Skip to content

Instantly share code, notes, and snippets.

@shwangtangjun

shwangtangjun/LaplacianShot.log Secret

Created April 29, 2021 02:59
Show Gist options
  • Save shwangtangjun/b31e0e01afbc378045d2274f65762c1f to your computer and use it in GitHub Desktop.
Save shwangtangjun/b31e0e01afbc378045d2274f65762c1f to your computer and use it in GitHub Desktop.
Download ZIP
Raw
LaplacianShot.log
[2021-04-28 21:45:56 train_lshot.py:38] INFO arch: resnet18
[2021-04-28 21:45:56 train_lshot.py:38] INFO batch_size: 256
[2021-04-28 21:45:56 train_lshot.py:38] INFO beta: -1.0
[2021-04-28 21:45:56 train_lshot.py:38] INFO config: ./configs/mini/softmax/resnet18.config
[2021-04-28 21:45:56 train_lshot.py:38] INFO cutmix_prob: 0
[2021-04-28 21:45:56 train_lshot.py:38] INFO data: ./data/images
[2021-04-28 21:45:56 train_lshot.py:38] INFO disable_random_resize: False
[2021-04-28 21:45:56 train_lshot.py:38] INFO disable_tqdm: False
[2021-04-28 21:45:56 train_lshot.py:38] INFO disable_train_augment: False
[2021-04-28 21:45:56 train_lshot.py:38] INFO do_meta_train: False
[2021-04-28 21:45:56 train_lshot.py:38] INFO enlarge: True
[2021-04-28 21:45:56 train_lshot.py:38] INFO epochs: 90
[2021-04-28 21:45:56 train_lshot.py:38] INFO eval_fc: False
[2021-04-28 21:45:56 train_lshot.py:38] INFO evaluate: False
[2021-04-28 21:45:56 train_lshot.py:38] INFO jitter: False
[2021-04-28 21:45:56 train_lshot.py:38] INFO knn: 3
[2021-04-28 21:45:56 train_lshot.py:38] INFO label_smooth: 0.1
[2021-04-28 21:45:56 train_lshot.py:38] INFO lmd: 1.0
[2021-04-28 21:45:56 train_lshot.py:38] INFO log_file: /LaplacianShot.log
[2021-04-28 21:45:56 train_lshot.py:38] INFO lr: 0.1
[2021-04-28 21:45:56 train_lshot.py:38] INFO lr_gamma: 0.1
[2021-04-28 21:45:56 train_lshot.py:38] INFO lr_stepsize: 30
[2021-04-28 21:45:56 train_lshot.py:38] INFO lshot: True
[2021-04-28 21:45:56 train_lshot.py:38] INFO meta_test_iter: 10000
[2021-04-28 21:45:56 train_lshot.py:38] INFO meta_train_iter: 100
[2021-04-28 21:45:56 train_lshot.py:38] INFO meta_train_metric: euclidean
[2021-04-28 21:45:56 train_lshot.py:38] INFO meta_train_query: 15
[2021-04-28 21:45:56 train_lshot.py:38] INFO meta_train_shot: 1
[2021-04-28 21:45:56 train_lshot.py:38] INFO meta_train_way: 30
[2021-04-28 21:45:56 train_lshot.py:38] INFO meta_val_interval: 4
[2021-04-28 21:45:56 train_lshot.py:38] INFO meta_val_iter: 500
[2021-04-28 21:45:56 train_lshot.py:38] INFO meta_val_metric: cosine
[2021-04-28 21:45:56 train_lshot.py:38] INFO meta_val_query: 15
[2021-04-28 21:45:56 train_lshot.py:38] INFO meta_val_shot: 1
[2021-04-28 21:45:56 train_lshot.py:38] INFO meta_val_way: 5
[2021-04-28 21:45:56 train_lshot.py:38] INFO nesterov: False
[2021-04-28 21:45:56 train_lshot.py:38] INFO num_NN: 1
[2021-04-28 21:45:56 train_lshot.py:38] INFO num_classes: 64
[2021-04-28 21:45:56 train_lshot.py:38] INFO optimizer: SGD
[2021-04-28 21:45:56 train_lshot.py:38] INFO plot_converge: False
[2021-04-28 21:45:56 train_lshot.py:38] INFO pretrain: None
[2021-04-28 21:45:56 train_lshot.py:38] INFO print_freq: 10
[2021-04-28 21:45:56 train_lshot.py:38] INFO proto_rect: True
[2021-04-28 21:45:56 train_lshot.py:38] INFO resume:
[2021-04-28 21:45:56 train_lshot.py:38] INFO save_path: ./results/mini/softmax/resnet18
[2021-04-28 21:45:56 train_lshot.py:38] INFO scheduler: multi_step
[2021-04-28 21:45:56 train_lshot.py:38] INFO seed: None
[2021-04-28 21:45:56 train_lshot.py:38] INFO split_dir: ./split/mini/
[2021-04-28 21:45:56 train_lshot.py:38] INFO start_epoch: 0
[2021-04-28 21:45:56 train_lshot.py:38] INFO tune_lmd: True
[2021-04-28 21:45:56 train_lshot.py:38] INFO weight_decay: 0.0001
[2021-04-28 21:45:56 train_lshot.py:38] INFO workers: 40
[2021-04-28 21:45:56 train_lshot.py:46] INFO => creating model 'resnet18'
[2021-04-28 21:45:56 train_lshot.py:49] INFO Number of model parameters: 11201664
[2021-04-28 21:46:15 train_lshot.py:257] INFO Epoch: [0][0/150] Time 14.408 (14.408) Data 6.141 (6.141) Loss 3.5586 (3.5586) Prec@1 1.562 (1.562) Prec@5 10.938 (10.938)
[2021-04-28 21:46:18 train_lshot.py:257] INFO Epoch: [0][10/150] Time 0.262 (1.556) Data 0.000 (0.559) Loss 3.4806 (3.5353) Prec@1 3.125 (2.983) Prec@5 16.406 (13.033)
[2021-04-28 21:46:20 train_lshot.py:257] INFO Epoch: [0][20/150] Time 0.266 (0.945) Data 0.000 (0.293) Loss 3.2679 (3.4723) Prec@1 6.641 (4.706) Prec@5 24.219 (16.778)
[2021-04-28 21:46:23 train_lshot.py:257] INFO Epoch: [0][30/150] Time 0.266 (0.726) Data 0.000 (0.199) Loss 3.2506 (3.3936) Prec@1 7.812 (5.444) Prec@5 24.609 (19.430)
[2021-04-28 21:46:26 train_lshot.py:257] INFO Epoch: [0][40/150] Time 0.264 (0.614) Data 0.001 (0.150) Loss 3.1505 (3.3387) Prec@1 9.375 (6.117) Prec@5 28.906 (21.446)
[2021-04-28 21:46:28 train_lshot.py:257] INFO Epoch: [0][50/150] Time 0.272 (0.546) Data 0.001 (0.121) Loss 3.1090 (3.2871) Prec@1 9.766 (6.679) Prec@5 29.688 (23.139)
[2021-04-28 21:46:31 train_lshot.py:257] INFO Epoch: [0][60/150] Time 0.282 (0.500) Data 0.001 (0.101) Loss 2.9922 (3.2416) Prec@1 10.938 (7.326) Prec@5 34.766 (24.763)
[2021-04-28 21:46:34 train_lshot.py:257] INFO Epoch: [0][70/150] Time 0.267 (0.467) Data 0.002 (0.087) Loss 2.9972 (3.2071) Prec@1 13.672 (7.812) Prec@5 35.547 (25.864)
[2021-04-28 21:46:36 train_lshot.py:257] INFO Epoch: [0][80/150] Time 0.264 (0.443) Data 0.000 (0.076) Loss 3.0083 (3.1771) Prec@1 8.203 (8.251) Prec@5 30.859 (26.943)
[2021-04-28 21:46:39 train_lshot.py:257] INFO Epoch: [0][90/150] Time 0.267 (0.423) Data 0.000 (0.068) Loss 2.9391 (3.1558) Prec@1 12.500 (8.585) Prec@5 36.719 (27.764)
[2021-04-28 21:46:42 train_lshot.py:257] INFO Epoch: [0][100/150] Time 0.265 (0.408) Data 0.000 (0.061) Loss 2.8755 (3.1335) Prec@1 14.844 (8.938) Prec@5 42.188 (28.585)
[2021-04-28 21:46:44 train_lshot.py:257] INFO Epoch: [0][110/150] Time 0.267 (0.395) Data 0.000 (0.056) Loss 3.0214 (3.1180) Prec@1 12.109 (9.160) Prec@5 33.203 (29.255)
[2021-04-28 21:46:47 train_lshot.py:257] INFO Epoch: [0][120/150] Time 0.268 (0.385) Data 0.000 (0.051) Loss 2.8905 (3.1010) Prec@1 12.891 (9.369) Prec@5 40.234 (29.839)
[2021-04-28 21:46:50 train_lshot.py:257] INFO Epoch: [0][130/150] Time 0.267 (0.376) Data 0.000 (0.047) Loss 2.9910 (3.0850) Prec@1 12.109 (9.733) Prec@5 35.156 (30.591)
[2021-04-28 21:46:52 train_lshot.py:257] INFO Epoch: [0][140/150] Time 0.266 (0.368) Data 0.000 (0.044) Loss 2.8978 (3.0688) Prec@1 15.234 (10.040) Prec@5 36.719 (31.258)
[2021-04-28 21:47:00 train_lshot.py:257] INFO Epoch: [1][0/150] Time 4.806 (4.806) Data 4.389 (4.389) Loss 2.8114 (2.8114) Prec@1 18.359 (18.359) Prec@5 46.094 (46.094)
[2021-04-28 21:47:04 train_lshot.py:257] INFO Epoch: [1][10/150] Time 0.357 (0.818) Data 0.000 (0.446) Loss 2.7219 (2.8046) Prec@1 16.406 (15.021) Prec@5 42.578 (42.294)
[2021-04-28 21:47:07 train_lshot.py:257] INFO Epoch: [1][20/150] Time 0.275 (0.568) Data 0.001 (0.235) Loss 2.7924 (2.7840) Prec@1 15.234 (15.551) Prec@5 42.578 (42.578)
[2021-04-28 21:47:10 train_lshot.py:257] INFO Epoch: [1][30/150] Time 0.270 (0.473) Data 0.000 (0.159) Loss 2.7843 (2.7844) Prec@1 18.750 (16.192) Prec@5 46.875 (42.540)
[2021-04-28 21:47:13 train_lshot.py:257] INFO Epoch: [1][40/150] Time 0.278 (0.424) Data 0.000 (0.120) Loss 2.7363 (2.7710) Prec@1 16.797 (16.387) Prec@5 44.922 (42.988)
[2021-04-28 21:47:15 train_lshot.py:257] INFO Epoch: [1][50/150] Time 0.269 (0.394) Data 0.000 (0.097) Loss 2.7868 (2.7578) Prec@1 19.141 (16.751) Prec@5 44.141 (43.421)
[2021-04-28 21:47:18 train_lshot.py:257] INFO Epoch: [1][60/150] Time 0.271 (0.374) Data 0.000 (0.081) Loss 2.6486 (2.7474) Prec@1 17.969 (17.053) Prec@5 49.609 (43.897)
[2021-04-28 21:47:21 train_lshot.py:257] INFO Epoch: [1][70/150] Time 0.274 (0.360) Data 0.001 (0.070) Loss 2.6661 (2.7421) Prec@1 17.578 (17.221) Prec@5 45.703 (44.064)
[2021-04-28 21:47:23 train_lshot.py:257] INFO Epoch: [1][80/150] Time 0.271 (0.350) Data 0.000 (0.061) Loss 2.7111 (2.7309) Prec@1 17.578 (17.544) Prec@5 49.219 (44.652)
[2021-04-28 21:47:26 train_lshot.py:257] INFO Epoch: [1][90/150] Time 0.277 (0.341) Data 0.000 (0.054) Loss 2.5480 (2.7219) Prec@1 20.312 (17.776) Prec@5 54.297 (45.106)
[2021-04-28 21:47:29 train_lshot.py:257] INFO Epoch: [1][100/150] Time 0.275 (0.335) Data 0.000 (0.049) Loss 2.7732 (2.7141) Prec@1 16.016 (17.891) Prec@5 43.359 (45.320)
[2021-04-28 21:47:32 train_lshot.py:257] INFO Epoch: [1][110/150] Time 0.272 (0.329) Data 0.000 (0.045) Loss 2.6918 (2.7065) Prec@1 20.703 (18.180) Prec@5 48.828 (45.573)
[2021-04-28 21:47:34 train_lshot.py:257] INFO Epoch: [1][120/150] Time 0.274 (0.324) Data 0.000 (0.041) Loss 2.5214 (2.6974) Prec@1 21.875 (18.366) Prec@5 52.344 (45.948)
[2021-04-28 21:47:37 train_lshot.py:257] INFO Epoch: [1][130/150] Time 0.289 (0.321) Data 0.000 (0.038) Loss 2.5554 (2.6875) Prec@1 21.094 (18.726) Prec@5 53.906 (46.371)
[2021-04-28 21:47:40 train_lshot.py:257] INFO Epoch: [1][140/150] Time 0.273 (0.318) Data 0.000 (0.035) Loss 2.4980 (2.6775) Prec@1 21.875 (18.955) Prec@5 55.859 (46.709)
[2021-04-28 21:47:48 train_lshot.py:257] INFO Epoch: [2][0/150] Time 4.627 (4.627) Data 4.179 (4.179) Loss 2.5581 (2.5581) Prec@1 18.359 (18.359) Prec@5 51.172 (51.172)
[2021-04-28 21:47:53 train_lshot.py:257] INFO Epoch: [2][10/150] Time 0.304 (0.897) Data 0.001 (0.538) Loss 2.5543 (2.5545) Prec@1 21.484 (21.733) Prec@5 54.688 (51.030)
[2021-04-28 21:47:56 train_lshot.py:257] INFO Epoch: [2][20/150] Time 0.283 (0.602) Data 0.000 (0.282) Loss 2.6113 (2.5335) Prec@1 19.141 (22.433) Prec@5 51.562 (52.697)
[2021-04-28 21:47:58 train_lshot.py:257] INFO Epoch: [2][30/150] Time 0.273 (0.498) Data 0.000 (0.191) Loss 2.4190 (2.5220) Prec@1 24.219 (23.034) Prec@5 58.984 (53.049)
[2021-04-28 21:48:01 train_lshot.py:257] INFO Epoch: [2][40/150] Time 0.285 (0.444) Data 0.000 (0.145) Loss 2.5458 (2.5221) Prec@1 24.609 (23.161) Prec@5 51.953 (52.934)
[2021-04-28 21:48:04 train_lshot.py:257] INFO Epoch: [2][50/150] Time 0.281 (0.413) Data 0.000 (0.117) Loss 2.4077 (2.5069) Prec@1 24.219 (23.491) Prec@5 53.516 (53.209)
[2021-04-28 21:48:07 train_lshot.py:257] INFO Epoch: [2][60/150] Time 0.273 (0.391) Data 0.000 (0.097) Loss 2.3849 (2.4926) Prec@1 27.734 (24.046) Prec@5 55.078 (53.797)
[2021-04-28 21:48:10 train_lshot.py:257] INFO Epoch: [2][70/150] Time 0.273 (0.375) Data 0.001 (0.084) Loss 2.4060 (2.4857) Prec@1 25.391 (24.114) Prec@5 55.859 (54.027)
[2021-04-28 21:48:12 train_lshot.py:257] INFO Epoch: [2][80/150] Time 0.272 (0.363) Data 0.000 (0.073) Loss 2.3712 (2.4801) Prec@1 26.172 (24.301) Prec@5 59.766 (54.326)
[2021-04-28 21:48:15 train_lshot.py:257] INFO Epoch: [2][90/150] Time 0.276 (0.353) Data 0.000 (0.065) Loss 2.3195 (2.4722) Prec@1 26.953 (24.438) Prec@5 59.375 (54.606)
[2021-04-28 21:48:18 train_lshot.py:257] INFO Epoch: [2][100/150] Time 0.277 (0.346) Data 0.000 (0.059) Loss 2.4954 (2.4696) Prec@1 25.391 (24.474) Prec@5 53.125 (54.746)
[2021-04-28 21:48:21 train_lshot.py:257] INFO Epoch: [2][110/150] Time 0.275 (0.340) Data 0.000 (0.054) Loss 2.2711 (2.4623) Prec@1 28.125 (24.669) Prec@5 62.891 (54.980)
[2021-04-28 21:48:24 train_lshot.py:257] INFO Epoch: [2][120/150] Time 0.286 (0.335) Data 0.000 (0.049) Loss 2.3912 (2.4542) Prec@1 27.344 (24.819) Prec@5 58.203 (55.340)
[2021-04-28 21:48:26 train_lshot.py:257] INFO Epoch: [2][130/150] Time 0.275 (0.330) Data 0.000 (0.046) Loss 2.3342 (2.4462) Prec@1 26.953 (25.000) Prec@5 61.328 (55.627)
[2021-04-28 21:48:29 train_lshot.py:257] INFO Epoch: [2][140/150] Time 0.282 (0.327) Data 0.001 (0.042) Loss 2.1942 (2.4386) Prec@1 27.344 (25.199) Prec@5 63.281 (55.979)
[2021-04-28 21:48:39 train_lshot.py:257] INFO Epoch: [3][0/150] Time 6.787 (6.787) Data 6.341 (6.341) Loss 2.3295 (2.3295) Prec@1 31.250 (31.250) Prec@5 62.891 (62.891)
[2021-04-28 21:48:42 train_lshot.py:257] INFO Epoch: [3][10/150] Time 0.279 (0.917) Data 0.000 (0.577) Loss 2.3259 (2.2837) Prec@1 28.906 (30.007) Prec@5 60.938 (61.506)
[2021-04-28 21:48:45 train_lshot.py:257] INFO Epoch: [3][20/150] Time 0.273 (0.613) Data 0.000 (0.302) Loss 2.2865 (2.2896) Prec@1 27.734 (29.260) Prec@5 60.938 (61.031)
[2021-04-28 21:48:48 train_lshot.py:257] INFO Epoch: [3][30/150] Time 0.281 (0.504) Data 0.000 (0.205) Loss 2.2556 (2.2772) Prec@1 31.250 (29.688) Prec@5 60.547 (61.190)
[2021-04-28 21:48:51 train_lshot.py:257] INFO Epoch: [3][40/150] Time 0.278 (0.451) Data 0.001 (0.155) Loss 2.2496 (2.2669) Prec@1 30.469 (30.345) Prec@5 62.109 (61.633)
[2021-04-28 21:48:53 train_lshot.py:257] INFO Epoch: [3][50/150] Time 0.272 (0.417) Data 0.000 (0.125) Loss 2.3916 (2.2791) Prec@1 27.734 (29.887) Prec@5 55.859 (61.282)
[2021-04-28 21:48:56 train_lshot.py:257] INFO Epoch: [3][60/150] Time 0.276 (0.395) Data 0.000 (0.104) Loss 2.2784 (2.2785) Prec@1 26.172 (29.899) Prec@5 58.984 (60.982)
[2021-04-28 21:48:59 train_lshot.py:257] INFO Epoch: [3][70/150] Time 0.273 (0.378) Data 0.001 (0.090) Loss 2.2461 (2.2733) Prec@1 29.297 (29.781) Prec@5 63.281 (61.339)
[2021-04-28 21:49:02 train_lshot.py:257] INFO Epoch: [3][80/150] Time 0.280 (0.366) Data 0.000 (0.079) Loss 2.1349 (2.2681) Prec@1 36.328 (29.914) Prec@5 64.062 (61.454)
[2021-04-28 21:49:05 train_lshot.py:257] INFO Epoch: [3][90/150] Time 0.284 (0.356) Data 0.000 (0.070) Loss 2.2231 (2.2660) Prec@1 29.688 (30.005) Prec@5 64.453 (61.534)
[2021-04-28 21:49:07 train_lshot.py:257] INFO Epoch: [3][100/150] Time 0.272 (0.349) Data 0.000 (0.063) Loss 2.0656 (2.2603) Prec@1 35.938 (30.167) Prec@5 69.531 (61.649)
[2021-04-28 21:49:10 train_lshot.py:257] INFO Epoch: [3][110/150] Time 0.280 (0.342) Data 0.000 (0.057) Loss 2.1851 (2.2500) Prec@1 33.984 (30.458) Prec@5 63.281 (62.067)
[2021-04-28 21:49:13 train_lshot.py:257] INFO Epoch: [3][120/150] Time 0.273 (0.337) Data 0.000 (0.053) Loss 2.2534 (2.2482) Prec@1 32.031 (30.430) Prec@5 65.234 (62.119)
[2021-04-28 21:49:16 train_lshot.py:257] INFO Epoch: [3][130/150] Time 0.276 (0.333) Data 0.000 (0.049) Loss 2.1837 (2.2440) Prec@1 33.984 (30.546) Prec@5 64.844 (62.217)
[2021-04-28 21:49:18 train_lshot.py:257] INFO Epoch: [3][140/150] Time 0.277 (0.329) Data 0.000 (0.045) Loss 2.0607 (2.2373) Prec@1 34.375 (30.721) Prec@5 67.188 (62.511)
[2021-04-28 21:49:49 train_lshot.py:119] INFO Meta Val 3: 0.4322933432161808
[2021-04-28 21:49:54 train_lshot.py:257] INFO Epoch: [4][0/150] Time 4.638 (4.638) Data 4.203 (4.203) Loss 2.0889 (2.0889) Prec@1 36.328 (36.328) Prec@5 66.406 (66.406)
[2021-04-28 21:49:59 train_lshot.py:257] INFO Epoch: [4][10/150] Time 0.357 (0.844) Data 0.002 (0.493) Loss 1.9796 (2.0960) Prec@1 35.938 (34.055) Prec@5 70.312 (67.507)
[2021-04-28 21:50:02 train_lshot.py:257] INFO Epoch: [4][20/150] Time 0.280 (0.578) Data 0.000 (0.259) Loss 2.0853 (2.1086) Prec@1 38.281 (34.263) Prec@5 67.578 (66.890)
[2021-04-28 21:50:05 train_lshot.py:257] INFO Epoch: [4][30/150] Time 0.280 (0.481) Data 0.000 (0.175) Loss 2.0420 (2.1034) Prec@1 33.594 (34.413) Prec@5 71.484 (66.658)
[2021-04-28 21:50:07 train_lshot.py:257] INFO Epoch: [4][40/150] Time 0.276 (0.432) Data 0.000 (0.133) Loss 2.0753 (2.0999) Prec@1 33.203 (34.356) Prec@5 68.359 (66.740)
[2021-04-28 21:50:10 train_lshot.py:257] INFO Epoch: [4][50/150] Time 0.281 (0.403) Data 0.000 (0.107) Loss 2.2526 (2.0982) Prec@1 31.250 (34.544) Prec@5 60.938 (66.743)
[2021-04-28 21:50:13 train_lshot.py:257] INFO Epoch: [4][60/150] Time 0.273 (0.383) Data 0.000 (0.089) Loss 1.9409 (2.0990) Prec@1 38.672 (34.241) Prec@5 70.703 (66.592)
[2021-04-28 21:50:16 train_lshot.py:257] INFO Epoch: [4][70/150] Time 0.281 (0.368) Data 0.001 (0.077) Loss 2.0649 (2.1020) Prec@1 31.250 (34.254) Prec@5 69.141 (66.522)
[2021-04-28 21:50:19 train_lshot.py:257] INFO Epoch: [4][80/150] Time 0.281 (0.357) Data 0.000 (0.067) Loss 2.0522 (2.1032) Prec@1 34.766 (34.211) Prec@5 66.797 (66.633)
[2021-04-28 21:50:21 train_lshot.py:257] INFO Epoch: [4][90/150] Time 0.277 (0.348) Data 0.000 (0.060) Loss 2.3176 (2.1035) Prec@1 30.859 (34.281) Prec@5 59.766 (66.544)
[2021-04-28 21:50:24 train_lshot.py:257] INFO Epoch: [4][100/150] Time 0.285 (0.342) Data 0.001 (0.054) Loss 2.1017 (2.1028) Prec@1 30.078 (34.232) Prec@5 66.406 (66.534)
[2021-04-28 21:50:27 train_lshot.py:257] INFO Epoch: [4][110/150] Time 0.276 (0.336) Data 0.000 (0.049) Loss 2.1051 (2.0999) Prec@1 32.422 (34.350) Prec@5 67.969 (66.621)
[2021-04-28 21:50:30 train_lshot.py:257] INFO Epoch: [4][120/150] Time 0.286 (0.331) Data 0.000 (0.045) Loss 2.1171 (2.0949) Prec@1 37.109 (34.527) Prec@5 65.234 (66.761)
[2021-04-28 21:50:33 train_lshot.py:257] INFO Epoch: [4][130/150] Time 0.286 (0.327) Data 0.000 (0.042) Loss 2.1259 (2.0927) Prec@1 35.938 (34.578) Prec@5 67.578 (66.833)
[2021-04-28 21:50:35 train_lshot.py:257] INFO Epoch: [4][140/150] Time 0.280 (0.324) Data 0.000 (0.039) Loss 2.0955 (2.0864) Prec@1 33.594 (34.846) Prec@5 65.625 (67.030)
[2021-04-28 21:50:45 train_lshot.py:257] INFO Epoch: [5][0/150] Time 6.117 (6.117) Data 5.653 (5.653) Loss 1.9672 (1.9672) Prec@1 38.281 (38.281) Prec@5 72.266 (72.266)
[2021-04-28 21:50:48 train_lshot.py:257] INFO Epoch: [5][10/150] Time 0.295 (0.881) Data 0.000 (0.515) Loss 2.0194 (1.9570) Prec@1 36.719 (38.601) Prec@5 70.703 (70.952)
[2021-04-28 21:50:51 train_lshot.py:257] INFO Epoch: [5][20/150] Time 0.279 (0.600) Data 0.000 (0.270) Loss 2.0827 (1.9675) Prec@1 35.156 (38.374) Prec@5 68.750 (70.815)
[2021-04-28 21:50:54 train_lshot.py:257] INFO Epoch: [5][30/150] Time 0.279 (0.496) Data 0.000 (0.183) Loss 1.8051 (1.9681) Prec@1 45.703 (38.306) Prec@5 74.609 (70.703)
[2021-04-28 21:50:57 train_lshot.py:257] INFO Epoch: [5][40/150] Time 0.288 (0.445) Data 0.000 (0.139) Loss 2.1073 (1.9720) Prec@1 32.422 (38.357) Prec@5 67.578 (70.655)
[2021-04-28 21:51:00 train_lshot.py:257] INFO Epoch: [5][50/150] Time 0.280 (0.413) Data 0.000 (0.111) Loss 1.7945 (1.9714) Prec@1 42.578 (38.320) Prec@5 74.609 (70.650)
[2021-04-28 21:51:02 train_lshot.py:257] INFO Epoch: [5][60/150] Time 0.285 (0.391) Data 0.000 (0.093) Loss 1.9361 (1.9677) Prec@1 37.500 (38.326) Prec@5 70.312 (70.613)
[2021-04-28 21:51:05 train_lshot.py:257] INFO Epoch: [5][70/150] Time 0.277 (0.375) Data 0.001 (0.080) Loss 1.9190 (1.9686) Prec@1 42.188 (38.397) Prec@5 70.703 (70.582)
[2021-04-28 21:51:08 train_lshot.py:257] INFO Epoch: [5][80/150] Time 0.278 (0.363) Data 0.000 (0.070) Loss 1.9167 (1.9642) Prec@1 39.453 (38.508) Prec@5 71.875 (70.631)
[2021-04-28 21:51:11 train_lshot.py:257] INFO Epoch: [5][90/150] Time 0.281 (0.354) Data 0.000 (0.063) Loss 1.8937 (1.9582) Prec@1 41.797 (38.749) Prec@5 71.484 (70.677)
[2021-04-28 21:51:14 train_lshot.py:257] INFO Epoch: [5][100/150] Time 0.278 (0.347) Data 0.000 (0.056) Loss 1.9546 (1.9512) Prec@1 39.844 (38.997) Prec@5 69.531 (70.889)
[2021-04-28 21:51:16 train_lshot.py:257] INFO Epoch: [5][110/150] Time 0.288 (0.341) Data 0.000 (0.051) Loss 1.8408 (1.9472) Prec@1 40.625 (39.073) Prec@5 71.094 (70.907)
[2021-04-28 21:51:19 train_lshot.py:257] INFO Epoch: [5][120/150] Time 0.286 (0.337) Data 0.000 (0.047) Loss 1.9802 (1.9484) Prec@1 37.109 (39.066) Prec@5 70.703 (70.835)
[2021-04-28 21:51:22 train_lshot.py:257] INFO Epoch: [5][130/150] Time 0.282 (0.333) Data 0.000 (0.044) Loss 1.8875 (1.9435) Prec@1 44.141 (39.238) Prec@5 68.750 (70.995)
[2021-04-28 21:51:25 train_lshot.py:257] INFO Epoch: [5][140/150] Time 0.283 (0.329) Data 0.000 (0.040) Loss 1.9433 (1.9402) Prec@1 38.672 (39.306) Prec@5 69.531 (71.119)
[2021-04-28 21:51:34 train_lshot.py:257] INFO Epoch: [6][0/150] Time 6.041 (6.041) Data 5.563 (5.563) Loss 1.7868 (1.7868) Prec@1 45.703 (45.703) Prec@5 76.562 (76.562)
[2021-04-28 21:51:38 train_lshot.py:257] INFO Epoch: [6][10/150] Time 0.299 (0.904) Data 0.000 (0.553) Loss 1.8586 (1.8650) Prec@1 38.281 (41.442) Prec@5 74.609 (72.621)
[2021-04-28 21:51:41 train_lshot.py:257] INFO Epoch: [6][20/150] Time 0.279 (0.608) Data 0.000 (0.290) Loss 1.8349 (1.8571) Prec@1 40.625 (41.481) Prec@5 73.047 (72.805)
[2021-04-28 21:51:44 train_lshot.py:257] INFO Epoch: [6][30/150] Time 0.284 (0.504) Data 0.000 (0.196) Loss 1.9328 (1.8638) Prec@1 39.453 (41.280) Prec@5 70.312 (72.896)
[2021-04-28 21:51:46 train_lshot.py:257] INFO Epoch: [6][40/150] Time 0.277 (0.449) Data 0.001 (0.149) Loss 1.8347 (1.8513) Prec@1 41.406 (41.711) Prec@5 75.000 (73.142)
[2021-04-28 21:51:49 train_lshot.py:257] INFO Epoch: [6][50/150] Time 0.276 (0.417) Data 0.000 (0.119) Loss 1.9024 (1.8535) Prec@1 39.844 (41.705) Prec@5 75.000 (73.055)
