 96.875 (97.288)
[2021-04-26 18:09:46 train_lshot.py:257] INFO Epoch: [62][80/150] Time 0.939 (1.125) Data 0.000 (0.191) Loss 0.4556 (0.4467) Prec@1 89.062 (89.477) Prec@5 97.266 (97.261)
[2021-04-26 18:09:56 train_lshot.py:257] INFO Epoch: [62][90/150] Time 0.938 (1.104) Data 0.000 (0.170) Loss 0.4340 (0.4473) Prec@1 90.234 (89.432) Prec@5 98.047 (97.257)
[2021-04-26 18:10:05 train_lshot.py:257] INFO Epoch: [62][100/150] Time 0.940 (1.087) Data 0.000 (0.153) Loss 0.4612 (0.4475) Prec@1 88.281 (89.337) Prec@5 98.047 (97.324)
[2021-04-26 18:10:14 train_lshot.py:257] INFO Epoch: [62][110/150] Time 0.937 (1.073) Data 0.000 (0.139) Loss 0.4354 (0.4462) Prec@1 90.625 (89.436) Prec@5 97.266 (97.368)
[2021-04-26 18:10:24 train_lshot.py:257] INFO Epoch: [62][120/150] Time 0.942 (1.062) Data 0.000 (0.128) Loss 0.4602 (0.4481) Prec@1 91.406 (89.376) Prec@5 97.656 (97.333)
[2021-04-26 18:10:33 train_lshot.py:257] INFO Epoch: [62][130/150] Time 0.935 (1.053) Data 0.000 (0.118) Loss 0.5369 (0.4471) Prec@1 85.156 (89.444) Prec@5 96.094 (97.361)
[2021-04-26 18:10:42 train_lshot.py:257] INFO Epoch: [62][140/150] Time 0.941 (1.044) Data 0.000 (0.110) Loss 0.4219 (0.4459) Prec@1 89.062 (89.473) Prec@5 97.266 (97.379)
[2021-04-26 18:11:04 train_lshot.py:257] INFO Epoch: [63][0/150] Time 12.718 (12.718) Data 11.766 (11.766) Loss 0.4722 (0.4722) Prec@1 89.453 (89.453) Prec@5 96.875 (96.875)
[2021-04-26 18:11:14 train_lshot.py:257] INFO Epoch: [63][10/150] Time 0.937 (2.007) Data 0.000 (1.070) Loss 0.4737 (0.4273) Prec@1 88.672 (89.844) Prec@5 98.828 (97.834)
[2021-04-26 18:11:23 train_lshot.py:257] INFO Epoch: [63][20/150] Time 0.929 (1.498) Data 0.000 (0.561) Loss 0.4579 (0.4326) Prec@1 89.062 (89.974) Prec@5 96.484 (97.619)
[2021-04-26 18:11:33 train_lshot.py:257] INFO Epoch: [63][30/150] Time 0.935 (1.317) Data 0.001 (0.380) Loss 0.3942 (0.4304) Prec@1 92.578 (90.134) Prec@5 96.875 (97.530)
[2021-04-26 18:11:42 train_lshot.py:257] INFO Epoch: [63][40/150] Time 0.933 (1.224) Data 0.000 (0.287) Loss 0.4272 (0.4249) Prec@1 91.016 (90.244) Prec@5 98.438 (97.647)
[2021-04-26 18:11:51 train_lshot.py:257] INFO Epoch: [63][50/150] Time 0.936 (1.168) Data 0.000 (0.231) Loss 0.4200 (0.4247) Prec@1 90.234 (90.349) Prec@5 96.094 (97.641)
[2021-04-26 18:12:01 train_lshot.py:257] INFO Epoch: [63][60/150] Time 0.942 (1.130) Data 0.000 (0.193) Loss 0.4624 (0.4281) Prec@1 88.672 (90.190) Prec@5 97.266 (97.464)
[2021-04-26 18:12:10 train_lshot.py:257] INFO Epoch: [63][70/150] Time 0.937 (1.103) Data 0.000 (0.166) Loss 0.4319 (0.4304) Prec@1 89.453 (90.146) Prec@5 97.656 (97.409)
[2021-04-26 18:12:19 train_lshot.py:257] INFO Epoch: [63][80/150] Time 0.936 (1.082) Data 0.000 (0.146) Loss 0.4749 (0.4355) Prec@1 90.234 (89.931) Prec@5 96.484 (97.323)
[2021-04-26 18:12:29 train_lshot.py:257] INFO Epoch: [63][90/150] Time 0.941 (1.066) Data 0.000 (0.130) Loss 0.4041 (0.4395) Prec@1 92.578 (89.766) Prec@5 96.484 (97.253)
[2021-04-26 18:12:38 train_lshot.py:257] INFO Epoch: [63][100/150] Time 0.931 (1.053) Data 0.000 (0.117) Loss 0.4354 (0.4402) Prec@1 89.453 (89.770) Prec@5 98.438 (97.266)
[2021-04-26 18:12:48 train_lshot.py:257] INFO Epoch: [63][110/150] Time 0.935 (1.043) Data 0.000 (0.106) Loss 0.4550 (0.4392) Prec@1 88.672 (89.787) Prec@5 98.828 (97.336)
[2021-04-26 18:12:57 train_lshot.py:257] INFO Epoch: [63][120/150] Time 0.934 (1.034) Data 0.000 (0.098) Loss 0.3673 (0.4400) Prec@1 93.359 (89.786) Prec@5 97.656 (97.346)
[2021-04-26 18:13:06 train_lshot.py:257] INFO Epoch: [63][130/150] Time 0.935 (1.026) Data 0.000 (0.090) Loss 0.5614 (0.4431) Prec@1 85.938 (89.677) Prec@5 94.531 (97.269)
[2021-04-26 18:13:16 train_lshot.py:257] INFO Epoch: [63][140/150] Time 0.926 (1.019) Data 0.000 (0.084) Loss 0.4048 (0.4438) Prec@1 90.625 (89.672) Prec@5 98.438 (97.257)
[2021-04-26 18:14:21 train_lshot.py:119] INFO Meta Val 63: 0.6110133471488952
[2021-04-26 18:14:35 train_lshot.py:257] INFO Epoch: [64][0/150] Time 12.936 (12.936) Data 11.987 (11.987) Loss 0.4132 (0.4132) Prec@1 90.234 (90.234) Prec@5 97.656 (97.656)
[2021-04-26 18:14:44 train_lshot.py:257] INFO Epoch: [64][10/150] Time 0.935 (2.019) Data 0.000 (1.090) Loss 0.4060 (0.4006) Prec@1 90.234 (91.122) Prec@5 98.828 (97.976)
[2021-04-26 18:14:54 train_lshot.py:257] INFO Epoch: [64][20/150] Time 0.939 (1.501) Data 0.000 (0.571) Loss 0.4871 (0.4150) Prec@1 89.844 (90.588) Prec@5 95.703 (97.861)
[2021-04-26 18:15:03 train_lshot.py:257] INFO Epoch: [64][30/150] Time 0.938 (1.318) Data 0.000 (0.387) Loss 0.4207 (0.4223) Prec@1 90.625 (90.398) Prec@5 97.266 (97.757)
[2021-04-26 18:15:12 train_lshot.py:257] INFO Epoch: [64][40/150] Time 0.934 (1.224) Data 0.000 (0.293) Loss 0.4567 (0.4223) Prec@1 89.062 (90.415) Prec@5 96.875 (97.647)
[2021-04-26 18:15:22 train_lshot.py:257] INFO Epoch: [64][50/150] Time 0.937 (1.167) Data 0.001 (0.236) Loss 0.4746 (0.4245) Prec@1 89.844 (90.219) Prec@5 96.484 (97.718)
[2021-04-26 18:15:31 train_lshot.py:257] INFO Epoch: [64][60/150] Time 0.932 (1.128) Data 0.001 (0.197) Loss 0.4242 (0.4253) Prec@1 93.750 (90.273) Prec@5 98.047 (97.675)
[2021-04-26 18:15:40 train_lshot.py:257] INFO Epoch: [64][70/150] Time 0.930 (1.101) Data 0.000 (0.169) Loss 0.5008 (0.4302) Prec@1 88.672 (90.075) Prec@5 96.875 (97.601)
[2021-04-26 18:15:50 train_lshot.py:257] INFO Epoch: [64][80/150] Time 0.936 (1.081) Data 0.000 (0.148) Loss 0.4170 (0.4330) Prec@1 90.625 (89.950) Prec@5 97.266 (97.598)
[2021-04-26 18:15:59 train_lshot.py:257] INFO Epoch: [64][90/150] Time 0.940 (1.064) Data 0.000 (0.132) Loss 0.4855 (0.4340) Prec@1 86.719 (89.870) Prec@5 97.266 (97.558)
[2021-04-26 18:16:08 train_lshot.py:257] INFO Epoch: [64][100/150] Time 0.935 (1.052) Data 0.000 (0.119) Loss 0.4589 (0.4344) Prec@1 86.719 (89.828) Prec@5 97.656 (97.517)
[2021-04-26 18:16:18 train_lshot.py:257] INFO Epoch: [64][110/150] Time 0.937 (1.041) Data 0.000 (0.108) Loss 0.4145 (0.4364) Prec@1 90.625 (89.724) Prec@5 96.875 (97.449)
[2021-04-26 18:16:27 train_lshot.py:257] INFO Epoch: [64][120/150] Time 0.938 (1.033) Data 0.000 (0.099) Loss 0.4416 (0.4372) Prec@1 91.797 (89.702) Prec@5 98.047 (97.456)
[2021-04-26 18:16:37 train_lshot.py:257] INFO Epoch: [64][130/150] Time 0.935 (1.025) Data 0.000 (0.092) Loss 0.4404 (0.4352) Prec@1 89.062 (89.754) Prec@5 97.656 (97.468)
[2021-04-26 18:16:46 train_lshot.py:257] INFO Epoch: [64][140/150] Time 0.936 (1.019) Data 0.000 (0.085) Loss 0.4781 (0.4364) Prec@1 90.234 (89.738) Prec@5 96.484 (97.446)
[2021-04-26 18:17:07 train_lshot.py:257] INFO Epoch: [65][0/150] Time 12.210 (12.210) Data 11.225 (11.225) Loss 0.4747 (0.4747) Prec@1 88.672 (88.672) Prec@5 95.703 (95.703)
[2021-04-26 18:17:17 train_lshot.py:257] INFO Epoch: [65][10/150] Time 0.933 (1.959) Data 0.000 (1.021) Loss 0.4388 (0.4157) Prec@1 89.844 (90.412) Prec@5 96.094 (97.479)
[2021-04-26 18:17:26 train_lshot.py:257] INFO Epoch: [65][20/150] Time 0.927 (1.472) Data 0.000 (0.535) Loss 0.4699 (0.4194) Prec@1 90.625 (90.402) Prec@5 96.875 (97.563)
[2021-04-26 18:17:36 train_lshot.py:257] INFO Epoch: [65][30/150] Time 0.940 (1.300) Data 0.000 (0.362) Loss 0.4604 (0.4268) Prec@1 90.234 (90.146) Prec@5 98.438 (97.555)
[2021-04-26 18:17:45 train_lshot.py:257] INFO Epoch: [65][40/150] Time 0.934 (1.211) Data 0.001 (0.274) Loss 0.4177 (0.4312) Prec@1 90.234 (89.863) Prec@5 98.047 (97.628)
[2021-04-26 18:17:54 train_lshot.py:257] INFO Epoch: [65][50/150] Time 0.932 (1.157) Data 0.000 (0.221) Loss 0.4316 (0.4333) Prec@1 88.672 (89.798) Prec@5 98.438 (97.610)
[2021-04-26 18:18:04 train_lshot.py:257] INFO Epoch: [65][60/150] Time 0.930 (1.121) Data 0.000 (0.184) Loss 0.3978 (0.4316) Prec@1 89.844 (89.895) Prec@5 98.438 (97.669)
[2021-04-26 18:18:13 train_lshot.py:257] INFO Epoch: [65][70/150] Time 0.939 (1.095) Data 0.000 (0.159) Loss 0.4827 (0.4342) Prec@1 88.672 (89.833) Prec@5 96.875 (97.596)
[2021-04-26 18:18:22 train_lshot.py:257] INFO Epoch: [65][80/150] Time 0.936 (1.075) Data 0.000 (0.139) Loss 0.3814 (0.4322) Prec@1 91.797 (89.868) Prec@5 98.047 (97.637)
[2021-04-26 18:18:32 train_lshot.py:257] INFO Epoch: [65][90/150] Time 0.935 (1.060) Data 0.000 (0.124) Loss 0.4732 (0.4326) Prec@1 88.281 (89.835) Prec@5 96.484 (97.635)
[2021-04-26 18:18:41 train_lshot.py:257] INFO Epoch: [65][100/150] Time 0.936 (1.048) Data 0.000 (0.112) Loss 0.4611 (0.4340) Prec@1 88.281 (89.774) Prec@5 97.656 (97.610)
[2021-04-26 18:18:50 train_lshot.py:257] INFO Epoch: [65][110/150] Time 0.935 (1.037) Data 0.000 (0.101) Loss 0.4636 (0.4349) Prec@1 88.672 (89.745) Prec@5 97.656 (97.607)
[2021-04-26 18:19:00 train_lshot.py:257] INFO Epoch: [65][120/150] Time 0.929 (1.029) Data 0.000 (0.093) Loss 0.4785 (0.4361) Prec@1 88.281 (89.744) Prec@5 96.875 (97.585)
[2021-04-26 18:19:09 train_lshot.py:257] INFO Epoch: [65][130/150] Time 0.933 (1.022) Data 0.000 (0.086) Loss 0.3944 (0.4364) Prec@1 91.406 (89.745) Prec@5 99.219 (97.570)
[2021-04-26 18:19:19 train_lshot.py:257] INFO Epoch: [65][140/150] Time 0.939 (1.016) Data 0.000 (0.080) Loss 0.3981 (0.4366) Prec@1 91.406 (89.716) Prec@5 99.219 (97.562)
[2021-04-26 18:19:39 train_lshot.py:257] INFO Epoch: [66][0/150] Time 11.484 (11.484) Data 10.547 (10.547) Loss 0.5052 (0.5052) Prec@1 87.109 (87.109) Prec@5 96.484 (96.484)