[2021-04-28 21:51:52 train_lshot.py:257] INFO Epoch: [6][60/150] Time 0.281 (0.395) Data 0.000 (0.100) Loss 1.8207 (1.8495) Prec@1 44.141 (41.963) Prec@5 74.219 (73.233)
[2021-04-28 21:51:55 train_lshot.py:257] INFO Epoch: [6][70/150] Time 0.285 (0.379) Data 0.001 (0.086) Loss 1.6601 (1.8429) Prec@1 51.172 (42.243) Prec@5 80.078 (73.421)
[2021-04-28 21:51:58 train_lshot.py:257] INFO Epoch: [6][80/150] Time 0.278 (0.366) Data 0.000 (0.075) Loss 1.7658 (1.8451) Prec@1 46.094 (42.183) Prec@5 73.047 (73.298)
[2021-04-28 21:52:01 train_lshot.py:257] INFO Epoch: [6][90/150] Time 0.279 (0.357) Data 0.000 (0.067) Loss 1.8235 (1.8408) Prec@1 41.797 (42.501) Prec@5 75.781 (73.489)
[2021-04-28 21:52:03 train_lshot.py:257] INFO Epoch: [6][100/150] Time 0.280 (0.349) Data 0.000 (0.061) Loss 1.8233 (1.8392) Prec@1 42.188 (42.439) Prec@5 73.828 (73.484)
[2021-04-28 21:52:06 train_lshot.py:257] INFO Epoch: [6][110/150] Time 0.282 (0.343) Data 0.000 (0.055) Loss 1.8886 (1.8372) Prec@1 39.062 (42.399) Prec@5 71.875 (73.564)
[2021-04-28 21:52:09 train_lshot.py:257] INFO Epoch: [6][120/150] Time 0.277 (0.338) Data 0.000 (0.051) Loss 1.7849 (1.8373) Prec@1 44.141 (42.401) Prec@5 76.562 (73.615)
[2021-04-28 21:52:12 train_lshot.py:257] INFO Epoch: [6][130/150] Time 0.274 (0.334) Data 0.000 (0.047) Loss 1.8009 (1.8347) Prec@1 43.750 (42.498) Prec@5 73.047 (73.607)
[2021-04-28 21:52:15 train_lshot.py:257] INFO Epoch: [6][140/150] Time 0.273 (0.330) Data 0.000 (0.043) Loss 1.7418 (1.8273) Prec@1 48.047 (42.786) Prec@5 74.609 (73.770)
[2021-04-28 21:52:22 train_lshot.py:257] INFO Epoch: [7][0/150] Time 4.513 (4.513) Data 4.046 (4.046) Loss 1.7884 (1.7884) Prec@1 42.969 (42.969) Prec@5 72.266 (72.266)
[2021-04-28 21:52:27 train_lshot.py:257] INFO Epoch: [7][10/150] Time 0.399 (0.871) Data 0.022 (0.504) Loss 1.6640 (1.7181) Prec@1 49.609 (46.733) Prec@5 78.125 (75.355)
[2021-04-28 21:52:30 train_lshot.py:257] INFO Epoch: [7][20/150] Time 0.281 (0.592) Data 0.000 (0.264) Loss 1.7219 (1.7342) Prec@1 47.656 (46.373) Prec@5 74.609 (75.614)
[2021-04-28 21:52:33 train_lshot.py:257] INFO Epoch: [7][30/150] Time 0.274 (0.493) Data 0.000 (0.179) Loss 1.7773 (1.7454) Prec@1 46.484 (45.968) Prec@5 75.781 (75.340)
[2021-04-28 21:52:36 train_lshot.py:257] INFO Epoch: [7][40/150] Time 0.279 (0.442) Data 0.000 (0.136) Loss 1.9138 (1.7495) Prec@1 41.797 (45.551) Prec@5 71.094 (75.419)
[2021-04-28 21:52:39 train_lshot.py:257] INFO Epoch: [7][50/150] Time 0.287 (0.411) Data 0.000 (0.109) Loss 1.6286 (1.7356) Prec@1 49.609 (45.741) Prec@5 76.562 (75.835)
[2021-04-28 21:52:41 train_lshot.py:257] INFO Epoch: [7][60/150] Time 0.277 (0.390) Data 0.000 (0.091) Loss 1.6500 (1.7301) Prec@1 47.656 (45.537) Prec@5 75.781 (76.005)
[2021-04-28 21:52:44 train_lshot.py:257] INFO Epoch: [7][70/150] Time 0.279 (0.375) Data 0.001 (0.078) Loss 1.8189 (1.7265) Prec@1 42.969 (45.665) Prec@5 76.562 (76.150)
[2021-04-28 21:52:47 train_lshot.py:257] INFO Epoch: [7][80/150] Time 0.273 (0.363) Data 0.000 (0.069) Loss 1.6701 (1.7211) Prec@1 45.312 (45.848) Prec@5 78.516 (76.360)
[2021-04-28 21:52:50 train_lshot.py:257] INFO Epoch: [7][90/150] Time 0.285 (0.354) Data 0.000 (0.061) Loss 1.7831 (1.7266) Prec@1 45.312 (45.742) Prec@5 73.438 (76.193)
[2021-04-28 21:52:53 train_lshot.py:257] INFO Epoch: [7][100/150] Time 0.282 (0.347) Data 0.000 (0.055) Loss 1.5821 (1.7234) Prec@1 50.000 (45.862) Prec@5 78.516 (76.207)
[2021-04-28 21:52:55 train_lshot.py:257] INFO Epoch: [7][110/150] Time 0.284 (0.341) Data 0.000 (0.050) Loss 1.5931 (1.7194) Prec@1 51.172 (45.995) Prec@5 78.125 (76.362)
[2021-04-28 21:52:58 train_lshot.py:257] INFO Epoch: [7][120/150] Time 0.286 (0.336) Data 0.000 (0.046) Loss 1.5343 (1.7162) Prec@1 50.000 (46.016) Prec@5 82.031 (76.479)
[2021-04-28 21:53:01 train_lshot.py:257] INFO Epoch: [7][130/150] Time 0.286 (0.332) Data 0.000 (0.043) Loss 1.7373 (1.7112) Prec@1 46.484 (46.183) Prec@5 75.391 (76.586)
[2021-04-28 21:53:04 train_lshot.py:257] INFO Epoch: [7][140/150] Time 0.296 (0.329) Data 0.000 (0.040) Loss 1.7342 (1.7113) Prec@1 47.266 (46.205) Prec@5 74.609 (76.599)
[2021-04-28 21:53:35 train_lshot.py:119] INFO Meta Val 7: 0.48410667768120763
[2021-04-28 21:53:42 train_lshot.py:257] INFO Epoch: [8][0/150] Time 6.467 (6.467) Data 6.048 (6.048) Loss 1.6108 (1.6108) Prec@1 49.609 (49.609) Prec@5 78.906 (78.906)
[2021-04-28 21:53:46 train_lshot.py:257] INFO Epoch: [8][10/150] Time 0.280 (0.908) Data 0.000 (0.593) Loss 1.6508 (1.6036) Prec@1 46.094 (49.432) Prec@5 78.906 (79.226)
[2021-04-28 21:53:49 train_lshot.py:257] INFO Epoch: [8][20/150] Time 0.279 (0.609) Data 0.000 (0.311) Loss 1.5094 (1.6218) Prec@1 51.562 (49.200) Prec@5 81.641 (78.609)
[2021-04-28 21:53:51 train_lshot.py:257] INFO Epoch: [8][30/150] Time 0.275 (0.503) Data 0.000 (0.211) Loss 1.6933 (1.6352) Prec@1 47.656 (48.816) Prec@5 76.172 (78.238)
[2021-04-28 21:53:54 train_lshot.py:257] INFO Epoch: [8][40/150] Time 0.282 (0.449) Data 0.000 (0.159) Loss 1.6577 (1.6464) Prec@1 49.609 (48.504) Prec@5 79.297 (78.077)
[2021-04-28 21:53:57 train_lshot.py:257] INFO Epoch: [8][50/150] Time 0.285 (0.419) Data 0.000 (0.128) Loss 1.6583 (1.6458) Prec@1 50.391 (48.644) Prec@5 78.906 (78.125)
[2021-04-28 21:54:00 train_lshot.py:257] INFO Epoch: [8][60/150] Time 0.286 (0.396) Data 0.000 (0.107) Loss 1.5065 (1.6410) Prec@1 56.250 (48.796) Prec@5 80.859 (78.272)
[2021-04-28 21:54:03 train_lshot.py:257] INFO Epoch: [8][70/150] Time 0.293 (0.380) Data 0.001 (0.092) Loss 1.5796 (1.6394) Prec@1 51.172 (48.812) Prec@5 78.906 (78.274)
[2021-04-28 21:54:06 train_lshot.py:257] INFO Epoch: [8][80/150] Time 0.280 (0.368) Data 0.000 (0.081) Loss 1.5790 (1.6430) Prec@1 46.875 (48.708) Prec@5 79.297 (78.207)
[2021-04-28 21:54:08 train_lshot.py:257] INFO Epoch: [8][90/150] Time 0.278 (0.357) Data 0.000 (0.072) Loss 1.6135 (1.6368) Prec@1 47.266 (48.824) Prec@5 78.125 (78.387)
[2021-04-28 21:54:11 train_lshot.py:257] INFO Epoch: [8][100/150] Time 0.274 (0.350) Data 0.000 (0.065) Loss 1.6925 (1.6344) Prec@1 49.609 (48.909) Prec@5 75.000 (78.477)
[2021-04-28 21:54:14 train_lshot.py:257] INFO Epoch: [8][110/150] Time 0.283 (0.345) Data 0.000 (0.059) Loss 1.6380 (1.6336) Prec@1 46.484 (48.962) Prec@5 80.469 (78.438)
[2021-04-28 21:54:17 train_lshot.py:257] INFO Epoch: [8][120/150] Time 0.290 (0.340) Data 0.000 (0.054) Loss 1.6293 (1.6321) Prec@1 47.266 (48.999) Prec@5 81.641 (78.525)
[2021-04-28 21:54:20 train_lshot.py:257] INFO Epoch: [8][130/150] Time 0.311 (0.336) Data 0.000 (0.050) Loss 1.7031 (1.6293) Prec@1 43.750 (49.076) Prec@5 79.297 (78.522)
[2021-04-28 21:54:23 train_lshot.py:257] INFO Epoch: [8][140/150] Time 0.280 (0.332) Data 0.000 (0.047) Loss 1.5927 (1.6298) Prec@1 47.656 (49.041) Prec@5 80.469 (78.557)
[2021-04-28 21:54:32 train_lshot.py:257] INFO Epoch: [9][0/150] Time 6.090 (6.090) Data 5.689 (5.689) Loss 1.5356 (1.5356) Prec@1 49.609 (49.609) Prec@5 79.297 (79.297)
[2021-04-28 21:54:36 train_lshot.py:257] INFO Epoch: [9][10/150] Time 0.324 (0.900) Data 0.000 (0.520) Loss 1.5393 (1.5441) Prec@1 54.297 (50.959) Prec@5 81.250 (80.646)
[2021-04-28 21:54:39 train_lshot.py:257] INFO Epoch: [9][20/150] Time 0.278 (0.607) Data 0.000 (0.273) Loss 1.4516 (1.5422) Prec@1 55.078 (51.265) Prec@5 82.812 (80.487)
[2021-04-28 21:54:42 train_lshot.py:257] INFO Epoch: [9][30/150] Time 0.275 (0.506) Data 0.000 (0.185) Loss 1.6932 (1.5365) Prec@1 43.359 (51.663) Prec@5 78.516 (80.544)
[2021-04-28 21:54:44 train_lshot.py:257] INFO Epoch: [9][40/150] Time 0.283 (0.451) Data 0.000 (0.140) Loss 1.5405 (1.5374) Prec@1 55.078 (51.696) Prec@5 80.078 (80.612)
[2021-04-28 21:54:47 train_lshot.py:257] INFO Epoch: [9][50/150] Time 0.279 (0.418) Data 0.000 (0.112) Loss 1.6097 (1.5399) Prec@1 48.047 (51.716) Prec@5 77.344 (80.407)
[2021-04-28 21:54:50 train_lshot.py:257] INFO Epoch: [9][60/150] Time 0.276 (0.395) Data 0.000 (0.094) Loss 1.4891 (1.5485) Prec@1 54.297 (51.370) Prec@5 82.031 (80.270)
[2021-04-28 21:54:53 train_lshot.py:257] INFO Epoch: [9][70/150] Time 0.284 (0.379) Data 0.001 (0.081) Loss 1.6079 (1.5513) Prec@1 49.219 (51.188) Prec@5 80.469 (80.249)
[2021-04-28 21:54:57 train_lshot.py:257] INFO Epoch: [9][80/150] Time 0.289 (0.380) Data 0.000 (0.071) Loss 1.4943 (1.5518) Prec@1 55.859 (51.278) Prec@5 82.422 (80.295)
[2021-04-28 21:54:59 train_lshot.py:257] INFO Epoch: [9][90/150] Time 0.276 (0.369) Data 0.000 (0.063) Loss 1.4747 (1.5487) Prec@1 53.516 (51.481) Prec@5 80.859 (80.331)
[2021-04-28 21:55:03 train_lshot.py:257] INFO Epoch: [9][100/150] Time 0.462 (0.368) Data 0.001 (0.057) Loss 1.6134 (1.5462) Prec@1 47.266 (51.593) Prec@5 79.688 (80.372)
[2021-04-28 21:55:06 train_lshot.py:257] INFO Epoch: [9][110/150] Time 0.287 (0.363) Data 0.000 (0.052) Loss 1.6234 (1.5476) Prec@1 49.609 (51.559) Prec@5 78.516 (80.374)
[2021-04-28 21:55:09 train_lshot.py:257] INFO Epoch: [9][120/150] Time 0.283 (0.356) Data 0.000 (0.048) Loss 1.6491 (1.5464) Prec@1 48.047 (51.595) Prec@5 76.562 (80.427)
[2021-04-28 21:55:12 train_lshot.py:257] INFO Epoch: [9][130/150] Time 0.327 (0.352) Data 0.000 (0.044) Loss 1.6517 (1.5433) Prec@1 46.484 (51.688) Prec@5 80.078 (80.519)
[2021-04-28 21:55:16 train_lshot.py:257] INFO Epoch: [9][140/150] Time 1.054 (0.353) Data 0.000 (0.041) Loss 1.7080 (1.5431) Prec@1 44.531 (51.731) Prec@5 77.734 (80.499)
[2021-04-28 21:55:26 train_lshot.py:257] INFO Epoch: [10][0/150] Time 6.783 (6.783) Data 6.358 (6.358) Loss 1.4106 (1.4106) Prec@1 56.641 (56.641) Prec@5 84.766 (84.766)
[2021-04-28 21:55:29 train_lshot.py:257] INFO Epoch: [10][10/150] Time 0.279 (0.925) Data 0.000 (0.583) Loss 1.5313 (1.4834) Prec@1 52.344 (53.906) Prec@5 80.078 (82.493)
[2021-04-28 21:55:32 train_lshot.py:257] INFO Epoch: [10][20/150] Time 0.282 (0.626) Data 0.000 (0.306) Loss 1.4510 (1.4486) Prec@1 54.688 (54.743) Prec@5 82.422 (83.092)
[2021-04-28 21:55:35 train_lshot.py:257] INFO Epoch: [10][30/150] Time 0.284 (0.514) Data 0.000 (0.207) Loss 1.6163 (1.4640) Prec@1 51.562 (54.272) Prec@5 79.297 (82.560)
[2021-04-28 21:55:38 train_lshot.py:257] INFO Epoch: [10][40/150] Time 0.278 (0.458) Data 0.001 (0.157) Loss 1.6147 (1.4618) Prec@1 51.562 (54.211) Prec@5 78.125 (82.584)
[2021-04-28 21:55:41 train_lshot.py:257] INFO Epoch: [10][50/150] Time 0.278 (0.423) Data 0.000 (0.126) Loss 1.6281 (1.4583) Prec@1 45.703 (54.435) Prec@5 79.297 (82.552)
[2021-04-28 21:55:44 train_lshot.py:257] INFO Epoch: [10][60/150] Time 0.278 (0.401) Data 0.000 (0.106) Loss 1.5651 (1.4623) Prec@1 55.078 (54.361) Prec@5 79.297 (82.441)
[2021-04-28 21:55:46 train_lshot.py:257] INFO Epoch: [10][70/150] Time 0.294 (0.384) Data 0.001 (0.091) Loss 1.5233 (1.4666) Prec@1 51.562 (54.165) Prec@5 77.344 (82.306)
[2021-04-28 21:55:49 train_lshot.py:257] INFO Epoch: [10][80/150] Time 0.380 (0.373) Data 0.000 (0.080) Loss 1.4850 (1.4655) Prec@1 52.344 (54.167) Prec@5 82.031 (82.350)
[2021-04-28 21:55:52 train_lshot.py:257] INFO Epoch: [10][90/150] Time 0.280 (0.365) Data 0.000 (0.071) Loss 1.4599 (1.4673) Prec@1 51.172 (54.125) Prec@5 83.984 (82.293)
[2021-04-28 21:55:55 train_lshot.py:257] INFO Epoch: [10][100/150] Time 0.288 (0.357) Data 0.000 (0.064) Loss 1.4414 (1.4718) Prec@1 51.953 (53.875) Prec@5 83.594 (82.205)
[2021-04-28 21:55:58 train_lshot.py:257] INFO Epoch: [10][110/150] Time 0.288 (0.351) Data 0.000 (0.058) Loss 1.5209 (1.4756) Prec@1 51.172 (53.702) Prec@5 78.906 (82.035)
[2021-04-28 21:56:01 train_lshot.py:257] INFO Epoch: [10][120/150] Time 0.286 (0.346) Data 0.000 (0.053) Loss 1.5043 (1.4747) Prec@1 50.391 (53.635) Prec@5 79.297 (81.989)
[2021-04-28 21:56:04 train_lshot.py:257] INFO Epoch: [10][130/150] Time 0.287 (0.341) Data 0.000 (0.049) Loss 1.5567 (1.4746) Prec@1 52.734 (53.653) Prec@5 77.734 (81.981)
[2021-04-28 21:56:07 train_lshot.py:257] INFO Epoch: [10][140/150] Time 0.283 (0.337) Data 0.000 (0.046) Loss 1.5973 (1.4732) Prec@1 46.875 (53.729) Prec@5 82.031 (81.979)
[2021-04-28 21:56:15 train_lshot.py:257] INFO Epoch: [11][0/150] Time 5.336 (5.336) Data 4.927 (4.927) Loss 1.3703 (1.3703) Prec@1 57.422 (57.422) Prec@5 83.594 (83.594)
[2021-04-28 21:56:19 train_lshot.py:257] INFO Epoch: [11][10/150] Time 0.371 (0.866) Data 0.003 (0.503) Loss 1.4931 (1.4419) Prec@1 53.125 (54.652) Prec@5 80.469 (82.741)
[2021-04-28 21:56:22 train_lshot.py:257] INFO Epoch: [11][20/150] Time 0.281 (0.596) Data 0.000 (0.264) Loss 1.5075 (1.4285) Prec@1 51.953 (54.929) Prec@5 79.297 (83.333)
[2021-04-28 21:56:25 train_lshot.py:257] INFO Epoch: [11][30/150] Time 0.281 (0.497) Data 0.000 (0.179) Loss 1.4644 (1.4379) Prec@1 53.125 (54.851) Prec@5 83.594 (82.863)
[2021-04-28 21:56:28 train_lshot.py:257] INFO Epoch: [11][40/150] Time 0.274 (0.444) Data 0.000 (0.136) Loss 1.5041 (1.4384) Prec@1 52.344 (54.830) Prec@5 83.984 (83.032)
[2021-04-28 21:56:31 train_lshot.py:257] INFO Epoch: [11][50/150] Time 0.287 (0.413) Data 0.001 (0.109) Loss 1.4739 (1.4431) Prec@1 53.516 (54.710) Prec@5 81.250 (82.812)
[2021-04-28 21:56:34 train_lshot.py:257] INFO Epoch: [11][60/150] Time 0.285 (0.391) Data 0.000 (0.091) Loss 1.3863 (1.4382) Prec@1 58.594 (54.764) Prec@5 85.547 (82.941)
[2021-04-28 21:56:37 train_lshot.py:257] INFO Epoch: [11][70/150] Time 0.285 (0.376) Data 0.001 (0.079) Loss 1.3947 (1.4355) Prec@1 55.078 (54.787) Prec@5 84.375 (82.967)
[2021-04-28 21:56:40 train_lshot.py:257] INFO Epoch: [11][80/150] Time 0.453 (0.367) Data 0.001 (0.069) Loss 1.3730 (1.4299) Prec@1 57.031 (55.112) Prec@5 83.203 (82.919)
[2021-04-28 21:56:43 train_lshot.py:257] INFO Epoch: [11][90/150] Time 0.282 (0.362) Data 0.000 (0.061) Loss 1.2932 (1.4220) Prec@1 60.938 (55.434) Prec@5 83.984 (83.040)
[2021-04-28 21:56:46 train_lshot.py:257] INFO Epoch: [11][100/150] Time 0.280 (0.354) Data 0.000 (0.055) Loss 1.4365 (1.4236) Prec@1 57.812 (55.465) Prec@5 81.250 (82.940)
[2021-04-28 21:56:50 train_lshot.py:257] INFO Epoch: [11][110/150] Time 0.286 (0.358) Data 0.000 (0.050) Loss 1.4218 (1.4226) Prec@1 57.812 (55.564) Prec@5 83.594 (83.003)
[2021-04-28 21:56:52 train_lshot.py:257] INFO Epoch: [11][120/150] Time 0.273 (0.352) Data 0.000 (0.046) Loss 1.3502 (1.4208) Prec@1 56.250 (55.704) Prec@5 84.766 (83.061)
[2021-04-28 21:56:55 train_lshot.py:257] INFO Epoch: [11][130/150] Time 0.285 (0.346) Data 0.000 (0.043) Loss 1.3143 (1.4137) Prec@1 58.984 (55.943) Prec@5 87.891 (83.275)
[2021-04-28 21:56:59 train_lshot.py:257] INFO Epoch: [11][140/150] Time 0.313 (0.346) Data 0.000 (0.040) Loss 1.4109 (1.4149) Prec@1 54.297 (55.904) Prec@5 83.203 (83.170)
[2021-04-28 21:57:30 train_lshot.py:119] INFO Meta Val 11: 0.5293333461284637
[2021-04-28 21:57:35 train_lshot.py:257] INFO Epoch: [12][0/150] Time 4.783 (4.783) Data 4.361 (4.361) Loss 1.4722 (1.4722) Prec@1 56.250 (56.250) Prec@5 82.812 (82.812)
[2021-04-28 21:57:41 train_lshot.py:257] INFO Epoch: [12][10/150] Time 0.305 (0.916) Data 0.001 (0.562) Loss 1.2718 (1.4006) Prec@1 58.594 (57.173) Prec@5 88.672 (83.132)
[2021-04-28 21:57:43 train_lshot.py:257] INFO Epoch: [12][20/150] Time 0.277 (0.613) Data 0.000 (0.294) Loss 1.3232 (1.3897) Prec@1 59.766 (57.626) Prec@5 83.594 (83.501)
[2021-04-28 21:57:46 train_lshot.py:257] INFO Epoch: [12][30/150] Time 0.284 (0.505) Data 0.000 (0.200) Loss 1.2788 (1.3831) Prec@1 58.203 (57.548) Prec@5 89.062 (83.644)
[2021-04-28 21:57:49 train_lshot.py:257] INFO Epoch: [12][40/150] Time 0.280 (0.454) Data 0.000 (0.151) Loss 1.3050 (1.3720) Prec@1 56.250 (57.470) Prec@5 83.594 (83.851)
[2021-04-28 21:57:52 train_lshot.py:257] INFO Epoch: [12][50/150] Time 0.277 (0.420) Data 0.000 (0.122) Loss 1.1650 (1.3728) Prec@1 68.359 (57.399) Prec@5 87.500 (83.824)
[2021-04-28 21:57:55 train_lshot.py:257] INFO Epoch: [12][60/150] Time 0.277 (0.397) Data 0.000 (0.102) Loss 1.2738 (1.3666) Prec@1 63.281 (57.582) Prec@5 85.156 (84.048)
[2021-04-28 21:57:58 train_lshot.py:257] INFO Epoch: [12][70/150] Time 0.279 (0.381) Data 0.001 (0.087) Loss 1.3079 (1.3616) Prec@1 56.641 (57.680) Prec@5 89.844 (84.204)
[2021-04-28 21:58:00 train_lshot.py:257] INFO Epoch: [12][80/150] Time 0.274 (0.367) Data 0.000 (0.077) Loss 1.2175 (1.3580) Prec@1 58.984 (57.750) Prec@5 88.281 (84.365)
[2021-04-28 21:58:04 train_lshot.py:257] INFO Epoch: [12][90/150] Time 0.291 (0.372) Data 0.000 (0.068) Loss 1.2567 (1.3596) Prec@1 59.766 (57.671) Prec@5 85.156 (84.379)
[2021-04-28 21:58:07 train_lshot.py:257] INFO Epoch: [12][100/150] Time 0.281 (0.363) Data 0.000 (0.062) Loss 1.3606 (1.3608) Prec@1 57.422 (57.696) Prec@5 82.812 (84.298)
[2021-04-28 21:58:10 train_lshot.py:257] INFO Epoch: [12][110/150] Time 0.289 (0.356) Data 0.000 (0.056) Loss 1.1951 (1.3581) Prec@1 66.406 (57.893) Prec@5 88.672 (84.273)
[2021-04-28 21:58:13 train_lshot.py:257] INFO Epoch: [12][120/150] Time 0.280 (0.350) Data 0.000 (0.051) Loss 1.3308 (1.3588) Prec@1 57.422 (57.896) Prec@5 84.766 (84.265)
[2021-04-28 21:58:16 train_lshot.py:257] INFO Epoch: [12][130/150] Time 0.288 (0.345) Data 0.000 (0.047) Loss 1.3703 (1.3589) Prec@1 57.031 (57.875) Prec@5 83.594 (84.232)
[2021-04-28 21:58:19 train_lshot.py:257] INFO Epoch: [12][140/150] Time 0.293 (0.341) Data 0.000 (0.044) Loss 1.3847 (1.3572) Prec@1 57.812 (57.912) Prec@5 84.375 (84.272)
[2021-04-28 21:58:29 train_lshot.py:257] INFO Epoch: [13][0/150] Time 5.837 (5.837) Data 5.452 (5.452) Loss 1.3073 (1.3073) Prec@1 60.547 (60.547) Prec@5 86.328 (86.328)
[2021-04-28 21:58:32 train_lshot.py:257] INFO Epoch: [13][10/150] Time 0.293 (0.872) Data 0.000 (0.497) Loss 1.4690 (1.3209) Prec@1 51.953 (59.553) Prec@5 83.203 (85.405)
[2021-04-28 21:58:35 train_lshot.py:257] INFO Epoch: [13][20/150] Time 0.281 (0.592) Data 0.000 (0.261) Loss 1.4126 (1.3125) Prec@1 55.078 (59.859) Prec@5 81.250 (85.268)
[2021-04-28 21:58:38 train_lshot.py:257] INFO Epoch: [13][30/150] Time 0.280 (0.494) Data 0.000 (0.177) Loss 1.2546 (1.2970) Prec@1 60.938 (60.244) Prec@5 88.672 (85.837)
[2021-04-28 21:58:41 train_lshot.py:257] INFO Epoch: [13][40/150] Time 0.284 (0.442) Data 0.001 (0.134) Loss 1.3341 (1.3060) Prec@1 57.812 (59.813) Prec@5 85.938 (85.880)
[2021-04-28 21:58:44 train_lshot.py:257] INFO Epoch: [13][50/150] Time 0.281 (0.410) Data 0.000 (0.108) Loss 1.3088 (1.3068) Prec@1 58.203 (59.766) Prec@5 85.547 (85.869)
[2021-04-28 21:58:47 train_lshot.py:257] INFO Epoch: [13][60/150] Time 0.287 (0.390) Data 0.000 (0.090) Loss 1.3948 (1.3025) Prec@1 57.812 (59.996) Prec@5 85.156 (85.848)
[2021-04-28 21:58:49 train_lshot.py:257] INFO Epoch: [13][70/150] Time 0.290 (0.375) Data 0.001 (0.077) Loss 1.4557 (1.2998) Prec@1 56.641 (60.112) Prec@5 80.859 (85.761)
[2021-04-28 21:58:52 train_lshot.py:257] INFO Epoch: [13][80/150] Time 0.286 (0.365) Data 0.001 (0.068) Loss 1.2045 (1.3010) Prec@1 60.938 (59.992) Prec@5 88.672 (85.672)
[2021-04-28 21:58:55 train_lshot.py:257] INFO Epoch: [13][90/150] Time 0.292 (0.357) Data 0.000 (0.060) Loss 1.3642 (1.3001) Prec@1 59.766 (59.980) Prec@5 84.766 (85.706)
[2021-04-28 21:58:58 train_lshot.py:257] INFO Epoch: [13][100/150] Time 0.352 (0.350) Data 0.000 (0.054) Loss 1.4270 (1.3003) Prec@1 53.906 (60.032) Prec@5 85.156 (85.647)
[2021-04-28 21:59:01 train_lshot.py:257] INFO Epoch: [13][110/150] Time 0.284 (0.346) Data 0.000 (0.050) Loss 1.2558 (1.3012) Prec@1 63.281 (60.058) Prec@5 88.281 (85.614)
[2021-04-28 21:59:04 train_lshot.py:257] INFO Epoch: [13][120/150] Time 0.287 (0.341) Data 0.000 (0.046) Loss 1.4069 (1.3049) Prec@1 55.078 (59.901) Prec@5 82.422 (85.540)
[2021-04-28 21:59:07 train_lshot.py:257] INFO Epoch: [13][130/150] Time 0.296 (0.338) Data 0.000 (0.042) Loss 1.2970 (1.3044) Prec@1 60.156 (59.906) Prec@5 85.156 (85.541)
[2021-04-28 21:59:10 train_lshot.py:257] INFO Epoch: [13][140/150] Time 0.284 (0.334) Data 0.000 (0.039) Loss 1.3015 (1.3049) Prec@1 61.719 (59.962) Prec@5 82.422 (85.436)
[2021-04-28 21:59:21 train_lshot.py:257] INFO Epoch: [14][0/150] Time 6.599 (6.599) Data 6.141 (6.141) Loss 1.2651 (1.2651) Prec@1 60.938 (60.938) Prec@5 85.547 (85.547)
[2021-04-28 21:59:24 train_lshot.py:257] INFO Epoch: [14][10/150] Time 0.281 (0.915) Data 0.000 (0.560) Loss 1.2204 (1.2675) Prec@1 61.328 (61.257) Prec@5 88.672 (86.825)
[2021-04-28 21:59:27 train_lshot.py:257] INFO Epoch: [14][20/150] Time 0.279 (0.614) Data 0.000 (0.293) Loss 1.1685 (1.2766) Prec@1 64.453 (60.993) Prec@5 88.281 (86.291)