[2021-04-26 18:19:49 train_lshot.py:257] INFO Epoch: [66][10/150] Time 0.931 (1.892) Data 0.000 (0.959) Loss 0.4660 (0.4308) Prec@1 89.844 (90.589) Prec@5 97.656 (97.372)
[2021-04-26 18:19:58 train_lshot.py:257] INFO Epoch: [66][20/150] Time 0.938 (1.437) Data 0.000 (0.503) Loss 0.3594 (0.4358) Prec@1 92.188 (90.309) Prec@5 98.438 (97.452)
[2021-04-26 18:20:07 train_lshot.py:257] INFO Epoch: [66][30/150] Time 0.939 (1.274) Data 0.000 (0.341) Loss 0.3964 (0.4352) Prec@1 91.406 (90.108) Prec@5 98.438 (97.669)
[2021-04-26 18:20:17 train_lshot.py:257] INFO Epoch: [66][40/150] Time 0.937 (1.191) Data 0.001 (0.258) Loss 0.3665 (0.4319) Prec@1 94.141 (90.263) Prec@5 98.828 (97.647)
[2021-04-26 18:20:26 train_lshot.py:257] INFO Epoch: [66][50/150] Time 0.928 (1.141) Data 0.000 (0.207) Loss 0.4188 (0.4313) Prec@1 92.188 (90.288) Prec@5 98.438 (97.649)
[2021-04-26 18:20:35 train_lshot.py:257] INFO Epoch: [66][60/150] Time 0.931 (1.107) Data 0.000 (0.173) Loss 0.4234 (0.4299) Prec@1 89.844 (90.318) Prec@5 98.047 (97.611)
[2021-04-26 18:20:45 train_lshot.py:257] INFO Epoch: [66][70/150] Time 0.942 (1.083) Data 0.000 (0.149) Loss 0.4012 (0.4294) Prec@1 89.844 (90.394) Prec@5 98.047 (97.590)
[2021-04-26 18:20:54 train_lshot.py:257] INFO Epoch: [66][80/150] Time 0.933 (1.065) Data 0.000 (0.131) Loss 0.4457 (0.4251) Prec@1 89.844 (90.504) Prec@5 97.656 (97.676)
[2021-04-26 18:21:04 train_lshot.py:257] INFO Epoch: [66][90/150] Time 0.929 (1.050) Data 0.000 (0.116) Loss 0.4488 (0.4262) Prec@1 90.234 (90.432) Prec@5 96.094 (97.639)
[2021-04-26 18:21:13 train_lshot.py:257] INFO Epoch: [66][100/150] Time 0.938 (1.039) Data 0.000 (0.105) Loss 0.4316 (0.4267) Prec@1 90.234 (90.408) Prec@5 96.484 (97.590)
[2021-04-26 18:21:22 train_lshot.py:257] INFO Epoch: [66][110/150] Time 0.941 (1.030) Data 0.000 (0.095) Loss 0.4000 (0.4264) Prec@1 91.797 (90.382) Prec@5 97.656 (97.582)
[2021-04-26 18:21:32 train_lshot.py:257] INFO Epoch: [66][120/150] Time 0.939 (1.022) Data 0.000 (0.088) Loss 0.4238 (0.4286) Prec@1 89.844 (90.341) Prec@5 98.047 (97.524)
[2021-04-26 18:21:41 train_lshot.py:257] INFO Epoch: [66][130/150] Time 0.933 (1.015) Data 0.000 (0.081) Loss 0.3719 (0.4288) Prec@1 92.578 (90.258) Prec@5 98.438 (97.528)
[2021-04-26 18:21:50 train_lshot.py:257] INFO Epoch: [66][140/150] Time 0.933 (1.010) Data 0.000 (0.075) Loss 0.3916 (0.4275) Prec@1 90.625 (90.306) Prec@5 98.438 (97.540)
[2021-04-26 18:22:13 train_lshot.py:257] INFO Epoch: [67][0/150] Time 13.585 (13.585) Data 12.618 (12.618) Loss 0.4205 (0.4205) Prec@1 90.625 (90.625) Prec@5 97.656 (97.656)
[2021-04-26 18:22:23 train_lshot.py:257] INFO Epoch: [67][10/150] Time 0.930 (2.083) Data 0.000 (1.147) Loss 0.4625 (0.4238) Prec@1 89.844 (90.305) Prec@5 96.484 (97.656)
[2021-04-26 18:22:32 train_lshot.py:257] INFO Epoch: [67][20/150] Time 0.935 (1.537) Data 0.001 (0.601) Loss 0.4471 (0.4353) Prec@1 91.406 (90.216) Prec@5 96.875 (97.247)
[2021-04-26 18:22:41 train_lshot.py:257] INFO Epoch: [67][30/150] Time 0.934 (1.342) Data 0.001 (0.408) Loss 0.4418 (0.4340) Prec@1 91.016 (90.096) Prec@5 96.875 (97.366)
[2021-04-26 18:22:51 train_lshot.py:257] INFO Epoch: [67][40/150] Time 0.938 (1.243) Data 0.001 (0.308) Loss 0.4040 (0.4335) Prec@1 91.406 (90.044) Prec@5 99.219 (97.361)
[2021-04-26 18:23:00 train_lshot.py:257] INFO Epoch: [67][50/150] Time 0.929 (1.183) Data 0.000 (0.248) Loss 0.4569 (0.4329) Prec@1 88.281 (89.982) Prec@5 96.484 (97.411)
[2021-04-26 18:23:09 train_lshot.py:257] INFO Epoch: [67][60/150] Time 0.937 (1.143) Data 0.000 (0.207) Loss 0.4038 (0.4350) Prec@1 90.234 (89.793) Prec@5 98.047 (97.400)
[2021-04-26 18:23:19 train_lshot.py:257] INFO Epoch: [67][70/150] Time 0.935 (1.114) Data 0.000 (0.178) Loss 0.4759 (0.4368) Prec@1 88.672 (89.767) Prec@5 96.484 (97.370)
[2021-04-26 18:23:28 train_lshot.py:257] INFO Epoch: [67][80/150] Time 0.944 (1.092) Data 0.000 (0.156) Loss 0.4309 (0.4354) Prec@1 90.625 (89.839) Prec@5 97.266 (97.386)
[2021-04-26 18:23:38 train_lshot.py:257] INFO Epoch: [67][90/150] Time 0.936 (1.075) Data 0.000 (0.139) Loss 0.3804 (0.4353) Prec@1 89.844 (89.809) Prec@5 99.219 (97.360)
[2021-04-26 18:23:47 train_lshot.py:257] INFO Epoch: [67][100/150] Time 0.938 (1.061) Data 0.000 (0.125) Loss 0.3891 (0.4349) Prec@1 91.016 (89.774) Prec@5 97.656 (97.374)
[2021-04-26 18:23:56 train_lshot.py:257] INFO Epoch: [67][110/150] Time 0.938 (1.050) Data 0.000 (0.114) Loss 0.5215 (0.4363) Prec@1 87.109 (89.703) Prec@5 95.312 (97.368)
[2021-04-26 18:24:06 train_lshot.py:257] INFO Epoch: [67][120/150] Time 0.934 (1.041) Data 0.000 (0.105) Loss 0.4141 (0.4346) Prec@1 91.016 (89.763) Prec@5 97.656 (97.372)
[2021-04-26 18:24:15 train_lshot.py:257] INFO Epoch: [67][130/150] Time 0.938 (1.033) Data 0.000 (0.097) Loss 0.3966 (0.4348) Prec@1 93.750 (89.781) Prec@5 97.656 (97.364)
[2021-04-26 18:24:24 train_lshot.py:257] INFO Epoch: [67][140/150] Time 0.927 (1.026) Data 0.000 (0.090) Loss 0.4414 (0.4340) Prec@1 89.844 (89.758) Prec@5 96.875 (97.388)
[2021-04-26 18:25:30 train_lshot.py:119] INFO Meta Val 67: 0.614053346812725
[2021-04-26 18:25:45 train_lshot.py:257] INFO Epoch: [68][0/150] Time 14.133 (14.133) Data 13.182 (13.182) Loss 0.3942 (0.3942) Prec@1 90.625 (90.625) Prec@5 98.828 (98.828)
[2021-04-26 18:25:54 train_lshot.py:257] INFO Epoch: [68][10/150] Time 0.940 (2.132) Data 0.000 (1.199) Loss 0.4550 (0.4222) Prec@1 91.016 (90.021) Prec@5 96.875 (97.621)
[2021-04-26 18:26:04 train_lshot.py:257] INFO Epoch: [68][20/150] Time 0.931 (1.560) Data 0.000 (0.628) Loss 0.4145 (0.4168) Prec@1 88.672 (90.086) Prec@5 98.828 (97.731)
[2021-04-26 18:26:13 train_lshot.py:257] INFO Epoch: [68][30/150] Time 0.932 (1.357) Data 0.000 (0.426) Loss 0.4152 (0.4214) Prec@1 90.625 (89.932) Prec@5 96.484 (97.669)
[2021-04-26 18:26:23 train_lshot.py:257] INFO Epoch: [68][40/150] Time 0.935 (1.258) Data 0.001 (0.327) Loss 0.4762 (0.4253) Prec@1 87.109 (89.729) Prec@5 97.656 (97.618)
[2021-04-26 18:26:32 train_lshot.py:257] INFO Epoch: [68][50/150] Time 0.931 (1.193) Data 0.000 (0.263) Loss 0.4363 (0.4233) Prec@1 90.625 (89.943) Prec@5 97.656 (97.664)
[2021-04-26 18:26:41 train_lshot.py:257] INFO Epoch: [68][60/150] Time 0.927 (1.151) Data 0.000 (0.220) Loss 0.4638 (0.4208) Prec@1 86.328 (90.068) Prec@5 97.656 (97.656)
[2021-04-26 18:26:51 train_lshot.py:257] INFO Epoch: [68][70/150] Time 0.932 (1.120) Data 0.000 (0.189) Loss 0.4229 (0.4190) Prec@1 89.453 (90.113) Prec@5 97.656 (97.651)
[2021-04-26 18:27:00 train_lshot.py:257] INFO Epoch: [68][80/150] Time 0.926 (1.097) Data 0.000 (0.166) Loss 0.3441 (0.4168) Prec@1 91.797 (90.234) Prec@5 99.219 (97.704)
[2021-04-26 18:27:09 train_lshot.py:257] INFO Epoch: [68][90/150] Time 0.934 (1.079) Data 0.000 (0.148) Loss 0.4431 (0.4172) Prec@1 89.453 (90.239) Prec@5 97.266 (97.712)
[2021-04-26 18:27:19 train_lshot.py:257] INFO Epoch: [68][100/150] Time 0.930 (1.065) Data 0.000 (0.133) Loss 0.3043 (0.4148) Prec@1 95.312 (90.354) Prec@5 99.219 (97.718)
[2021-04-26 18:27:28 train_lshot.py:257] INFO Epoch: [68][110/150] Time 0.935 (1.053) Data 0.000 (0.121) Loss 0.4412 (0.4173) Prec@1 90.234 (90.361) Prec@5 97.656 (97.698)
[2021-04-26 18:27:37 train_lshot.py:257] INFO Epoch: [68][120/150] Time 0.935 (1.043) Data 0.000 (0.111) Loss 0.4549 (0.4173) Prec@1 89.453 (90.380) Prec@5 97.266 (97.692)
[2021-04-26 18:27:47 train_lshot.py:257] INFO Epoch: [68][130/150] Time 0.941 (1.035) Data 0.000 (0.103) Loss 0.4447 (0.4166) Prec@1 88.281 (90.416) Prec@5 98.047 (97.713)
[2021-04-26 18:27:56 train_lshot.py:257] INFO Epoch: [68][140/150] Time 0.935 (1.028) Data 0.000 (0.095) Loss 0.3903 (0.4154) Prec@1 91.797 (90.470) Prec@5 96.875 (97.717)
[2021-04-26 18:28:22 train_lshot.py:257] INFO Epoch: [69][0/150] Time 16.718 (16.718) Data 15.767 (15.767) Loss 0.4666 (0.4666) Prec@1 89.453 (89.453) Prec@5 95.312 (95.312)
[2021-04-26 18:28:31 train_lshot.py:257] INFO Epoch: [69][10/150] Time 0.936 (2.368) Data 0.000 (1.434) Loss 0.4219 (0.4340) Prec@1 90.234 (89.524) Prec@5 97.266 (97.017)
[2021-04-26 18:28:41 train_lshot.py:257] INFO Epoch: [69][20/150] Time 0.932 (1.686) Data 0.001 (0.752) Loss 0.3822 (0.4209) Prec@1 89.844 (90.141) Prec@5 98.438 (97.507)
[2021-04-26 18:28:50 train_lshot.py:257] INFO Epoch: [69][30/150] Time 0.938 (1.444) Data 0.000 (0.509) Loss 0.3972 (0.4104) Prec@1 92.578 (90.587) Prec@5 99.219 (97.757)
[2021-04-26 18:28:59 train_lshot.py:257] INFO Epoch: [69][40/150] Time 0.932 (1.320) Data 0.000 (0.385) Loss 0.4466 (0.4118) Prec@1 88.281 (90.520) Prec@5 98.438 (97.799)
[2021-04-26 18:29:09 train_lshot.py:257] INFO Epoch: [69][50/150] Time 0.936 (1.244) Data 0.000 (0.310) Loss 0.4212 (0.4103) Prec@1 89.453 (90.625) Prec@5 96.484 (97.725)
[2021-04-26 18:29:18 train_lshot.py:257] INFO Epoch: [69][60/150] Time 0.941 (1.194) Data 0.000 (0.259) Loss 0.4058 (0.4067) Prec@1 89.844 (90.759) Prec@5 98.828 (97.778)
[2021-04-26 18:29:28 train_lshot.py:257] INFO Epoch: [69][70/150] Time 0.934 (1.159) Data 0.002 (0.223) Loss 0.3879 (0.4090) Prec@1 91.406 (90.686) Prec@5 98.438 (97.750)
[2021-04-26 18:29:37 train_lshot.py:257] INFO Epoch: [69][80/150] Time 0.941 (1.131) Data 0.000 (0.196) Loss 0.3661 (0.4081) Prec@1 93.750 (90.702) Prec@5 99.609 (97.806)
[2021-04-26 18:29:46 train_lshot.py:257] INFO Epoch: [69][90/150] Time 0.929 (1.110) Data 0.000 (0.174) Loss 0.4129 (0.4067) Prec@1 90.625 (90.805) Prec@5 96.484 (97.862)
[2021-04-26 18:29:56 train_lshot.py:257] INFO Epoch: [69][100/150] Time 0.931 (1.093) Data 0.000 (0.157) Loss 0.3918 (0.4065) Prec@1 91.406 (90.784) Prec@5 98.438 (97.838)
[2021-04-26 18:30:05 train_lshot.py:257] INFO Epoch: [69][110/150] Time 0.941 (1.079) Data 0.000 (0.143) Loss 0.4951 (0.4085) Prec@1 88.672 (90.716) Prec@5 94.922 (97.811)
[2021-04-26 18:30:14 train_lshot.py:257] INFO Epoch: [69][120/150] Time 0.944 (1.067) Data 0.000 (0.131) Loss 0.3841 (0.4088) Prec@1 91.016 (90.641) Prec@5 98.828 (97.847)
[2021-04-26 18:30:24 train_lshot.py:257] INFO Epoch: [69][130/150] Time 0.941 (1.057) Data 0.000 (0.121) Loss 0.4351 (0.4079) Prec@1 89.453 (90.667) Prec@5 97.266 (97.844)
[2021-04-26 18:30:33 train_lshot.py:257] INFO Epoch: [69][140/150] Time 0.926 (1.049) Data 0.000 (0.112) Loss 0.4837 (0.4079) Prec@1 87.891 (90.644) Prec@5 96.484 (97.839)
[2021-04-26 18:30:57 train_lshot.py:257] INFO Epoch: [70][0/150] Time 14.045 (14.045) Data 13.084 (13.084) Loss 0.3544 (0.3544) Prec@1 93.750 (93.750) Prec@5 97.656 (97.656)
[2021-04-26 18:31:06 train_lshot.py:257] INFO Epoch: [70][10/150] Time 0.941 (2.125) Data 0.000 (1.190) Loss 0.4364 (0.3987) Prec@1 90.234 (91.122) Prec@5 97.656 (98.011)
[2021-04-26 18:31:15 train_lshot.py:257] INFO Epoch: [70][20/150] Time 0.933 (1.558) Data 0.001 (0.624) Loss 0.3569 (0.4007) Prec@1 91.406 (91.071) Prec@5 98.047 (97.824)
[2021-04-26 18:31:25 train_lshot.py:257] INFO Epoch: [70][30/150] Time 0.936 (1.358) Data 0.000 (0.425) Loss 0.5008 (0.4134) Prec@1 88.672 (90.398) Prec@5 94.922 (97.530)
[2021-04-26 18:31:34 train_lshot.py:257] INFO Epoch: [70][40/150] Time 0.939 (1.255) Data 0.002 (0.321) Loss 0.4143 (0.4172) Prec@1 89.844 (90.301) Prec@5 97.266 (97.437)
[2021-04-26 18:31:43 train_lshot.py:257] INFO Epoch: [70][50/150] Time 0.934 (1.192) Data 0.001 (0.258) Loss 0.3079 (0.4170) Prec@1 94.141 (90.211) Prec@5 99.219 (97.457)
[2021-04-26 18:31:53 train_lshot.py:257] INFO Epoch: [70][60/150] Time 0.941 (1.150) Data 0.001 (0.216) Loss 0.3800 (0.4164) Prec@1 91.797 (90.247) Prec@5 98.438 (97.477)
[2021-04-26 18:32:02 train_lshot.py:257] INFO Epoch: [70][70/150] Time 0.934 (1.120) Data 0.001 (0.186) Loss 0.4455 (0.4117) Prec@1 90.234 (90.465) Prec@5 97.656 (97.546)
[2021-04-26 18:32:11 train_lshot.py:257] INFO Epoch: [70][80/150] Time 0.931 (1.097) Data 0.000 (0.163) Loss 0.3395 (0.4120) Prec@1 93.750 (90.451) Prec@5 98.828 (97.594)
[2021-04-26 18:32:21 train_lshot.py:257] INFO Epoch: [70][90/150] Time 0.933 (1.079) Data 0.000 (0.145) Loss 0.3601 (0.4122) Prec@1 91.797 (90.449) Prec@5 98.047 (97.600)
[2021-04-26 18:32:30 train_lshot.py:257] INFO Epoch: [70][100/150] Time 0.940 (1.065) Data 0.000 (0.131) Loss 0.4277 (0.4125) Prec@1 92.969 (90.474) Prec@5 96.094 (97.618)
[2021-04-26 18:32:39 train_lshot.py:257] INFO Epoch: [70][110/150] Time 0.932 (1.053) Data 0.000 (0.119) Loss 0.3879 (0.4134) Prec@1 90.625 (90.470) Prec@5 98.047 (97.618)
[2021-04-26 18:32:49 train_lshot.py:257] INFO Epoch: [70][120/150] Time 0.936 (1.043) Data 0.000 (0.109) Loss 0.3728 (0.4135) Prec@1 92.578 (90.483) Prec@5 99.219 (97.618)
[2021-04-26 18:32:58 train_lshot.py:257] INFO Epoch: [70][130/150] Time 0.932 (1.035) Data 0.000 (0.101) Loss 0.4148 (0.4115) Prec@1 91.406 (90.544) Prec@5 96.875 (97.641)
[2021-04-26 18:33:07 train_lshot.py:257] INFO Epoch: [70][140/150] Time 0.938 (1.027) Data 0.000 (0.094) Loss 0.4158 (0.4120) Prec@1 92.188 (90.545) Prec@5 97.266 (97.656)
[2021-04-26 18:33:32 train_lshot.py:257] INFO Epoch: [71][0/150] Time 15.560 (15.560) Data 14.603 (14.603) Loss 0.4430 (0.4430) Prec@1 90.625 (90.625) Prec@5 98.828 (98.828)
[2021-04-26 18:33:42 train_lshot.py:257] INFO Epoch: [71][10/150] Time 0.953 (2.262) Data 0.022 (1.330) Loss 0.4389 (0.4291) Prec@1 87.891 (89.453) Prec@5 98.438 (97.727)
[2021-04-26 18:33:51 train_lshot.py:257] INFO Epoch: [71][20/150] Time 0.933 (1.629) Data 0.000 (0.697) Loss 0.4025 (0.4171) Prec@1 91.406 (90.383) Prec@5 98.828 (97.879)
[2021-04-26 18:34:00 train_lshot.py:257] INFO Epoch: [71][30/150] Time 0.936 (1.405) Data 0.001 (0.472) Loss 0.4083 (0.4181) Prec@1 90.625 (90.360) Prec@5 98.047 (97.782)
[2021-04-26 18:34:10 train_lshot.py:257] INFO Epoch: [71][40/150] Time 0.925 (1.290) Data 0.000 (0.357) Loss 0.4371 (0.4181) Prec@1 90.625 (90.339) Prec@5 96.484 (97.732)
[2021-04-26 18:34:19 train_lshot.py:257] INFO Epoch: [71][50/150] Time 0.938 (1.221) Data 0.001 (0.288) Loss 0.4069 (0.4194) Prec@1 91.406 (90.165) Prec@5 97.656 (97.626)
[2021-04-26 18:34:29 train_lshot.py:257] INFO Epoch: [71][60/150] Time 0.938 (1.174) Data 0.000 (0.241) Loss 0.3739 (0.4152) Prec@1 91.406 (90.305) Prec@5 97.266 (97.618)
[2021-04-26 18:34:38 train_lshot.py:257] INFO Epoch: [71][70/150] Time 0.934 (1.141) Data 0.000 (0.207) Loss 0.3648 (0.4124) Prec@1 91.406 (90.372) Prec@5 97.656 (97.651)
[2021-04-26 18:34:47 train_lshot.py:257] INFO Epoch: [71][80/150] Time 0.935 (1.115) Data 0.000 (0.181) Loss 0.4036 (0.4142) Prec@1 91.797 (90.321) Prec@5 97.266 (97.608)
[2021-04-26 18:34:57 train_lshot.py:257] INFO Epoch: [71][90/150] Time 0.938 (1.096) Data 0.000 (0.161) Loss 0.4629 (0.4123) Prec@1 86.719 (90.359) Prec@5 96.875 (97.665)
[2021-04-26 18:35:06 train_lshot.py:257] INFO Epoch: [71][100/150] Time 0.938 (1.080) Data 0.000 (0.145) Loss 0.3848 (0.4126) Prec@1 91.797 (90.416) Prec@5 97.266 (97.676)
[2021-04-26 18:35:15 train_lshot.py:257] INFO Epoch: [71][110/150] Time 0.934 (1.067) Data 0.000 (0.132) Loss 0.4102 (0.4124) Prec@1 91.797 (90.400) Prec@5 98.047 (97.684)
[2021-04-26 18:35:25 train_lshot.py:257] INFO Epoch: [71][120/150] Time 0.951 (1.057) Data 0.000 (0.121) Loss 0.3855 (0.4128) Prec@1 91.797 (90.405) Prec@5 97.266 (97.695)
[2021-04-26 18:35:34 train_lshot.py:257] INFO Epoch: [71][130/150] Time 0.937 (1.048) Data 0.000 (0.112) Loss 0.3336 (0.4103) Prec@1 92.969 (90.509) Prec@5 98.047 (97.707)
[2021-04-26 18:35:43 train_lshot.py:257] INFO Epoch: [71][140/150] Time 0.933 (1.040) Data 0.000 (0.104) Loss 0.3836 (0.4100) Prec@1 90.234 (90.514) Prec@5 97.656 (97.723)
[2021-04-26 18:36:49 train_lshot.py:119] INFO Meta Val 71: 0.6059733473658562
[2021-04-26 18:37:03 train_lshot.py:257] INFO Epoch: [72][0/150] Time 13.133 (13.133) Data 12.179 (12.179) Loss 0.4461 (0.4461) Prec@1 89.453 (89.453) Prec@5 98.438 (98.438)
[2021-04-26 18:37:12 train_lshot.py:257] INFO Epoch: [72][10/150] Time 0.962 (2.045) Data 0.000 (1.108) Loss 0.3544 (0.3926) Prec@1 91.797 (90.803) Prec@5 97.266 (97.763)
[2021-04-26 18:37:21 train_lshot.py:257] INFO Epoch: [72][20/150] Time 0.944 (1.516) Data 0.000 (0.581) Loss 0.4340 (0.4052) Prec@1 89.453 (90.718) Prec@5 98.828 (97.675)
[2021-04-26 18:37:31 train_lshot.py:257] INFO Epoch: [72][30/150] Time 0.934 (1.328) Data 0.000 (0.394) Loss 0.3431 (0.4016) Prec@1 92.188 (90.877) Prec@5 99.219 (97.757)
[2021-04-26 18:37:40 train_lshot.py:257] INFO Epoch: [72][40/150] Time 0.931 (1.232) Data 0.000 (0.298) Loss 0.4114 (0.4033) Prec@1 89.844 (90.892) Prec@5 97.656 (97.771)
[2021-04-26 18:37:49 train_lshot.py:257] INFO Epoch: [72][50/150] Time 0.927 (1.174) Data 0.000 (0.240) Loss 0.4104 (0.4032) Prec@1 90.234 (90.862) Prec@5 96.875 (97.825)
[2021-04-26 18:37:59 train_lshot.py:257] INFO Epoch: [72][60/150] Time 0.928 (1.134) Data 0.000 (0.200) Loss 0.4262 (0.4038) Prec@1 87.891 (90.843) Prec@5 98.047 (97.816)
[2021-04-26 18:38:08 train_lshot.py:257] INFO Epoch: [72][70/150] Time 0.936 (1.106) Data 0.000 (0.172) Loss 0.4491 (0.4073) Prec@1 89.844 (90.724) Prec@5 98.047 (97.772)
[2021-04-26 18:38:17 train_lshot.py:257] INFO Epoch: [72][80/150] Time 0.938 (1.085) Data 0.000 (0.151) Loss 0.3920 (0.4059) Prec@1 90.625 (90.755) Prec@5 98.047 (97.767)
[2021-04-26 18:38:27 train_lshot.py:257] INFO Epoch: [72][90/150] Time 0.930 (1.069) Data 0.000 (0.135) Loss 0.3845 (0.4058) Prec@1 92.188 (90.737) Prec@5 97.656 (97.768)
[2021-04-26 18:38:36 train_lshot.py:257] INFO Epoch: [72][100/150] Time 0.937 (1.055) Data 0.000 (0.121) Loss 0.4075 (0.4055) Prec@1 91.406 (90.764) Prec@5 97.266 (97.753)
[2021-04-26 18:38:45 train_lshot.py:257] INFO Epoch: [72][110/150] Time 0.928 (1.044) Data 0.000 (0.110) Loss 0.4044 (0.4082) Prec@1 91.797 (90.678) Prec@5 97.656 (97.758)
[2021-04-26 18:38:55 train_lshot.py:257] INFO Epoch: [72][120/150] Time 0.933 (1.035) Data 0.000 (0.101) Loss 0.4482 (0.4077) Prec@1 89.062 (90.670) Prec@5 97.656 (97.753)
[2021-04-26 18:39:04 train_lshot.py:257] INFO Epoch: [72][130/150] Time 0.934 (1.027) Data 0.000 (0.094) Loss 0.4530 (0.4079) Prec@1 89.844 (90.661) Prec@5 96.094 (97.722)
[2021-04-26 18:39:13 train_lshot.py:257] INFO Epoch: [72][140/150] Time 0.936 (1.021) Data 0.000 (0.087) Loss 0.4793 (0.4081) Prec@1 87.500 (90.678) Prec@5 96.484 (97.714)
[2021-04-26 18:39:38 train_lshot.py:257] INFO Epoch: [73][0/150] Time 14.990 (14.990) Data 14.026 (14.026) Loss 0.4569 (0.4569) Prec@1 87.500 (87.500) Prec@5 96.875 (96.875)
[2021-04-26 18:39:47 train_lshot.py:257] INFO Epoch: [73][10/150] Time 0.935 (2.215) Data 0.000 (1.275) Loss 0.4775 (0.4127) Prec@1 86.719 (90.447) Prec@5 95.703 (97.124)