[2021-04-28 21:59:30 train_lshot.py:257] INFO Epoch: [14][30/150] Time 0.286 (0.509) Data 0.000 (0.199) Loss 1.3021 (1.2694) Prec@1 59.766 (61.089) Prec@5 85.938 (86.341)
[2021-04-28 21:59:33 train_lshot.py:257] INFO Epoch: [14][40/150] Time 0.279 (0.454) Data 0.000 (0.150) Loss 1.3248 (1.2663) Prec@1 60.938 (60.985) Prec@5 84.766 (86.185)
[2021-04-28 21:59:36 train_lshot.py:257] INFO Epoch: [14][50/150] Time 0.276 (0.420) Data 0.000 (0.121) Loss 1.2524 (1.2626) Prec@1 59.766 (61.229) Prec@5 88.281 (86.305)
[2021-04-28 21:59:39 train_lshot.py:257] INFO Epoch: [14][60/150] Time 0.284 (0.397) Data 0.000 (0.101) Loss 1.2867 (1.2654) Prec@1 60.938 (61.008) Prec@5 85.938 (86.328)
[2021-04-28 21:59:41 train_lshot.py:257] INFO Epoch: [14][70/150] Time 0.295 (0.381) Data 0.001 (0.087) Loss 1.3906 (1.2684) Prec@1 58.594 (60.998) Prec@5 83.594 (86.218)
[2021-04-28 21:59:44 train_lshot.py:257] INFO Epoch: [14][80/150] Time 0.286 (0.370) Data 0.000 (0.076) Loss 1.2831 (1.2692) Prec@1 59.766 (60.904) Prec@5 87.109 (86.082)
[2021-04-28 21:59:47 train_lshot.py:257] INFO Epoch: [14][90/150] Time 0.295 (0.360) Data 0.000 (0.068) Loss 1.2634 (1.2670) Prec@1 60.547 (60.916) Prec@5 87.109 (86.131)
[2021-04-28 21:59:51 train_lshot.py:257] INFO Epoch: [14][100/150] Time 0.349 (0.360) Data 0.000 (0.061) Loss 1.3997 (1.2738) Prec@1 54.297 (60.686) Prec@5 83.594 (85.961)
[2021-04-28 21:59:54 train_lshot.py:257] INFO Epoch: [14][110/150] Time 0.281 (0.354) Data 0.000 (0.056) Loss 1.2498 (1.2732) Prec@1 64.453 (60.677) Prec@5 85.156 (85.945)
[2021-04-28 21:59:56 train_lshot.py:257] INFO Epoch: [14][120/150] Time 0.278 (0.348) Data 0.000 (0.051) Loss 1.1903 (1.2727) Prec@1 66.016 (60.747) Prec@5 86.719 (85.921)
[2021-04-28 21:59:59 train_lshot.py:257] INFO Epoch: [14][130/150] Time 0.287 (0.344) Data 0.000 (0.047) Loss 1.2397 (1.2740) Prec@1 62.500 (60.738) Prec@5 85.156 (85.878)
[2021-04-28 22:00:02 train_lshot.py:257] INFO Epoch: [14][140/150] Time 0.283 (0.340) Data 0.000 (0.044) Loss 1.2243 (1.2724) Prec@1 60.938 (60.782) Prec@5 88.281 (85.901)
[2021-04-28 22:00:12 train_lshot.py:257] INFO Epoch: [15][0/150] Time 6.534 (6.534) Data 6.080 (6.080) Loss 1.1209 (1.1209) Prec@1 66.797 (66.797) Prec@5 87.109 (87.109)
[2021-04-28 22:00:16 train_lshot.py:257] INFO Epoch: [15][10/150] Time 0.286 (0.902) Data 0.000 (0.554) Loss 1.1676 (1.2318) Prec@1 64.453 (61.754) Prec@5 83.984 (86.399)
[2021-04-28 22:00:19 train_lshot.py:257] INFO Epoch: [15][20/150] Time 0.280 (0.609) Data 0.000 (0.290) Loss 1.1883 (1.2254) Prec@1 64.062 (62.202) Prec@5 89.453 (86.923)
[2021-04-28 22:00:21 train_lshot.py:257] INFO Epoch: [15][30/150] Time 0.289 (0.503) Data 0.000 (0.197) Loss 1.2660 (1.2105) Prec@1 61.719 (62.765) Prec@5 83.984 (87.160)
[2021-04-28 22:00:24 train_lshot.py:257] INFO Epoch: [15][40/150] Time 0.277 (0.449) Data 0.001 (0.149) Loss 1.0777 (1.2087) Prec@1 64.062 (62.786) Prec@5 90.625 (87.195)
[2021-04-28 22:00:27 train_lshot.py:257] INFO Epoch: [15][50/150] Time 0.292 (0.416) Data 0.000 (0.120) Loss 1.1370 (1.2040) Prec@1 66.016 (63.067) Prec@5 88.672 (87.209)
[2021-04-28 22:00:30 train_lshot.py:257] INFO Epoch: [15][60/150] Time 0.283 (0.395) Data 0.000 (0.100) Loss 1.2459 (1.2012) Prec@1 64.062 (63.268) Prec@5 86.719 (87.308)
[2021-04-28 22:00:33 train_lshot.py:257] INFO Epoch: [15][70/150] Time 0.283 (0.380) Data 0.001 (0.086) Loss 1.1396 (1.2045) Prec@1 63.672 (63.078) Prec@5 90.625 (87.214)
[2021-04-28 22:00:36 train_lshot.py:257] INFO Epoch: [15][80/150] Time 0.290 (0.368) Data 0.000 (0.076) Loss 1.1605 (1.2079) Prec@1 66.016 (62.895) Prec@5 89.062 (87.191)
[2021-04-28 22:00:38 train_lshot.py:257] INFO Epoch: [15][90/150] Time 0.289 (0.359) Data 0.000 (0.067) Loss 1.1960 (1.2122) Prec@1 65.234 (62.693) Prec@5 87.109 (87.109)
[2021-04-28 22:00:42 train_lshot.py:257] INFO Epoch: [15][100/150] Time 0.312 (0.358) Data 0.000 (0.061) Loss 1.3460 (1.2135) Prec@1 57.031 (62.635) Prec@5 86.719 (87.125)
[2021-04-28 22:00:45 train_lshot.py:257] INFO Epoch: [15][110/150] Time 0.281 (0.351) Data 0.000 (0.055) Loss 1.2652 (1.2152) Prec@1 58.984 (62.591) Prec@5 87.891 (87.067)
[2021-04-28 22:00:48 train_lshot.py:257] INFO Epoch: [15][120/150] Time 0.276 (0.345) Data 0.000 (0.051) Loss 1.2181 (1.2176) Prec@1 64.844 (62.639) Prec@5 84.766 (86.906)
[2021-04-28 22:00:50 train_lshot.py:257] INFO Epoch: [15][130/150] Time 0.283 (0.341) Data 0.000 (0.047) Loss 1.3603 (1.2192) Prec@1 58.594 (62.625) Prec@5 84.375 (86.844)
[2021-04-28 22:00:54 train_lshot.py:257] INFO Epoch: [15][140/150] Time 0.285 (0.340) Data 0.000 (0.044) Loss 1.2431 (1.2190) Prec@1 63.672 (62.647) Prec@5 87.891 (86.868)
[2021-04-28 22:01:25 train_lshot.py:119] INFO Meta Val 15: 0.5486400126516819
[2021-04-28 22:01:32 train_lshot.py:257] INFO Epoch: [16][0/150] Time 5.934 (5.934) Data 5.406 (5.406) Loss 1.0647 (1.0647) Prec@1 69.141 (69.141) Prec@5 90.234 (90.234)
[2021-04-28 22:01:35 train_lshot.py:257] INFO Epoch: [16][10/150] Time 0.274 (0.891) Data 0.000 (0.533) Loss 1.2402 (1.1683) Prec@1 63.281 (64.844) Prec@5 86.328 (87.749)
[2021-04-28 22:01:38 train_lshot.py:257] INFO Epoch: [16][20/150] Time 0.278 (0.598) Data 0.001 (0.279) Loss 1.1759 (1.1710) Prec@1 67.188 (65.067) Prec@5 86.328 (87.593)
[2021-04-28 22:01:41 train_lshot.py:257] INFO Epoch: [16][30/150] Time 0.278 (0.496) Data 0.000 (0.189) Loss 1.2616 (1.1833) Prec@1 60.156 (64.491) Prec@5 87.891 (87.172)
[2021-04-28 22:01:44 train_lshot.py:257] INFO Epoch: [16][40/150] Time 0.282 (0.447) Data 0.000 (0.143) Loss 1.1327 (1.1765) Prec@1 62.500 (64.615) Prec@5 88.672 (87.357)
[2021-04-28 22:01:47 train_lshot.py:257] INFO Epoch: [16][50/150] Time 0.279 (0.414) Data 0.000 (0.115) Loss 1.2630 (1.1796) Prec@1 60.547 (64.239) Prec@5 87.109 (87.416)
[2021-04-28 22:01:49 train_lshot.py:257] INFO Epoch: [16][60/150] Time 0.283 (0.392) Data 0.000 (0.096) Loss 1.1920 (1.1824) Prec@1 62.500 (64.184) Prec@5 88.281 (87.423)
[2021-04-28 22:01:52 train_lshot.py:257] INFO Epoch: [16][70/150] Time 0.281 (0.376) Data 0.001 (0.083) Loss 1.2748 (1.1856) Prec@1 59.375 (63.925) Prec@5 86.719 (87.445)
[2021-04-28 22:01:55 train_lshot.py:257] INFO Epoch: [16][80/150] Time 0.274 (0.364) Data 0.000 (0.073) Loss 1.2739 (1.1847) Prec@1 60.938 (64.000) Prec@5 84.766 (87.524)
[2021-04-28 22:01:59 train_lshot.py:257] INFO Epoch: [16][90/150] Time 1.070 (0.363) Data 0.000 (0.065) Loss 1.2010 (1.1822) Prec@1 63.672 (63.951) Prec@5 87.500 (87.582)
[2021-04-28 22:02:02 train_lshot.py:257] INFO Epoch: [16][100/150] Time 0.289 (0.361) Data 0.000 (0.058) Loss 1.2319 (1.1815) Prec@1 60.547 (63.861) Prec@5 86.719 (87.620)
[2021-04-28 22:02:05 train_lshot.py:257] INFO Epoch: [16][110/150] Time 0.279 (0.354) Data 0.000 (0.053) Loss 1.2302 (1.1801) Prec@1 62.500 (63.950) Prec@5 87.109 (87.627)
[2021-04-28 22:02:08 train_lshot.py:257] INFO Epoch: [16][120/150] Time 0.277 (0.348) Data 0.000 (0.049) Loss 1.1789 (1.1825) Prec@1 66.797 (63.930) Prec@5 87.891 (87.587)
[2021-04-28 22:02:12 train_lshot.py:257] INFO Epoch: [16][130/150] Time 0.292 (0.353) Data 0.000 (0.045) Loss 1.1073 (1.1830) Prec@1 68.750 (63.881) Prec@5 87.500 (87.619)
[2021-04-28 22:02:15 train_lshot.py:257] INFO Epoch: [16][140/150] Time 0.282 (0.348) Data 0.000 (0.042) Loss 1.2448 (1.1857) Prec@1 63.672 (63.774) Prec@5 85.156 (87.522)
[2021-04-28 22:02:24 train_lshot.py:257] INFO Epoch: [17][0/150] Time 6.381 (6.381) Data 5.946 (5.946) Loss 1.2405 (1.2405) Prec@1 62.500 (62.500) Prec@5 86.719 (86.719)
[2021-04-28 22:02:28 train_lshot.py:257] INFO Epoch: [17][10/150] Time 0.343 (0.903) Data 0.001 (0.543) Loss 1.1261 (1.1327) Prec@1 63.672 (66.761) Prec@5 89.453 (88.210)
[2021-04-28 22:02:31 train_lshot.py:257] INFO Epoch: [17][20/150] Time 0.280 (0.610) Data 0.000 (0.285) Loss 1.1367 (1.1432) Prec@1 64.844 (66.202) Prec@5 88.281 (87.872)
[2021-04-28 22:02:33 train_lshot.py:257] INFO Epoch: [17][30/150] Time 0.287 (0.507) Data 0.000 (0.193) Loss 1.1479 (1.1540) Prec@1 62.891 (65.260) Prec@5 89.453 (87.966)
[2021-04-28 22:02:36 train_lshot.py:257] INFO Epoch: [17][40/150] Time 0.275 (0.453) Data 0.000 (0.146) Loss 1.1596 (1.1615) Prec@1 62.891 (64.958) Prec@5 88.672 (87.805)
[2021-04-28 22:02:39 train_lshot.py:257] INFO Epoch: [17][50/150] Time 0.281 (0.420) Data 0.000 (0.117) Loss 1.0889 (1.1598) Prec@1 67.188 (64.966) Prec@5 88.672 (87.868)
[2021-04-28 22:02:42 train_lshot.py:257] INFO Epoch: [17][60/150] Time 0.284 (0.398) Data 0.000 (0.098) Loss 1.0300 (1.1537) Prec@1 69.922 (65.113) Prec@5 87.500 (87.788)
[2021-04-28 22:02:45 train_lshot.py:257] INFO Epoch: [17][70/150] Time 0.291 (0.382) Data 0.001 (0.085) Loss 1.1794 (1.1515) Prec@1 63.281 (65.080) Prec@5 89.062 (87.819)
[2021-04-28 22:02:48 train_lshot.py:257] INFO Epoch: [17][80/150] Time 0.294 (0.370) Data 0.000 (0.074) Loss 1.2795 (1.1517) Prec@1 62.109 (65.037) Prec@5 86.719 (87.934)
[2021-04-28 22:02:51 train_lshot.py:257] INFO Epoch: [17][90/150] Time 0.346 (0.366) Data 0.000 (0.066) Loss 1.1599 (1.1517) Prec@1 65.234 (64.990) Prec@5 86.719 (87.968)
[2021-04-28 22:02:54 train_lshot.py:257] INFO Epoch: [17][100/150] Time 0.289 (0.358) Data 0.000 (0.059) Loss 1.0330 (1.1520) Prec@1 68.750 (64.867) Prec@5 89.844 (88.003)
[2021-04-28 22:02:57 train_lshot.py:257] INFO Epoch: [17][110/150] Time 0.288 (0.352) Data 0.000 (0.054) Loss 1.2112 (1.1524) Prec@1 65.234 (64.854) Prec@5 87.500 (87.986)
[2021-04-28 22:03:00 train_lshot.py:257] INFO Epoch: [17][120/150] Time 0.431 (0.349) Data 0.000 (0.050) Loss 1.1769 (1.1514) Prec@1 66.406 (64.841) Prec@5 86.328 (87.933)
[2021-04-28 22:03:03 train_lshot.py:257] INFO Epoch: [17][130/150] Time 0.282 (0.346) Data 0.000 (0.046) Loss 1.1494 (1.1523) Prec@1 63.672 (64.751) Prec@5 87.891 (87.909)
[2021-04-28 22:03:06 train_lshot.py:257] INFO Epoch: [17][140/150] Time 0.292 (0.341) Data 0.000 (0.043) Loss 1.1688 (1.1502) Prec@1 61.328 (64.783) Prec@5 88.672 (87.965)
[2021-04-28 22:03:14 train_lshot.py:257] INFO Epoch: [18][0/150] Time 4.834 (4.834) Data 4.453 (4.453) Loss 1.0835 (1.0835) Prec@1 67.188 (67.188) Prec@5 89.844 (89.844)
[2021-04-28 22:03:18 train_lshot.py:257] INFO Epoch: [18][10/150] Time 0.329 (0.825) Data 0.001 (0.444) Loss 1.0914 (1.1082) Prec@1 69.531 (66.300) Prec@5 87.891 (88.530)
[2021-04-28 22:03:21 train_lshot.py:257] INFO Epoch: [18][20/150] Time 0.280 (0.575) Data 0.000 (0.233) Loss 1.1928 (1.1202) Prec@1 64.844 (65.978) Prec@5 85.547 (88.300)
[2021-04-28 22:03:24 train_lshot.py:257] INFO Epoch: [18][30/150] Time 0.284 (0.482) Data 0.000 (0.158) Loss 1.1395 (1.1271) Prec@1 65.234 (65.675) Prec@5 88.672 (88.357)
[2021-04-28 22:03:27 train_lshot.py:257] INFO Epoch: [18][40/150] Time 0.277 (0.433) Data 0.000 (0.120) Loss 1.1007 (1.1306) Prec@1 64.844 (65.568) Prec@5 89.453 (88.338)
[2021-04-28 22:03:30 train_lshot.py:257] INFO Epoch: [18][50/150] Time 0.281 (0.403) Data 0.001 (0.096) Loss 1.1045 (1.1297) Prec@1 65.234 (65.763) Prec@5 89.062 (88.419)
[2021-04-28 22:03:33 train_lshot.py:257] INFO Epoch: [18][60/150] Time 0.282 (0.384) Data 0.000 (0.080) Loss 1.1377 (1.1289) Prec@1 67.578 (65.683) Prec@5 87.109 (88.441)
[2021-04-28 22:03:36 train_lshot.py:257] INFO Epoch: [18][70/150] Time 0.283 (0.370) Data 0.001 (0.069) Loss 1.1129 (1.1268) Prec@1 68.750 (65.697) Prec@5 88.281 (88.501)
[2021-04-28 22:03:39 train_lshot.py:257] INFO Epoch: [18][80/150] Time 0.282 (0.360) Data 0.000 (0.061) Loss 1.1971 (1.1250) Prec@1 62.891 (65.731) Prec@5 87.891 (88.542)
[2021-04-28 22:03:41 train_lshot.py:257] INFO Epoch: [18][90/150] Time 0.289 (0.352) Data 0.000 (0.054) Loss 1.2180 (1.1291) Prec@1 61.328 (65.591) Prec@5 85.547 (88.500)
[2021-04-28 22:03:45 train_lshot.py:257] INFO Epoch: [18][100/150] Time 0.299 (0.357) Data 0.000 (0.049) Loss 1.1622 (1.1256) Prec@1 67.969 (65.718) Prec@5 85.938 (88.614)
[2021-04-28 22:03:48 train_lshot.py:257] INFO Epoch: [18][110/150] Time 0.286 (0.351) Data 0.000 (0.044) Loss 1.1129 (1.1231) Prec@1 63.672 (65.762) Prec@5 89.453 (88.640)
[2021-04-28 22:03:52 train_lshot.py:257] INFO Epoch: [18][120/150] Time 0.406 (0.349) Data 0.000 (0.041) Loss 1.3382 (1.1243) Prec@1 58.203 (65.738) Prec@5 84.375 (88.569)
[2021-04-28 22:03:55 train_lshot.py:257] INFO Epoch: [18][130/150] Time 0.282 (0.345) Data 0.000 (0.038) Loss 1.2049 (1.1239) Prec@1 61.328 (65.831) Prec@5 87.891 (88.535)
[2021-04-28 22:03:57 train_lshot.py:257] INFO Epoch: [18][140/150] Time 0.281 (0.341) Data 0.000 (0.035) Loss 1.1276 (1.1257) Prec@1 66.406 (65.761) Prec@5 91.016 (88.503)
[2021-04-28 22:04:05 train_lshot.py:257] INFO Epoch: [19][0/150] Time 4.249 (4.249) Data 3.807 (3.807) Loss 1.0672 (1.0672) Prec@1 68.750 (68.750) Prec@5 89.062 (89.062)
[2021-04-28 22:04:09 train_lshot.py:257] INFO Epoch: [19][10/150] Time 0.351 (0.773) Data 0.000 (0.375) Loss 0.9897 (1.0682) Prec@1 70.703 (68.040) Prec@5 92.969 (90.305)
[2021-04-28 22:04:13 train_lshot.py:257] INFO Epoch: [19][20/150] Time 0.291 (0.559) Data 0.000 (0.197) Loss 1.1341 (1.0837) Prec@1 64.062 (67.206) Prec@5 85.938 (89.732)
[2021-04-28 22:04:16 train_lshot.py:257] INFO Epoch: [19][30/150] Time 0.286 (0.473) Data 0.000 (0.134) Loss 1.1712 (1.0885) Prec@1 64.453 (67.326) Prec@5 91.016 (89.592)
[2021-04-28 22:04:18 train_lshot.py:257] INFO Epoch: [19][40/150] Time 0.294 (0.427) Data 0.000 (0.101) Loss 1.0134 (1.0881) Prec@1 67.578 (67.035) Prec@5 91.016 (89.634)
[2021-04-28 22:04:21 train_lshot.py:257] INFO Epoch: [19][50/150] Time 0.279 (0.398) Data 0.000 (0.081) Loss 1.0945 (1.0884) Prec@1 66.406 (66.866) Prec@5 90.234 (89.560)
[2021-04-28 22:04:24 train_lshot.py:257] INFO Epoch: [19][60/150] Time 0.291 (0.379) Data 0.000 (0.068) Loss 0.9804 (1.0814) Prec@1 66.016 (67.021) Prec@5 92.188 (89.632)
[2021-04-28 22:04:27 train_lshot.py:257] INFO Epoch: [19][70/150] Time 0.280 (0.366) Data 0.001 (0.059) Loss 1.0998 (1.0776) Prec@1 67.578 (67.210) Prec@5 85.938 (89.679)
[2021-04-28 22:04:30 train_lshot.py:257] INFO Epoch: [19][80/150] Time 0.295 (0.356) Data 0.000 (0.051) Loss 1.1339 (1.0827) Prec@1 64.062 (67.009) Prec@5 89.453 (89.588)
[2021-04-28 22:04:33 train_lshot.py:257] INFO Epoch: [19][90/150] Time 0.280 (0.348) Data 0.000 (0.046) Loss 1.1654 (1.0848) Prec@1 64.844 (67.007) Prec@5 85.547 (89.496)
[2021-04-28 22:04:36 train_lshot.py:257] INFO Epoch: [19][100/150] Time 0.287 (0.344) Data 0.000 (0.041) Loss 1.0758 (1.0846) Prec@1 66.016 (66.913) Prec@5 89.453 (89.484)
[2021-04-28 22:04:39 train_lshot.py:257] INFO Epoch: [19][110/150] Time 0.283 (0.339) Data 0.000 (0.038) Loss 1.0574 (1.0860) Prec@1 66.797 (66.853) Prec@5 87.500 (89.425)
[2021-04-28 22:04:41 train_lshot.py:257] INFO Epoch: [19][120/150] Time 0.291 (0.335) Data 0.000 (0.035) Loss 1.1085 (1.0854) Prec@1 64.844 (66.897) Prec@5 88.281 (89.408)
[2021-04-28 22:04:44 train_lshot.py:257] INFO Epoch: [19][130/150] Time 0.284 (0.331) Data 0.000 (0.032) Loss 1.1524 (1.0855) Prec@1 63.672 (66.964) Prec@5 86.719 (89.346)
[2021-04-28 22:04:47 train_lshot.py:257] INFO Epoch: [19][140/150] Time 0.295 (0.328) Data 0.000 (0.030) Loss 1.1484 (1.0862) Prec@1 64.062 (66.935) Prec@5 85.938 (89.295)
[2021-04-28 22:05:18 train_lshot.py:119] INFO Meta Val 19: 0.584586679905653
[2021-04-28 22:05:25 train_lshot.py:257] INFO Epoch: [20][0/150] Time 6.328 (6.328) Data 5.965 (5.965) Loss 0.9740 (0.9740) Prec@1 71.094 (71.094) Prec@5 91.406 (91.406)
[2021-04-28 22:05:28 train_lshot.py:257] INFO Epoch: [20][10/150] Time 0.331 (0.854) Data 0.000 (0.543) Loss 0.9712 (1.0354) Prec@1 68.359 (68.075) Prec@5 92.188 (90.589)
[2021-04-28 22:05:31 train_lshot.py:257] INFO Epoch: [20][20/150] Time 0.291 (0.583) Data 0.000 (0.285) Loss 0.9976 (1.0325) Prec@1 68.750 (68.434) Prec@5 92.969 (90.086)
[2021-04-28 22:05:34 train_lshot.py:257] INFO Epoch: [20][30/150] Time 0.279 (0.487) Data 0.000 (0.193) Loss 1.0038 (1.0450) Prec@1 69.922 (68.296) Prec@5 91.016 (89.768)
[2021-04-28 22:05:37 train_lshot.py:257] INFO Epoch: [20][40/150] Time 0.281 (0.437) Data 0.001 (0.146) Loss 1.0500 (1.0434) Prec@1 67.188 (68.464) Prec@5 91.406 (89.758)
[2021-04-28 22:05:40 train_lshot.py:257] INFO Epoch: [20][50/150] Time 0.278 (0.408) Data 0.000 (0.118) Loss 1.1048 (1.0435) Prec@1 67.578 (68.589) Prec@5 86.719 (89.675)
[2021-04-28 22:05:42 train_lshot.py:257] INFO Epoch: [20][60/150] Time 0.285 (0.388) Data 0.000 (0.098) Loss 1.1162 (1.0461) Prec@1 64.844 (68.545) Prec@5 88.281 (89.690)
[2021-04-28 22:05:45 train_lshot.py:257] INFO Epoch: [20][70/150] Time 0.279 (0.373) Data 0.001 (0.085) Loss 1.0775 (1.0481) Prec@1 68.359 (68.579) Prec@5 89.062 (89.706)
[2021-04-28 22:05:48 train_lshot.py:257] INFO Epoch: [20][80/150] Time 0.273 (0.361) Data 0.000 (0.074) Loss 1.1450 (1.0500) Prec@1 66.406 (68.446) Prec@5 88.672 (89.752)
[2021-04-28 22:05:51 train_lshot.py:257] INFO Epoch: [20][90/150] Time 0.286 (0.352) Data 0.000 (0.066) Loss 1.0356 (1.0508) Prec@1 69.531 (68.334) Prec@5 91.016 (89.818)
[2021-04-28 22:05:54 train_lshot.py:257] INFO Epoch: [20][100/150] Time 0.282 (0.346) Data 0.000 (0.060) Loss 0.9668 (1.0539) Prec@1 70.703 (68.243) Prec@5 91.797 (89.654)
[2021-04-28 22:05:57 train_lshot.py:257] INFO Epoch: [20][110/150] Time 0.406 (0.341) Data 0.000 (0.054) Loss 1.1872 (1.0517) Prec@1 63.672 (68.314) Prec@5 86.328 (89.685)
[2021-04-28 22:06:00 train_lshot.py:257] INFO Epoch: [20][120/150] Time 0.284 (0.339) Data 0.000 (0.050) Loss 0.9545 (1.0524) Prec@1 70.703 (68.350) Prec@5 91.797 (89.705)
[2021-04-28 22:06:03 train_lshot.py:257] INFO Epoch: [20][130/150] Time 0.291 (0.335) Data 0.000 (0.046) Loss 1.0727 (1.0521) Prec@1 68.359 (68.333) Prec@5 91.016 (89.680)
[2021-04-28 22:06:06 train_lshot.py:257] INFO Epoch: [20][140/150] Time 0.311 (0.334) Data 0.000 (0.043) Loss 0.9798 (1.0509) Prec@1 71.875 (68.406) Prec@5 92.188 (89.725)
[2021-04-28 22:06:14 train_lshot.py:257] INFO Epoch: [21][0/150] Time 5.454 (5.454) Data 5.031 (5.031) Loss 0.9883 (0.9883) Prec@1 72.656 (72.656) Prec@5 91.406 (91.406)
[2021-04-28 22:06:19 train_lshot.py:257] INFO Epoch: [21][10/150] Time 0.297 (0.892) Data 0.000 (0.536) Loss 1.0253 (1.0218) Prec@1 70.703 (69.673) Prec@5 91.797 (90.980)
[2021-04-28 22:06:22 train_lshot.py:257] INFO Epoch: [21][20/150] Time 0.282 (0.604) Data 0.000 (0.281) Loss 0.9551 (1.0194) Prec@1 71.484 (69.364) Prec@5 91.797 (91.053)
[2021-04-28 22:06:25 train_lshot.py:257] INFO Epoch: [21][30/150] Time 0.283 (0.505) Data 0.000 (0.190) Loss 1.1594 (1.0190) Prec@1 64.453 (69.556) Prec@5 87.500 (90.789)
[2021-04-28 22:06:27 train_lshot.py:257] INFO Epoch: [21][40/150] Time 0.289 (0.451) Data 0.001 (0.144) Loss 1.0060 (1.0124) Prec@1 69.141 (69.550) Prec@5 89.844 (90.958)
[2021-04-28 22:06:30 train_lshot.py:257] INFO Epoch: [21][50/150] Time 0.281 (0.418) Data 0.001 (0.116) Loss 1.0434 (1.0144) Prec@1 69.922 (69.616) Prec@5 89.062 (90.732)
[2021-04-28 22:06:33 train_lshot.py:257] INFO Epoch: [21][60/150] Time 0.274 (0.396) Data 0.000 (0.097) Loss 1.1093 (1.0135) Prec@1 64.062 (69.647) Prec@5 87.891 (90.619)
[2021-04-28 22:06:36 train_lshot.py:257] INFO Epoch: [21][70/150] Time 0.282 (0.381) Data 0.001 (0.083) Loss 0.9812 (1.0169) Prec@1 71.484 (69.460) Prec@5 90.625 (90.520)
[2021-04-28 22:06:39 train_lshot.py:257] INFO Epoch: [21][80/150] Time 0.291 (0.369) Data 0.000 (0.073) Loss 0.9474 (1.0170) Prec@1 72.656 (69.536) Prec@5 91.016 (90.480)
[2021-04-28 22:06:43 train_lshot.py:257] INFO Epoch: [21][90/150] Time 0.327 (0.374) Data 0.000 (0.065) Loss 0.9796 (1.0159) Prec@1 71.484 (69.570) Prec@5 91.016 (90.483)
[2021-04-28 22:06:46 train_lshot.py:257] INFO Epoch: [21][100/150] Time 0.280 (0.365) Data 0.000 (0.059) Loss 1.0346 (1.0184) Prec@1 67.578 (69.531) Prec@5 90.625 (90.408)
[2021-04-28 22:06:49 train_lshot.py:257] INFO Epoch: [21][110/150] Time 0.286 (0.358) Data 0.000 (0.053) Loss 1.0719 (1.0181) Prec@1 66.016 (69.514) Prec@5 88.672 (90.431)
[2021-04-28 22:06:51 train_lshot.py:257] INFO Epoch: [21][120/150] Time 0.279 (0.352) Data 0.000 (0.049) Loss 1.0227 (1.0174) Prec@1 68.750 (69.534) Prec@5 90.234 (90.435)
[2021-04-28 22:06:56 train_lshot.py:257] INFO Epoch: [21][130/150] Time 0.296 (0.357) Data 0.000 (0.045) Loss 1.0697 (1.0199) Prec@1 69.922 (69.522) Prec@5 89.453 (90.357)
[2021-04-28 22:06:59 train_lshot.py:257] INFO Epoch: [21][140/150] Time 0.286 (0.352) Data 0.000 (0.042) Loss 1.0440 (1.0234) Prec@1 69.531 (69.432) Prec@5 87.109 (90.279)