[2021-04-26 18:39:57 train_lshot.py:257] INFO Epoch: [73][20/150] Time 0.940 (1.604) Data 0.001 (0.668) Loss 0.3961 (0.4035) Prec@1 90.625 (90.737) Prec@5 98.828 (97.489)
[2021-04-26 18:40:06 train_lshot.py:257] INFO Epoch: [73][30/150] Time 0.934 (1.388) Data 0.001 (0.453) Loss 0.3943 (0.4068) Prec@1 91.406 (90.814) Prec@5 98.438 (97.681)
[2021-04-26 18:40:15 train_lshot.py:257] INFO Epoch: [73][40/150] Time 0.934 (1.277) Data 0.000 (0.343) Loss 0.4280 (0.4051) Prec@1 89.844 (90.854) Prec@5 97.656 (97.675)
[2021-04-26 18:40:25 train_lshot.py:257] INFO Epoch: [73][50/150] Time 0.938 (1.210) Data 0.000 (0.276) Loss 0.4250 (0.4069) Prec@1 91.406 (90.755) Prec@5 97.266 (97.610)
[2021-04-26 18:40:34 train_lshot.py:257] INFO Epoch: [73][60/150] Time 0.939 (1.165) Data 0.000 (0.230) Loss 0.3910 (0.4062) Prec@1 93.359 (90.830) Prec@5 98.828 (97.618)
[2021-04-26 18:40:43 train_lshot.py:257] INFO Epoch: [73][70/150] Time 0.945 (1.133) Data 0.002 (0.198) Loss 0.5176 (0.4094) Prec@1 87.500 (90.675) Prec@5 95.312 (97.596)
[2021-04-26 18:40:53 train_lshot.py:257] INFO Epoch: [73][80/150] Time 0.935 (1.109) Data 0.000 (0.174) Loss 0.3947 (0.4078) Prec@1 91.406 (90.736) Prec@5 97.656 (97.627)
[2021-04-26 18:41:02 train_lshot.py:257] INFO Epoch: [73][90/150] Time 0.936 (1.090) Data 0.000 (0.155) Loss 0.3445 (0.4080) Prec@1 94.141 (90.771) Prec@5 98.047 (97.609)
[2021-04-26 18:41:11 train_lshot.py:257] INFO Epoch: [73][100/150] Time 0.924 (1.075) Data 0.000 (0.139) Loss 0.4786 (0.4097) Prec@1 87.891 (90.683) Prec@5 96.875 (97.633)
[2021-04-26 18:41:21 train_lshot.py:257] INFO Epoch: [73][110/150] Time 0.932 (1.062) Data 0.000 (0.127) Loss 0.3724 (0.4108) Prec@1 91.016 (90.621) Prec@5 98.047 (97.600)
[2021-04-26 18:41:30 train_lshot.py:257] INFO Epoch: [73][120/150] Time 0.936 (1.052) Data 0.000 (0.116) Loss 0.4658 (0.4114) Prec@1 89.453 (90.619) Prec@5 95.703 (97.579)
[2021-04-26 18:41:40 train_lshot.py:257] INFO Epoch: [73][130/150] Time 0.938 (1.044) Data 0.000 (0.107) Loss 0.3257 (0.4107) Prec@1 92.578 (90.628) Prec@5 99.219 (97.629)
[2021-04-26 18:41:49 train_lshot.py:257] INFO Epoch: [73][140/150] Time 0.941 (1.036) Data 0.000 (0.100) Loss 0.3539 (0.4104) Prec@1 90.625 (90.622) Prec@5 98.828 (97.631)
[2021-04-26 18:42:11 train_lshot.py:257] INFO Epoch: [74][0/150] Time 12.844 (12.844) Data 11.823 (11.823) Loss 0.3820 (0.3820) Prec@1 91.016 (91.016) Prec@5 97.656 (97.656)
[2021-04-26 18:42:21 train_lshot.py:257] INFO Epoch: [74][10/150] Time 0.930 (2.036) Data 0.000 (1.095) Loss 0.4335 (0.4021) Prec@1 88.281 (90.554) Prec@5 98.047 (97.905)
[2021-04-26 18:42:30 train_lshot.py:257] INFO Epoch: [74][20/150] Time 0.939 (1.514) Data 0.001 (0.574) Loss 0.3787 (0.4101) Prec@1 92.188 (90.439) Prec@5 98.438 (97.600)
[2021-04-26 18:42:40 train_lshot.py:257] INFO Epoch: [74][30/150] Time 0.939 (1.328) Data 0.000 (0.389) Loss 0.4488 (0.4083) Prec@1 89.062 (90.625) Prec@5 96.875 (97.593)
[2021-04-26 18:42:49 train_lshot.py:257] INFO Epoch: [74][40/150] Time 0.932 (1.232) Data 0.001 (0.294) Loss 0.4322 (0.4127) Prec@1 88.672 (90.501) Prec@5 98.438 (97.599)
[2021-04-26 18:42:58 train_lshot.py:257] INFO Epoch: [74][50/150] Time 0.937 (1.174) Data 0.001 (0.237) Loss 0.3808 (0.4101) Prec@1 91.016 (90.556) Prec@5 98.047 (97.695)
[2021-04-26 18:43:08 train_lshot.py:257] INFO Epoch: [74][60/150] Time 0.935 (1.135) Data 0.001 (0.198) Loss 0.3953 (0.4062) Prec@1 89.844 (90.651) Prec@5 97.656 (97.733)
[2021-04-26 18:43:17 train_lshot.py:257] INFO Epoch: [74][70/150] Time 0.931 (1.107) Data 0.000 (0.170) Loss 0.4324 (0.4091) Prec@1 89.062 (90.531) Prec@5 97.656 (97.673)
[2021-04-26 18:43:26 train_lshot.py:257] INFO Epoch: [74][80/150] Time 0.927 (1.086) Data 0.000 (0.149) Loss 0.4055 (0.4083) Prec@1 89.844 (90.553) Prec@5 96.094 (97.685)
[2021-04-26 18:43:36 train_lshot.py:257] INFO Epoch: [74][90/150] Time 0.938 (1.069) Data 0.000 (0.133) Loss 0.3562 (0.4082) Prec@1 92.578 (90.501) Prec@5 98.438 (97.703)
[2021-04-26 18:43:45 train_lshot.py:257] INFO Epoch: [74][100/150] Time 0.934 (1.056) Data 0.000 (0.120) Loss 0.3638 (0.4067) Prec@1 93.359 (90.610) Prec@5 98.047 (97.734)
[2021-04-26 18:43:54 train_lshot.py:257] INFO Epoch: [74][110/150] Time 0.939 (1.045) Data 0.000 (0.109) Loss 0.4274 (0.4056) Prec@1 88.281 (90.706) Prec@5 96.484 (97.706)
[2021-04-26 18:44:04 train_lshot.py:257] INFO Epoch: [74][120/150] Time 0.942 (1.036) Data 0.000 (0.100) Loss 0.3623 (0.4072) Prec@1 92.578 (90.683) Prec@5 97.656 (97.650)
[2021-04-26 18:44:13 train_lshot.py:257] INFO Epoch: [74][130/150] Time 0.927 (1.028) Data 0.000 (0.092) Loss 0.3521 (0.4074) Prec@1 92.188 (90.700) Prec@5 98.828 (97.620)
[2021-04-26 18:44:22 train_lshot.py:257] INFO Epoch: [74][140/150] Time 0.938 (1.022) Data 0.000 (0.086) Loss 0.4545 (0.4069) Prec@1 87.891 (90.755) Prec@5 97.656 (97.637)
[2021-04-26 18:44:45 train_lshot.py:257] INFO Epoch: [75][0/150] Time 13.063 (13.063) Data 12.110 (12.110) Loss 0.3977 (0.3977) Prec@1 89.062 (89.062) Prec@5 98.047 (98.047)
[2021-04-26 18:44:54 train_lshot.py:257] INFO Epoch: [75][10/150] Time 0.933 (2.038) Data 0.000 (1.101) Loss 0.3812 (0.4047) Prec@1 91.797 (90.376) Prec@5 99.219 (97.834)
[2021-04-26 18:45:04 train_lshot.py:257] INFO Epoch: [75][20/150] Time 0.937 (1.512) Data 0.000 (0.577) Loss 0.4470 (0.4115) Prec@1 88.281 (90.327) Prec@5 96.875 (97.489)
[2021-04-26 18:45:13 train_lshot.py:257] INFO Epoch: [75][30/150] Time 0.938 (1.325) Data 0.000 (0.391) Loss 0.3928 (0.4073) Prec@1 92.969 (90.638) Prec@5 98.047 (97.593)
[2021-04-26 18:45:22 train_lshot.py:257] INFO Epoch: [75][40/150] Time 0.945 (1.229) Data 0.001 (0.296) Loss 0.3675 (0.4067) Prec@1 90.625 (90.739) Prec@5 98.828 (97.628)
[2021-04-26 18:45:32 train_lshot.py:257] INFO Epoch: [75][50/150] Time 0.938 (1.172) Data 0.000 (0.238) Loss 0.3995 (0.4110) Prec@1 89.844 (90.472) Prec@5 98.047 (97.557)
[2021-04-26 18:45:41 train_lshot.py:257] INFO Epoch: [75][60/150] Time 0.934 (1.133) Data 0.000 (0.199) Loss 0.3280 (0.4079) Prec@1 92.969 (90.619) Prec@5 99.219 (97.624)
[2021-04-26 18:45:50 train_lshot.py:257] INFO Epoch: [75][70/150] Time 0.943 (1.105) Data 0.002 (0.171) Loss 0.3772 (0.4093) Prec@1 94.531 (90.686) Prec@5 96.484 (97.596)
[2021-04-26 18:46:00 train_lshot.py:257] INFO Epoch: [75][80/150] Time 0.938 (1.084) Data 0.000 (0.150) Loss 0.4431 (0.4084) Prec@1 88.672 (90.755) Prec@5 95.312 (97.574)
[2021-04-26 18:46:09 train_lshot.py:257] INFO Epoch: [75][90/150] Time 0.935 (1.068) Data 0.000 (0.134) Loss 0.3878 (0.4087) Prec@1 90.234 (90.767) Prec@5 98.047 (97.536)
[2021-04-26 18:46:18 train_lshot.py:257] INFO Epoch: [75][100/150] Time 0.931 (1.055) Data 0.000 (0.120) Loss 0.4039 (0.4080) Prec@1 92.188 (90.803) Prec@5 96.875 (97.567)
[2021-04-26 18:46:28 train_lshot.py:257] INFO Epoch: [75][110/150] Time 0.932 (1.044) Data 0.000 (0.110) Loss 0.4602 (0.4069) Prec@1 90.234 (90.829) Prec@5 97.266 (97.611)
[2021-04-26 18:46:37 train_lshot.py:257] INFO Epoch: [75][120/150] Time 0.935 (1.035) Data 0.000 (0.101) Loss 0.4062 (0.4070) Prec@1 89.844 (90.790) Prec@5 98.828 (97.634)
[2021-04-26 18:46:46 train_lshot.py:257] INFO Epoch: [75][130/150] Time 0.935 (1.028) Data 0.000 (0.093) Loss 0.3701 (0.4078) Prec@1 91.016 (90.759) Prec@5 98.047 (97.612)
[2021-04-26 18:46:56 train_lshot.py:257] INFO Epoch: [75][140/150] Time 0.938 (1.022) Data 0.000 (0.086) Loss 0.3641 (0.4078) Prec@1 93.750 (90.811) Prec@5 98.047 (97.601)
[2021-04-26 18:48:02 train_lshot.py:119] INFO Meta Val 75: 0.6120533480048179
[2021-04-26 18:48:20 train_lshot.py:257] INFO Epoch: [76][0/150] Time 17.509 (17.509) Data 16.547 (16.547) Loss 0.3848 (0.3848) Prec@1 89.453 (89.453) Prec@5 98.047 (98.047)
[2021-04-26 18:48:30 train_lshot.py:257] INFO Epoch: [76][10/150] Time 0.933 (2.442) Data 0.000 (1.507) Loss 0.3271 (0.4113) Prec@1 92.969 (90.199) Prec@5 98.828 (97.585)
[2021-04-26 18:48:39 train_lshot.py:257] INFO Epoch: [76][20/150] Time 0.930 (1.725) Data 0.001 (0.790) Loss 0.3365 (0.3989) Prec@1 94.531 (90.792) Prec@5 98.047 (97.861)
[2021-04-26 18:48:49 train_lshot.py:257] INFO Epoch: [76][30/150] Time 0.937 (1.470) Data 0.001 (0.536) Loss 0.4342 (0.4001) Prec@1 88.672 (90.827) Prec@5 98.047 (97.870)
[2021-04-26 18:48:58 train_lshot.py:257] INFO Epoch: [76][40/150] Time 0.938 (1.340) Data 0.002 (0.405) Loss 0.4048 (0.3989) Prec@1 91.016 (90.816) Prec@5 96.875 (97.837)
[2021-04-26 18:49:07 train_lshot.py:257] INFO Epoch: [76][50/150] Time 0.938 (1.261) Data 0.001 (0.326) Loss 0.3915 (0.4001) Prec@1 90.234 (90.801) Prec@5 98.828 (97.817)
[2021-04-26 18:49:17 train_lshot.py:257] INFO Epoch: [76][60/150] Time 0.935 (1.208) Data 0.000 (0.273) Loss 0.3856 (0.4009) Prec@1 91.797 (90.785) Prec@5 97.266 (97.823)
[2021-04-26 18:49:26 train_lshot.py:257] INFO Epoch: [76][70/150] Time 0.931 (1.170) Data 0.000 (0.234) Loss 0.4351 (0.3981) Prec@1 91.406 (90.999) Prec@5 97.266 (97.838)
[2021-04-26 18:49:35 train_lshot.py:257] INFO Epoch: [76][80/150] Time 0.937 (1.141) Data 0.000 (0.205) Loss 0.3922 (0.3994) Prec@1 91.406 (90.943) Prec@5 98.828 (97.806)
[2021-04-26 18:49:45 train_lshot.py:257] INFO Epoch: [76][90/150] Time 0.939 (1.118) Data 0.000 (0.183) Loss 0.3929 (0.4006) Prec@1 90.625 (90.947) Prec@5 98.438 (97.776)
[2021-04-26 18:49:54 train_lshot.py:257] INFO Epoch: [76][100/150] Time 0.939 (1.100) Data 0.000 (0.165) Loss 0.4470 (0.3994) Prec@1 89.844 (90.985) Prec@5 97.656 (97.795)
[2021-04-26 18:50:03 train_lshot.py:257] INFO Epoch: [76][110/150] Time 0.938 (1.086) Data 0.000 (0.150) Loss 0.3865 (0.3987) Prec@1 92.188 (91.019) Prec@5 98.828 (97.793)
[2021-04-26 18:50:13 train_lshot.py:257] INFO Epoch: [76][120/150] Time 0.932 (1.073) Data 0.000 (0.138) Loss 0.4256 (0.3993) Prec@1 88.281 (90.945) Prec@5 98.047 (97.779)
[2021-04-26 18:50:22 train_lshot.py:257] INFO Epoch: [76][130/150] Time 0.929 (1.063) Data 0.000 (0.127) Loss 0.4422 (0.3992) Prec@1 89.453 (90.938) Prec@5 98.047 (97.767)
[2021-04-26 18:50:32 train_lshot.py:257] INFO Epoch: [76][140/150] Time 0.932 (1.054) Data 0.000 (0.118) Loss 0.4632 (0.3993) Prec@1 89.453 (90.957) Prec@5 95.312 (97.764)
[2021-04-26 18:50:55 train_lshot.py:257] INFO Epoch: [77][0/150] Time 13.696 (13.696) Data 12.753 (12.753) Loss 0.3280 (0.3280) Prec@1 93.359 (93.359) Prec@5 97.656 (97.656)
[2021-04-26 18:51:04 train_lshot.py:257] INFO Epoch: [77][10/150] Time 0.936 (2.094) Data 0.000 (1.160) Loss 0.3844 (0.3839) Prec@1 91.406 (91.264) Prec@5 97.656 (98.331)
[2021-04-26 18:51:13 train_lshot.py:257] INFO Epoch: [77][20/150] Time 0.935 (1.543) Data 0.000 (0.608) Loss 0.4322 (0.3959) Prec@1 91.016 (90.997) Prec@5 97.266 (98.103)
[2021-04-26 18:51:23 train_lshot.py:257] INFO Epoch: [77][30/150] Time 0.930 (1.346) Data 0.000 (0.412) Loss 0.3817 (0.4106) Prec@1 92.578 (90.549) Prec@5 98.047 (97.908)
[2021-04-26 18:51:32 train_lshot.py:257] INFO Epoch: [77][40/150] Time 0.939 (1.246) Data 0.002 (0.312) Loss 0.3924 (0.4033) Prec@1 91.797 (90.835) Prec@5 98.438 (97.933)
[2021-04-26 18:51:41 train_lshot.py:257] INFO Epoch: [77][50/150] Time 0.936 (1.186) Data 0.001 (0.251) Loss 0.3800 (0.4025) Prec@1 90.625 (90.801) Prec@5 97.656 (97.947)
[2021-04-26 18:51:51 train_lshot.py:257] INFO Epoch: [77][60/150] Time 0.939 (1.145) Data 0.000 (0.210) Loss 0.3790 (0.4021) Prec@1 91.797 (90.836) Prec@5 97.656 (97.957)
[2021-04-26 18:52:00 train_lshot.py:257] INFO Epoch: [77][70/150] Time 0.942 (1.116) Data 0.000 (0.180) Loss 0.3848 (0.4038) Prec@1 92.188 (90.774) Prec@5 96.875 (97.871)
[2021-04-26 18:52:10 train_lshot.py:257] INFO Epoch: [77][80/150] Time 0.933 (1.093) Data 0.000 (0.158) Loss 0.4093 (0.4013) Prec@1 91.406 (90.852) Prec@5 96.875 (97.902)
[2021-04-26 18:52:19 train_lshot.py:257] INFO Epoch: [77][90/150] Time 0.931 (1.076) Data 0.000 (0.141) Loss 0.4137 (0.3998) Prec@1 88.672 (90.908) Prec@5 97.656 (97.892)
[2021-04-26 18:52:28 train_lshot.py:257] INFO Epoch: [77][100/150] Time 0.940 (1.062) Data 0.000 (0.127) Loss 0.3460 (0.3998) Prec@1 94.922 (90.923) Prec@5 99.609 (97.888)
[2021-04-26 18:52:38 train_lshot.py:257] INFO Epoch: [77][110/150] Time 0.935 (1.051) Data 0.000 (0.115) Loss 0.3820 (0.3993) Prec@1 92.969 (90.949) Prec@5 97.656 (97.892)
[2021-04-26 18:52:47 train_lshot.py:257] INFO Epoch: [77][120/150] Time 0.937 (1.042) Data 0.000 (0.106) Loss 0.4139 (0.4010) Prec@1 90.234 (90.906) Prec@5 97.266 (97.840)
[2021-04-26 18:52:56 train_lshot.py:257] INFO Epoch: [77][130/150] Time 0.935 (1.034) Data 0.000 (0.098) Loss 0.3781 (0.4009) Prec@1 92.578 (90.896) Prec@5 97.266 (97.844)
[2021-04-26 18:53:06 train_lshot.py:257] INFO Epoch: [77][140/150] Time 0.947 (1.027) Data 0.000 (0.091) Loss 0.4342 (0.4011) Prec@1 89.844 (90.905) Prec@5 97.656 (97.850)
[2021-04-26 18:53:31 train_lshot.py:257] INFO Epoch: [78][0/150] Time 16.213 (16.213) Data 15.253 (15.253) Loss 0.3547 (0.3547) Prec@1 91.797 (91.797) Prec@5 99.609 (99.609)
[2021-04-26 18:53:41 train_lshot.py:257] INFO Epoch: [78][10/150] Time 0.940 (2.324) Data 0.000 (1.387) Loss 0.3604 (0.3905) Prec@1 91.016 (90.945) Prec@5 98.828 (98.118)
[2021-04-26 18:53:50 train_lshot.py:257] INFO Epoch: [78][20/150] Time 0.938 (1.664) Data 0.001 (0.727) Loss 0.4270 (0.4045) Prec@1 89.062 (90.644) Prec@5 97.266 (97.786)
[2021-04-26 18:54:00 train_lshot.py:257] INFO Epoch: [78][30/150] Time 0.939 (1.429) Data 0.000 (0.493) Loss 0.4585 (0.4104) Prec@1 89.844 (90.713) Prec@5 96.094 (97.455)
[2021-04-26 18:54:09 train_lshot.py:257] INFO Epoch: [78][40/150] Time 0.940 (1.309) Data 0.001 (0.373) Loss 0.3676 (0.4054) Prec@1 92.578 (90.968) Prec@5 98.438 (97.618)
[2021-04-26 18:54:18 train_lshot.py:257] INFO Epoch: [78][50/150] Time 0.945 (1.237) Data 0.001 (0.300) Loss 0.4247 (0.4085) Prec@1 91.016 (90.832) Prec@5 97.656 (97.626)
[2021-04-26 18:54:28 train_lshot.py:257] INFO Epoch: [78][60/150] Time 0.937 (1.188) Data 0.000 (0.251) Loss 0.4106 (0.4057) Prec@1 89.844 (90.894) Prec@5 96.875 (97.682)
[2021-04-26 18:54:37 train_lshot.py:257] INFO Epoch: [78][70/150] Time 0.931 (1.152) Data 0.000 (0.216) Loss 0.4533 (0.4065) Prec@1 90.625 (90.917) Prec@5 96.484 (97.651)
[2021-04-26 18:54:46 train_lshot.py:257] INFO Epoch: [78][80/150] Time 0.939 (1.126) Data 0.000 (0.189) Loss 0.4391 (0.4067) Prec@1 91.797 (90.905) Prec@5 96.875 (97.666)
[2021-04-26 18:54:56 train_lshot.py:257] INFO Epoch: [78][90/150] Time 0.935 (1.106) Data 0.000 (0.168) Loss 0.5025 (0.4089) Prec@1 87.891 (90.870) Prec@5 96.094 (97.618)
[2021-04-26 18:55:05 train_lshot.py:257] INFO Epoch: [78][100/150] Time 0.936 (1.089) Data 0.000 (0.152) Loss 0.3340 (0.4076) Prec@1 93.359 (90.873) Prec@5 99.219 (97.656)
[2021-04-26 18:55:15 train_lshot.py:257] INFO Epoch: [78][110/150] Time 0.934 (1.075) Data 0.000 (0.138) Loss 0.3662 (0.4080) Prec@1 92.188 (90.850) Prec@5 98.828 (97.663)
[2021-04-26 18:55:24 train_lshot.py:257] INFO Epoch: [78][120/150] Time 0.934 (1.064) Data 0.000 (0.127) Loss 0.4070 (0.4088) Prec@1 91.797 (90.790) Prec@5 97.266 (97.656)
[2021-04-26 18:55:33 train_lshot.py:257] INFO Epoch: [78][130/150] Time 0.935 (1.054) Data 0.000 (0.117) Loss 0.4324 (0.4092) Prec@1 91.406 (90.750) Prec@5 98.828 (97.671)
[2021-04-26 18:55:43 train_lshot.py:257] INFO Epoch: [78][140/150] Time 0.929 (1.046) Data 0.000 (0.109) Loss 0.3809 (0.4086) Prec@1 91.797 (90.761) Prec@5 98.438 (97.678)
[2021-04-26 18:56:06 train_lshot.py:257] INFO Epoch: [79][0/150] Time 14.119 (14.119) Data 13.160 (13.160) Loss 0.4091 (0.4091) Prec@1 89.844 (89.844) Prec@5 97.266 (97.266)
[2021-04-26 18:56:16 train_lshot.py:257] INFO Epoch: [79][10/150] Time 0.932 (2.134) Data 0.000 (1.198) Loss 0.3270 (0.4117) Prec@1 93.750 (90.909) Prec@5 98.828 (97.372)
[2021-04-26 18:56:25 train_lshot.py:257] INFO Epoch: [79][20/150] Time 0.937 (1.567) Data 0.001 (0.630) Loss 0.4008 (0.4062) Prec@1 89.844 (90.960) Prec@5 98.828 (97.638)
[2021-04-26 18:56:34 train_lshot.py:257] INFO Epoch: [79][30/150] Time 0.944 (1.363) Data 0.001 (0.427) Loss 0.4028 (0.4078) Prec@1 91.406 (90.776) Prec@5 96.875 (97.644)
[2021-04-26 18:56:44 train_lshot.py:257] INFO Epoch: [79][40/150] Time 0.935 (1.259) Data 0.001 (0.323) Loss 0.4100 (0.4069) Prec@1 89.844 (90.720) Prec@5 97.656 (97.609)
[2021-04-26 18:56:53 train_lshot.py:257] INFO Epoch: [79][50/150] Time 0.931 (1.196) Data 0.000 (0.260) Loss 0.4151 (0.4074) Prec@1 91.016 (90.778) Prec@5 98.047 (97.595)
[2021-04-26 18:57:02 train_lshot.py:257] INFO Epoch: [79][60/150] Time 0.934 (1.153) Data 0.001 (0.218) Loss 0.3456 (0.4081) Prec@1 93.359 (90.657) Prec@5 98.438 (97.592)
[2021-04-26 18:57:12 train_lshot.py:257] INFO Epoch: [79][70/150] Time 0.931 (1.122) Data 0.000 (0.187) Loss 0.4035 (0.4089) Prec@1 90.625 (90.658) Prec@5 97.266 (97.568)
[2021-04-26 18:57:21 train_lshot.py:257] INFO Epoch: [79][80/150] Time 0.928 (1.102) Data 0.000 (0.167) Loss 0.4123 (0.4081) Prec@1 89.844 (90.664) Prec@5 97.266 (97.598)
[2021-04-26 18:57:31 train_lshot.py:257] INFO Epoch: [79][90/150] Time 0.934 (1.084) Data 0.000 (0.148) Loss 0.4081 (0.4067) Prec@1 89.844 (90.715) Prec@5 96.484 (97.630)
[2021-04-26 18:57:40 train_lshot.py:257] INFO Epoch: [79][100/150] Time 0.936 (1.069) Data 0.000 (0.134) Loss 0.4368 (0.4061) Prec@1 90.625 (90.807) Prec@5 97.266 (97.652)
[2021-04-26 18:57:49 train_lshot.py:257] INFO Epoch: [79][110/150] Time 0.935 (1.057) Data 0.000 (0.122) Loss 0.3239 (0.4057) Prec@1 93.359 (90.727) Prec@5 98.828 (97.663)
[2021-04-26 18:57:59 train_lshot.py:257] INFO Epoch: [79][120/150] Time 0.926 (1.047) Data 0.000 (0.112) Loss 0.3949 (0.4058) Prec@1 90.234 (90.702) Prec@5 97.656 (97.701)
[2021-04-26 18:58:08 train_lshot.py:257] INFO Epoch: [79][130/150] Time 0.935 (1.039) Data 0.000 (0.103) Loss 0.4009 (0.4063) Prec@1 89.844 (90.691) Prec@5 98.047 (97.704)
[2021-04-26 18:58:18 train_lshot.py:257] INFO Epoch: [79][140/150] Time 0.941 (1.031) Data 0.000 (0.096) Loss 0.3399 (0.4055) Prec@1 92.969 (90.714) Prec@5 98.828 (97.739)
[2021-04-26 18:59:23 train_lshot.py:119] INFO Meta Val 79: 0.6148266800045967
[2021-04-26 18:59:37 train_lshot.py:257] INFO Epoch: [80][0/150] Time 12.783 (12.783) Data 11.834 (11.834) Loss 0.4224 (0.4224) Prec@1 90.234 (90.234) Prec@5 97.266 (97.266)
[2021-04-26 18:59:46 train_lshot.py:257] INFO Epoch: [80][10/150] Time 0.934 (2.014) Data 0.000 (1.079) Loss 0.3682 (0.4020) Prec@1 90.234 (90.128) Prec@5 98.047 (97.869)
[2021-04-26 18:59:55 train_lshot.py:257] INFO Epoch: [80][20/150] Time 0.939 (1.502) Data 0.000 (0.566) Loss 0.3687 (0.3935) Prec@1 92.188 (90.997) Prec@5 98.047 (97.972)