[2021-04-28 22:07:06 train_lshot.py:257] INFO Epoch: [22][0/150] Time 4.538 (4.538) Data 4.074 (4.074) Loss 0.9028 (0.9028) Prec@1 72.656 (72.656) Prec@5 92.188 (92.188)
[2021-04-28 22:07:11 train_lshot.py:257] INFO Epoch: [22][10/150] Time 0.341 (0.826) Data 0.000 (0.435) Loss 0.9250 (0.9618) Prec@1 73.047 (71.200) Prec@5 91.016 (91.513)
[2021-04-28 22:07:14 train_lshot.py:257] INFO Epoch: [22][20/150] Time 0.281 (0.581) Data 0.000 (0.228) Loss 0.9942 (0.9723) Prec@1 69.922 (70.647) Prec@5 90.625 (91.425)
[2021-04-28 22:07:17 train_lshot.py:257] INFO Epoch: [22][30/150] Time 0.275 (0.484) Data 0.001 (0.155) Loss 0.8499 (0.9729) Prec@1 75.391 (70.791) Prec@5 92.578 (91.167)
[2021-04-28 22:07:19 train_lshot.py:257] INFO Epoch: [22][40/150] Time 0.284 (0.435) Data 0.000 (0.117) Loss 0.9057 (0.9733) Prec@1 70.703 (70.608) Prec@5 92.188 (91.235)
[2021-04-28 22:07:22 train_lshot.py:257] INFO Epoch: [22][50/150] Time 0.291 (0.405) Data 0.000 (0.094) Loss 1.0114 (0.9854) Prec@1 70.312 (70.228) Prec@5 90.234 (90.908)
[2021-04-28 22:07:25 train_lshot.py:257] INFO Epoch: [22][60/150] Time 0.278 (0.385) Data 0.000 (0.079) Loss 0.8964 (0.9914) Prec@1 72.656 (70.108) Prec@5 93.750 (90.990)
[2021-04-28 22:07:28 train_lshot.py:257] INFO Epoch: [22][70/150] Time 0.292 (0.371) Data 0.001 (0.068) Loss 1.1155 (0.9993) Prec@1 67.188 (69.845) Prec@5 87.891 (90.801)
[2021-04-28 22:07:31 train_lshot.py:257] INFO Epoch: [22][80/150] Time 0.281 (0.361) Data 0.000 (0.060) Loss 0.8968 (1.0024) Prec@1 76.562 (69.864) Prec@5 92.188 (90.726)
[2021-04-28 22:07:34 train_lshot.py:257] INFO Epoch: [22][90/150] Time 0.282 (0.353) Data 0.000 (0.053) Loss 1.0864 (1.0055) Prec@1 68.750 (69.729) Prec@5 88.672 (90.616)
[2021-04-28 22:07:37 train_lshot.py:257] INFO Epoch: [22][100/150] Time 0.280 (0.347) Data 0.000 (0.048) Loss 1.0627 (1.0081) Prec@1 66.406 (69.663) Prec@5 89.453 (90.598)
[2021-04-28 22:07:41 train_lshot.py:257] INFO Epoch: [22][110/150] Time 0.309 (0.353) Data 0.000 (0.043) Loss 1.0848 (1.0103) Prec@1 64.062 (69.566) Prec@5 91.016 (90.555)
[2021-04-28 22:07:44 train_lshot.py:257] INFO Epoch: [22][120/150] Time 0.283 (0.347) Data 0.000 (0.040) Loss 1.0555 (1.0085) Prec@1 69.531 (69.599) Prec@5 90.625 (90.612)
[2021-04-28 22:07:46 train_lshot.py:257] INFO Epoch: [22][130/150] Time 0.288 (0.342) Data 0.000 (0.037) Loss 1.0020 (1.0073) Prec@1 70.703 (69.588) Prec@5 89.062 (90.631)
[2021-04-28 22:07:49 train_lshot.py:257] INFO Epoch: [22][140/150] Time 0.287 (0.339) Data 0.000 (0.034) Loss 1.0302 (1.0080) Prec@1 69.141 (69.612) Prec@5 91.016 (90.600)
[2021-04-28 22:07:58 train_lshot.py:257] INFO Epoch: [23][0/150] Time 5.650 (5.650) Data 5.224 (5.224) Loss 0.9527 (0.9527) Prec@1 71.094 (71.094) Prec@5 92.969 (92.969)
[2021-04-28 22:08:02 train_lshot.py:257] INFO Epoch: [23][10/150] Time 0.335 (0.858) Data 0.001 (0.479) Loss 0.9709 (0.9778) Prec@1 71.484 (70.455) Prec@5 89.062 (90.767)
[2021-04-28 22:08:05 train_lshot.py:257] INFO Epoch: [23][20/150] Time 0.292 (0.588) Data 0.000 (0.251) Loss 1.0046 (0.9745) Prec@1 67.578 (70.517) Prec@5 92.969 (91.202)
[2021-04-28 22:08:08 train_lshot.py:257] INFO Epoch: [23][30/150] Time 0.285 (0.492) Data 0.000 (0.170) Loss 0.9979 (0.9735) Prec@1 71.094 (71.270) Prec@5 91.797 (91.053)
[2021-04-28 22:08:11 train_lshot.py:257] INFO Epoch: [23][40/150] Time 0.276 (0.442) Data 0.000 (0.129) Loss 0.9762 (0.9675) Prec@1 71.484 (71.532) Prec@5 92.578 (91.244)
[2021-04-28 22:08:14 train_lshot.py:257] INFO Epoch: [23][50/150] Time 0.279 (0.410) Data 0.000 (0.104) Loss 1.0039 (0.9675) Prec@1 68.359 (71.599) Prec@5 89.453 (91.230)
[2021-04-28 22:08:16 train_lshot.py:257] INFO Epoch: [23][60/150] Time 0.279 (0.390) Data 0.000 (0.087) Loss 0.9613 (0.9713) Prec@1 73.438 (71.523) Prec@5 89.453 (91.099)
[2021-04-28 22:08:19 train_lshot.py:257] INFO Epoch: [23][70/150] Time 0.294 (0.376) Data 0.002 (0.075) Loss 1.0530 (0.9759) Prec@1 69.531 (71.154) Prec@5 88.672 (91.049)
[2021-04-28 22:08:22 train_lshot.py:257] INFO Epoch: [23][80/150] Time 0.292 (0.365) Data 0.000 (0.065) Loss 0.9076 (0.9738) Prec@1 75.781 (71.306) Prec@5 92.578 (91.054)
[2021-04-28 22:08:25 train_lshot.py:257] INFO Epoch: [23][90/150] Time 0.288 (0.356) Data 0.000 (0.058) Loss 1.0214 (0.9800) Prec@1 66.797 (70.982) Prec@5 90.234 (90.938)
[2021-04-28 22:08:28 train_lshot.py:257] INFO Epoch: [23][100/150] Time 0.291 (0.349) Data 0.000 (0.053) Loss 0.9335 (0.9808) Prec@1 73.828 (70.924) Prec@5 91.406 (90.931)
[2021-04-28 22:08:31 train_lshot.py:257] INFO Epoch: [23][110/150] Time 0.284 (0.343) Data 0.000 (0.048) Loss 1.0807 (0.9844) Prec@1 67.578 (70.742) Prec@5 87.500 (90.808)
[2021-04-28 22:08:34 train_lshot.py:257] INFO Epoch: [23][120/150] Time 0.285 (0.339) Data 0.000 (0.044) Loss 0.9792 (0.9844) Prec@1 71.484 (70.703) Prec@5 91.797 (90.835)
[2021-04-28 22:08:37 train_lshot.py:257] INFO Epoch: [23][130/150] Time 0.301 (0.338) Data 0.000 (0.041) Loss 1.0219 (0.9873) Prec@1 68.359 (70.590) Prec@5 89.453 (90.813)
[2021-04-28 22:08:40 train_lshot.py:257] INFO Epoch: [23][140/150] Time 0.296 (0.334) Data 0.000 (0.038) Loss 0.9249 (0.9857) Prec@1 73.438 (70.706) Prec@5 92.578 (90.838)
[2021-04-28 22:09:12 train_lshot.py:119] INFO Meta Val 23: 0.5669600124955178
[2021-04-28 22:09:18 train_lshot.py:257] INFO Epoch: [24][0/150] Time 5.672 (5.672) Data 5.163 (5.163) Loss 0.9131 (0.9131) Prec@1 73.828 (73.828) Prec@5 92.188 (92.188)
[2021-04-28 22:09:22 train_lshot.py:257] INFO Epoch: [24][10/150] Time 0.291 (0.877) Data 0.001 (0.488) Loss 0.8979 (0.9017) Prec@1 74.219 (73.544) Prec@5 93.359 (92.330)
[2021-04-28 22:09:24 train_lshot.py:257] INFO Epoch: [24][20/150] Time 0.286 (0.593) Data 0.000 (0.256) Loss 0.9020 (0.9149) Prec@1 72.266 (72.935) Prec@5 91.016 (92.206)
[2021-04-28 22:09:27 train_lshot.py:257] INFO Epoch: [24][30/150] Time 0.291 (0.492) Data 0.000 (0.173) Loss 0.9821 (0.9301) Prec@1 69.922 (72.341) Prec@5 90.625 (91.583)
[2021-04-28 22:09:30 train_lshot.py:257] INFO Epoch: [24][40/150] Time 0.278 (0.442) Data 0.000 (0.131) Loss 0.8804 (0.9336) Prec@1 76.172 (72.151) Prec@5 92.969 (91.654)
[2021-04-28 22:09:33 train_lshot.py:257] INFO Epoch: [24][50/150] Time 0.290 (0.411) Data 0.000 (0.106) Loss 0.8472 (0.9320) Prec@1 75.781 (72.166) Prec@5 94.531 (91.820)
[2021-04-28 22:09:36 train_lshot.py:257] INFO Epoch: [24][60/150] Time 0.278 (0.389) Data 0.000 (0.088) Loss 1.0168 (0.9459) Prec@1 69.922 (71.715) Prec@5 90.234 (91.496)
[2021-04-28 22:09:39 train_lshot.py:257] INFO Epoch: [24][70/150] Time 0.284 (0.374) Data 0.001 (0.076) Loss 0.9905 (0.9494) Prec@1 71.094 (71.605) Prec@5 89.453 (91.390)
[2021-04-28 22:09:41 train_lshot.py:257] INFO Epoch: [24][80/150] Time 0.273 (0.362) Data 0.000 (0.067) Loss 0.9794 (0.9540) Prec@1 68.359 (71.446) Prec@5 91.016 (91.363)
[2021-04-28 22:09:44 train_lshot.py:257] INFO Epoch: [24][90/150] Time 0.283 (0.354) Data 0.000 (0.059) Loss 0.9865 (0.9549) Prec@1 70.312 (71.403) Prec@5 88.281 (91.277)
[2021-04-28 22:09:47 train_lshot.py:257] INFO Epoch: [24][100/150] Time 0.283 (0.347) Data 0.000 (0.053) Loss 1.0088 (0.9565) Prec@1 68.359 (71.283) Prec@5 89.062 (91.178)
[2021-04-28 22:09:50 train_lshot.py:257] INFO Epoch: [24][110/150] Time 0.288 (0.342) Data 0.000 (0.049) Loss 0.9244 (0.9558) Prec@1 72.656 (71.284) Prec@5 92.969 (91.209)
[2021-04-28 22:09:53 train_lshot.py:257] INFO Epoch: [24][120/150] Time 0.347 (0.339) Data 0.000 (0.045) Loss 0.9543 (0.9574) Prec@1 72.266 (71.287) Prec@5 93.359 (91.200)
[2021-04-28 22:09:56 train_lshot.py:257] INFO Epoch: [24][130/150] Time 0.285 (0.336) Data 0.000 (0.041) Loss 0.9883 (0.9577) Prec@1 69.531 (71.249) Prec@5 88.672 (91.177)
[2021-04-28 22:10:00 train_lshot.py:257] INFO Epoch: [24][140/150] Time 0.352 (0.339) Data 0.000 (0.038) Loss 1.1016 (0.9599) Prec@1 71.484 (71.235) Prec@5 85.156 (91.107)
[2021-04-28 22:10:10 train_lshot.py:257] INFO Epoch: [25][0/150] Time 6.954 (6.954) Data 6.534 (6.534) Loss 0.9413 (0.9413) Prec@1 74.609 (74.609) Prec@5 89.844 (89.844)
[2021-04-28 22:10:13 train_lshot.py:257] INFO Epoch: [25][10/150] Time 0.294 (0.945) Data 0.006 (0.595) Loss 0.8290 (0.9116) Prec@1 75.000 (73.580) Prec@5 94.531 (92.152)
[2021-04-28 22:10:16 train_lshot.py:257] INFO Epoch: [25][20/150] Time 0.277 (0.629) Data 0.000 (0.312) Loss 0.8918 (0.9216) Prec@1 74.609 (72.898) Prec@5 92.188 (92.057)
[2021-04-28 22:10:19 train_lshot.py:257] INFO Epoch: [25][30/150] Time 0.279 (0.522) Data 0.000 (0.211) Loss 0.9082 (0.9102) Prec@1 71.875 (72.959) Prec@5 92.188 (92.162)
[2021-04-28 22:10:22 train_lshot.py:257] INFO Epoch: [25][40/150] Time 0.285 (0.464) Data 0.000 (0.160) Loss 1.0750 (0.9156) Prec@1 67.578 (72.694) Prec@5 90.625 (92.292)
[2021-04-28 22:10:25 train_lshot.py:257] INFO Epoch: [25][50/150] Time 0.294 (0.429) Data 0.000 (0.129) Loss 0.9122 (0.9260) Prec@1 71.484 (72.281) Prec@5 92.969 (92.149)
[2021-04-28 22:10:28 train_lshot.py:257] INFO Epoch: [25][60/150] Time 0.286 (0.405) Data 0.000 (0.108) Loss 0.9551 (0.9278) Prec@1 72.656 (72.471) Prec@5 90.234 (92.059)
[2021-04-28 22:10:31 train_lshot.py:257] INFO Epoch: [25][70/150] Time 0.301 (0.389) Data 0.001 (0.093) Loss 0.9024 (0.9268) Prec@1 73.438 (72.508) Prec@5 92.578 (92.017)
[2021-04-28 22:10:33 train_lshot.py:257] INFO Epoch: [25][80/150] Time 0.281 (0.375) Data 0.000 (0.081) Loss 0.9174 (0.9258) Prec@1 74.609 (72.622) Prec@5 90.234 (91.966)
[2021-04-28 22:10:36 train_lshot.py:257] INFO Epoch: [25][90/150] Time 0.285 (0.366) Data 0.000 (0.072) Loss 0.8489 (0.9266) Prec@1 76.172 (72.648) Prec@5 92.969 (91.934)
[2021-04-28 22:10:39 train_lshot.py:257] INFO Epoch: [25][100/150] Time 0.287 (0.358) Data 0.001 (0.065) Loss 0.9317 (0.9307) Prec@1 71.484 (72.447) Prec@5 92.188 (91.866)
[2021-04-28 22:10:42 train_lshot.py:257] INFO Epoch: [25][110/150] Time 0.303 (0.354) Data 0.000 (0.059) Loss 0.8588 (0.9336) Prec@1 72.656 (72.329) Prec@5 93.750 (91.825)
[2021-04-28 22:10:45 train_lshot.py:257] INFO Epoch: [25][120/150] Time 0.287 (0.348) Data 0.000 (0.054) Loss 0.8865 (0.9336) Prec@1 73.828 (72.321) Prec@5 93.750 (91.774)
[2021-04-28 22:10:48 train_lshot.py:257] INFO Epoch: [25][130/150] Time 0.285 (0.344) Data 0.000 (0.050) Loss 0.9927 (0.9365) Prec@1 70.703 (72.215) Prec@5 90.234 (91.693)
[2021-04-28 22:10:51 train_lshot.py:257] INFO Epoch: [25][140/150] Time 0.280 (0.340) Data 0.000 (0.047) Loss 0.8385 (0.9357) Prec@1 78.906 (72.288) Prec@5 91.406 (91.678)
[2021-04-28 22:10:59 train_lshot.py:257] INFO Epoch: [26][0/150] Time 5.286 (5.286) Data 4.852 (4.852) Loss 0.9629 (0.9629) Prec@1 71.484 (71.484) Prec@5 90.234 (90.234)
[2021-04-28 22:11:03 train_lshot.py:257] INFO Epoch: [26][10/150] Time 0.336 (0.859) Data 0.001 (0.476) Loss 0.8601 (0.9010) Prec@1 77.734 (73.509) Prec@5 93.750 (92.649)
[2021-04-28 22:11:06 train_lshot.py:257] INFO Epoch: [26][20/150] Time 0.277 (0.589) Data 0.000 (0.250) Loss 0.9525 (0.8909) Prec@1 72.656 (73.772) Prec@5 91.406 (92.467)
[2021-04-28 22:11:09 train_lshot.py:257] INFO Epoch: [26][30/150] Time 0.279 (0.492) Data 0.000 (0.169) Loss 0.8190 (0.9038) Prec@1 76.953 (73.362) Prec@5 92.578 (91.961)
[2021-04-28 22:11:12 train_lshot.py:257] INFO Epoch: [26][40/150] Time 0.284 (0.440) Data 0.000 (0.128) Loss 0.8747 (0.9062) Prec@1 70.703 (73.333) Prec@5 94.531 (91.940)
[2021-04-28 22:11:15 train_lshot.py:257] INFO Epoch: [26][50/150] Time 0.283 (0.409) Data 0.000 (0.103) Loss 0.9541 (0.9116) Prec@1 71.875 (73.116) Prec@5 88.281 (91.850)
[2021-04-28 22:11:18 train_lshot.py:257] INFO Epoch: [26][60/150] Time 0.283 (0.388) Data 0.000 (0.086) Loss 0.8139 (0.9108) Prec@1 80.859 (73.085) Prec@5 91.797 (91.726)
[2021-04-28 22:11:21 train_lshot.py:257] INFO Epoch: [26][70/150] Time 0.291 (0.374) Data 0.001 (0.074) Loss 0.8697 (0.9135) Prec@1 74.219 (72.948) Prec@5 93.750 (91.714)
[2021-04-28 22:11:25 train_lshot.py:257] INFO Epoch: [26][80/150] Time 0.298 (0.378) Data 0.000 (0.065) Loss 0.9059 (0.9110) Prec@1 71.875 (72.960) Prec@5 91.797 (91.792)
[2021-04-28 22:11:27 train_lshot.py:257] INFO Epoch: [26][90/150] Time 0.285 (0.368) Data 0.000 (0.058) Loss 0.8701 (0.9155) Prec@1 73.047 (72.798) Prec@5 92.969 (91.784)
[2021-04-28 22:11:30 train_lshot.py:257] INFO Epoch: [26][100/150] Time 0.290 (0.360) Data 0.000 (0.052) Loss 0.9415 (0.9181) Prec@1 72.266 (72.734) Prec@5 92.188 (91.727)
[2021-04-28 22:11:34 train_lshot.py:257] INFO Epoch: [26][110/150] Time 0.304 (0.361) Data 0.000 (0.048) Loss 1.0197 (0.9213) Prec@1 69.922 (72.628) Prec@5 89.844 (91.649)
[2021-04-28 22:11:37 train_lshot.py:257] INFO Epoch: [26][120/150] Time 0.272 (0.355) Data 0.000 (0.044) Loss 0.8984 (0.9231) Prec@1 73.047 (72.569) Prec@5 93.359 (91.593)
[2021-04-28 22:11:40 train_lshot.py:257] INFO Epoch: [26][130/150] Time 0.293 (0.349) Data 0.000 (0.040) Loss 0.9438 (0.9218) Prec@1 74.609 (72.570) Prec@5 89.844 (91.633)
[2021-04-28 22:11:43 train_lshot.py:257] INFO Epoch: [26][140/150] Time 0.275 (0.344) Data 0.000 (0.037) Loss 0.8758 (0.9226) Prec@1 74.219 (72.537) Prec@5 91.797 (91.633)
[2021-04-28 22:11:52 train_lshot.py:257] INFO Epoch: [27][0/150] Time 5.957 (5.957) Data 5.589 (5.589) Loss 0.8440 (0.8440) Prec@1 74.219 (74.219) Prec@5 94.922 (94.922)
[2021-04-28 22:11:55 train_lshot.py:257] INFO Epoch: [27][10/150] Time 0.276 (0.895) Data 0.000 (0.559) Loss 0.7939 (0.8724) Prec@1 79.688 (74.929) Prec@5 93.750 (92.827)
[2021-04-28 22:11:58 train_lshot.py:257] INFO Epoch: [27][20/150] Time 0.279 (0.609) Data 0.000 (0.293) Loss 0.8413 (0.8666) Prec@1 77.734 (74.758) Prec@5 93.359 (92.764)
[2021-04-28 22:12:01 train_lshot.py:257] INFO Epoch: [27][30/150] Time 0.284 (0.503) Data 0.000 (0.199) Loss 1.0075 (0.8764) Prec@1 71.484 (74.471) Prec@5 89.062 (92.465)
[2021-04-28 22:12:04 train_lshot.py:257] INFO Epoch: [27][40/150] Time 0.285 (0.448) Data 0.001 (0.150) Loss 0.8736 (0.8813) Prec@1 75.000 (74.019) Prec@5 94.922 (92.454)
[2021-04-28 22:12:07 train_lshot.py:257] INFO Epoch: [27][50/150] Time 0.287 (0.416) Data 0.000 (0.121) Loss 0.9076 (0.8840) Prec@1 73.438 (73.797) Prec@5 90.625 (92.440)
[2021-04-28 22:12:10 train_lshot.py:257] INFO Epoch: [27][60/150] Time 0.285 (0.394) Data 0.000 (0.101) Loss 0.8632 (0.8874) Prec@1 75.000 (73.668) Prec@5 92.969 (92.488)
[2021-04-28 22:12:13 train_lshot.py:257] INFO Epoch: [27][70/150] Time 0.283 (0.379) Data 0.001 (0.087) Loss 0.7859 (0.8835) Prec@1 78.516 (73.867) Prec@5 92.969 (92.496)
[2021-04-28 22:12:15 train_lshot.py:257] INFO Epoch: [27][80/150] Time 0.284 (0.367) Data 0.000 (0.076) Loss 0.8675 (0.8829) Prec@1 74.219 (74.002) Prec@5 93.359 (92.448)
[2021-04-28 22:12:19 train_lshot.py:257] INFO Epoch: [27][90/150] Time 0.295 (0.363) Data 0.000 (0.068) Loss 0.8401 (0.8841) Prec@1 75.000 (73.888) Prec@5 92.969 (92.394)
[2021-04-28 22:12:22 train_lshot.py:257] INFO Epoch: [27][100/150] Time 0.279 (0.355) Data 0.000 (0.061) Loss 0.8711 (0.8843) Prec@1 76.172 (73.859) Prec@5 93.359 (92.381)
[2021-04-28 22:12:24 train_lshot.py:257] INFO Epoch: [27][110/150] Time 0.287 (0.349) Data 0.000 (0.056) Loss 0.9738 (0.8881) Prec@1 71.484 (73.723) Prec@5 89.453 (92.328)
[2021-04-28 22:12:27 train_lshot.py:257] INFO Epoch: [27][120/150] Time 0.282 (0.344) Data 0.000 (0.051) Loss 0.8573 (0.8896) Prec@1 74.219 (73.618) Prec@5 91.406 (92.275)
[2021-04-28 22:12:30 train_lshot.py:257] INFO Epoch: [27][130/150] Time 0.292 (0.340) Data 0.000 (0.047) Loss 0.7743 (0.8931) Prec@1 78.516 (73.548) Prec@5 92.188 (92.199)
[2021-04-28 22:12:33 train_lshot.py:257] INFO Epoch: [27][140/150] Time 0.297 (0.336) Data 0.001 (0.044) Loss 0.8959 (0.8945) Prec@1 72.266 (73.476) Prec@5 91.016 (92.154)
[2021-04-28 22:13:04 train_lshot.py:119] INFO Meta Val 27: 0.583013346850872
[2021-04-28 22:13:10 train_lshot.py:257] INFO Epoch: [28][0/150] Time 5.520 (5.520) Data 5.060 (5.060) Loss 0.8118 (0.8118) Prec@1 78.125 (78.125) Prec@5 93.359 (93.359)
[2021-04-28 22:13:13 train_lshot.py:257] INFO Epoch: [28][10/150] Time 0.312 (0.835) Data 0.001 (0.491) Loss 0.7366 (0.8661) Prec@1 80.469 (75.888) Prec@5 91.797 (92.436)
[2021-04-28 22:13:16 train_lshot.py:257] INFO Epoch: [28][20/150] Time 0.275 (0.577) Data 0.000 (0.257) Loss 0.7835 (0.8763) Prec@1 78.516 (74.926) Prec@5 92.578 (92.411)
[2021-04-28 22:13:19 train_lshot.py:257] INFO Epoch: [28][30/150] Time 0.278 (0.482) Data 0.000 (0.174) Loss 0.7777 (0.8690) Prec@1 80.078 (74.975) Prec@5 92.578 (92.515)
[2021-04-28 22:13:22 train_lshot.py:257] INFO Epoch: [28][40/150] Time 0.288 (0.435) Data 0.000 (0.132) Loss 0.7968 (0.8629) Prec@1 75.391 (74.962) Prec@5 94.922 (92.740)
[2021-04-28 22:13:25 train_lshot.py:257] INFO Epoch: [28][50/150] Time 0.278 (0.405) Data 0.000 (0.106) Loss 0.9107 (0.8705) Prec@1 72.266 (74.625) Prec@5 91.797 (92.601)
[2021-04-28 22:13:28 train_lshot.py:257] INFO Epoch: [28][60/150] Time 0.287 (0.385) Data 0.000 (0.089) Loss 0.9490 (0.8678) Prec@1 71.094 (74.494) Prec@5 93.359 (92.713)
[2021-04-28 22:13:31 train_lshot.py:257] INFO Epoch: [28][70/150] Time 0.280 (0.371) Data 0.001 (0.076) Loss 0.8172 (0.8705) Prec@1 75.781 (74.340) Prec@5 96.094 (92.727)
[2021-04-28 22:13:33 train_lshot.py:257] INFO Epoch: [28][80/150] Time 0.279 (0.360) Data 0.000 (0.067) Loss 0.8226 (0.8714) Prec@1 75.000 (74.344) Prec@5 94.141 (92.699)
[2021-04-28 22:13:36 train_lshot.py:257] INFO Epoch: [28][90/150] Time 0.279 (0.351) Data 0.000 (0.060) Loss 0.9273 (0.8731) Prec@1 74.609 (74.275) Prec@5 91.797 (92.664)
[2021-04-28 22:13:39 train_lshot.py:257] INFO Epoch: [28][100/150] Time 0.298 (0.345) Data 0.001 (0.054) Loss 1.0160 (0.8743) Prec@1 69.922 (74.261) Prec@5 89.062 (92.621)
[2021-04-28 22:13:43 train_lshot.py:257] INFO Epoch: [28][110/150] Time 0.492 (0.348) Data 0.000 (0.049) Loss 0.8145 (0.8747) Prec@1 75.000 (74.247) Prec@5 93.750 (92.575)
[2021-04-28 22:13:46 train_lshot.py:257] INFO Epoch: [28][120/150] Time 0.284 (0.345) Data 0.000 (0.045) Loss 0.8890 (0.8752) Prec@1 75.781 (74.206) Prec@5 91.406 (92.562)
[2021-04-28 22:13:49 train_lshot.py:257] INFO Epoch: [28][130/150] Time 0.278 (0.340) Data 0.000 (0.042) Loss 0.8636 (0.8770) Prec@1 77.344 (74.219) Prec@5 91.797 (92.524)
[2021-04-28 22:13:51 train_lshot.py:257] INFO Epoch: [28][140/150] Time 0.298 (0.335) Data 0.000 (0.039) Loss 0.9028 (0.8776) Prec@1 69.141 (74.180) Prec@5 94.141 (92.542)
[2021-04-28 22:14:01 train_lshot.py:257] INFO Epoch: [29][0/150] Time 6.575 (6.575) Data 6.175 (6.175) Loss 0.8421 (0.8421) Prec@1 74.609 (74.609) Prec@5 92.578 (92.578)
[2021-04-28 22:14:05 train_lshot.py:257] INFO Epoch: [29][10/150] Time 0.293 (0.920) Data 0.000 (0.562) Loss 0.8058 (0.8310) Prec@1 75.000 (75.639) Prec@5 93.750 (92.933)
[2021-04-28 22:14:08 train_lshot.py:257] INFO Epoch: [29][20/150] Time 0.279 (0.616) Data 0.000 (0.295) Loss 0.7943 (0.8399) Prec@1 78.125 (75.558) Prec@5 92.578 (92.690)
[2021-04-28 22:14:11 train_lshot.py:257] INFO Epoch: [29][30/150] Time 0.281 (0.514) Data 0.004 (0.200) Loss 0.8136 (0.8321) Prec@1 77.734 (75.781) Prec@5 93.750 (92.981)
[2021-04-28 22:14:13 train_lshot.py:257] INFO Epoch: [29][40/150] Time 0.291 (0.458) Data 0.001 (0.151) Loss 0.8952 (0.8368) Prec@1 72.656 (75.457) Prec@5 89.844 (92.902)
[2021-04-28 22:14:16 train_lshot.py:257] INFO Epoch: [29][50/150] Time 0.291 (0.423) Data 0.000 (0.122) Loss 0.8977 (0.8358) Prec@1 71.484 (75.452) Prec@5 93.359 (92.984)
[2021-04-28 22:14:19 train_lshot.py:257] INFO Epoch: [29][60/150] Time 0.285 (0.401) Data 0.000 (0.102) Loss 0.8283 (0.8367) Prec@1 76.562 (75.429) Prec@5 93.750 (93.097)
[2021-04-28 22:14:22 train_lshot.py:257] INFO Epoch: [29][70/150] Time 0.297 (0.384) Data 0.001 (0.088) Loss 0.8339 (0.8407) Prec@1 74.219 (75.259) Prec@5 94.531 (93.139)
[2021-04-28 22:14:25 train_lshot.py:257] INFO Epoch: [29][80/150] Time 0.286 (0.372) Data 0.000 (0.077) Loss 0.7512 (0.8401) Prec@1 78.125 (75.313) Prec@5 93.750 (93.162)
[2021-04-28 22:14:28 train_lshot.py:257] INFO Epoch: [29][90/150] Time 0.281 (0.362) Data 0.000 (0.068) Loss 0.7995 (0.8403) Prec@1 78.516 (75.215) Prec@5 94.141 (93.231)
[2021-04-28 22:14:31 train_lshot.py:257] INFO Epoch: [29][100/150] Time 0.351 (0.359) Data 0.000 (0.062) Loss 0.7721 (0.8464) Prec@1 77.734 (75.035) Prec@5 94.141 (93.147)