[2021-04-26 19:00:05 train_lshot.py:257] INFO Epoch: [80][30/150] Time 0.937 (1.319) Data 0.000 (0.384) Loss 0.3899 (0.3955) Prec@1 91.406 (91.041) Prec@5 98.047 (97.984)
[2021-04-26 19:00:14 train_lshot.py:257] INFO Epoch: [80][40/150] Time 0.939 (1.226) Data 0.001 (0.290) Loss 0.4373 (0.4006) Prec@1 88.281 (90.997) Prec@5 97.656 (97.923)
[2021-04-26 19:00:23 train_lshot.py:257] INFO Epoch: [80][50/150] Time 0.940 (1.170) Data 0.001 (0.234) Loss 0.4442 (0.4011) Prec@1 89.062 (90.947) Prec@5 98.047 (97.963)
[2021-04-26 19:00:33 train_lshot.py:257] INFO Epoch: [80][60/150] Time 0.936 (1.133) Data 0.001 (0.196) Loss 0.4559 (0.4003) Prec@1 88.281 (91.022) Prec@5 95.312 (97.906)
[2021-04-26 19:00:42 train_lshot.py:257] INFO Epoch: [80][70/150] Time 0.949 (1.108) Data 0.002 (0.170) Loss 0.4543 (0.4017) Prec@1 87.891 (90.961) Prec@5 97.266 (97.860)
[2021-04-26 19:00:52 train_lshot.py:257] INFO Epoch: [80][80/150] Time 0.938 (1.087) Data 0.000 (0.149) Loss 0.3940 (0.4029) Prec@1 89.844 (90.914) Prec@5 97.656 (97.820)
[2021-04-26 19:01:01 train_lshot.py:257] INFO Epoch: [80][90/150] Time 0.942 (1.070) Data 0.000 (0.133) Loss 0.4942 (0.4018) Prec@1 88.281 (90.921) Prec@5 95.703 (97.845)
[2021-04-26 19:01:10 train_lshot.py:257] INFO Epoch: [80][100/150] Time 0.942 (1.057) Data 0.000 (0.120) Loss 0.4580 (0.4021) Prec@1 87.500 (90.911) Prec@5 96.875 (97.826)
[2021-04-26 19:01:20 train_lshot.py:257] INFO Epoch: [80][110/150] Time 0.941 (1.046) Data 0.000 (0.109) Loss 0.4479 (0.4024) Prec@1 90.625 (90.924) Prec@5 96.875 (97.829)
[2021-04-26 19:01:29 train_lshot.py:257] INFO Epoch: [80][120/150] Time 0.938 (1.037) Data 0.000 (0.100) Loss 0.4275 (0.4029) Prec@1 89.062 (90.893) Prec@5 96.875 (97.802)
[2021-04-26 19:01:39 train_lshot.py:257] INFO Epoch: [80][130/150] Time 0.943 (1.030) Data 0.000 (0.092) Loss 0.3388 (0.4005) Prec@1 94.922 (91.004) Prec@5 98.828 (97.859)
[2021-04-26 19:01:48 train_lshot.py:257] INFO Epoch: [80][140/150] Time 0.927 (1.023) Data 0.000 (0.086) Loss 0.3316 (0.4009) Prec@1 93.750 (90.999) Prec@5 99.219 (97.853)
[2021-04-26 19:02:10 train_lshot.py:257] INFO Epoch: [81][0/150] Time 12.980 (12.980) Data 12.026 (12.026) Loss 0.4375 (0.4375) Prec@1 88.672 (88.672) Prec@5 96.875 (96.875)
[2021-04-26 19:02:20 train_lshot.py:257] INFO Epoch: [81][10/150] Time 0.947 (2.032) Data 0.001 (1.094) Loss 0.3820 (0.4179) Prec@1 92.188 (90.199) Prec@5 98.438 (97.656)
[2021-04-26 19:02:29 train_lshot.py:257] INFO Epoch: [81][20/150] Time 0.936 (1.509) Data 0.001 (0.573) Loss 0.3318 (0.4129) Prec@1 92.969 (90.885) Prec@5 98.438 (97.563)
[2021-04-26 19:02:38 train_lshot.py:257] INFO Epoch: [81][30/150] Time 0.934 (1.324) Data 0.001 (0.389) Loss 0.4850 (0.4100) Prec@1 85.938 (90.814) Prec@5 96.094 (97.732)
[2021-04-26 19:02:48 train_lshot.py:257] INFO Epoch: [81][40/150] Time 0.938 (1.230) Data 0.000 (0.294) Loss 0.5136 (0.4145) Prec@1 88.281 (90.635) Prec@5 95.312 (97.618)
[2021-04-26 19:02:57 train_lshot.py:257] INFO Epoch: [81][50/150] Time 0.940 (1.173) Data 0.001 (0.236) Loss 0.3608 (0.4113) Prec@1 93.359 (90.778) Prec@5 98.047 (97.656)
[2021-04-26 19:03:07 train_lshot.py:257] INFO Epoch: [81][60/150] Time 0.940 (1.134) Data 0.001 (0.198) Loss 0.4059 (0.4092) Prec@1 90.625 (90.747) Prec@5 96.875 (97.688)
[2021-04-26 19:03:16 train_lshot.py:257] INFO Epoch: [81][70/150] Time 0.944 (1.106) Data 0.002 (0.170) Loss 0.4848 (0.4117) Prec@1 88.281 (90.708) Prec@5 96.875 (97.629)
[2021-04-26 19:03:25 train_lshot.py:257] INFO Epoch: [81][80/150] Time 0.930 (1.085) Data 0.000 (0.149) Loss 0.4413 (0.4134) Prec@1 89.453 (90.615) Prec@5 96.875 (97.603)
[2021-04-26 19:03:35 train_lshot.py:257] INFO Epoch: [81][90/150] Time 0.937 (1.069) Data 0.000 (0.133) Loss 0.4621 (0.4128) Prec@1 87.891 (90.604) Prec@5 96.875 (97.622)
[2021-04-26 19:03:44 train_lshot.py:257] INFO Epoch: [81][100/150] Time 0.935 (1.055) Data 0.000 (0.120) Loss 0.4921 (0.4120) Prec@1 86.719 (90.621) Prec@5 97.266 (97.633)
[2021-04-26 19:03:53 train_lshot.py:257] INFO Epoch: [81][110/150] Time 0.931 (1.044) Data 0.000 (0.109) Loss 0.4109 (0.4119) Prec@1 91.016 (90.618) Prec@5 98.047 (97.632)
[2021-04-26 19:04:03 train_lshot.py:257] INFO Epoch: [81][120/150] Time 0.935 (1.036) Data 0.000 (0.100) Loss 0.4910 (0.4131) Prec@1 88.672 (90.554) Prec@5 95.703 (97.608)
[2021-04-26 19:04:12 train_lshot.py:257] INFO Epoch: [81][130/150] Time 0.941 (1.028) Data 0.000 (0.092) Loss 0.3682 (0.4111) Prec@1 91.406 (90.637) Prec@5 98.047 (97.641)
[2021-04-26 19:04:21 train_lshot.py:257] INFO Epoch: [81][140/150] Time 0.941 (1.022) Data 0.000 (0.086) Loss 0.3599 (0.4094) Prec@1 90.625 (90.714) Prec@5 98.828 (97.695)
[2021-04-26 19:04:43 train_lshot.py:257] INFO Epoch: [82][0/150] Time 12.262 (12.262) Data 11.318 (11.318) Loss 0.3781 (0.3781) Prec@1 92.969 (92.969) Prec@5 99.609 (99.609)
[2021-04-26 19:04:53 train_lshot.py:257] INFO Epoch: [82][10/150] Time 0.933 (1.970) Data 0.000 (1.034) Loss 0.3919 (0.3979) Prec@1 92.188 (91.158) Prec@5 98.047 (97.585)
[2021-04-26 19:05:02 train_lshot.py:257] INFO Epoch: [82][20/150] Time 0.936 (1.479) Data 0.000 (0.542) Loss 0.4533 (0.4007) Prec@1 89.844 (90.997) Prec@5 97.266 (97.638)
[2021-04-26 19:05:11 train_lshot.py:257] INFO Epoch: [82][30/150] Time 0.942 (1.305) Data 0.000 (0.367) Loss 0.4120 (0.4008) Prec@1 89.062 (91.066) Prec@5 99.219 (97.744)
[2021-04-26 19:05:21 train_lshot.py:257] INFO Epoch: [82][40/150] Time 0.938 (1.216) Data 0.000 (0.278) Loss 0.3471 (0.4032) Prec@1 93.359 (90.892) Prec@5 98.828 (97.752)
[2021-04-26 19:05:30 train_lshot.py:257] INFO Epoch: [82][50/150] Time 0.932 (1.161) Data 0.001 (0.224) Loss 0.3484 (0.4062) Prec@1 92.969 (90.778) Prec@5 98.828 (97.633)
[2021-04-26 19:05:39 train_lshot.py:257] INFO Epoch: [82][60/150] Time 0.941 (1.124) Data 0.001 (0.187) Loss 0.3586 (0.4014) Prec@1 93.359 (90.958) Prec@5 97.266 (97.733)
[2021-04-26 19:05:49 train_lshot.py:257] INFO Epoch: [82][70/150] Time 0.940 (1.098) Data 0.002 (0.161) Loss 0.4407 (0.4036) Prec@1 91.016 (90.889) Prec@5 96.484 (97.689)
[2021-04-26 19:05:58 train_lshot.py:257] INFO Epoch: [82][80/150] Time 0.939 (1.079) Data 0.000 (0.141) Loss 0.3586 (0.4001) Prec@1 93.359 (91.020) Prec@5 98.828 (97.762)
[2021-04-26 19:06:08 train_lshot.py:257] INFO Epoch: [82][90/150] Time 0.936 (1.063) Data 0.000 (0.125) Loss 0.3582 (0.4010) Prec@1 91.797 (91.050) Prec@5 98.828 (97.755)
[2021-04-26 19:06:17 train_lshot.py:257] INFO Epoch: [82][100/150] Time 0.933 (1.051) Data 0.000 (0.113) Loss 0.3380 (0.3995) Prec@1 93.750 (91.139) Prec@5 98.047 (97.749)
[2021-04-26 19:06:26 train_lshot.py:257] INFO Epoch: [82][110/150] Time 0.933 (1.041) Data 0.000 (0.103) Loss 0.4743 (0.3974) Prec@1 89.453 (91.248) Prec@5 96.875 (97.786)
[2021-04-26 19:06:36 train_lshot.py:257] INFO Epoch: [82][120/150] Time 0.949 (1.033) Data 0.000 (0.094) Loss 0.3743 (0.3987) Prec@1 91.406 (91.196) Prec@5 98.828 (97.776)
[2021-04-26 19:06:45 train_lshot.py:257] INFO Epoch: [82][130/150] Time 0.938 (1.025) Data 0.000 (0.087) Loss 0.3830 (0.3993) Prec@1 91.406 (91.135) Prec@5 98.047 (97.784)
[2021-04-26 19:06:55 train_lshot.py:257] INFO Epoch: [82][140/150] Time 0.933 (1.019) Data 0.000 (0.081) Loss 0.3619 (0.4005) Prec@1 91.797 (91.068) Prec@5 98.828 (97.731)
[2021-04-26 19:07:17 train_lshot.py:257] INFO Epoch: [83][0/150] Time 13.349 (13.349) Data 12.399 (12.399) Loss 0.4634 (0.4634) Prec@1 87.500 (87.500) Prec@5 97.266 (97.266)
[2021-04-26 19:07:27 train_lshot.py:257] INFO Epoch: [83][10/150] Time 0.931 (2.079) Data 0.000 (1.143) Loss 0.4716 (0.3995) Prec@1 89.453 (90.874) Prec@5 96.484 (98.082)
[2021-04-26 19:07:36 train_lshot.py:257] INFO Epoch: [83][20/150] Time 0.937 (1.535) Data 0.001 (0.599) Loss 0.4656 (0.4060) Prec@1 89.453 (90.792) Prec@5 96.484 (97.712)
[2021-04-26 19:07:46 train_lshot.py:257] INFO Epoch: [83][30/150] Time 0.933 (1.343) Data 0.000 (0.406) Loss 0.4795 (0.4087) Prec@1 87.891 (90.663) Prec@5 97.266 (97.606)
[2021-04-26 19:07:55 train_lshot.py:257] INFO Epoch: [83][40/150] Time 0.935 (1.244) Data 0.001 (0.307) Loss 0.3586 (0.4018) Prec@1 91.406 (90.825) Prec@5 98.438 (97.771)
[2021-04-26 19:08:04 train_lshot.py:257] INFO Epoch: [83][50/150] Time 0.932 (1.183) Data 0.000 (0.247) Loss 0.3754 (0.4048) Prec@1 91.406 (90.847) Prec@5 98.438 (97.679)
[2021-04-26 19:08:14 train_lshot.py:257] INFO Epoch: [83][60/150] Time 0.935 (1.143) Data 0.001 (0.207) Loss 0.4137 (0.4070) Prec@1 91.016 (90.759) Prec@5 97.266 (97.682)
[2021-04-26 19:08:23 train_lshot.py:257] INFO Epoch: [83][70/150] Time 0.940 (1.114) Data 0.000 (0.178) Loss 0.3657 (0.4045) Prec@1 92.969 (90.878) Prec@5 98.438 (97.728)
[2021-04-26 19:08:33 train_lshot.py:257] INFO Epoch: [83][80/150] Time 0.939 (1.092) Data 0.000 (0.156) Loss 0.4645 (0.4028) Prec@1 89.844 (90.914) Prec@5 96.875 (97.796)
[2021-04-26 19:08:42 train_lshot.py:257] INFO Epoch: [83][90/150] Time 0.936 (1.075) Data 0.000 (0.139) Loss 0.4254 (0.4046) Prec@1 90.625 (90.835) Prec@5 97.266 (97.772)
[2021-04-26 19:08:51 train_lshot.py:257] INFO Epoch: [83][100/150] Time 0.929 (1.061) Data 0.000 (0.125) Loss 0.3910 (0.4053) Prec@1 91.797 (90.807) Prec@5 97.656 (97.765)
[2021-04-26 19:09:01 train_lshot.py:257] INFO Epoch: [83][110/150] Time 0.932 (1.050) Data 0.000 (0.114) Loss 0.4376 (0.4046) Prec@1 90.234 (90.871) Prec@5 96.875 (97.751)
[2021-04-26 19:09:10 train_lshot.py:257] INFO Epoch: [83][120/150] Time 0.931 (1.040) Data 0.000 (0.104) Loss 0.4579 (0.4056) Prec@1 89.844 (90.835) Prec@5 96.484 (97.705)
[2021-04-26 19:09:19 train_lshot.py:257] INFO Epoch: [83][130/150] Time 0.930 (1.032) Data 0.000 (0.096) Loss 0.4226 (0.4053) Prec@1 90.625 (90.777) Prec@5 96.484 (97.725)
[2021-04-26 19:09:29 train_lshot.py:257] INFO Epoch: [83][140/150] Time 0.936 (1.025) Data 0.000 (0.090) Loss 0.3903 (0.4054) Prec@1 91.016 (90.802) Prec@5 98.047 (97.706)
[2021-04-26 19:10:35 train_lshot.py:119] INFO Meta Val 83: 0.6137600141763687
[2021-04-26 19:10:47 train_lshot.py:257] INFO Epoch: [84][0/150] Time 11.221 (11.221) Data 10.277 (10.277) Loss 0.4137 (0.4137) Prec@1 91.016 (91.016) Prec@5 97.266 (97.266)
[2021-04-26 19:10:56 train_lshot.py:257] INFO Epoch: [84][10/150] Time 0.935 (1.869) Data 0.000 (0.936) Loss 0.4686 (0.4092) Prec@1 87.109 (90.945) Prec@5 96.484 (97.727)
[2021-04-26 19:11:05 train_lshot.py:257] INFO Epoch: [84][20/150] Time 0.936 (1.425) Data 0.001 (0.492) Loss 0.4309 (0.4102) Prec@1 92.578 (91.053) Prec@5 97.266 (97.749)
[2021-04-26 19:11:15 train_lshot.py:257] INFO Epoch: [84][30/150] Time 0.936 (1.267) Data 0.001 (0.333) Loss 0.3576 (0.4076) Prec@1 92.188 (91.016) Prec@5 97.656 (97.732)
[2021-04-26 19:11:24 train_lshot.py:257] INFO Epoch: [84][40/150] Time 0.937 (1.187) Data 0.000 (0.252) Loss 0.3441 (0.4013) Prec@1 93.750 (91.244) Prec@5 99.219 (97.771)
[2021-04-26 19:11:33 train_lshot.py:257] INFO Epoch: [84][50/150] Time 0.939 (1.138) Data 0.001 (0.203) Loss 0.4087 (0.4014) Prec@1 86.719 (91.199) Prec@5 98.438 (97.771)
[2021-04-26 19:11:43 train_lshot.py:257] INFO Epoch: [84][60/150] Time 0.933 (1.105) Data 0.000 (0.170) Loss 0.3718 (0.3981) Prec@1 92.578 (91.259) Prec@5 99.219 (97.784)
[2021-04-26 19:11:52 train_lshot.py:257] INFO Epoch: [84][70/150] Time 0.939 (1.081) Data 0.002 (0.146) Loss 0.4265 (0.4046) Prec@1 89.062 (90.966) Prec@5 97.266 (97.722)
[2021-04-26 19:12:02 train_lshot.py:257] INFO Epoch: [84][80/150] Time 0.939 (1.064) Data 0.000 (0.128) Loss 0.4786 (0.4070) Prec@1 87.891 (90.876) Prec@5 96.094 (97.656)
[2021-04-26 19:12:11 train_lshot.py:257] INFO Epoch: [84][90/150] Time 0.936 (1.050) Data 0.000 (0.114) Loss 0.3465 (0.4069) Prec@1 93.359 (90.861) Prec@5 98.438 (97.630)
[2021-04-26 19:12:20 train_lshot.py:257] INFO Epoch: [84][100/150] Time 0.936 (1.039) Data 0.000 (0.103) Loss 0.3600 (0.4070) Prec@1 92.969 (90.857) Prec@5 98.047 (97.656)
[2021-04-26 19:12:30 train_lshot.py:257] INFO Epoch: [84][110/150] Time 0.935 (1.030) Data 0.000 (0.093) Loss 0.3564 (0.4072) Prec@1 92.969 (90.847) Prec@5 97.656 (97.667)
[2021-04-26 19:12:39 train_lshot.py:257] INFO Epoch: [84][120/150] Time 0.936 (1.022) Data 0.000 (0.086) Loss 0.4012 (0.4066) Prec@1 89.844 (90.822) Prec@5 97.266 (97.676)
[2021-04-26 19:12:49 train_lshot.py:257] INFO Epoch: [84][130/150] Time 0.937 (1.016) Data 0.000 (0.079) Loss 0.4218 (0.4056) Prec@1 89.844 (90.846) Prec@5 97.266 (97.686)
[2021-04-26 19:12:58 train_lshot.py:257] INFO Epoch: [84][140/150] Time 0.938 (1.011) Data 0.000 (0.074) Loss 0.4073 (0.4057) Prec@1 91.016 (90.830) Prec@5 98.047 (97.689)
[2021-04-26 19:13:25 train_lshot.py:257] INFO Epoch: [85][0/150] Time 17.844 (17.844) Data 16.883 (16.883) Loss 0.3582 (0.3582) Prec@1 91.406 (91.406) Prec@5 99.219 (99.219)
[2021-04-26 19:13:35 train_lshot.py:257] INFO Epoch: [85][10/150] Time 0.933 (2.474) Data 0.000 (1.536) Loss 0.4088 (0.3906) Prec@1 90.625 (91.939) Prec@5 97.656 (97.905)
[2021-04-26 19:13:44 train_lshot.py:257] INFO Epoch: [85][20/150] Time 0.933 (1.758) Data 0.000 (0.819) Loss 0.3782 (0.4019) Prec@1 93.750 (91.239) Prec@5 98.438 (97.749)
[2021-04-26 19:13:54 train_lshot.py:257] INFO Epoch: [85][30/150] Time 0.935 (1.493) Data 0.000 (0.555) Loss 0.4218 (0.3946) Prec@1 90.234 (91.394) Prec@5 96.094 (97.883)
[2021-04-26 19:14:03 train_lshot.py:257] INFO Epoch: [85][40/150] Time 0.937 (1.357) Data 0.001 (0.420) Loss 0.4470 (0.3946) Prec@1 92.188 (91.416) Prec@5 96.094 (97.780)
[2021-04-26 19:14:12 train_lshot.py:257] INFO Epoch: [85][50/150] Time 0.941 (1.274) Data 0.000 (0.338) Loss 0.3547 (0.3903) Prec@1 93.359 (91.475) Prec@5 98.828 (97.894)
[2021-04-26 19:14:22 train_lshot.py:257] INFO Epoch: [85][60/150] Time 0.937 (1.219) Data 0.000 (0.283) Loss 0.4009 (0.3922) Prec@1 90.625 (91.317) Prec@5 97.656 (97.874)
[2021-04-26 19:14:31 train_lshot.py:257] INFO Epoch: [85][70/150] Time 0.931 (1.182) Data 0.002 (0.245) Loss 0.3828 (0.3954) Prec@1 91.406 (91.186) Prec@5 98.438 (97.821)
[2021-04-26 19:14:41 train_lshot.py:257] INFO Epoch: [85][80/150] Time 0.934 (1.153) Data 0.000 (0.216) Loss 0.3762 (0.3958) Prec@1 90.625 (91.107) Prec@5 98.438 (97.849)
[2021-04-26 19:14:50 train_lshot.py:257] INFO Epoch: [85][90/150] Time 0.934 (1.129) Data 0.000 (0.193) Loss 0.4240 (0.3954) Prec@1 90.625 (91.192) Prec@5 96.484 (97.867)
[2021-04-26 19:14:59 train_lshot.py:257] INFO Epoch: [85][100/150] Time 0.933 (1.110) Data 0.000 (0.173) Loss 0.4802 (0.3960) Prec@1 89.453 (91.170) Prec@5 97.656 (97.869)
[2021-04-26 19:15:09 train_lshot.py:257] INFO Epoch: [85][110/150] Time 0.933 (1.094) Data 0.000 (0.158) Loss 0.4452 (0.3967) Prec@1 85.938 (91.121) Prec@5 98.438 (97.878)
[2021-04-26 19:15:18 train_lshot.py:257] INFO Epoch: [85][120/150] Time 0.929 (1.081) Data 0.000 (0.145) Loss 0.4353 (0.3969) Prec@1 90.234 (91.122) Prec@5 97.656 (97.866)
[2021-04-26 19:15:28 train_lshot.py:257] INFO Epoch: [85][130/150] Time 0.942 (1.070) Data 0.000 (0.134) Loss 0.3693 (0.3979) Prec@1 90.234 (91.090) Prec@5 99.219 (97.847)
[2021-04-26 19:15:37 train_lshot.py:257] INFO Epoch: [85][140/150] Time 0.932 (1.060) Data 0.000 (0.124) Loss 0.4801 (0.3974) Prec@1 87.109 (91.115) Prec@5 96.484 (97.847)
[2021-04-26 19:15:58 train_lshot.py:257] INFO Epoch: [86][0/150] Time 12.112 (12.112) Data 11.174 (11.174) Loss 0.4659 (0.4659) Prec@1 89.844 (89.844) Prec@5 97.266 (97.266)
[2021-04-26 19:16:08 train_lshot.py:257] INFO Epoch: [86][10/150] Time 0.927 (1.953) Data 0.000 (1.021) Loss 0.4032 (0.4078) Prec@1 91.016 (90.838) Prec@5 98.047 (97.372)
[2021-04-26 19:16:17 train_lshot.py:257] INFO Epoch: [86][20/150] Time 0.934 (1.467) Data 0.000 (0.535) Loss 0.4244 (0.4099) Prec@1 88.281 (90.606) Prec@5 98.438 (97.600)
[2021-04-26 19:16:26 train_lshot.py:257] INFO Epoch: [86][30/150] Time 0.929 (1.295) Data 0.000 (0.363) Loss 0.3347 (0.4058) Prec@1 92.578 (90.864) Prec@5 99.609 (97.744)
[2021-04-26 19:16:36 train_lshot.py:257] INFO Epoch: [86][40/150] Time 0.930 (1.208) Data 0.000 (0.275) Loss 0.3730 (0.4026) Prec@1 90.234 (90.958) Prec@5 99.219 (97.837)
[2021-04-26 19:16:45 train_lshot.py:257] INFO Epoch: [86][50/150] Time 0.936 (1.155) Data 0.000 (0.221) Loss 0.3235 (0.4014) Prec@1 93.750 (90.924) Prec@5 98.438 (97.924)
[2021-04-26 19:16:55 train_lshot.py:257] INFO Epoch: [86][60/150] Time 0.942 (1.120) Data 0.001 (0.185) Loss 0.4198 (0.4051) Prec@1 90.234 (90.804) Prec@5 97.656 (97.855)
[2021-04-26 19:17:04 train_lshot.py:257] INFO Epoch: [86][70/150] Time 0.942 (1.094) Data 0.002 (0.159) Loss 0.4298 (0.4048) Prec@1 89.453 (90.807) Prec@5 97.656 (97.827)
[2021-04-26 19:17:13 train_lshot.py:257] INFO Epoch: [86][80/150] Time 0.937 (1.075) Data 0.000 (0.139) Loss 0.3951 (0.4066) Prec@1 89.453 (90.731) Prec@5 97.656 (97.806)
[2021-04-26 19:17:23 train_lshot.py:257] INFO Epoch: [86][90/150] Time 0.938 (1.059) Data 0.000 (0.124) Loss 0.3431 (0.4045) Prec@1 92.969 (90.810) Prec@5 97.656 (97.785)
[2021-04-26 19:17:32 train_lshot.py:257] INFO Epoch: [86][100/150] Time 0.933 (1.047) Data 0.000 (0.112) Loss 0.3499 (0.4042) Prec@1 92.578 (90.838) Prec@5 98.828 (97.776)
[2021-04-26 19:17:41 train_lshot.py:257] INFO Epoch: [86][110/150] Time 0.941 (1.038) Data 0.000 (0.102) Loss 0.3256 (0.4062) Prec@1 93.750 (90.804) Prec@5 98.828 (97.744)
[2021-04-26 19:17:51 train_lshot.py:257] INFO Epoch: [86][120/150] Time 0.934 (1.029) Data 0.000 (0.093) Loss 0.4493 (0.4052) Prec@1 90.625 (90.845) Prec@5 96.875 (97.750)
[2021-04-26 19:18:00 train_lshot.py:257] INFO Epoch: [86][130/150] Time 0.944 (1.022) Data 0.000 (0.086) Loss 0.3242 (0.4038) Prec@1 92.578 (90.917) Prec@5 99.609 (97.758)
[2021-04-26 19:18:10 train_lshot.py:257] INFO Epoch: [86][140/150] Time 0.943 (1.016) Data 0.000 (0.080) Loss 0.3630 (0.4039) Prec@1 92.969 (90.910) Prec@5 97.656 (97.778)
[2021-04-26 19:18:34 train_lshot.py:257] INFO Epoch: [87][0/150] Time 15.381 (15.381) Data 14.433 (14.433) Loss 0.3670 (0.3670) Prec@1 92.578 (92.578) Prec@5 97.656 (97.656)
[2021-04-26 19:18:44 train_lshot.py:257] INFO Epoch: [87][10/150] Time 0.936 (2.247) Data 0.000 (1.313) Loss 0.3784 (0.3879) Prec@1 91.016 (91.442) Prec@5 98.047 (97.692)
[2021-04-26 19:18:53 train_lshot.py:257] INFO Epoch: [87][20/150] Time 0.943 (1.623) Data 0.001 (0.688) Loss 0.4302 (0.3902) Prec@1 91.406 (91.462) Prec@5 98.828 (98.103)
[2021-04-26 19:19:03 train_lshot.py:257] INFO Epoch: [87][30/150] Time 0.930 (1.402) Data 0.000 (0.466) Loss 0.3869 (0.3961) Prec@1 91.406 (91.116) Prec@5 98.438 (98.047)