[2021-04-28 22:14:34 train_lshot.py:257] INFO Epoch: [29][110/150] Time 0.281 (0.354) Data 0.000 (0.056) Loss 0.8945 (0.8487) Prec@1 72.656 (74.993) Prec@5 94.141 (93.050)
[2021-04-28 22:14:37 train_lshot.py:257] INFO Epoch: [29][120/150] Time 0.281 (0.348) Data 0.000 (0.051) Loss 0.8947 (0.8522) Prec@1 72.656 (74.813) Prec@5 92.188 (92.978)
[2021-04-28 22:14:40 train_lshot.py:257] INFO Epoch: [29][130/150] Time 0.294 (0.343) Data 0.000 (0.048) Loss 0.8821 (0.8547) Prec@1 74.609 (74.738) Prec@5 90.625 (92.894)
[2021-04-28 22:14:42 train_lshot.py:257] INFO Epoch: [29][140/150] Time 0.292 (0.339) Data 0.000 (0.044) Loss 0.8584 (0.8552) Prec@1 73.828 (74.698) Prec@5 94.141 (92.891)
[2021-04-28 22:14:50 train_lshot.py:257] INFO Epoch: [30][0/150] Time 5.036 (5.036) Data 4.618 (4.618) Loss 0.6570 (0.6570) Prec@1 78.906 (78.906) Prec@5 96.094 (96.094)
[2021-04-28 22:14:55 train_lshot.py:257] INFO Epoch: [30][10/150] Time 0.357 (0.872) Data 0.001 (0.478) Loss 0.9023 (0.7988) Prec@1 71.484 (77.379) Prec@5 91.797 (93.892)
[2021-04-28 22:14:58 train_lshot.py:257] INFO Epoch: [30][20/150] Time 0.276 (0.592) Data 0.000 (0.251) Loss 0.8812 (0.8062) Prec@1 73.438 (77.418) Prec@5 93.750 (93.750)
[2021-04-28 22:15:01 train_lshot.py:257] INFO Epoch: [30][30/150] Time 0.274 (0.494) Data 0.000 (0.170) Loss 0.7644 (0.8123) Prec@1 76.562 (76.966) Prec@5 95.312 (93.435)
[2021-04-28 22:15:04 train_lshot.py:257] INFO Epoch: [30][40/150] Time 0.280 (0.443) Data 0.000 (0.129) Loss 0.7781 (0.8169) Prec@1 75.781 (76.658) Prec@5 94.141 (93.207)
[2021-04-28 22:15:06 train_lshot.py:257] INFO Epoch: [30][50/150] Time 0.280 (0.411) Data 0.000 (0.104) Loss 0.7627 (0.8166) Prec@1 77.344 (76.478) Prec@5 94.141 (93.336)
[2021-04-28 22:15:09 train_lshot.py:257] INFO Epoch: [30][60/150] Time 0.277 (0.390) Data 0.000 (0.087) Loss 0.7522 (0.8161) Prec@1 80.859 (76.422) Prec@5 93.359 (93.366)
[2021-04-28 22:15:12 train_lshot.py:257] INFO Epoch: [30][70/150] Time 0.276 (0.375) Data 0.001 (0.075) Loss 0.9379 (0.8292) Prec@1 69.141 (75.825) Prec@5 91.016 (93.128)
[2021-04-28 22:15:15 train_lshot.py:257] INFO Epoch: [30][80/150] Time 0.282 (0.364) Data 0.000 (0.065) Loss 0.8631 (0.8322) Prec@1 74.219 (75.646) Prec@5 92.969 (93.152)
[2021-04-28 22:15:18 train_lshot.py:257] INFO Epoch: [30][90/150] Time 0.288 (0.356) Data 0.000 (0.058) Loss 0.9980 (0.8374) Prec@1 66.797 (75.425) Prec@5 90.625 (93.102)
[2021-04-28 22:15:21 train_lshot.py:257] INFO Epoch: [30][100/150] Time 0.302 (0.352) Data 0.000 (0.052) Loss 0.9572 (0.8400) Prec@1 71.094 (75.367) Prec@5 92.188 (93.046)
[2021-04-28 22:15:24 train_lshot.py:257] INFO Epoch: [30][110/150] Time 0.285 (0.346) Data 0.000 (0.048) Loss 0.9252 (0.8393) Prec@1 69.922 (75.355) Prec@5 93.750 (93.071)
[2021-04-28 22:15:27 train_lshot.py:257] INFO Epoch: [30][120/150] Time 0.297 (0.342) Data 0.001 (0.044) Loss 0.8105 (0.8421) Prec@1 76.562 (75.239) Prec@5 91.016 (92.914)
[2021-04-28 22:15:30 train_lshot.py:257] INFO Epoch: [30][130/150] Time 0.279 (0.337) Data 0.000 (0.041) Loss 0.8872 (0.8451) Prec@1 72.266 (75.110) Prec@5 91.797 (92.846)
[2021-04-28 22:15:33 train_lshot.py:257] INFO Epoch: [30][140/150] Time 0.289 (0.335) Data 0.000 (0.038) Loss 0.8406 (0.8473) Prec@1 75.000 (75.061) Prec@5 94.531 (92.855)
[2021-04-28 22:15:42 train_lshot.py:257] INFO Epoch: [31][0/150] Time 6.330 (6.330) Data 5.864 (5.864) Loss 0.8167 (0.8167) Prec@1 77.344 (77.344) Prec@5 93.359 (93.359)
[2021-04-28 22:15:46 train_lshot.py:257] INFO Epoch: [31][10/150] Time 0.281 (0.973) Data 0.000 (0.623) Loss 0.7839 (0.8045) Prec@1 79.297 (76.953) Prec@5 94.141 (93.786)
[2021-04-28 22:15:49 train_lshot.py:257] INFO Epoch: [31][20/150] Time 0.274 (0.643) Data 0.000 (0.327) Loss 0.7928 (0.7923) Prec@1 78.125 (77.474) Prec@5 91.797 (93.955)
[2021-04-28 22:15:52 train_lshot.py:257] INFO Epoch: [31][30/150] Time 0.276 (0.528) Data 0.000 (0.222) Loss 0.8956 (0.8078) Prec@1 72.266 (76.777) Prec@5 90.234 (93.359)
[2021-04-28 22:15:55 train_lshot.py:257] INFO Epoch: [31][40/150] Time 0.277 (0.468) Data 0.001 (0.168) Loss 0.8786 (0.8069) Prec@1 70.703 (76.553) Prec@5 93.359 (93.483)
[2021-04-28 22:15:58 train_lshot.py:257] INFO Epoch: [31][50/150] Time 0.283 (0.431) Data 0.001 (0.135) Loss 0.7416 (0.8050) Prec@1 79.297 (76.562) Prec@5 93.359 (93.444)
[2021-04-28 22:16:01 train_lshot.py:257] INFO Epoch: [31][60/150] Time 0.277 (0.406) Data 0.000 (0.113) Loss 0.8648 (0.8089) Prec@1 75.000 (76.422) Prec@5 92.188 (93.327)
[2021-04-28 22:16:03 train_lshot.py:257] INFO Epoch: [31][70/150] Time 0.281 (0.389) Data 0.001 (0.097) Loss 0.8442 (0.8134) Prec@1 73.828 (76.265) Prec@5 93.750 (93.233)
[2021-04-28 22:16:07 train_lshot.py:257] INFO Epoch: [31][80/150] Time 0.322 (0.381) Data 0.000 (0.085) Loss 0.7862 (0.8167) Prec@1 75.391 (76.119) Prec@5 95.312 (93.263)
[2021-04-28 22:16:10 train_lshot.py:257] INFO Epoch: [31][90/150] Time 0.281 (0.371) Data 0.000 (0.076) Loss 0.7990 (0.8171) Prec@1 77.734 (76.099) Prec@5 92.969 (93.274)
[2021-04-28 22:16:12 train_lshot.py:257] INFO Epoch: [31][100/150] Time 0.279 (0.362) Data 0.000 (0.068) Loss 0.7268 (0.8180) Prec@1 81.641 (76.176) Prec@5 94.922 (93.247)
[2021-04-28 22:16:16 train_lshot.py:257] INFO Epoch: [31][110/150] Time 0.294 (0.367) Data 0.000 (0.062) Loss 0.9560 (0.8215) Prec@1 72.266 (76.080) Prec@5 90.234 (93.201)
[2021-04-28 22:16:19 train_lshot.py:257] INFO Epoch: [31][120/150] Time 0.284 (0.360) Data 0.000 (0.057) Loss 0.8677 (0.8211) Prec@1 71.875 (75.981) Prec@5 92.188 (93.182)
[2021-04-28 22:16:22 train_lshot.py:257] INFO Epoch: [31][130/150] Time 0.278 (0.353) Data 0.000 (0.053) Loss 0.8825 (0.8227) Prec@1 73.438 (75.909) Prec@5 92.188 (93.210)
[2021-04-28 22:16:26 train_lshot.py:257] INFO Epoch: [31][140/150] Time 0.680 (0.357) Data 0.000 (0.049) Loss 0.8245 (0.8226) Prec@1 75.781 (75.931) Prec@5 91.406 (93.215)
[2021-04-28 22:16:57 train_lshot.py:119] INFO Meta Val 31: 0.597706680893898
[2021-04-28 22:17:04 train_lshot.py:257] INFO Epoch: [32][0/150] Time 6.478 (6.478) Data 6.094 (6.094) Loss 0.7299 (0.7299) Prec@1 78.906 (78.906) Prec@5 94.922 (94.922)
[2021-04-28 22:17:08 train_lshot.py:257] INFO Epoch: [32][10/150] Time 0.293 (0.903) Data 0.000 (0.562) Loss 0.8181 (0.7961) Prec@1 75.781 (77.202) Prec@5 92.969 (93.786)
[2021-04-28 22:17:10 train_lshot.py:257] INFO Epoch: [32][20/150] Time 0.280 (0.608) Data 0.000 (0.294) Loss 0.7823 (0.7913) Prec@1 71.875 (77.065) Prec@5 95.312 (93.862)
[2021-04-28 22:17:13 train_lshot.py:257] INFO Epoch: [32][30/150] Time 0.284 (0.502) Data 0.000 (0.200) Loss 0.8965 (0.7921) Prec@1 76.953 (77.155) Prec@5 92.188 (93.826)
[2021-04-28 22:17:16 train_lshot.py:257] INFO Epoch: [32][40/150] Time 0.279 (0.449) Data 0.001 (0.151) Loss 0.7438 (0.7898) Prec@1 78.906 (77.258) Prec@5 95.703 (93.798)
[2021-04-28 22:17:19 train_lshot.py:257] INFO Epoch: [32][50/150] Time 0.277 (0.416) Data 0.000 (0.122) Loss 0.8422 (0.7853) Prec@1 76.172 (77.543) Prec@5 94.141 (93.765)
[2021-04-28 22:17:22 train_lshot.py:257] INFO Epoch: [32][60/150] Time 0.279 (0.394) Data 0.002 (0.102) Loss 0.8176 (0.7855) Prec@1 75.781 (77.459) Prec@5 93.750 (93.788)
[2021-04-28 22:17:25 train_lshot.py:257] INFO Epoch: [32][70/150] Time 0.280 (0.378) Data 0.001 (0.087) Loss 0.9214 (0.7916) Prec@1 73.438 (77.179) Prec@5 91.406 (93.756)
[2021-04-28 22:17:27 train_lshot.py:257] INFO Epoch: [32][80/150] Time 0.281 (0.366) Data 0.000 (0.077) Loss 0.9670 (0.7976) Prec@1 75.781 (77.045) Prec@5 89.453 (93.673)
[2021-04-28 22:17:30 train_lshot.py:257] INFO Epoch: [32][90/150] Time 0.281 (0.356) Data 0.000 (0.068) Loss 0.8054 (0.7983) Prec@1 75.781 (76.996) Prec@5 93.359 (93.673)
[2021-04-28 22:17:33 train_lshot.py:257] INFO Epoch: [32][100/150] Time 0.282 (0.354) Data 0.000 (0.062) Loss 0.7273 (0.7991) Prec@1 78.906 (76.942) Prec@5 96.875 (93.704)
[2021-04-28 22:17:36 train_lshot.py:257] INFO Epoch: [32][110/150] Time 0.284 (0.347) Data 0.000 (0.056) Loss 0.7298 (0.8013) Prec@1 78.516 (76.841) Prec@5 96.094 (93.666)
[2021-04-28 22:17:39 train_lshot.py:257] INFO Epoch: [32][120/150] Time 0.276 (0.342) Data 0.000 (0.051) Loss 0.7658 (0.8034) Prec@1 78.125 (76.743) Prec@5 94.531 (93.595)
[2021-04-28 22:17:42 train_lshot.py:257] INFO Epoch: [32][130/150] Time 0.495 (0.342) Data 0.000 (0.048) Loss 0.7657 (0.8060) Prec@1 80.859 (76.664) Prec@5 96.094 (93.577)
[2021-04-28 22:17:46 train_lshot.py:257] INFO Epoch: [32][140/150] Time 0.283 (0.340) Data 0.000 (0.044) Loss 0.8507 (0.8073) Prec@1 73.828 (76.549) Prec@5 94.141 (93.617)
[2021-04-28 22:17:53 train_lshot.py:257] INFO Epoch: [33][0/150] Time 4.367 (4.367) Data 3.977 (3.977) Loss 0.8160 (0.8160) Prec@1 76.953 (76.953) Prec@5 91.797 (91.797)
[2021-04-28 22:17:57 train_lshot.py:257] INFO Epoch: [33][10/150] Time 0.361 (0.773) Data 0.000 (0.362) Loss 0.7960 (0.7788) Prec@1 76.953 (77.592) Prec@5 94.141 (94.176)
[2021-04-28 22:18:00 train_lshot.py:257] INFO Epoch: [33][20/150] Time 0.296 (0.558) Data 0.001 (0.190) Loss 0.7568 (0.7855) Prec@1 77.344 (77.344) Prec@5 95.703 (93.955)
[2021-04-28 22:18:03 train_lshot.py:257] INFO Epoch: [33][30/150] Time 0.297 (0.474) Data 0.000 (0.129) Loss 0.7338 (0.7755) Prec@1 79.688 (77.974) Prec@5 94.531 (94.153)
[2021-04-28 22:18:06 train_lshot.py:257] INFO Epoch: [33][40/150] Time 0.282 (0.427) Data 0.000 (0.098) Loss 0.6939 (0.7715) Prec@1 81.250 (77.877) Prec@5 95.703 (94.379)
[2021-04-28 22:18:09 train_lshot.py:257] INFO Epoch: [33][50/150] Time 0.283 (0.399) Data 0.000 (0.079) Loss 0.8003 (0.7762) Prec@1 76.953 (77.650) Prec@5 94.141 (94.179)
[2021-04-28 22:18:12 train_lshot.py:257] INFO Epoch: [33][60/150] Time 0.282 (0.380) Data 0.000 (0.066) Loss 0.9630 (0.7847) Prec@1 70.703 (77.357) Prec@5 89.844 (93.910)
[2021-04-28 22:18:15 train_lshot.py:257] INFO Epoch: [33][70/150] Time 0.280 (0.367) Data 0.001 (0.057) Loss 0.7687 (0.7896) Prec@1 75.000 (77.085) Prec@5 94.531 (93.849)
[2021-04-28 22:18:18 train_lshot.py:257] INFO Epoch: [33][80/150] Time 0.280 (0.357) Data 0.000 (0.050) Loss 0.8731 (0.7913) Prec@1 74.609 (77.045) Prec@5 94.141 (93.793)
[2021-04-28 22:18:21 train_lshot.py:257] INFO Epoch: [33][90/150] Time 0.289 (0.356) Data 0.000 (0.044) Loss 0.7605 (0.7939) Prec@1 74.219 (76.906) Prec@5 94.141 (93.729)
[2021-04-28 22:18:24 train_lshot.py:257] INFO Epoch: [33][100/150] Time 0.285 (0.348) Data 0.000 (0.040) Loss 0.8702 (0.7963) Prec@1 76.172 (76.860) Prec@5 91.797 (93.673)
[2021-04-28 22:18:27 train_lshot.py:257] INFO Epoch: [33][110/150] Time 0.277 (0.342) Data 0.000 (0.036) Loss 0.8622 (0.7988) Prec@1 74.609 (76.833) Prec@5 92.188 (93.616)
[2021-04-28 22:18:30 train_lshot.py:257] INFO Epoch: [33][120/150] Time 0.285 (0.338) Data 0.000 (0.033) Loss 0.7613 (0.7983) Prec@1 80.078 (76.905) Prec@5 93.359 (93.634)
[2021-04-28 22:18:32 train_lshot.py:257] INFO Epoch: [33][130/150] Time 0.286 (0.334) Data 0.001 (0.031) Loss 0.7374 (0.7988) Prec@1 80.078 (76.935) Prec@5 96.875 (93.634)
[2021-04-28 22:18:35 train_lshot.py:257] INFO Epoch: [33][140/150] Time 0.279 (0.331) Data 0.000 (0.029) Loss 0.8230 (0.8006) Prec@1 76.172 (76.884) Prec@5 92.578 (93.592)
[2021-04-28 22:18:45 train_lshot.py:257] INFO Epoch: [34][0/150] Time 6.980 (6.980) Data 6.572 (6.572) Loss 0.6144 (0.6144) Prec@1 82.812 (82.812) Prec@5 96.875 (96.875)
[2021-04-28 22:18:49 train_lshot.py:257] INFO Epoch: [34][10/150] Time 0.291 (0.921) Data 0.000 (0.598) Loss 0.7969 (0.7584) Prec@1 72.266 (76.918) Prec@5 95.312 (94.531)
[2021-04-28 22:18:51 train_lshot.py:257] INFO Epoch: [34][20/150] Time 0.286 (0.620) Data 0.000 (0.314) Loss 0.7615 (0.7705) Prec@1 78.125 (77.065) Prec@5 94.531 (94.159)
[2021-04-28 22:18:54 train_lshot.py:257] INFO Epoch: [34][30/150] Time 0.279 (0.510) Data 0.000 (0.213) Loss 0.6897 (0.7740) Prec@1 81.250 (77.092) Prec@5 96.875 (94.090)
[2021-04-28 22:18:57 train_lshot.py:257] INFO Epoch: [34][40/150] Time 0.280 (0.455) Data 0.001 (0.161) Loss 0.7716 (0.7847) Prec@1 78.516 (76.991) Prec@5 93.359 (93.845)
[2021-04-28 22:19:00 train_lshot.py:257] INFO Epoch: [34][50/150] Time 0.276 (0.421) Data 0.000 (0.129) Loss 0.7296 (0.7830) Prec@1 76.562 (77.091) Prec@5 95.703 (93.903)
[2021-04-28 22:19:03 train_lshot.py:257] INFO Epoch: [34][60/150] Time 0.276 (0.397) Data 0.000 (0.108) Loss 0.7067 (0.7829) Prec@1 80.469 (77.248) Prec@5 94.531 (93.769)
[2021-04-28 22:19:05 train_lshot.py:257] INFO Epoch: [34][70/150] Time 0.278 (0.381) Data 0.001 (0.093) Loss 0.7012 (0.7778) Prec@1 79.688 (77.404) Prec@5 94.531 (93.866)
[2021-04-28 22:19:08 train_lshot.py:257] INFO Epoch: [34][80/150] Time 0.285 (0.369) Data 0.000 (0.082) Loss 0.6710 (0.7786) Prec@1 81.250 (77.334) Prec@5 93.750 (93.832)
[2021-04-28 22:19:12 train_lshot.py:257] INFO Epoch: [34][90/150] Time 0.389 (0.365) Data 0.000 (0.073) Loss 0.7139 (0.7806) Prec@1 82.031 (77.301) Prec@5 95.312 (93.857)
[2021-04-28 22:19:15 train_lshot.py:257] INFO Epoch: [34][100/150] Time 0.277 (0.358) Data 0.000 (0.065) Loss 0.8106 (0.7804) Prec@1 75.000 (77.328) Prec@5 93.750 (93.851)
[2021-04-28 22:19:17 train_lshot.py:257] INFO Epoch: [34][110/150] Time 0.277 (0.351) Data 0.000 (0.060) Loss 0.8376 (0.7835) Prec@1 72.266 (77.273) Prec@5 93.750 (93.796)
[2021-04-28 22:19:20 train_lshot.py:257] INFO Epoch: [34][120/150] Time 0.283 (0.346) Data 0.000 (0.055) Loss 0.7933 (0.7853) Prec@1 78.906 (77.266) Prec@5 92.969 (93.718)
[2021-04-28 22:19:23 train_lshot.py:257] INFO Epoch: [34][130/150] Time 0.281 (0.341) Data 0.000 (0.051) Loss 0.8892 (0.7869) Prec@1 76.953 (77.293) Prec@5 89.844 (93.693)
[2021-04-28 22:19:26 train_lshot.py:257] INFO Epoch: [34][140/150] Time 0.282 (0.337) Data 0.000 (0.047) Loss 0.8071 (0.7876) Prec@1 76.953 (77.208) Prec@5 92.578 (93.678)
[2021-04-28 22:19:34 train_lshot.py:257] INFO Epoch: [35][0/150] Time 5.529 (5.529) Data 5.114 (5.114) Loss 0.7340 (0.7340) Prec@1 78.125 (78.125) Prec@5 94.141 (94.141)
[2021-04-28 22:19:39 train_lshot.py:257] INFO Epoch: [35][10/150] Time 0.299 (0.887) Data 0.001 (0.527) Loss 0.7848 (0.7660) Prec@1 79.297 (78.196) Prec@5 93.750 (93.892)
[2021-04-28 22:19:42 train_lshot.py:257] INFO Epoch: [35][20/150] Time 0.274 (0.599) Data 0.000 (0.276) Loss 0.7735 (0.7445) Prec@1 78.516 (78.981) Prec@5 94.922 (94.289)
[2021-04-28 22:19:44 train_lshot.py:257] INFO Epoch: [35][30/150] Time 0.285 (0.499) Data 0.000 (0.187) Loss 0.8382 (0.7564) Prec@1 77.734 (78.755) Prec@5 91.016 (93.964)
[2021-04-28 22:19:47 train_lshot.py:257] INFO Epoch: [35][40/150] Time 0.280 (0.446) Data 0.000 (0.142) Loss 0.7460 (0.7594) Prec@1 79.297 (78.506) Prec@5 94.141 (94.103)
[2021-04-28 22:19:50 train_lshot.py:257] INFO Epoch: [35][50/150] Time 0.285 (0.414) Data 0.001 (0.114) Loss 0.7157 (0.7562) Prec@1 80.859 (78.562) Prec@5 95.703 (94.141)
[2021-04-28 22:19:53 train_lshot.py:257] INFO Epoch: [35][60/150] Time 0.282 (0.392) Data 0.000 (0.095) Loss 0.8880 (0.7604) Prec@1 75.391 (78.458) Prec@5 91.406 (94.173)
[2021-04-28 22:19:57 train_lshot.py:257] INFO Epoch: [35][70/150] Time 0.292 (0.392) Data 0.001 (0.082) Loss 0.7571 (0.7612) Prec@1 78.906 (78.296) Prec@5 92.969 (94.141)
[2021-04-28 22:20:00 train_lshot.py:257] INFO Epoch: [35][80/150] Time 0.283 (0.378) Data 0.000 (0.072) Loss 0.8175 (0.7647) Prec@1 78.125 (78.019) Prec@5 93.750 (94.150)
[2021-04-28 22:20:02 train_lshot.py:257] INFO Epoch: [35][90/150] Time 0.280 (0.368) Data 0.000 (0.064) Loss 0.7256 (0.7698) Prec@1 77.734 (77.850) Prec@5 95.312 (94.085)
[2021-04-28 22:20:05 train_lshot.py:257] INFO Epoch: [35][100/150] Time 0.295 (0.359) Data 0.000 (0.058) Loss 0.7919 (0.7712) Prec@1 77.344 (77.858) Prec@5 93.750 (94.071)
[2021-04-28 22:20:09 train_lshot.py:257] INFO Epoch: [35][110/150] Time 1.031 (0.359) Data 0.000 (0.053) Loss 0.8204 (0.7717) Prec@1 76.172 (77.717) Prec@5 93.750 (94.105)
[2021-04-28 22:20:12 train_lshot.py:257] INFO Epoch: [35][120/150] Time 0.286 (0.358) Data 0.000 (0.048) Loss 0.8642 (0.7743) Prec@1 76.172 (77.657) Prec@5 94.141 (94.108)
[2021-04-28 22:20:15 train_lshot.py:257] INFO Epoch: [35][130/150] Time 0.281 (0.352) Data 0.000 (0.045) Loss 0.8563 (0.7765) Prec@1 73.438 (77.588) Prec@5 92.578 (94.081)
[2021-04-28 22:20:18 train_lshot.py:257] INFO Epoch: [35][140/150] Time 0.280 (0.347) Data 0.000 (0.041) Loss 0.6825 (0.7752) Prec@1 80.469 (77.629) Prec@5 95.703 (94.107)
[2021-04-28 22:20:49 train_lshot.py:119] INFO Meta Val 35: 0.583040011703968
[2021-04-28 22:20:57 train_lshot.py:257] INFO Epoch: [36][0/150] Time 7.936 (7.936) Data 7.564 (7.564) Loss 0.7414 (0.7414) Prec@1 80.469 (80.469) Prec@5 92.578 (92.578)
[2021-04-28 22:21:00 train_lshot.py:257] INFO Epoch: [36][10/150] Time 0.292 (0.987) Data 0.000 (0.689) Loss 0.7230 (0.7259) Prec@1 80.469 (80.007) Prec@5 94.922 (94.496)
[2021-04-28 22:21:03 train_lshot.py:257] INFO Epoch: [36][20/150] Time 0.275 (0.650) Data 0.000 (0.361) Loss 0.7477 (0.7361) Prec@1 79.297 (79.334) Prec@5 93.359 (94.196)
[2021-04-28 22:21:06 train_lshot.py:257] INFO Epoch: [36][30/150] Time 0.274 (0.529) Data 0.000 (0.245) Loss 0.7218 (0.7432) Prec@1 79.688 (78.969) Prec@5 94.141 (94.216)
[2021-04-28 22:21:08 train_lshot.py:257] INFO Epoch: [36][40/150] Time 0.276 (0.470) Data 0.000 (0.185) Loss 0.7688 (0.7500) Prec@1 78.906 (78.706) Prec@5 94.531 (94.131)
[2021-04-28 22:21:11 train_lshot.py:257] INFO Epoch: [36][50/150] Time 0.282 (0.433) Data 0.000 (0.149) Loss 0.7504 (0.7539) Prec@1 78.906 (78.493) Prec@5 94.531 (94.095)
[2021-04-28 22:21:14 train_lshot.py:257] INFO Epoch: [36][60/150] Time 0.279 (0.408) Data 0.000 (0.125) Loss 0.7440 (0.7519) Prec@1 78.906 (78.522) Prec@5 93.750 (94.121)
[2021-04-28 22:21:17 train_lshot.py:257] INFO Epoch: [36][70/150] Time 0.281 (0.390) Data 0.001 (0.107) Loss 0.6744 (0.7510) Prec@1 83.203 (78.708) Prec@5 95.312 (94.157)
[2021-04-28 22:21:20 train_lshot.py:257] INFO Epoch: [36][80/150] Time 0.289 (0.377) Data 0.000 (0.094) Loss 0.7921 (0.7523) Prec@1 77.734 (78.704) Prec@5 94.141 (94.131)
[2021-04-28 22:21:22 train_lshot.py:257] INFO Epoch: [36][90/150] Time 0.277 (0.366) Data 0.000 (0.084) Loss 0.7547 (0.7565) Prec@1 78.906 (78.443) Prec@5 94.141 (94.055)
[2021-04-28 22:21:25 train_lshot.py:257] INFO Epoch: [36][100/150] Time 0.279 (0.357) Data 0.000 (0.075) Loss 0.8887 (0.7625) Prec@1 71.875 (78.191) Prec@5 92.578 (93.959)
[2021-04-28 22:21:28 train_lshot.py:257] INFO Epoch: [36][110/150] Time 0.276 (0.350) Data 0.000 (0.069) Loss 0.7234 (0.7615) Prec@1 82.031 (78.213) Prec@5 94.531 (94.007)
[2021-04-28 22:21:31 train_lshot.py:257] INFO Epoch: [36][120/150] Time 0.276 (0.345) Data 0.000 (0.063) Loss 0.7955 (0.7637) Prec@1 75.391 (78.138) Prec@5 92.578 (93.976)
[2021-04-28 22:21:34 train_lshot.py:257] INFO Epoch: [36][130/150] Time 0.287 (0.340) Data 0.000 (0.058) Loss 0.7169 (0.7629) Prec@1 78.906 (78.167) Prec@5 94.531 (94.009)
[2021-04-28 22:21:37 train_lshot.py:257] INFO Epoch: [36][140/150] Time 0.300 (0.337) Data 0.000 (0.054) Loss 0.7897 (0.7642) Prec@1 76.953 (78.103) Prec@5 93.359 (93.999)
[2021-04-28 22:21:46 train_lshot.py:257] INFO Epoch: [37][0/150] Time 6.765 (6.765) Data 6.369 (6.369) Loss 0.6440 (0.6440) Prec@1 81.250 (81.250) Prec@5 97.266 (97.266)
[2021-04-28 22:21:50 train_lshot.py:257] INFO Epoch: [37][10/150] Time 0.288 (0.938) Data 0.000 (0.583) Loss 0.7485 (0.6995) Prec@1 77.734 (80.895) Prec@5 94.531 (94.389)
[2021-04-28 22:21:53 train_lshot.py:257] INFO Epoch: [37][20/150] Time 0.280 (0.628) Data 0.000 (0.306) Loss 0.6759 (0.7052) Prec@1 81.250 (80.301) Prec@5 97.266 (94.475)
[2021-04-28 22:21:56 train_lshot.py:257] INFO Epoch: [37][30/150] Time 0.284 (0.518) Data 0.000 (0.207) Loss 0.8029 (0.7049) Prec@1 76.562 (80.141) Prec@5 92.578 (94.632)
[2021-04-28 22:21:59 train_lshot.py:257] INFO Epoch: [37][40/150] Time 0.283 (0.461) Data 0.001 (0.157) Loss 0.7654 (0.7114) Prec@1 76.562 (79.792) Prec@5 94.922 (94.712)
[2021-04-28 22:22:01 train_lshot.py:257] INFO Epoch: [37][50/150] Time 0.278 (0.426) Data 0.000 (0.126) Loss 0.7303 (0.7150) Prec@1 80.859 (79.779) Prec@5 94.922 (94.677)
[2021-04-28 22:22:04 train_lshot.py:257] INFO Epoch: [37][60/150] Time 0.288 (0.402) Data 0.000 (0.105) Loss 0.8232 (0.7194) Prec@1 77.344 (79.547) Prec@5 92.578 (94.614)
[2021-04-28 22:22:07 train_lshot.py:257] INFO Epoch: [37][70/150] Time 0.288 (0.386) Data 0.001 (0.091) Loss 0.6733 (0.7260) Prec@1 83.984 (79.434) Prec@5 96.875 (94.537)
[2021-04-28 22:22:10 train_lshot.py:257] INFO Epoch: [37][80/150] Time 0.276 (0.373) Data 0.000 (0.079) Loss 0.8401 (0.7325) Prec@1 73.438 (79.234) Prec@5 94.141 (94.425)
[2021-04-28 22:22:13 train_lshot.py:257] INFO Epoch: [37][90/150] Time 0.286 (0.363) Data 0.000 (0.071) Loss 0.7406 (0.7329) Prec@1 78.906 (79.172) Prec@5 93.750 (94.437)
[2021-04-28 22:22:16 train_lshot.py:257] INFO Epoch: [37][100/150] Time 0.288 (0.355) Data 0.000 (0.064) Loss 0.7965 (0.7356) Prec@1 75.391 (79.076) Prec@5 93.359 (94.392)
[2021-04-28 22:22:18 train_lshot.py:257] INFO Epoch: [37][110/150] Time 0.287 (0.349) Data 0.000 (0.058) Loss 0.6534 (0.7338) Prec@1 82.422 (79.121) Prec@5 96.094 (94.443)
[2021-04-28 22:22:21 train_lshot.py:257] INFO Epoch: [37][120/150] Time 0.284 (0.344) Data 0.000 (0.053) Loss 0.7894 (0.7361) Prec@1 75.000 (79.016) Prec@5 96.094 (94.399)
[2021-04-28 22:22:25 train_lshot.py:257] INFO Epoch: [37][130/150] Time 0.300 (0.345) Data 0.000 (0.049) Loss 0.7667 (0.7391) Prec@1 79.688 (78.972) Prec@5 91.797 (94.355)
[2021-04-28 22:22:28 train_lshot.py:257] INFO Epoch: [37][140/150] Time 0.288 (0.340) Data 0.000 (0.046) Loss 0.8150 (0.7413) Prec@1 78.906 (78.903) Prec@5 93.750 (94.321)
[2021-04-28 22:22:37 train_lshot.py:257] INFO Epoch: [38][0/150] Time 5.948 (5.948) Data 5.505 (5.505) Loss 0.7469 (0.7469) Prec@1 78.906 (78.906) Prec@5 92.969 (92.969)
[2021-04-28 22:22:40 train_lshot.py:257] INFO Epoch: [38][10/150] Time 0.306 (0.884) Data 0.001 (0.504) Loss 0.6942 (0.7264) Prec@1 80.469 (79.332) Prec@5 97.266 (94.247)
[2021-04-28 22:22:43 train_lshot.py:257] INFO Epoch: [38][20/150] Time 0.276 (0.598) Data 0.000 (0.264) Loss 0.6772 (0.6946) Prec@1 82.031 (80.394) Prec@5 96.875 (95.164)
[2021-04-28 22:22:46 train_lshot.py:257] INFO Epoch: [38][30/150] Time 0.284 (0.498) Data 0.000 (0.179) Loss 0.7152 (0.6869) Prec@1 78.906 (80.670) Prec@5 94.531 (95.300)
[2021-04-28 22:22:49 train_lshot.py:257] INFO Epoch: [38][40/150] Time 0.274 (0.445) Data 0.000 (0.135) Loss 0.6301 (0.6979) Prec@1 82.812 (80.269) Prec@5 97.266 (95.208)
[2021-04-28 22:22:52 train_lshot.py:257] INFO Epoch: [38][50/150] Time 0.284 (0.412) Data 0.000 (0.109) Loss 0.6990 (0.7040) Prec@1 80.859 (80.193) Prec@5 93.750 (94.945)
[2021-04-28 22:22:55 train_lshot.py:257] INFO Epoch: [38][60/150] Time 0.276 (0.391) Data 0.000 (0.091) Loss 0.7495 (0.7127) Prec@1 76.953 (79.809) Prec@5 94.922 (94.883)
[2021-04-28 22:22:57 train_lshot.py:257] INFO Epoch: [38][70/150] Time 0.280 (0.376) Data 0.001 (0.078) Loss 0.6193 (0.7094) Prec@1 83.203 (79.985) Prec@5 96.875 (94.900)
[2021-04-28 22:23:01 train_lshot.py:257] INFO Epoch: [38][80/150] Time 0.285 (0.375) Data 0.000 (0.069) Loss 0.7669 (0.7124) Prec@1 77.734 (79.948) Prec@5 93.359 (94.878)
[2021-04-28 22:23:04 train_lshot.py:257] INFO Epoch: [38][90/150] Time 0.275 (0.365) Data 0.000 (0.061) Loss 0.8851 (0.7168) Prec@1 76.562 (79.829) Prec@5 89.453 (94.780)
[2021-04-28 22:23:07 train_lshot.py:257] INFO Epoch: [38][100/150] Time 0.273 (0.356) Data 0.000 (0.055) Loss 0.6831 (0.7194) Prec@1 78.906 (79.629) Prec@5 94.922 (94.725)
[2021-04-28 22:23:10 train_lshot.py:257] INFO Epoch: [38][110/150] Time 0.290 (0.350) Data 0.000 (0.050) Loss 0.6269 (0.7197) Prec@1 82.031 (79.614) Prec@5 96.875 (94.721)
[2021-04-28 22:23:12 train_lshot.py:257] INFO Epoch: [38][120/150] Time 0.277 (0.344) Data 0.000 (0.046) Loss 0.8007 (0.7221) Prec@1 75.391 (79.587) Prec@5 92.188 (94.718)
[2021-04-28 22:23:15 train_lshot.py:257] INFO Epoch: [38][130/150] Time 0.275 (0.340) Data 0.000 (0.043) Loss 0.8006 (0.7249) Prec@1 76.562 (79.428) Prec@5 92.188 (94.659)
[2021-04-28 22:23:18 train_lshot.py:257] INFO Epoch: [38][140/150] Time 0.275 (0.336) Data 0.000 (0.040) Loss 0.7351 (0.7277) Prec@1 79.688 (79.358) Prec@5 94.531 (94.625)
[2021-04-28 22:23:27 train_lshot.py:257] INFO Epoch: [39][0/150] Time 6.258 (6.258) Data 5.831 (5.831) Loss 0.6947 (0.6947) Prec@1 80.859 (80.859) Prec@5 97.266 (97.266)
[2021-04-28 22:23:31 train_lshot.py:257] INFO Epoch: [39][10/150] Time 0.388 (0.915) Data 0.001 (0.531) Loss 0.7952 (0.7153) Prec@1 78.125 (80.504) Prec@5 94.141 (95.064)
[2021-04-28 22:23:34 train_lshot.py:257] INFO Epoch: [39][20/150] Time 0.279 (0.620) Data 0.000 (0.279) Loss 0.7476 (0.7144) Prec@1 77.344 (80.115) Prec@5 92.969 (95.331)
[2021-04-28 22:23:37 train_lshot.py:257] INFO Epoch: [39][30/150] Time 0.273 (0.510) Data 0.000 (0.189) Loss 0.7843 (0.7166) Prec@1 76.953 (79.788) Prec@5 93.750 (95.136)
[2021-04-28 22:23:40 train_lshot.py:257] INFO Epoch: [39][40/150] Time 0.283 (0.454) Data 0.000 (0.143) Loss 0.8114 (0.7162) Prec@1 75.391 (79.783) Prec@5 90.625 (95.008)
[2021-04-28 22:23:43 train_lshot.py:257] INFO Epoch: [39][50/150] Time 0.279 (0.420) Data 0.000 (0.115) Loss 0.6380 (0.7180) Prec@1 83.594 (79.833) Prec@5 94.922 (94.914)
[2021-04-28 22:23:45 train_lshot.py:257] INFO Epoch: [39][60/150] Time 0.281 (0.397) Data 0.000 (0.096) Loss 0.6344 (0.7230) Prec@1 84.766 (79.623) Prec@5 94.922 (94.877)
[2021-04-28 22:23:48 train_lshot.py:257] INFO Epoch: [39][70/150] Time 0.288 (0.381) Data 0.001 (0.083) Loss 0.6709 (0.7240) Prec@1 79.297 (79.539) Prec@5 97.266 (94.845)
[2021-04-28 22:23:51 train_lshot.py:257] INFO Epoch: [39][80/150] Time 0.276 (0.369) Data 0.000 (0.072) Loss 0.7697 (0.7235) Prec@1 77.734 (79.442) Prec@5 93.750 (94.811)
[2021-04-28 22:23:54 train_lshot.py:257] INFO Epoch: [39][90/150] Time 0.283 (0.359) Data 0.000 (0.065) Loss 0.6918 (0.7259) Prec@1 81.641 (79.344) Prec@5 94.922 (94.767)
[2021-04-28 22:23:57 train_lshot.py:257] INFO Epoch: [39][100/150] Time 0.287 (0.352) Data 0.000 (0.058) Loss 0.7136 (0.7285) Prec@1 77.344 (79.227) Prec@5 95.312 (94.694)
[2021-04-28 22:24:00 train_lshot.py:257] INFO Epoch: [39][110/150] Time 0.282 (0.346) Data 0.000 (0.053) Loss 0.7095 (0.7288) Prec@1 81.250 (79.307) Prec@5 96.484 (94.679)
[2021-04-28 22:24:02 train_lshot.py:257] INFO Epoch: [39][120/150] Time 0.287 (0.341) Data 0.000 (0.049) Loss 0.7563 (0.7291) Prec@1 76.953 (79.326) Prec@5 92.188 (94.635)
[2021-04-28 22:24:06 train_lshot.py:257] INFO Epoch: [39][130/150] Time 0.307 (0.345) Data 0.000 (0.045) Loss 0.6393 (0.7285) Prec@1 80.078 (79.333) Prec@5 96.094 (94.600)
[2021-04-28 22:24:09 train_lshot.py:257] INFO Epoch: [39][140/150] Time 0.274 (0.341) Data 0.000 (0.042) Loss 0.8293 (0.7276) Prec@1 75.781 (79.355) Prec@5 92.188 (94.620)
[2021-04-28 22:24:40 train_lshot.py:119] INFO Meta Val 39: 0.6086666813492775
[2021-04-28 22:24:46 train_lshot.py:257] INFO Epoch: [40][0/150] Time 5.525 (5.525) Data 5.186 (5.186) Loss 0.7138 (0.7138) Prec@1 76.953 (76.953) Prec@5 94.141 (94.141)
[2021-04-28 22:24:50 train_lshot.py:257] INFO Epoch: [40][10/150] Time 0.292 (0.881) Data 0.001 (0.584) Loss 0.8556 (0.7143) Prec@1 76.562 (79.084) Prec@5 91.797 (95.028)
[2021-04-28 22:24:53 train_lshot.py:257] INFO Epoch: [40][20/150] Time 0.283 (0.597) Data 0.000 (0.306) Loss 0.7715 (0.7064) Prec@1 78.125 (79.725) Prec@5 92.969 (94.903)
[2021-04-28 22:24:56 train_lshot.py:257] INFO Epoch: [40][30/150] Time 0.282 (0.494) Data 0.000 (0.207) Loss 0.7327 (0.7078) Prec@1 81.250 (79.826) Prec@5 91.797 (94.733)
[2021-04-28 22:24:59 train_lshot.py:257] INFO Epoch: [40][40/150] Time 0.283 (0.445) Data 0.001 (0.157) Loss 0.7137 (0.6988) Prec@1 79.688 (80.145) Prec@5 94.922 (94.970)
[2021-04-28 22:25:02 train_lshot.py:257] INFO Epoch: [40][50/150] Time 0.284 (0.413) Data 0.001 (0.126) Loss 0.6429 (0.7031) Prec@1 83.203 (80.086) Prec@5 97.266 (94.953)
[2021-04-28 22:25:04 train_lshot.py:257] INFO Epoch: [40][60/150] Time 0.280 (0.391) Data 0.000 (0.106) Loss 0.6537 (0.7011) Prec@1 82.812 (80.174) Prec@5 94.922 (94.973)
[2021-04-28 22:25:07 train_lshot.py:257] INFO Epoch: [40][70/150] Time 0.278 (0.376) Data 0.001 (0.091) Loss 0.6363 (0.7024) Prec@1 82.031 (80.221) Prec@5 96.875 (94.916)
[2021-04-28 22:25:10 train_lshot.py:257] INFO Epoch: [40][80/150] Time 0.287 (0.364) Data 0.000 (0.080) Loss 0.6707 (0.7066) Prec@1 82.031 (80.184) Prec@5 95.703 (94.792)
[2021-04-28 22:25:13 train_lshot.py:257] INFO Epoch: [40][90/150] Time 0.273 (0.354) Data 0.000 (0.071) Loss 0.7297 (0.7074) Prec@1 80.078 (80.185) Prec@5 94.141 (94.763)
[2021-04-28 22:25:16 train_lshot.py:257] INFO Epoch: [40][100/150] Time 0.273 (0.347) Data 0.000 (0.064) Loss 0.5781 (0.7050) Prec@1 83.594 (80.217) Prec@5 97.266 (94.833)
[2021-04-28 22:25:18 train_lshot.py:257] INFO Epoch: [40][110/150] Time 0.290 (0.341) Data 0.000 (0.058) Loss 0.6901 (0.7053) Prec@1 78.125 (80.106) Prec@5 94.531 (94.855)
[2021-04-28 22:25:21 train_lshot.py:257] INFO Epoch: [40][120/150] Time 0.285 (0.336) Data 0.001 (0.053) Loss 0.7611 (0.7050) Prec@1 74.609 (80.052) Prec@5 94.531 (94.886)
[2021-04-28 22:25:25 train_lshot.py:257] INFO Epoch: [40][130/150] Time 0.320 (0.338) Data 0.000 (0.049) Loss 0.7842 (0.7065) Prec@1 77.344 (80.042) Prec@5 91.797 (94.818)
[2021-04-28 22:25:28 train_lshot.py:257] INFO Epoch: [40][140/150] Time 0.281 (0.335) Data 0.000 (0.046) Loss 0.6965 (0.7092) Prec@1 80.469 (79.951) Prec@5 95.312 (94.767)
[2021-04-28 22:25:37 train_lshot.py:257] INFO Epoch: [41][0/150] Time 5.878 (5.878) Data 5.473 (5.473) Loss 0.7024 (0.7024) Prec@1 82.422 (82.422) Prec@5 94.922 (94.922)
[2021-04-28 22:25:40 train_lshot.py:257] INFO Epoch: [41][10/150] Time 0.348 (0.867) Data 0.004 (0.499) Loss 0.6692 (0.6815) Prec@1 83.594 (81.001) Prec@5 94.531 (95.632)
[2021-04-28 22:25:43 train_lshot.py:257] INFO Epoch: [41][20/150] Time 0.280 (0.591) Data 0.000 (0.262) Loss 0.7237 (0.6884) Prec@1 81.250 (80.562) Prec@5 94.141 (95.331)
[2021-04-28 22:25:46 train_lshot.py:257] INFO Epoch: [41][30/150] Time 0.285 (0.495) Data 0.000 (0.178) Loss 0.6856 (0.6843) Prec@1 78.906 (80.494) Prec@5 96.484 (95.577)
[2021-04-28 22:25:49 train_lshot.py:257] INFO Epoch: [41][40/150] Time 0.286 (0.442) Data 0.000 (0.134) Loss 0.6442 (0.6853) Prec@1 82.422 (80.669) Prec@5 96.875 (95.474)
[2021-04-28 22:25:52 train_lshot.py:257] INFO Epoch: [41][50/150] Time 0.281 (0.411) Data 0.000 (0.108) Loss 0.6905 (0.6894) Prec@1 81.250 (80.668) Prec@5 96.484 (95.351)
[2021-04-28 22:25:55 train_lshot.py:257] INFO Epoch: [41][60/150] Time 0.281 (0.389) Data 0.001 (0.090) Loss 0.6800 (0.6899) Prec@1 82.031 (80.648) Prec@5 94.531 (95.268)
[2021-04-28 22:25:57 train_lshot.py:257] INFO Epoch: [41][70/150] Time 0.286 (0.374) Data 0.001 (0.078) Loss 0.6870 (0.6912) Prec@1 79.297 (80.656) Prec@5 93.750 (95.208)
[2021-04-28 22:26:00 train_lshot.py:257] INFO Epoch: [41][80/150] Time 0.283 (0.363) Data 0.000 (0.068) Loss 0.7700 (0.6937) Prec@1 78.906 (80.536) Prec@5 94.531 (95.144)
[2021-04-28 22:26:03 train_lshot.py:257] INFO Epoch: [41][90/150] Time 0.286 (0.355) Data 0.000 (0.061) Loss 0.7189 (0.6959) Prec@1 79.297 (80.495) Prec@5 92.578 (95.102)
[2021-04-28 22:26:06 train_lshot.py:257] INFO Epoch: [41][100/150] Time 0.447 (0.349) Data 0.000 (0.055) Loss 0.7063 (0.6976) Prec@1 80.469 (80.434) Prec@5 94.531 (95.080)
[2021-04-28 22:26:09 train_lshot.py:257] INFO Epoch: [41][110/150] Time 0.293 (0.347) Data 0.002 (0.050) Loss 0.7128 (0.6970) Prec@1 79.688 (80.522) Prec@5 95.312 (95.112)
[2021-04-28 22:26:12 train_lshot.py:257] INFO Epoch: [41][120/150] Time 0.290 (0.342) Data 0.000 (0.046) Loss 0.8374 (0.6995) Prec@1 74.609 (80.420) Prec@5 93.359 (95.025)
[2021-04-28 22:26:15 train_lshot.py:257] INFO Epoch: [41][130/150] Time 0.280 (0.337) Data 0.000 (0.042) Loss 0.7669 (0.7032) Prec@1 78.125 (80.272) Prec@5 94.531 (94.922)
[2021-04-28 22:26:18 train_lshot.py:257] INFO Epoch: [41][140/150] Time 0.347 (0.337) Data 0.000 (0.039) Loss 0.7947 (0.7065) Prec@1 77.344 (80.161) Prec@5 90.625 (94.847)
[2021-04-28 22:26:27 train_lshot.py:257] INFO Epoch: [42][0/150] Time 5.876 (5.876) Data 5.490 (5.490) Loss 0.5945 (0.5945) Prec@1 83.984 (83.984) Prec@5 98.438 (98.438)
[2021-04-28 22:26:31 train_lshot.py:257] INFO Epoch: [42][10/150] Time 0.313 (0.874) Data 0.001 (0.503) Loss 0.6832 (0.6638) Prec@1 79.688 (81.641) Prec@5 95.312 (95.526)
[2021-04-28 22:26:34 train_lshot.py:257] INFO Epoch: [42][20/150] Time 0.279 (0.599) Data 0.000 (0.264) Loss 0.7161 (0.6723) Prec@1 78.125 (81.250) Prec@5 95.312 (95.182)
[2021-04-28 22:26:37 train_lshot.py:257] INFO Epoch: [42][30/150] Time 0.280 (0.502) Data 0.000 (0.179) Loss 0.5770 (0.6889) Prec@1 85.156 (80.670) Prec@5 97.266 (94.947)
[2021-04-28 22:26:40 train_lshot.py:257] INFO Epoch: [42][40/150] Time 0.280 (0.448) Data 0.000 (0.135) Loss 0.7300 (0.6918) Prec@1 77.734 (80.650) Prec@5 96.094 (94.922)
[2021-04-28 22:26:43 train_lshot.py:257] INFO Epoch: [42][50/150] Time 0.289 (0.415) Data 0.000 (0.109) Loss 0.6937 (0.6898) Prec@1 82.031 (80.737) Prec@5 94.922 (95.052)
[2021-04-28 22:26:45 train_lshot.py:257] INFO Epoch: [42][60/150] Time 0.283 (0.393) Data 0.000 (0.091) Loss 0.7205 (0.6932) Prec@1 80.859 (80.610) Prec@5 92.578 (94.903)
[2021-04-28 22:26:48 train_lshot.py:257] INFO Epoch: [42][70/150] Time 0.276 (0.377) Data 0.001 (0.078) Loss 0.6893 (0.6952) Prec@1 82.812 (80.595) Prec@5 94.531 (94.933)
[2021-04-28 22:26:51 train_lshot.py:257] INFO Epoch: [42][80/150] Time 0.291 (0.366) Data 0.001 (0.069) Loss 0.7388 (0.6960) Prec@1 78.906 (80.522) Prec@5 95.312 (94.917)
[2021-04-28 22:26:55 train_lshot.py:257] INFO Epoch: [42][90/150] Time 0.347 (0.369) Data 0.000 (0.061) Loss 0.5944 (0.6960) Prec@1 82.812 (80.525) Prec@5 96.875 (94.930)
[2021-04-28 22:26:58 train_lshot.py:257] INFO Epoch: [42][100/150] Time 0.274 (0.361) Data 0.000 (0.055) Loss 0.6097 (0.6997) Prec@1 83.984 (80.372) Prec@5 96.094 (94.829)
[2021-04-28 22:27:01 train_lshot.py:257] INFO Epoch: [42][110/150] Time 0.282 (0.354) Data 0.000 (0.050) Loss 0.7108 (0.7015) Prec@1 82.422 (80.402) Prec@5 94.531 (94.802)
[2021-04-28 22:27:04 train_lshot.py:257] INFO Epoch: [42][120/150] Time 0.364 (0.348) Data 0.000 (0.046) Loss 0.7554 (0.7020) Prec@1 79.297 (80.369) Prec@5 94.531 (94.773)
[2021-04-28 22:27:07 train_lshot.py:257] INFO Epoch: [42][130/150] Time 0.283 (0.345) Data 0.000 (0.043) Loss 0.7096 (0.7009) Prec@1 80.078 (80.427) Prec@5 95.703 (94.758)
[2021-04-28 22:27:09 train_lshot.py:257] INFO Epoch: [42][140/150] Time 0.280 (0.341) Data 0.000 (0.040) Loss 0.7187 (0.7013) Prec@1 78.125 (80.416) Prec@5 94.531 (94.761)
[2021-04-28 22:27:19 train_lshot.py:257] INFO Epoch: [43][0/150] Time 6.395 (6.395) Data 5.941 (5.941) Loss 0.6569 (0.6569) Prec@1 81.250 (81.250) Prec@5 95.703 (95.703)
[2021-04-28 22:27:23 train_lshot.py:257] INFO Epoch: [43][10/150] Time 0.296 (0.933) Data 0.000 (0.582) Loss 0.5973 (0.6415) Prec@1 84.766 (82.209) Prec@5 95.312 (95.632)
[2021-04-28 22:27:25 train_lshot.py:257] INFO Epoch: [43][20/150] Time 0.276 (0.623) Data 0.000 (0.305) Loss 0.5718 (0.6513) Prec@1 84.375 (82.366) Prec@5 98.438 (95.424)
[2021-04-28 22:27:28 train_lshot.py:257] INFO Epoch: [43][30/150] Time 0.275 (0.514) Data 0.000 (0.207) Loss 0.6634 (0.6552) Prec@1 84.766 (82.460) Prec@5 94.922 (95.401)
[2021-04-28 22:27:31 train_lshot.py:257] INFO Epoch: [43][40/150] Time 0.277 (0.457) Data 0.000 (0.156) Loss 0.7110 (0.6574) Prec@1 75.781 (82.041) Prec@5 96.094 (95.474)
[2021-04-28 22:27:34 train_lshot.py:257] INFO Epoch: [43][50/150] Time 0.275 (0.423) Data 0.000 (0.126) Loss 0.6133 (0.6605) Prec@1 81.641 (81.801) Prec@5 96.484 (95.343)
[2021-04-28 22:27:37 train_lshot.py:257] INFO Epoch: [43][60/150] Time 0.277 (0.399) Data 0.000 (0.105) Loss 0.7306 (0.6686) Prec@1 79.688 (81.487) Prec@5 94.531 (95.229)
[2021-04-28 22:27:40 train_lshot.py:257] INFO Epoch: [43][70/150] Time 0.285 (0.383) Data 0.001 (0.091) Loss 0.6315 (0.6705) Prec@1 81.641 (81.432) Prec@5 96.484 (95.235)
[2021-04-28 22:27:42 train_lshot.py:257] INFO Epoch: [43][80/150] Time 0.283 (0.371) Data 0.000 (0.079) Loss 0.6543 (0.6702) Prec@1 82.422 (81.404) Prec@5 96.094 (95.240)
[2021-04-28 22:27:46 train_lshot.py:257] INFO Epoch: [43][90/150] Time 0.292 (0.365) Data 0.000 (0.071) Loss 0.6927 (0.6729) Prec@1 82.422 (81.302) Prec@5 95.703 (95.222)
[2021-04-28 22:27:48 train_lshot.py:257] INFO Epoch: [43][100/150] Time 0.277 (0.357) Data 0.000 (0.064) Loss 0.6724 (0.6739) Prec@1 80.078 (81.258) Prec@5 94.922 (95.196)
[2021-04-28 22:27:51 train_lshot.py:257] INFO Epoch: [43][110/150] Time 0.290 (0.350) Data 0.000 (0.058) Loss 0.6980 (0.6751) Prec@1 80.078 (81.204) Prec@5 96.094 (95.200)
[2021-04-28 22:27:54 train_lshot.py:257] INFO Epoch: [43][120/150] Time 0.280 (0.345) Data 0.000 (0.053) Loss 0.7517 (0.6774) Prec@1 77.734 (81.114) Prec@5 94.141 (95.212)
[2021-04-28 22:27:57 train_lshot.py:257] INFO Epoch: [43][130/150] Time 0.283 (0.340) Data 0.000 (0.049) Loss 0.5730 (0.6762) Prec@1 82.422 (81.134) Prec@5 96.875 (95.271)
[2021-04-28 22:28:00 train_lshot.py:257] INFO Epoch: [43][140/150] Time 0.298 (0.336) Data 0.000 (0.046) Loss 0.6541 (0.6781) Prec@1 81.250 (81.059) Prec@5 95.703 (95.229)
[2021-04-28 22:28:31 train_lshot.py:119] INFO Meta Val 43: 0.5960000120103359
[2021-04-28 22:28:37 train_lshot.py:257] INFO Epoch: [44][0/150] Time 5.726 (5.726) Data 5.289 (5.289) Loss 0.6133 (0.6133) Prec@1 85.156 (85.156) Prec@5 94.922 (94.922)
[2021-04-28 22:28:41 train_lshot.py:257] INFO Epoch: [44][10/150] Time 0.372 (0.865) Data 0.001 (0.483) Loss 0.6594 (0.6408) Prec@1 82.031 (82.741) Prec@5 95.703 (95.632)
[2021-04-28 22:28:44 train_lshot.py:257] INFO Epoch: [44][20/150] Time 0.279 (0.587) Data 0.001 (0.253) Loss 0.6334 (0.6461) Prec@1 84.766 (82.738) Prec@5 96.484 (95.443)
[2021-04-28 22:28:46 train_lshot.py:257] INFO Epoch: [44][30/150] Time 0.275 (0.488) Data 0.000 (0.172) Loss 0.6231 (0.6455) Prec@1 84.766 (82.649) Prec@5 96.094 (95.439)
[2021-04-28 22:28:49 train_lshot.py:257] INFO Epoch: [44][40/150] Time 0.280 (0.440) Data 0.001 (0.130) Loss 0.6425 (0.6476) Prec@1 83.203 (82.479) Prec@5 95.312 (95.417)
[2021-04-28 22:28:52 train_lshot.py:257] INFO Epoch: [44][50/150] Time 0.277 (0.408) Data 0.000 (0.105) Loss 0.7463 (0.6486) Prec@1 78.125 (82.269) Prec@5 92.188 (95.435)
[2021-04-28 22:28:55 train_lshot.py:257] INFO Epoch: [44][60/150] Time 0.282 (0.387) Data 0.000 (0.087) Loss 0.5791 (0.6472) Prec@1 85.938 (82.351) Prec@5 95.703 (95.434)
[2021-04-28 22:28:58 train_lshot.py:257] INFO Epoch: [44][70/150] Time 0.279 (0.372) Data 0.001 (0.075) Loss 0.6949 (0.6525) Prec@1 79.688 (82.136) Prec@5 95.703 (95.263)
[2021-04-28 22:29:00 train_lshot.py:257] INFO Epoch: [44][80/150] Time 0.272 (0.360) Data 0.000 (0.066) Loss 0.7439 (0.6506) Prec@1 78.125 (82.133) Prec@5 94.531 (95.390)
[2021-04-28 22:29:03 train_lshot.py:257] INFO Epoch: [44][90/150] Time 0.280 (0.351) Data 0.000 (0.059) Loss 0.5731 (0.6504) Prec@1 84.766 (82.091) Prec@5 96.875 (95.420)
[2021-04-28 22:29:06 train_lshot.py:257] INFO Epoch: [44][100/150] Time 0.276 (0.344) Data 0.000 (0.053) Loss 0.6970 (0.6554) Prec@1 78.906 (81.985) Prec@5 94.531 (95.343)
[2021-04-28 22:29:09 train_lshot.py:257] INFO Epoch: [44][110/150] Time 0.293 (0.339) Data 0.000 (0.048) Loss 0.6961 (0.6609) Prec@1 79.297 (81.743) Prec@5 95.703 (95.298)
[2021-04-28 22:29:12 train_lshot.py:257] INFO Epoch: [44][120/150] Time 0.285 (0.335) Data 0.000 (0.044) Loss 0.6035 (0.6643) Prec@1 85.547 (81.628) Prec@5 94.531 (95.251)
[2021-04-28 22:29:15 train_lshot.py:257] INFO Epoch: [44][130/150] Time 0.289 (0.335) Data 0.000 (0.041) Loss 0.6270 (0.6673) Prec@1 81.250 (81.566) Prec@5 95.703 (95.229)
[2021-04-28 22:29:18 train_lshot.py:257] INFO Epoch: [44][140/150] Time 0.303 (0.331) Data 0.000 (0.038) Loss 0.7073 (0.6695) Prec@1 78.516 (81.461) Prec@5 95.312 (95.224)
[2021-04-28 22:29:26 train_lshot.py:257] INFO Epoch: [45][0/150] Time 5.029 (5.029) Data 4.630 (4.630) Loss 0.6035 (0.6035) Prec@1 83.594 (83.594) Prec@5 94.141 (94.141)
[2021-04-28 22:29:31 train_lshot.py:257] INFO Epoch: [45][10/150] Time 0.303 (0.906) Data 0.001 (0.528) Loss 0.6498 (0.6381) Prec@1 84.766 (82.102) Prec@5 94.531 (95.561)
[2021-04-28 22:29:34 train_lshot.py:257] INFO Epoch: [45][20/150] Time 0.275 (0.608) Data 0.000 (0.277) Loss 0.6481 (0.6519) Prec@1 83.203 (81.752) Prec@5 97.266 (95.461)
[2021-04-28 22:29:37 train_lshot.py:257] INFO Epoch: [45][30/150] Time 0.274 (0.504) Data 0.001 (0.188) Loss 0.7089 (0.6509) Prec@1 81.250 (82.006) Prec@5 94.531 (95.602)
[2021-04-28 22:29:39 train_lshot.py:257] INFO Epoch: [45][40/150] Time 0.282 (0.450) Data 0.000 (0.142) Loss 0.5926 (0.6484) Prec@1 84.766 (82.069) Prec@5 97.656 (95.703)
[2021-04-28 22:29:42 train_lshot.py:257] INFO Epoch: [45][50/150] Time 0.279 (0.416) Data 0.000 (0.114) Loss 0.6364 (0.6522) Prec@1 80.859 (81.901) Prec@5 96.875 (95.665)
[2021-04-28 22:29:45 train_lshot.py:257] INFO Epoch: [45][60/150] Time 0.274 (0.394) Data 0.000 (0.096) Loss 0.5939 (0.6561) Prec@1 82.422 (81.884) Prec@5 97.266 (95.588)
[2021-04-28 22:29:49 train_lshot.py:257] INFO Epoch: [45][70/150] Time 0.302 (0.395) Data 0.001 (0.083) Loss 0.6206 (0.6573) Prec@1 81.641 (81.894) Prec@5 98.047 (95.560)
[2021-04-28 22:29:52 train_lshot.py:257] INFO Epoch: [45][80/150] Time 0.277 (0.381) Data 0.000 (0.072) Loss 0.6306 (0.6561) Prec@1 83.984 (82.002) Prec@5 96.094 (95.539)
[2021-04-28 22:29:55 train_lshot.py:257] INFO Epoch: [45][90/150] Time 0.273 (0.370) Data 0.000 (0.064) Loss 0.7758 (0.6593) Prec@1 79.297 (81.877) Prec@5 93.750 (95.523)
[2021-04-28 22:29:57 train_lshot.py:257] INFO Epoch: [45][100/150] Time 0.280 (0.361) Data 0.000 (0.058) Loss 0.5968 (0.6594) Prec@1 82.422 (81.784) Prec@5 95.312 (95.541)
[2021-04-28 22:30:00 train_lshot.py:257] INFO Epoch: [45][110/150] Time 0.284 (0.355) Data 0.000 (0.053) Loss 0.5792 (0.6614) Prec@1 83.594 (81.679) Prec@5 98.047 (95.527)
[2021-04-28 22:30:03 train_lshot.py:257] INFO Epoch: [45][120/150] Time 0.276 (0.349) Data 0.000 (0.049) Loss 0.6055 (0.6625) Prec@1 83.203 (81.586) Prec@5 96.875 (95.490)
[2021-04-28 22:30:06 train_lshot.py:257] INFO Epoch: [45][130/150] Time 0.281 (0.344) Data 0.000 (0.045) Loss 0.7174 (0.6641) Prec@1 79.688 (81.551) Prec@5 96.094 (95.444)
[2021-04-28 22:30:10 train_lshot.py:257] INFO Epoch: [45][140/150] Time 0.316 (0.347) Data 0.000 (0.042) Loss 0.7582 (0.6660) Prec@1 78.906 (81.513) Prec@5 93.750 (95.396)
[2021-04-28 22:30:18 train_lshot.py:257] INFO Epoch: [46][0/150] Time 4.622 (4.622) Data 4.172 (4.172) Loss 0.6655 (0.6655) Prec@1 81.641 (81.641) Prec@5 96.875 (96.875)
[2021-04-28 22:30:23 train_lshot.py:257] INFO Epoch: [46][10/150] Time 0.343 (0.882) Data 0.004 (0.502) Loss 0.6343 (0.6154) Prec@1 81.250 (84.020) Prec@5 96.484 (95.952)
[2021-04-28 22:30:26 train_lshot.py:257] INFO Epoch: [46][20/150] Time 0.281 (0.602) Data 0.000 (0.263) Loss 0.6188 (0.6185) Prec@1 81.250 (83.761) Prec@5 95.312 (95.722)
[2021-04-28 22:30:28 train_lshot.py:257] INFO Epoch: [46][30/150] Time 0.286 (0.500) Data 0.000 (0.178) Loss 0.7117 (0.6087) Prec@1 79.688 (84.035) Prec@5 94.531 (95.880)
[2021-04-28 22:30:31 train_lshot.py:257] INFO Epoch: [46][40/150] Time 0.286 (0.447) Data 0.000 (0.135) Loss 0.6145 (0.6016) Prec@1 82.422 (84.213) Prec@5 94.922 (95.960)
[2021-04-28 22:30:34 train_lshot.py:257] INFO Epoch: [46][50/150] Time 0.279 (0.414) Data 0.000 (0.109) Loss 0.5557 (0.5929) Prec@1 86.328 (84.475) Prec@5 95.703 (96.032)
[2021-04-28 22:30:37 train_lshot.py:257] INFO Epoch: [46][60/150] Time 0.283 (0.393) Data 0.000 (0.091) Loss 0.5793 (0.5839) Prec@1 82.422 (84.766) Prec@5 96.094 (96.113)
[2021-04-28 22:30:40 train_lshot.py:257] INFO Epoch: [46][70/150] Time 0.277 (0.377) Data 0.001 (0.078) Loss 0.4961 (0.5761) Prec@1 89.844 (85.046) Prec@5 97.266 (96.209)
[2021-04-28 22:30:43 train_lshot.py:257] INFO Epoch: [46][80/150] Time 0.292 (0.366) Data 0.000 (0.068) Loss 0.5183 (0.5707) Prec@1 88.672 (85.209) Prec@5 95.703 (96.224)
[2021-04-28 22:30:45 train_lshot.py:257] INFO Epoch: [46][90/150] Time 0.284 (0.356) Data 0.000 (0.061) Loss 0.4934 (0.5648) Prec@1 89.844 (85.410) Prec@5 97.656 (96.296)
[2021-04-28 22:30:48 train_lshot.py:257] INFO Epoch: [46][100/150] Time 0.417 (0.351) Data 0.000 (0.055) Loss 0.5469 (0.5606) Prec@1 84.766 (85.528) Prec@5 96.094 (96.330)
[2021-04-28 22:30:51 train_lshot.py:257] INFO Epoch: [46][110/150] Time 0.284 (0.347) Data 0.000 (0.050) Loss 0.5685 (0.5578) Prec@1 84.375 (85.586) Prec@5 96.484 (96.361)
[2021-04-28 22:30:54 train_lshot.py:257] INFO Epoch: [46][120/150] Time 0.286 (0.342) Data 0.000 (0.046) Loss 0.4870 (0.5566) Prec@1 89.844 (85.686) Prec@5 98.438 (96.384)
[2021-04-28 22:30:57 train_lshot.py:257] INFO Epoch: [46][130/150] Time 0.286 (0.337) Data 0.000 (0.042) Loss 0.5136 (0.5544) Prec@1 86.719 (85.744) Prec@5 97.656 (96.398)
[2021-04-28 22:31:00 train_lshot.py:257] INFO Epoch: [46][140/150] Time 0.283 (0.334) Data 0.000 (0.039) Loss 0.4587 (0.5514) Prec@1 90.625 (85.890) Prec@5 97.266 (96.446)
[2021-04-28 22:31:08 train_lshot.py:257] INFO Epoch: [47][0/150] Time 4.022 (4.022) Data 3.667 (3.667) Loss 0.5928 (0.5928) Prec@1 85.547 (85.547) Prec@5 94.922 (94.922)
[2021-04-28 22:31:14 train_lshot.py:257] INFO Epoch: [47][10/150] Time 0.385 (0.880) Data 0.003 (0.503) Loss 0.4911 (0.4827) Prec@1 86.719 (88.707) Prec@5 97.266 (97.017)
[2021-04-28 22:31:17 train_lshot.py:257] INFO Epoch: [47][20/150] Time 0.275 (0.600) Data 0.000 (0.264) Loss 0.4226 (0.4832) Prec@1 91.797 (88.690) Prec@5 98.047 (97.117)
[2021-04-28 22:31:20 train_lshot.py:257] INFO Epoch: [47][30/150] Time 0.275 (0.499) Data 0.000 (0.179) Loss 0.6092 (0.4936) Prec@1 84.375 (88.231) Prec@5 94.531 (96.976)
[2021-04-28 22:31:23 train_lshot.py:257] INFO Epoch: [47][40/150] Time 0.274 (0.446) Data 0.000 (0.135) Loss 0.5047 (0.4923) Prec@1 87.109 (88.205) Prec@5 98.438 (97.113)
[2021-04-28 22:31:25 train_lshot.py:257] INFO Epoch: [47][50/150] Time 0.290 (0.414) Data 0.000 (0.109) Loss 0.5531 (0.4953) Prec@1 85.156 (88.013) Prec@5 96.094 (97.151)
[2021-04-28 22:31:28 train_lshot.py:257] INFO Epoch: [47][60/150] Time 0.286 (0.393) Data 0.000 (0.091) Loss 0.6178 (0.4931) Prec@1 83.984 (88.128) Prec@5 94.531 (97.144)
[2021-04-28 22:31:31 train_lshot.py:257] INFO Epoch: [47][70/150] Time 0.282 (0.377) Data 0.001 (0.078) Loss 0.4419 (0.4970) Prec@1 88.672 (87.973) Prec@5 98.047 (97.040)
[2021-04-28 22:31:34 train_lshot.py:257] INFO Epoch: [47][80/150] Time 0.283 (0.365) Data 0.000 (0.069) Loss 0.5578 (0.4982) Prec@1 86.328 (87.973) Prec@5 97.266 (97.053)
[2021-04-28 22:31:37 train_lshot.py:257] INFO Epoch: [47][90/150] Time 0.291 (0.356) Data 0.000 (0.061) Loss 0.4856 (0.4978) Prec@1 89.844 (87.951) Prec@5 98.438 (97.047)
[2021-04-28 22:31:39 train_lshot.py:257] INFO Epoch: [47][100/150] Time 0.287 (0.349) Data 0.000 (0.055) Loss 0.4724 (0.4976) Prec@1 87.891 (87.922) Prec@5 97.656 (97.030)
[2021-04-28 22:31:42 train_lshot.py:257] INFO Epoch: [47][110/150] Time 0.343 (0.344) Data 0.000 (0.050) Loss 0.5190 (0.4963) Prec@1 84.766 (87.972) Prec@5 96.875 (97.069)
[2021-04-28 22:31:45 train_lshot.py:257] INFO Epoch: [47][120/150] Time 0.281 (0.340) Data 0.000 (0.046) Loss 0.5271 (0.4977) Prec@1 83.594 (87.946) Prec@5 98.047 (97.059)
[2021-04-28 22:31:48 train_lshot.py:257] INFO Epoch: [47][130/150] Time 0.286 (0.336) Data 0.000 (0.043) Loss 0.5338 (0.4983) Prec@1 87.500 (87.941) Prec@5 96.875 (97.051)
[2021-04-28 22:31:51 train_lshot.py:257] INFO Epoch: [47][140/150] Time 0.292 (0.333) Data 0.000 (0.040) Loss 0.4178 (0.4974) Prec@1 91.797 (87.968) Prec@5 96.875 (97.074)
[2021-04-28 22:32:22 train_lshot.py:119] INFO Meta Val 47: 0.601520014166832
[2021-04-28 22:32:29 train_lshot.py:257] INFO Epoch: [48][0/150] Time 6.596 (6.596) Data 6.086 (6.086) Loss 0.5060 (0.5060) Prec@1 86.328 (86.328) Prec@5 98.047 (98.047)
[2021-04-28 22:32:32 train_lshot.py:257] INFO Epoch: [48][10/150] Time 0.289 (0.908) Data 0.000 (0.568) Loss 0.4547 (0.4909) Prec@1 88.281 (87.784) Prec@5 96.484 (96.946)
[2021-04-28 22:32:35 train_lshot.py:257] INFO Epoch: [48][20/150] Time 0.279 (0.609) Data 0.000 (0.298) Loss 0.4600 (0.4822) Prec@1 89.062 (88.486) Prec@5 96.875 (97.284)
[2021-04-28 22:32:38 train_lshot.py:257] INFO Epoch: [48][30/150] Time 0.279 (0.503) Data 0.000 (0.202) Loss 0.4971 (0.4810) Prec@1 87.109 (88.445) Prec@5 97.656 (97.266)
[2021-04-28 22:32:41 train_lshot.py:257] INFO Epoch: [48][40/150] Time 0.280 (0.451) Data 0.000 (0.153) Loss 0.5439 (0.4830) Prec@1 85.547 (88.319) Prec@5 95.703 (97.218)
[2021-04-28 22:32:43 train_lshot.py:257] INFO Epoch: [48][50/150] Time 0.273 (0.417) Data 0.000 (0.123) Loss 0.5347 (0.4878) Prec@1 85.938 (88.105) Prec@5 95.312 (97.074)
[2021-04-28 22:32:46 train_lshot.py:257] INFO Epoch: [48][60/150] Time 0.277 (0.394) Data 0.000 (0.103) Loss 0.4743 (0.4864) Prec@1 88.281 (88.153) Prec@5 98.438 (97.099)
[2021-04-28 22:32:49 train_lshot.py:257] INFO Epoch: [48][70/150] Time 0.287 (0.378) Data 0.001 (0.088) Loss 0.4370 (0.4842) Prec@1 89.062 (88.287) Prec@5 98.828 (97.150)
[2021-04-28 22:32:52 train_lshot.py:257] INFO Epoch: [48][80/150] Time 0.287 (0.366) Data 0.000 (0.077) Loss 0.5114 (0.4861) Prec@1 86.328 (88.272) Prec@5 97.656 (97.179)
[2021-04-28 22:32:55 train_lshot.py:257] INFO Epoch: [48][90/150] Time 0.299 (0.358) Data 0.000 (0.069) Loss 0.4400 (0.4843) Prec@1 89.844 (88.401) Prec@5 97.656 (97.197)
[2021-04-28 22:32:58 train_lshot.py:257] INFO Epoch: [48][100/150] Time 0.284 (0.351) Data 0.000 (0.062) Loss 0.5516 (0.4852) Prec@1 87.109 (88.347) Prec@5 95.703 (97.200)
[2021-04-28 22:33:00 train_lshot.py:257] INFO Epoch: [48][110/150] Time 0.280 (0.345) Data 0.000 (0.057) Loss 0.4879 (0.4855) Prec@1 88.281 (88.338) Prec@5 96.094 (97.178)
[2021-04-28 22:33:03 train_lshot.py:257] INFO Epoch: [48][120/150] Time 0.287 (0.340) Data 0.000 (0.052) Loss 0.4454 (0.4822) Prec@1 89.062 (88.514) Prec@5 97.656 (97.220)
[2021-04-28 22:33:06 train_lshot.py:257] INFO Epoch: [48][130/150] Time 0.287 (0.336) Data 0.000 (0.048) Loss 0.5055 (0.4822) Prec@1 88.281 (88.523) Prec@5 97.656 (97.236)
[2021-04-28 22:33:10 train_lshot.py:257] INFO Epoch: [48][140/150] Time 0.315 (0.338) Data 0.000 (0.045) Loss 0.5698 (0.4826) Prec@1 84.375 (88.461) Prec@5 94.141 (97.235)
[2021-04-28 22:33:19 train_lshot.py:257] INFO Epoch: [49][0/150] Time 6.228 (6.228) Data 5.809 (5.809) Loss 0.5700 (0.5700) Prec@1 84.375 (84.375) Prec@5 95.703 (95.703)
[2021-04-28 22:33:23 train_lshot.py:257] INFO Epoch: [49][10/150] Time 0.306 (0.911) Data 0.001 (0.529) Loss 0.5979 (0.4902) Prec@1 83.203 (88.210) Prec@5 95.703 (96.911)
[2021-04-28 22:33:26 train_lshot.py:257] INFO Epoch: [49][20/150] Time 0.276 (0.612) Data 0.000 (0.277) Loss 0.5114 (0.4830) Prec@1 88.672 (88.449) Prec@5 97.656 (97.191)
[2021-04-28 22:33:29 train_lshot.py:257] INFO Epoch: [49][30/150] Time 0.292 (0.507) Data 0.000 (0.188) Loss 0.3980 (0.4741) Prec@1 91.016 (88.684) Prec@5 98.047 (97.278)
[2021-04-28 22:33:31 train_lshot.py:257] INFO Epoch: [49][40/150] Time 0.286 (0.451) Data 0.000 (0.142) Loss 0.4857 (0.4710) Prec@1 90.625 (88.796) Prec@5 96.875 (97.323)
[2021-04-28 22:33:34 train_lshot.py:257] INFO Epoch: [49][50/150] Time 0.282 (0.417) Data 0.000 (0.114) Loss 0.4351 (0.4732) Prec@1 91.406 (88.779) Prec@5 97.266 (97.220)
[2021-04-28 22:33:37 train_lshot.py:257] INFO Epoch: [49][60/150] Time 0.282 (0.395) Data 0.000 (0.096) Loss 0.4345 (0.4691) Prec@1 89.062 (88.928) Prec@5 98.438 (97.336)
[2021-04-28 22:33:40 train_lshot.py:257] INFO Epoch: [49][70/150] Time 0.279 (0.379) Data 0.001 (0.082) Loss 0.4788 (0.4696) Prec@1 87.891 (88.908) Prec@5 96.875 (97.321)
[2021-04-28 22:33:43 train_lshot.py:257] INFO Epoch: [49][80/150] Time 0.288 (0.367) Data 0.000 (0.072) Loss 0.4393 (0.4691) Prec@1 89.844 (88.947) Prec@5 97.656 (97.304)
[2021-04-28 22:33:47 train_lshot.py:257] INFO Epoch: [49][90/150] Time 0.347 (0.371) Data 0.000 (0.064) Loss 0.4797 (0.4698) Prec@1 88.281 (88.955) Prec@5 97.656 (97.266)
[2021-04-28 22:33:50 train_lshot.py:257] INFO Epoch: [49][100/150] Time 0.277 (0.363) Data 0.000 (0.058) Loss 0.4520 (0.4689) Prec@1 89.062 (89.001) Prec@5 96.094 (97.277)
[2021-04-28 22:33:52 train_lshot.py:257] INFO Epoch: [49][110/150] Time 0.276 (0.356) Data 0.000 (0.053) Loss 0.5064 (0.4700) Prec@1 86.328 (88.982) Prec@5 97.656 (97.259)
[2021-04-28 22:33:55 train_lshot.py:257] INFO Epoch: [49][120/150] Time 0.290 (0.350) Data 0.000 (0.048) Loss 0.4090 (0.4707) Prec@1 91.016 (88.940) Prec@5 98.828 (97.220)
[2021-04-28 22:33:58 train_lshot.py:257] INFO Epoch: [49][130/150] Time 0.281 (0.345) Data 0.000 (0.045) Loss 0.5691 (0.4726) Prec@1 87.109 (88.907) Prec@5 94.922 (97.167)
[2021-04-28 22:34:02 train_lshot.py:257] INFO Epoch: [49][140/150] Time 0.295 (0.350) Data 0.000 (0.042) Loss 0.4689 (0.4731) Prec@1 89.453 (88.838) Prec@5 97.656 (97.169)
[2021-04-28 22:34:10 train_lshot.py:257] INFO Epoch: [50][0/150] Time 5.086 (5.086) Data 4.613 (4.613) Loss 0.4546 (0.4546) Prec@1 89.453 (89.453) Prec@5 97.656 (97.656)
[2021-04-28 22:34:14 train_lshot.py:257] INFO Epoch: [50][10/150] Time 0.412 (0.820) Data 0.003 (0.424) Loss 0.4749 (0.4665) Prec@1 86.719 (88.601) Prec@5 97.266 (97.124)
[2021-04-28 22:34:17 train_lshot.py:257] INFO Epoch: [50][20/150] Time 0.279 (0.567) Data 0.000 (0.222) Loss 0.4481 (0.4741) Prec@1 89.062 (88.337) Prec@5 96.094 (97.098)
[2021-04-28 22:34:20 train_lshot.py:257] INFO Epoch: [50][30/150] Time 0.284 (0.476) Data 0.000 (0.151) Loss 0.4477 (0.4723) Prec@1 91.016 (88.584) Prec@5 96.875 (97.316)
[2021-04-28 22:34:23 train_lshot.py:257] INFO Epoch: [50][40/150] Time 0.281 (0.429) Data 0.000 (0.114) Loss 0.5738 (0.4756) Prec@1 83.594 (88.529) Prec@5 96.484 (97.228)
[2021-04-28 22:34:26 train_lshot.py:257] INFO Epoch: [50][50/150] Time 0.286 (0.400) Data 0.000 (0.092) Loss 0.4991 (0.4727) Prec@1 87.891 (88.580) Prec@5 96.875 (97.365)
[2021-04-28 22:34:28 train_lshot.py:257] INFO Epoch: [50][60/150] Time 0.280 (0.380) Data 0.000 (0.077) Loss 0.5270 (0.4712) Prec@1 85.938 (88.672) Prec@5 96.094 (97.336)
[2021-04-28 22:34:31 train_lshot.py:257] INFO Epoch: [50][70/150] Time 0.286 (0.367) Data 0.001 (0.066) Loss 0.4896 (0.4692) Prec@1 87.500 (88.732) Prec@5 97.266 (97.321)
[2021-04-28 22:34:34 train_lshot.py:257] INFO Epoch: [50][80/150] Time 0.289 (0.358) Data 0.000 (0.058) Loss 0.4448 (0.4694) Prec@1 89.062 (88.696) Prec@5 98.438 (97.333)
[2021-04-28 22:34:37 train_lshot.py:257] INFO Epoch: [50][90/150] Time 0.287 (0.349) Data 0.000 (0.052) Loss 0.5556 (0.4699) Prec@1 85.547 (88.698) Prec@5 96.094 (97.326)
[2021-04-28 22:34:40 train_lshot.py:257] INFO Epoch: [50][100/150] Time 0.287 (0.343) Data 0.000 (0.047) Loss 0.4372 (0.4702) Prec@1 90.625 (88.722) Prec@5 97.266 (97.297)
[2021-04-28 22:34:43 train_lshot.py:257] INFO Epoch: [50][110/150] Time 0.293 (0.338) Data 0.000 (0.042) Loss 0.5029 (0.4690) Prec@1 87.891 (88.813) Prec@5 98.047 (97.315)
[2021-04-28 22:34:46 train_lshot.py:257] INFO Epoch: [50][120/150] Time 0.432 (0.336) Data 0.000 (0.039) Loss 0.4295 (0.4666) Prec@1 88.672 (88.898) Prec@5 98.047 (97.356)
[2021-04-28 22:34:49 train_lshot.py:257] INFO Epoch: [50][130/150] Time 0.289 (0.334) Data 0.000 (0.036) Loss 0.4721 (0.4671) Prec@1 90.625 (88.898) Prec@5 96.094 (97.325)
[2021-04-28 22:34:52 train_lshot.py:257] INFO Epoch: [50][140/150] Time 0.312 (0.331) Data 0.000 (0.033) Loss 0.5389 (0.4668) Prec@1 87.891 (88.905) Prec@5 95.703 (97.357)
[2021-04-28 22:35:01 train_lshot.py:257] INFO Epoch: [51][0/150] Time 6.008 (6.008) Data 5.583 (5.583) Loss 0.4468 (0.4468) Prec@1 89.453 (89.453) Prec@5 98.438 (98.438)
[2021-04-28 22:35:05 train_lshot.py:257] INFO Epoch: [51][10/150] Time 0.278 (0.871) Data 0.000 (0.508) Loss 0.5074 (0.4478) Prec@1 89.453 (89.950) Prec@5 95.703 (97.301)
[2021-04-28 22:35:08 train_lshot.py:257] INFO Epoch: [51][20/150] Time 0.292 (0.597) Data 0.000 (0.266) Loss 0.4258 (0.4558) Prec@1 89.844 (89.695) Prec@5 98.047 (97.117)
[2021-04-28 22:35:10 train_lshot.py:257] INFO Epoch: [51][30/150] Time 0.277 (0.495) Data 0.000 (0.181) Loss 0.4361 (0.4482) Prec@1 87.500 (89.693) Prec@5 96.484 (97.354)
[2021-04-28 22:35:13 train_lshot.py:257] INFO Epoch: [51][40/150] Time 0.286 (0.443) Data 0.001 (0.137) Loss 0.4944 (0.4501) Prec@1 87.891 (89.577) Prec@5 96.484 (97.361)
[2021-04-28 22:35:16 train_lshot.py:257] INFO Epoch: [51][50/150] Time 0.284 (0.412) Data 0.000 (0.110) Loss 0.4447 (0.4502) Prec@1 88.281 (89.614) Prec@5 98.828 (97.457)
[2021-04-28 22:35:19 train_lshot.py:257] INFO Epoch: [51][60/150] Time 0.281 (0.391) Data 0.000 (0.092) Loss 0.5266 (0.4499) Prec@1 87.109 (89.562) Prec@5 95.703 (97.477)
[2021-04-28 22:35:22 train_lshot.py:257] INFO Epoch: [51][70/150] Time 0.315 (0.376) Data 0.001 (0.079) Loss 0.4911 (0.4528) Prec@1 87.109 (89.365) Prec@5 96.094 (97.403)
[2021-04-28 22:35:25 train_lshot.py:257] INFO Epoch: [51][80/150] Time 0.293 (0.365) Data 0.000 (0.069) Loss 0.3906 (0.4527) Prec@1 90.234 (89.381) Prec@5 99.609 (97.396)
[2021-04-28 22:35:27 train_lshot.py:257] INFO Epoch: [51][90/150] Time 0.287 (0.356) Data 0.000 (0.062) Loss 0.4258 (0.4526) Prec@1 92.188 (89.393) Prec@5 96.875 (97.446)
[2021-04-28 22:35:30 train_lshot.py:257] INFO Epoch: [51][100/150] Time 0.285 (0.350) Data 0.000 (0.056) Loss 0.4637 (0.4515) Prec@1 85.938 (89.407) Prec@5 98.047 (97.451)
[2021-04-28 22:35:33 train_lshot.py:257] INFO Epoch: [51][110/150] Time 0.295 (0.344) Data 0.000 (0.051) Loss 0.4618 (0.4508) Prec@1 89.453 (89.439) Prec@5 97.266 (97.449)
[2021-04-28 22:35:37 train_lshot.py:257] INFO Epoch: [51][120/150] Time 1.346 (0.348) Data 0.000 (0.046) Loss 0.5133 (0.4541) Prec@1 87.109 (89.359) Prec@5 96.875 (97.398)
[2021-04-28 22:35:40 train_lshot.py:257] INFO Epoch: [51][130/150] Time 0.293 (0.347) Data 0.000 (0.043) Loss 0.4254 (0.4522) Prec@1 90.625 (89.414) Prec@5 98.438 (97.448)
[2021-04-28 22:35:43 train_lshot.py:257] INFO Epoch: [51][140/150] Time 0.277 (0.342) Data 0.000 (0.040) Loss 0.4672 (0.4528) Prec@1 86.719 (89.381) Prec@5 97.656 (97.435)
[2021-04-28 22:36:14 train_lshot.py:119] INFO Meta Val 51: 0.6030666797161103
[2021-04-28 22:36:19 train_lshot.py:257] INFO Epoch: [52][0/150] Time 4.796 (4.796) Data 4.409 (4.409) Loss 0.4552 (0.4552) Prec@1 88.281 (88.281) Prec@5 97.656 (97.656)
[2021-04-28 22:36:23 train_lshot.py:257] INFO Epoch: [52][10/150] Time 0.305 (0.786) Data 0.000 (0.423) Loss 0.4028 (0.4448) Prec@1 91.406 (89.773) Prec@5 97.266 (97.372)
[2021-04-28 22:36:26 train_lshot.py:257] INFO Epoch: [52][20/150] Time 0.277 (0.550) Data 0.000 (0.222) Loss 0.5004 (0.4497) Prec@1 88.672 (89.528) Prec@5 96.094 (97.247)
[2021-04-28 22:36:29 train_lshot.py:257] INFO Epoch: [52][30/150] Time 0.280 (0.463) Data 0.000 (0.150) Loss 0.4029 (0.4530) Prec@1 91.016 (89.264) Prec@5 98.438 (97.278)
[2021-04-28 22:36:32 train_lshot.py:257] INFO Epoch: [52][40/150] Time 0.284 (0.422) Data 0.000 (0.114) Loss 0.3987 (0.4511) Prec@1 92.188 (89.567) Prec@5 97.656 (97.275)
[2021-04-28 22:36:35 train_lshot.py:257] INFO Epoch: [52][50/150] Time 0.302 (0.394) Data 0.000 (0.092) Loss 0.4620 (0.4533) Prec@1 89.062 (89.308) Prec@5 97.656 (97.342)
[2021-04-28 22:36:37 train_lshot.py:257] INFO Epoch: [52][60/150] Time 0.276 (0.375) Data 0.000 (0.077) Loss 0.4586 (0.4533) Prec@1 88.281 (89.242) Prec@5 97.656 (97.317)
[2021-04-28 22:36:40 train_lshot.py:257] INFO Epoch: [52][70/150] Time 0.284 (0.362) Data 0.001 (0.066) Loss 0.4338 (0.4517) Prec@1 91.406 (89.310) Prec@5 97.656 (97.398)
[2021-04-28 22:36:43 train_lshot.py:257] INFO Epoch: [52][80/150] Time 0.279 (0.352) Data 0.000 (0.058) Loss 0.4640 (0.4548) Prec@1 86.328 (89.188) Prec@5 97.656 (97.285)
[2021-04-28 22:36:47 train_lshot.py:257] INFO Epoch: [52][90/150] Time 0.288 (0.357) Data 0.000 (0.051) Loss 0.4982 (0.4568) Prec@1 86.719 (89.196) Prec@5 97.266 (97.240)
[2021-04-28 22:36:50 train_lshot.py:257] INFO Epoch: [52][100/150] Time 0.290 (0.349) Data 0.002 (0.046) Loss 0.4361 (0.4563) Prec@1 89.453 (89.264) Prec@5 96.875 (97.242)
[2021-04-28 22:36:53 train_lshot.py:257] INFO Epoch: [52][110/150] Time 1.014 (0.350) Data 0.000 (0.042) Loss 0.4670 (0.4565) Prec@1 88.672 (89.235) Prec@5 97.266 (97.259)
[2021-04-28 22:36:57 train_lshot.py:257] INFO Epoch: [52][120/150] Time 0.283 (0.349) Data 0.000 (0.039) Loss 0.4361 (0.4563) Prec@1 89.844 (89.263) Prec@5 97.656 (97.269)
[2021-04-28 22:37:00 train_lshot.py:257] INFO Epoch: [52][130/150] Time 0.280 (0.343) Data 0.000 (0.036) Loss 0.4549 (0.4560) Prec@1 90.234 (89.256) Prec@5 98.438 (97.281)
[2021-04-28 22:37:03 train_lshot.py:257] INFO Epoch: [52][140/150] Time 0.368 (0.340) Data 0.000 (0.033) Loss 0.4694 (0.4556) Prec@1 88.281 (89.281) Prec@5 98.438 (97.296)
[2021-04-28 22:37:13 train_lshot.py:257] INFO Epoch: [53][0/150] Time 7.387 (7.387) Data 7.001 (7.001) Loss 0.4608 (0.4608) Prec@1 90.625 (90.625) Prec@5 96.094 (96.094)
[2021-04-28 22:37:16 train_lshot.py:257] INFO Epoch: [53][10/150] Time 0.291 (0.967) Data 0.001 (0.638) Loss 0.4083 (0.4377) Prec@1 91.016 (89.986) Prec@5 98.047 (97.585)
[2021-04-28 22:37:19 train_lshot.py:257] INFO Epoch: [53][20/150] Time 0.282 (0.641) Data 0.000 (0.334) Loss 0.3913 (0.4362) Prec@1 90.625 (90.123) Prec@5 98.438 (97.675)
[2021-04-28 22:37:22 train_lshot.py:257] INFO Epoch: [53][30/150] Time 0.281 (0.531) Data 0.000 (0.227) Loss 0.4883 (0.4411) Prec@1 86.328 (89.756) Prec@5 96.875 (97.833)
[2021-04-28 22:37:25 train_lshot.py:257] INFO Epoch: [53][40/150] Time 0.280 (0.471) Data 0.000 (0.171) Loss 0.4325 (0.4430) Prec@1 91.016 (89.634) Prec@5 98.438 (97.752)
[2021-04-28 22:37:28 train_lshot.py:257] INFO Epoch: [53][50/150] Time 0.295 (0.434) Data 0.000 (0.138) Loss 0.4673 (0.4424) Prec@1 88.672 (89.622) Prec@5 96.875 (97.702)
[2021-04-28 22:37:31 train_lshot.py:257] INFO Epoch: [53][60/150] Time 0.278 (0.409) Data 0.000 (0.115) Loss 0.3714 (0.4399) Prec@1 92.578 (89.722) Prec@5 99.219 (97.752)
[2021-04-28 22:37:34 train_lshot.py:257] INFO Epoch: [53][70/150] Time 0.354 (0.395) Data 0.001 (0.099) Loss 0.4754 (0.4428) Prec@1 89.062 (89.673) Prec@5 96.875 (97.640)
[2021-04-28 22:37:37 train_lshot.py:257] INFO Epoch: [53][80/150] Time 0.287 (0.383) Data 0.000 (0.087) Loss 0.4447 (0.4428) Prec@1 89.062 (89.641) Prec@5 97.266 (97.680)
[2021-04-28 22:37:40 train_lshot.py:257] INFO Epoch: [53][90/150] Time 0.287 (0.371) Data 0.000 (0.077) Loss 0.4586 (0.4446) Prec@1 89.453 (89.608) Prec@5 95.703 (97.626)
[2021-04-28 22:37:42 train_lshot.py:257] INFO Epoch: [53][100/150] Time 0.291 (0.363) Data 0.000 (0.070) Loss 0.4311 (0.4452) Prec@1 91.797 (89.623) Prec@5 96.875 (97.629)
[2021-04-28 22:37:46 train_lshot.py:257] INFO Epoch: [53][110/150] Time 0.292 (0.358) Data 0.000 (0.064) Loss 0.5021 (0.4453) Prec@1 89.453 (89.580) Prec@5 96.875 (97.607)
[2021-04-28 22:37:49 train_lshot.py:257] INFO Epoch: [53][120/150] Time 0.497 (0.354) Data 0.000 (0.058) Loss 0.4739 (0.4457) Prec@1 86.719 (89.498) Prec@5 97.266 (97.592)
[2021-04-28 22:37:52 train_lshot.py:257] INFO Epoch: [53][130/150] Time 0.286 (0.352) Data 0.000 (0.054) Loss 0.5171 (0.4464) Prec@1 87.500 (89.480) Prec@5 96.875 (97.606)
[2021-04-28 22:37:55 train_lshot.py:257] INFO Epoch: [53][140/150] Time 0.286 (0.347) Data 0.000 (0.050) Loss 0.5072 (0.4453) Prec@1 87.891 (89.506) Prec@5 96.875 (97.615)
[2021-04-28 22:38:05 train_lshot.py:257] INFO Epoch: [54][0/150] Time 7.025 (7.025) Data 6.617 (6.617) Loss 0.4697 (0.4697) Prec@1 89.062 (89.062) Prec@5 98.438 (98.438)
[2021-04-28 22:38:08 train_lshot.py:257] INFO Epoch: [54][10/150] Time 0.286 (0.937) Data 0.000 (0.603) Loss 0.3879 (0.4422) Prec@1 90.625 (89.844) Prec@5 97.656 (97.763)
[2021-04-28 22:38:11 train_lshot.py:257] INFO Epoch: [54][20/150] Time 0.279 (0.626) Data 0.000 (0.316) Loss 0.4383 (0.4429) Prec@1 90.625 (89.862) Prec@5 97.656 (97.619)
[2021-04-28 22:38:14 train_lshot.py:257] INFO Epoch: [54][30/150] Time 0.281 (0.519) Data 0.000 (0.214) Loss 0.4372 (0.4352) Prec@1 89.062 (90.008) Prec@5 97.266 (97.732)
[2021-04-28 22:38:17 train_lshot.py:257] INFO Epoch: [54][40/150] Time 0.285 (0.462) Data 0.001 (0.162) Loss 0.4331 (0.4327) Prec@1 89.062 (89.939) Prec@5 97.266 (97.761)
[2021-04-28 22:38:20 train_lshot.py:257] INFO Epoch: [54][50/150] Time 0.278 (0.426) Data 0.000 (0.130) Loss 0.4327 (0.4352) Prec@1 89.453 (89.805) Prec@5 98.828 (97.779)
[2021-04-28 22:38:23 train_lshot.py:257] INFO Epoch: [54][60/150] Time 0.314 (0.407) Data 0.000 (0.109) Loss 0.3908 (0.4391) Prec@1 91.797 (89.575) Prec@5 98.828 (97.714)
[2021-04-28 22:38:26 train_lshot.py:257] INFO Epoch: [54][70/150] Time 0.276 (0.390) Data 0.001 (0.094) Loss 0.4392 (0.4385) Prec@1 90.234 (89.679) Prec@5 97.266 (97.689)
[2021-04-28 22:38:28 train_lshot.py:257] INFO Epoch: [54][80/150] Time 0.284 (0.377) Data 0.001 (0.082) Loss 0.4859 (0.4379) Prec@1 87.891 (89.718) Prec@5 96.875 (97.671)
[2021-04-28 22:38:33 train_lshot.py:257] INFO Epoch: [54][90/150] Time 0.292 (0.381) Data 0.000 (0.073) Loss 0.3681 (0.4375) Prec@1 92.969 (89.766) Prec@5 99.609 (97.643)
[2021-04-28 22:38:35 train_lshot.py:257] INFO Epoch: [54][100/150] Time 0.277 (0.371) Data 0.000 (0.066) Loss 0.3995 (0.4361) Prec@1 91.016 (89.851) Prec@5 98.438 (97.668)
[2021-04-28 22:38:38 train_lshot.py:257] INFO Epoch: [54][110/150] Time 0.286 (0.363) Data 0.000 (0.060) Loss 0.4309 (0.4380) Prec@1 89.844 (89.773) Prec@5 97.656 (97.632)
[2021-04-28 22:38:41 train_lshot.py:257] INFO Epoch: [54][120/150] Time 0.285 (0.357) Data 0.000 (0.055) Loss 0.4155 (0.4389) Prec@1 91.406 (89.818) Prec@5 98.047 (97.595)
[2021-04-28 22:38:44 train_lshot.py:257] INFO Epoch: [54][130/150] Time 0.286 (0.352) Data 0.000 (0.051) Loss 0.4727 (0.4371) Prec@1 87.891 (89.927) Prec@5 96.875 (97.626)
[2021-04-28 22:38:47 train_lshot.py:257] INFO Epoch: [54][140/150] Time 0.291 (0.347) Data 0.000 (0.047) Loss 0.4257 (0.4374) Prec@1 91.016 (89.921) Prec@5 98.047 (97.637)
[2021-04-28 22:38:54 train_lshot.py:257] INFO Epoch: [55][0/150] Time 4.150 (4.150) Data 3.684 (3.684) Loss 0.3418 (0.3418) Prec@1 92.188 (92.188) Prec@5 99.609 (99.609)
[2021-04-28 22:39:00 train_lshot.py:257] INFO Epoch: [55][10/150] Time 0.288 (0.953) Data 0.001 (0.586) Loss 0.4035 (0.4243) Prec@1 91.406 (90.128) Prec@5 97.656 (97.940)
[2021-04-28 22:39:03 train_lshot.py:257] INFO Epoch: [55][20/150] Time 0.284 (0.633) Data 0.000 (0.307) Loss 0.4205 (0.4355) Prec@1 91.406 (89.900) Prec@5 97.656 (97.656)
[2021-04-28 22:39:06 train_lshot.py:257] INFO Epoch: [55][30/150] Time 0.278 (0.523) Data 0.000 (0.208) Loss 0.4338 (0.4312) Prec@1 90.234 (90.121) Prec@5 96.875 (97.719)
[2021-04-28 22:39:09 train_lshot.py:257] INFO Epoch: [55][40/150] Time 0.274 (0.464) Data 0.000 (0.157) Loss 0.5141 (0.4341) Prec@1 88.281 (89.977) Prec@5 94.922 (97.647)
[2021-04-28 22:39:12 train_lshot.py:257] INFO Epoch: [55][50/150] Time 0.275 (0.429) Data 0.000 (0.127) Loss 0.4335 (0.4361) Prec@1 90.234 (89.982) Prec@5 98.047 (97.618)
[2021-04-28 22:39:15 train_lshot.py:257] INFO Epoch: [55][60/150] Time 0.275 (0.404) Data 0.000 (0.106) Loss 0.4771 (0.4353) Prec@1 88.672 (89.997) Prec@5 96.484 (97.637)
[2021-04-28 22:39:17 train_lshot.py:257] INFO Epoch: [55][70/150] Time 0.285 (0.387) Data 0.001 (0.091) Loss 0.4764 (0.4381) Prec@1 87.500 (89.849) Prec@5 98.438 (97.645)
[2021-04-28 22:39:20 train_lshot.py:257] INFO Epoch: [55][80/150] Time 0.281 (0.375) Data 0.000 (0.080) Loss 0.4990 (0.4399) Prec@1 87.109 (89.762) Prec@5 97.266 (97.690)
[2021-04-28 22:39:23 train_lshot.py:257] INFO Epoch: [55][90/150] Time 0.286 (0.365) Data 0.000 (0.071) Loss 0.5059 (0.4425) Prec@1 88.281 (89.706) Prec@5 96.094 (97.600)
[2021-04-28 22:39:26 train_lshot.py:257] INFO Epoch: [55][100/150] Time 0.293 (0.357) Data 0.000 (0.064) Loss 0.4069 (0.4417) Prec@1 92.188 (89.712) Prec@5 97.656 (97.594)
[2021-04-28 22:39:29 train_lshot.py:257] INFO Epoch: [55][110/150] Time 0.290 (0.351) Data 0.000 (0.058) Loss 0.4525 (0.4406) Prec@1 90.234 (89.745) Prec@5 97.266 (97.611)
[2021-04-28 22:39:32 train_lshot.py:257] INFO Epoch: [55][120/150] Time 0.281 (0.346) Data 0.000 (0.054) Loss 0.4676 (0.4421) Prec@1 91.406 (89.724) Prec@5 97.266 (97.595)
[2021-04-28 22:39:35 train_lshot.py:257] INFO Epoch: [55][130/150] Time 0.287 (0.341) Data 0.000 (0.050) Loss 0.3856 (0.4390) Prec@1 92.188 (89.841) Prec@5 98.438 (97.629)
[2021-04-28 22:39:37 train_lshot.py:257] INFO Epoch: [55][140/150] Time 0.285 (0.337) Data 0.000 (0.046) Loss 0.4571 (0.4388) Prec@1 90.234 (89.894) Prec@5 96.875 (97.642)
[2021-04-28 22:40:08 train_lshot.py:119] INFO Meta Val 55: 0.6044266790747642
[2021-04-28 22:40:14 train_lshot.py:257] INFO Epoch: [56][0/150] Time 5.591 (5.591) Data 5.130 (5.130) Loss 0.4315 (0.4315) Prec@1 89.453 (89.453) Prec@5 97.656 (97.656)
[2021-04-28 22:40:18 train_lshot.py:257] INFO Epoch: [56][10/150] Time 0.279 (0.883) Data 0.000 (0.514) Loss 0.4403 (0.4212) Prec@1 89.453 (90.057) Prec@5 95.703 (97.585)
[2021-04-28 22:40:21 train_lshot.py:257] INFO Epoch: [56][20/150] Time 0.280 (0.597) Data 0.000 (0.269) Loss 0.4123 (0.4262) Prec@1 88.281 (89.732) Prec@5 98.828 (97.675)
[2021-04-28 22:40:24 train_lshot.py:257] INFO Epoch: [56][30/150] Time 0.278 (0.495) Data 0.001 (0.183) Loss 0.4484 (0.4294) Prec@1 91.016 (89.919) Prec@5 98.047 (97.593)
[2021-04-28 22:40:27 train_lshot.py:257] INFO Epoch: [56][40/150] Time 0.275 (0.444) Data 0.000 (0.138) Loss 0.3957 (0.4337) Prec@1 90.625 (89.872) Prec@5 98.438 (97.456)
[2021-04-28 22:40:30 train_lshot.py:257] INFO Epoch: [56][50/150] Time 0.291 (0.412) Data 0.000 (0.111) Loss 0.4911 (0.4342) Prec@1 88.281 (89.859) Prec@5 97.656 (97.503)
[2021-04-28 22:40:33 train_lshot.py:257] INFO Epoch: [56][60/150] Time 0.280 (0.390) Data 0.000 (0.093) Loss 0.4444 (0.4319) Prec@1 91.016 (89.933) Prec@5 98.828 (97.586)
[2021-04-28 22:40:35 train_lshot.py:257] INFO Epoch: [56][70/150] Time 0.286 (0.375) Data 0.001 (0.080) Loss 0.4925 (0.4295) Prec@1 89.453 (90.053) Prec@5 96.484 (97.651)
[2021-04-28 22:40:38 train_lshot.py:257] INFO Epoch: [56][80/150] Time 0.281 (0.363) Data 0.000 (0.070) Loss 0.4321 (0.4304) Prec@1 91.016 (90.061) Prec@5 98.047 (97.651)
[2021-04-28 22:40:41 train_lshot.py:257] INFO Epoch: [56][90/150] Time 0.275 (0.354) Data 0.000 (0.062) Loss 0.4041 (0.4323) Prec@1 90.625 (89.968) Prec@5 98.438 (97.635)
[2021-04-28 22:40:44 train_lshot.py:257] INFO Epoch: [56][100/150] Time 0.275 (0.348) Data 0.000 (0.056) Loss 0.3277 (0.4303) Prec@1 94.141 (90.049) Prec@5 98.828 (97.660)
[2021-04-28 22:40:47 train_lshot.py:257] INFO Epoch: [56][110/150] Time 0.278 (0.342) Data 0.000 (0.051) Loss 0.5203 (0.4299) Prec@1 86.328 (90.027) Prec@5 95.312 (97.646)
[2021-04-28 22:40:50 train_lshot.py:257] INFO Epoch: [56][120/150] Time 0.286 (0.337) Data 0.000 (0.047) Loss 0.3644 (0.4291) Prec@1 92.188 (90.076) Prec@5 98.438 (97.685)
[2021-04-28 22:40:52 train_lshot.py:257] INFO Epoch: [56][130/150] Time 0.284 (0.334) Data 0.000 (0.043) Loss 0.3971 (0.4306) Prec@1 89.453 (89.972) Prec@5 99.609 (97.671)
[2021-04-28 22:40:55 train_lshot.py:257] INFO Epoch: [56][140/150] Time 0.292 (0.330) Data 0.000 (0.040) Loss 0.4740 (0.4305) Prec@1 88.281 (89.982) Prec@5 96.875 (97.673)
[2021-04-28 22:41:04 train_lshot.py:257] INFO Epoch: [57][0/150] Time 6.097 (6.097) Data 5.644 (5.644) Loss 0.4519 (0.4519) Prec@1 89.453 (89.453) Prec@5 96.484 (96.484)
[2021-04-28 22:41:09 train_lshot.py:257] INFO Epoch: [57][10/150] Time 0.305 (0.937) Data 0.001 (0.603) Loss 0.3258 (0.4312) Prec@1 94.531 (90.376) Prec@5 98.438 (97.514)
[2021-04-28 22:41:12 train_lshot.py:257] INFO Epoch: [57][20/150] Time 0.283 (0.627) Data 0.000 (0.316) Loss 0.5136 (0.4274) Prec@1 87.500 (90.402) Prec@5 96.094 (97.545)
[2021-04-28 22:41:14 train_lshot.py:257] INFO Epoch: [57][30/150] Time 0.277 (0.517) Data 0.000 (0.214) Loss 0.4308 (0.4216) Prec@1 90.625 (90.537) Prec@5 97.266 (97.707)
[2021-04-28 22:41:17 train_lshot.py:257] INFO Epoch: [57][40/150] Time 0.275 (0.459) Data 0.000 (0.162) Loss 0.4352 (0.4181) Prec@1 89.844 (90.701) Prec@5 96.484 (97.761)
[2021-04-28 22:41:20 train_lshot.py:257] INFO Epoch: [57][50/150] Time 0.279 (0.425) Data 0.001 (0.130) Loss 0.4101 (0.4215) Prec@1 89.062 (90.548) Prec@5 98.047 (97.725)
[2021-04-28 22:41:24 train_lshot.py:257] INFO Epoch: [57][60/150] Time 0.301 (0.421) Data 0.000 (0.109) Loss 0.4168 (0.4262) Prec@1 89.844 (90.247) Prec@5 97.656 (97.746)
[2021-04-28 22:41:27 train_lshot.py:257] INFO Epoch: [57][70/150] Time 0.276 (0.402) Data 0.001 (0.094) Loss 0.4312 (0.4217) Prec@1 91.016 (90.438) Prec@5 96.484 (97.805)
[2021-04-28 22:41:30 train_lshot.py:257] INFO Epoch: [57][80/150] Time 0.282 (0.386) Data 0.000 (0.082) Loss 0.4726 (0.4238) Prec@1 89.062 (90.292) Prec@5 96.484 (97.801)
[2021-04-28 22:41:33 train_lshot.py:257] INFO Epoch: [57][90/150] Time 0.376 (0.377) Data 0.000 (0.073) Loss 0.3862 (0.4232) Prec@1 92.578 (90.277) Prec@5 98.047 (97.806)
[2021-04-28 22:41:36 train_lshot.py:257] INFO Epoch: [57][100/150] Time 0.286 (0.369) Data 0.000 (0.066) Loss 0.5236 (0.4240) Prec@1 86.328 (90.231) Prec@5 95.312 (97.768)
[2021-04-28 22:41:39 train_lshot.py:257] INFO Epoch: [57][110/150] Time 0.280 (0.362) Data 0.000 (0.060) Loss 0.4052 (0.4230) Prec@1 92.578 (90.294) Prec@5 98.438 (97.776)
[2021-04-28 22:41:41 train_lshot.py:257] INFO Epoch: [57][120/150] Time 0.288 (0.356) Data 0.000 (0.055) Loss 0.3825 (0.4251) Prec@1 91.797 (90.170) Prec@5 99.219 (97.753)
[2021-04-28 22:41:44 train_lshot.py:257] INFO Epoch: [57][130/150] Time 0.276 (0.350) Data 0.000 (0.051) Loss 0.3724 (0.4261) Prec@1 92.578 (90.184) Prec@5 97.656 (97.737)
[2021-04-28 22:41:48 train_lshot.py:257] INFO Epoch: [57][140/150] Time 0.377 (0.353) Data 0.000 (0.047) Loss 0.4573 (0.4279) Prec@1 90.234 (90.107) Prec@5 96.484 (97.712)
[2021-04-28 22:41:56 train_lshot.py:257] INFO Epoch: [58][0/150] Time 4.394 (4.394) Data 3.964 (3.964) Loss 0.3469 (0.3469) Prec@1 93.359 (93.359) Prec@5 98.438 (98.438)
[2021-04-28 22:42:00 train_lshot.py:257] INFO Epoch: [58][10/150] Time 0.425 (0.772) Data 0.001 (0.372) Loss 0.4884 (0.4241) Prec@1 87.109 (90.305) Prec@5 95.703 (97.195)
[2021-04-28 22:42:03 train_lshot.py:257] INFO Epoch: [58][20/150] Time 0.302 (0.569) Data 0.001 (0.197) Loss 0.4088 (0.4214) Prec@1 89.844 (90.179) Prec@5 98.828 (97.321)
[2021-04-28 22:42:06 train_lshot.py:257] INFO Epoch: [58][30/150] Time 0.290 (0.477) Data 0.000 (0.133) Loss 0.3848 (0.4188) Prec@1 91.797 (90.499) Prec@5 98.047 (97.480)
[2021-04-28 22:42:09 train_lshot.py:257] INFO Epoch: [58][40/150] Time 0.276 (0.429) Data 0.000 (0.101) Loss 0.4278 (0.4129) Prec@1 91.016 (90.720) Prec@5 97.656 (97.590)
[2021-04-28 22:42:12 train_lshot.py:257] INFO Epoch: [58][50/150] Time 0.275 (0.399) Data 0.000 (0.081) Loss 0.4143 (0.4165) Prec@1 92.969 (90.548) Prec@5 96.484 (97.595)
[2021-04-28 22:42:15 train_lshot.py:257] INFO Epoch: [58][60/150] Time 0.276 (0.380) Data 0.000 (0.068) Loss 0.4031 (0.4172) Prec@1 90.234 (90.523) Prec@5 98.047 (97.682)
[2021-04-28 22:42:17 train_lshot.py:257] INFO Epoch: [58][70/150] Time 0.286 (0.366) Data 0.001 (0.058) Loss 0.3409 (0.4199) Prec@1 94.531 (90.520) Prec@5 99.609 (97.629)
[2021-04-28 22:42:20 train_lshot.py:257] INFO Epoch: [58][80/150] Time 0.280 (0.356) Data 0.000 (0.051) Loss 0.4065 (0.4204) Prec@1 90.234 (90.490) Prec@5 97.656 (97.647)
[2021-04-28 22:42:24 train_lshot.py:257] INFO Epoch: [58][90/150] Time 0.287 (0.362) Data 0.000 (0.046) Loss 0.4558 (0.4220) Prec@1 89.453 (90.496) Prec@5 97.266 (97.618)
[2021-04-28 22:42:27 train_lshot.py:257] INFO Epoch: [58][100/150] Time 0.277 (0.354) Data 0.000 (0.041) Loss 0.4454 (0.4231) Prec@1 87.891 (90.435) Prec@5 97.656 (97.590)
[2021-04-28 22:42:30 train_lshot.py:257] INFO Epoch: [58][110/150] Time 0.280 (0.348) Data 0.000 (0.037) Loss 0.3928 (0.4231) Prec@1 90.625 (90.431) Prec@5 96.875 (97.607)
[2021-04-28 22:42:33 train_lshot.py:257] INFO Epoch: [58][120/150] Time 0.284 (0.342) Data 0.000 (0.034) Loss 0.4028 (0.4225) Prec@1 90.234 (90.464) Prec@5 98.047 (97.618)
[2021-04-28 22:42:36 train_lshot.py:257] INFO Epoch: [58][130/150] Time 0.288 (0.338) Data 0.000 (0.032) Loss 0.4391 (0.4240) Prec@1 89.844 (90.446) Prec@5 97.656 (97.597)
[2021-04-28 22:42:40 train_lshot.py:257] INFO Epoch: [58][140/150] Time 0.393 (0.342) Data 0.000 (0.030) Loss 0.4932 (0.4235) Prec@1 86.719 (90.456) Prec@5 96.484 (97.606)
[2021-04-28 22:42:48 train_lshot.py:257] INFO Epoch: [59][0/150] Time 5.186 (5.186) Data 4.778 (4.778) Loss 0.3413 (0.3413) Prec@1 94.141 (94.141) Prec@5 98.828 (98.828)
[2021-04-28 22:42:52 train_lshot.py:257] INFO Epoch: [59][10/150] Time 0.342 (0.851) Data 0.000 (0.458) Loss 0.3887 (0.4123) Prec@1 89.844 (90.803) Prec@5 98.047 (97.763)
[2021-04-28 22:42:55 train_lshot.py:257] INFO Epoch: [59][20/150] Time 0.279 (0.581) Data 0.000 (0.240) Loss 0.4569 (0.4147) Prec@1 90.234 (90.551) Prec@5 96.484 (97.768)
[2021-04-28 22:42:58 train_lshot.py:257] INFO Epoch: [59][30/150] Time 0.275 (0.486) Data 0.000 (0.163) Loss 0.4064 (0.4115) Prec@1 92.188 (90.902) Prec@5 98.828 (98.009)
[2021-04-28 22:43:01 train_lshot.py:257] INFO Epoch: [59][40/150] Time 0.279 (0.435) Data 0.000 (0.123) Loss 0.4315 (0.4132) Prec@1 88.281 (90.844) Prec@5 98.828 (97.894)
[2021-04-28 22:43:03 train_lshot.py:257] INFO Epoch: [59][50/150] Time 0.294 (0.404) Data 0.000 (0.099) Loss 0.4552 (0.4165) Prec@1 88.672 (90.778) Prec@5 97.266 (97.840)
[2021-04-28 22:43:06 train_lshot.py:257] INFO Epoch: [59][60/150] Time 0.282 (0.385) Data 0.000 (0.083) Loss 0.4692 (0.4156) Prec@1 88.672 (90.830) Prec@5 96.875 (97.848)
[2021-04-28 22:43:09 train_lshot.py:257] INFO Epoch: [59][70/150] Time 0.284 (0.371) Data 0.001 (0.071) Loss 0.4242 (0.4143) Prec@1 91.406 (90.928) Prec@5 98.047 (97.871)
[2021-04-28 22:43:12 train_lshot.py:257] INFO Epoch: [59][80/150] Time 0.293 (0.361) Data 0.000 (0.063) Loss 0.3773 (0.4156) Prec@1 91.797 (90.905) Prec@5 98.438 (97.840)
[2021-04-28 22:43:15 train_lshot.py:257] INFO Epoch: [59][90/150] Time 0.284 (0.353) Data 0.000 (0.056) Loss 0.4373 (0.4163) Prec@1 91.406 (90.792) Prec@5 96.484 (97.819)
[2021-04-28 22:43:18 train_lshot.py:257] INFO Epoch: [59][100/150] Time 0.288 (0.346) Data 0.000 (0.050) Loss 0.3914 (0.4163) Prec@1 91.016 (90.710) Prec@5 98.828 (97.799)
[2021-04-28 22:43:21 train_lshot.py:257] INFO Epoch: [59][110/150] Time 0.285 (0.340) Data 0.000 (0.046) Loss 0.4191 (0.4162) Prec@1 89.453 (90.724) Prec@5 98.047 (97.765)
[2021-04-28 22:43:23 train_lshot.py:257] INFO Epoch: [59][120/150] Time 0.276 (0.336) Data 0.000 (0.042) Loss 0.4631 (0.4172) Prec@1 89.062 (90.680) Prec@5 96.094 (97.743)
[2021-04-28 22:43:26 train_lshot.py:257] INFO Epoch: [59][130/150] Time 0.281 (0.332) Data 0.000 (0.039) Loss 0.4771 (0.4176) Prec@1 87.891 (90.652) Prec@5 97.656 (97.740)
[2021-04-28 22:43:29 train_lshot.py:257] INFO Epoch: [59][140/150] Time 0.297 (0.329) Data 0.000 (0.036) Loss 0.3783 (0.4169) Prec@1 92.969 (90.691) Prec@5 97.656 (97.753)
[2021-04-28 22:44:00 train_lshot.py:119] INFO Meta Val 59: 0.6059733461141587
[2021-04-28 22:44:07 train_lshot.py:257] INFO Epoch: [60][0/150] Time 6.614 (6.614) Data 6.149 (6.149) Loss 0.4447 (0.4447) Prec@1 89.844 (89.844) Prec@5 97.656 (97.656)
[2021-04-28 22:44:10 train_lshot.py:257] INFO Epoch: [60][10/150] Time 0.306 (0.912) Data 0.000 (0.559) Loss 0.4701 (0.4045) Prec@1 89.453 (91.158) Prec@5 97.266 (97.550)
[2021-04-28 22:44:13 train_lshot.py:257] INFO Epoch: [60][20/150] Time 0.273 (0.612) Data 0.000 (0.293) Loss 0.3628 (0.4069) Prec@1 91.016 (90.923) Prec@5 98.438 (97.749)
[2021-04-28 22:44:16 train_lshot.py:257] INFO Epoch: [60][30/150] Time 0.288 (0.505) Data 0.000 (0.199) Loss 0.3459 (0.4115) Prec@1 93.750 (90.839) Prec@5 97.266 (97.593)
[2021-04-28 22:44:19 train_lshot.py:257] INFO Epoch: [60][40/150] Time 0.281 (0.452) Data 0.001 (0.150) Loss 0.3280 (0.4081) Prec@1 94.141 (90.835) Prec@5 99.609 (97.647)
[2021-04-28 22:44:22 train_lshot.py:257] INFO Epoch: [60][50/150] Time 0.279 (0.418) Data 0.000 (0.121) Loss 0.3609 (0.4087) Prec@1 90.625 (90.786) Prec@5 98.828 (97.679)
[2021-04-28 22:44:25 train_lshot.py:257] INFO Epoch: [60][60/150] Time 0.282 (0.396) Data 0.000 (0.101) Loss 0.4383 (0.4072) Prec@1 91.406 (90.920) Prec@5 97.266 (97.695)
[2021-04-28 22:44:27 train_lshot.py:257] INFO Epoch: [60][70/150] Time 0.280 (0.380) Data 0.001 (0.087) Loss 0.4181 (0.4102) Prec@1 90.625 (90.790) Prec@5 97.266 (97.706)
[2021-04-28 22:44:30 train_lshot.py:257] INFO Epoch: [60][80/150] Time 0.274 (0.367) Data 0.000 (0.076) Loss 0.3871 (0.4140) Prec@1 92.578 (90.639) Prec@5 97.656 (97.676)
[2021-04-28 22:44:33 train_lshot.py:257] INFO Epoch: [60][90/150] Time 0.288 (0.358) Data 0.000 (0.068) Loss 0.4452 (0.4151) Prec@1 89.844 (90.595) Prec@5 96.875 (97.648)
[2021-04-28 22:44:36 train_lshot.py:257] INFO Epoch: [60][100/150] Time 0.378 (0.351) Data 0.000 (0.061) Loss 0.4216 (0.4146) Prec@1 90.625 (90.625) Prec@5 98.047 (97.676)
[2021-04-28 22:44:39 train_lshot.py:257] INFO Epoch: [60][110/150] Time 0.284 (0.347) Data 0.000 (0.056) Loss 0.3865 (0.4156) Prec@1 91.016 (90.618) Prec@5 98.438 (97.656)
[2021-04-28 22:44:42 train_lshot.py:257] INFO Epoch: [60][120/150] Time 0.865 (0.346) Data 0.000 (0.051) Loss 0.4260 (0.4157) Prec@1 89.844 (90.602) Prec@5 97.656 (97.663)
[2021-04-28 22:44:46 train_lshot.py:257] INFO Epoch: [60][130/150] Time 0.282 (0.344) Data 0.000 (0.047) Loss 0.3687 (0.4149) Prec@1 92.188 (90.649) Prec@5 97