[2021-04-26 19:19:12 train_lshot.py:257] INFO Epoch: [87][40/150] Time 0.935 (1.289) Data 0.000 (0.353) Loss 0.4337 (0.3997) Prec@1 91.016 (91.120) Prec@5 95.312 (97.866)
[2021-04-26 19:19:21 train_lshot.py:257] INFO Epoch: [87][50/150] Time 0.942 (1.223) Data 0.000 (0.287) Loss 0.3646 (0.4064) Prec@1 92.578 (90.801) Prec@5 97.266 (97.763)
[2021-04-26 19:19:31 train_lshot.py:257] INFO Epoch: [87][60/150] Time 0.932 (1.177) Data 0.000 (0.240) Loss 0.4065 (0.4068) Prec@1 91.016 (90.811) Prec@5 98.047 (97.720)
[2021-04-26 19:19:40 train_lshot.py:257] INFO Epoch: [87][70/150] Time 0.943 (1.143) Data 0.002 (0.207) Loss 0.3972 (0.4050) Prec@1 91.797 (90.906) Prec@5 96.875 (97.772)
[2021-04-26 19:19:50 train_lshot.py:257] INFO Epoch: [87][80/150] Time 0.939 (1.118) Data 0.000 (0.181) Loss 0.3911 (0.4017) Prec@1 91.406 (91.011) Prec@5 98.047 (97.811)
[2021-04-26 19:19:59 train_lshot.py:257] INFO Epoch: [87][90/150] Time 0.940 (1.098) Data 0.000 (0.161) Loss 0.3960 (0.4045) Prec@1 90.625 (90.943) Prec@5 97.656 (97.776)
[2021-04-26 19:20:08 train_lshot.py:257] INFO Epoch: [87][100/150] Time 0.934 (1.082) Data 0.000 (0.145) Loss 0.3634 (0.4028) Prec@1 94.141 (91.016) Prec@5 97.656 (97.788)
[2021-04-26 19:20:18 train_lshot.py:257] INFO Epoch: [87][110/150] Time 0.936 (1.069) Data 0.000 (0.132) Loss 0.3401 (0.4030) Prec@1 92.578 (90.987) Prec@5 98.828 (97.769)
[2021-04-26 19:20:27 train_lshot.py:257] INFO Epoch: [87][120/150] Time 0.937 (1.058) Data 0.000 (0.121) Loss 0.3549 (0.4035) Prec@1 94.531 (90.990) Prec@5 98.828 (97.782)
[2021-04-26 19:20:36 train_lshot.py:257] INFO Epoch: [87][130/150] Time 0.933 (1.049) Data 0.000 (0.112) Loss 0.4301 (0.4039) Prec@1 91.016 (90.983) Prec@5 97.266 (97.746)
[2021-04-26 19:20:46 train_lshot.py:257] INFO Epoch: [87][140/150] Time 0.944 (1.041) Data 0.000 (0.104) Loss 0.4507 (0.4043) Prec@1 89.062 (90.963) Prec@5 96.875 (97.723)
[2021-04-26 19:21:54 train_lshot.py:119] INFO Meta Val 87: 0.6217333474755287
[2021-04-26 19:22:07 train_lshot.py:257] INFO Epoch: [88][0/150] Time 12.397 (12.397) Data 11.453 (11.453) Loss 0.4204 (0.4204) Prec@1 90.625 (90.625) Prec@5 98.438 (98.438)
[2021-04-26 19:22:17 train_lshot.py:257] INFO Epoch: [88][10/150] Time 0.951 (1.976) Data 0.000 (1.042) Loss 0.3626 (0.3931) Prec@1 92.188 (91.158) Prec@5 100.000 (98.047)
[2021-04-26 19:22:26 train_lshot.py:257] INFO Epoch: [88][20/150] Time 0.932 (1.480) Data 0.000 (0.546) Loss 0.4103 (0.3860) Prec@1 89.062 (91.536) Prec@5 97.266 (97.972)
[2021-04-26 19:22:35 train_lshot.py:257] INFO Epoch: [88][30/150] Time 0.941 (1.304) Data 0.001 (0.370) Loss 0.3344 (0.3893) Prec@1 93.359 (91.293) Prec@5 98.828 (97.996)
[2021-04-26 19:22:45 train_lshot.py:257] INFO Epoch: [88][40/150] Time 0.933 (1.215) Data 0.001 (0.280) Loss 0.3830 (0.3923) Prec@1 92.188 (91.178) Prec@5 98.438 (97.952)
[2021-04-26 19:22:54 train_lshot.py:257] INFO Epoch: [88][50/150] Time 0.933 (1.160) Data 0.001 (0.226) Loss 0.4206 (0.3944) Prec@1 89.453 (91.115) Prec@5 98.828 (97.963)
[2021-04-26 19:23:03 train_lshot.py:257] INFO Epoch: [88][60/150] Time 0.931 (1.123) Data 0.000 (0.189) Loss 0.4208 (0.3960) Prec@1 91.406 (91.092) Prec@5 96.875 (97.912)
[2021-04-26 19:23:13 train_lshot.py:257] INFO Epoch: [88][70/150] Time 0.945 (1.097) Data 0.001 (0.162) Loss 0.3587 (0.3974) Prec@1 94.531 (91.076) Prec@5 96.875 (97.838)
[2021-04-26 19:23:22 train_lshot.py:257] INFO Epoch: [88][80/150] Time 0.937 (1.077) Data 0.000 (0.142) Loss 0.4129 (0.3958) Prec@1 91.016 (91.117) Prec@5 97.656 (97.849)
[2021-04-26 19:23:32 train_lshot.py:257] INFO Epoch: [88][90/150] Time 0.935 (1.062) Data 0.000 (0.127) Loss 0.4709 (0.3990) Prec@1 88.672 (91.033) Prec@5 96.875 (97.798)
[2021-04-26 19:23:41 train_lshot.py:257] INFO Epoch: [88][100/150] Time 0.938 (1.049) Data 0.000 (0.114) Loss 0.4183 (0.3980) Prec@1 90.625 (91.112) Prec@5 97.266 (97.795)
[2021-04-26 19:23:50 train_lshot.py:257] INFO Epoch: [88][110/150] Time 0.942 (1.039) Data 0.000 (0.104) Loss 0.4125 (0.3951) Prec@1 90.234 (91.241) Prec@5 98.047 (97.871)
[2021-04-26 19:24:00 train_lshot.py:257] INFO Epoch: [88][120/150] Time 0.937 (1.031) Data 0.000 (0.095) Loss 0.3943 (0.3954) Prec@1 90.625 (91.209) Prec@5 98.047 (97.866)
[2021-04-26 19:24:09 train_lshot.py:257] INFO Epoch: [88][130/150] Time 0.936 (1.024) Data 0.000 (0.088) Loss 0.4336 (0.3968) Prec@1 89.453 (91.177) Prec@5 98.438 (97.841)
[2021-04-26 19:24:18 train_lshot.py:257] INFO Epoch: [88][140/150] Time 0.935 (1.018) Data 0.000 (0.082) Loss 0.3615 (0.3972) Prec@1 90.625 (91.196) Prec@5 98.438 (97.825)
[2021-04-26 19:24:41 train_lshot.py:257] INFO Epoch: [89][0/150] Time 12.663 (12.663) Data 11.694 (11.694) Loss 0.3743 (0.3743) Prec@1 90.625 (90.625) Prec@5 98.047 (98.047)
[2021-04-26 19:24:50 train_lshot.py:257] INFO Epoch: [89][10/150] Time 0.932 (2.002) Data 0.000 (1.064) Loss 0.4706 (0.3936) Prec@1 88.672 (91.229) Prec@5 96.094 (97.763)
[2021-04-26 19:24:59 train_lshot.py:257] INFO Epoch: [89][20/150] Time 0.942 (1.496) Data 0.001 (0.558) Loss 0.4382 (0.3920) Prec@1 89.844 (91.220) Prec@5 98.438 (97.861)
[2021-04-26 19:25:09 train_lshot.py:257] INFO Epoch: [89][30/150] Time 0.933 (1.316) Data 0.001 (0.378) Loss 0.3075 (0.3908) Prec@1 94.531 (91.192) Prec@5 99.219 (97.858)
[2021-04-26 19:25:18 train_lshot.py:257] INFO Epoch: [89][40/150] Time 0.932 (1.224) Data 0.000 (0.286) Loss 0.3326 (0.3947) Prec@1 93.750 (91.025) Prec@5 98.828 (97.856)
[2021-04-26 19:25:27 train_lshot.py:257] INFO Epoch: [89][50/150] Time 0.947 (1.168) Data 0.000 (0.230) Loss 0.3899 (0.3935) Prec@1 91.797 (91.085) Prec@5 98.047 (97.901)
[2021-04-26 19:25:37 train_lshot.py:257] INFO Epoch: [89][60/150] Time 0.944 (1.131) Data 0.001 (0.193) Loss 0.3893 (0.3963) Prec@1 90.234 (90.958) Prec@5 97.656 (97.848)
[2021-04-26 19:25:46 train_lshot.py:257] INFO Epoch: [89][70/150] Time 0.944 (1.104) Data 0.002 (0.166) Loss 0.4128 (0.4001) Prec@1 89.844 (90.873) Prec@5 98.438 (97.843)
[2021-04-26 19:25:56 train_lshot.py:257] INFO Epoch: [89][80/150] Time 0.933 (1.083) Data 0.000 (0.145) Loss 0.4620 (0.4000) Prec@1 88.672 (90.890) Prec@5 96.875 (97.830)
[2021-04-26 19:26:05 train_lshot.py:257] INFO Epoch: [89][90/150] Time 0.938 (1.067) Data 0.000 (0.129) Loss 0.4237 (0.3999) Prec@1 89.453 (90.891) Prec@5 97.266 (97.815)
[2021-04-26 19:26:14 train_lshot.py:257] INFO Epoch: [89][100/150] Time 0.932 (1.054) Data 0.000 (0.116) Loss 0.4344 (0.4010) Prec@1 91.016 (90.911) Prec@5 95.312 (97.799)
[2021-04-26 19:26:24 train_lshot.py:257] INFO Epoch: [89][110/150] Time 0.941 (1.044) Data 0.000 (0.106) Loss 0.3233 (0.4019) Prec@1 94.141 (90.907) Prec@5 98.438 (97.772)
[2021-04-26 19:26:33 train_lshot.py:257] INFO Epoch: [89][120/150] Time 0.933 (1.035) Data 0.000 (0.097) Loss 0.4367 (0.4035) Prec@1 89.062 (90.874) Prec@5 98.047 (97.724)
[2021-04-26 19:26:43 train_lshot.py:257] INFO Epoch: [89][130/150] Time 0.937 (1.028) Data 0.000 (0.090) Loss 0.3099 (0.4009) Prec@1 94.922 (90.962) Prec@5 99.219 (97.752)
[2021-04-26 19:26:52 train_lshot.py:257] INFO Epoch: [89][140/150] Time 0.938 (1.021) Data 0.000 (0.083) Loss 0.3823 (0.4007) Prec@1 92.969 (91.027) Prec@5 98.047 (97.745)
[2021-04-26 19:28:23 train_lshot.py:570] INFO validation lmd=0.10: Best
feature CL2N
GVP 1Shot 0.7321(0.0089)
GVP_5Shot 0.8255(0.0062))
[2021-04-26 19:28:26 train_lshot.py:570] INFO validation lmd=0.30: Best
feature CL2N
GVP 1Shot 0.7289(0.0092)
GVP_5Shot 0.8269(0.0063))
[2021-04-26 19:28:29 train_lshot.py:570] INFO validation lmd=0.50: Best
feature CL2N
GVP 1Shot 0.7299(0.0092)
GVP_5Shot 0.8239(0.0064))
[2021-04-26 19:28:32 train_lshot.py:570] INFO validation lmd=0.70: Best
feature CL2N
GVP 1Shot 0.7393(0.0093)
GVP_5Shot 0.8142(0.0066))
[2021-04-26 19:28:35 train_lshot.py:570] INFO validation lmd=0.80: Best
feature CL2N
GVP 1Shot 0.7396(0.0089)
GVP_5Shot 0.8183(0.0066))
[2021-04-26 19:28:38 train_lshot.py:570] INFO validation lmd=1.00: Best
feature CL2N
GVP 1Shot 0.7374(0.0088)
GVP_5Shot 0.8012(0.0065))
[2021-04-26 19:28:42 train_lshot.py:570] INFO validation lmd=1.20: Best
feature CL2N
GVP 1Shot 0.7220(0.0088)
GVP_5Shot 0.7881(0.0070))
[2021-04-26 19:28:45 train_lshot.py:570] INFO validation lmd=1.50: Best
feature CL2N
GVP 1Shot 0.7092(0.0088)
GVP_5Shot 0.7432(0.0079))
[2021-04-26 19:28:45 train_lshot.py:580] INFO Best lambda on validation:
0.80 with 1 shot acc 0.7396
0.30 with 5 shot acc 0.8269
[2021-04-26 19:28:45 train_lshot.py:707] INFO Proto-rectification = True in Evaluation
[2021-04-26 19:30:04 train_lshot.py:713] INFO Run with lambda 0.8 for 1 shot
[2021-04-26 19:31:23 train_lshot.py:717] INFO Run with lambda 0.3 for 5 shot
[2021-04-26 19:32:34 train_lshot.py:724] INFO Meta Test: LAST
feature UN L2N CL2N
GVP 1Shot 0.6551(0.0021) 0.6629(0.0020) 0.7077(0.0020)
GVP_5Shot 0.7463(0.0019) 0.7448(0.0019) 0.8048(0.0015)
[2021-04-26 19:33:01 train_lshot.py:730] INFO Run with lambda 0.8 for 1 shot
[2021-04-26 19:34:22 train_lshot.py:734] INFO Run with lambda 0.3 for 5 shot
[2021-04-26 19:35:33 train_lshot.py:741] INFO Meta Test: BEST
feature UN L2N CL2N
GVP 1Shot 0.6719(0.0020) 0.6792(0.0020) 0.7194(0.0019)
GVP_5Shot 0.7650(0.0018) 0.7650(0.0018) 0.8143(0.0015)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment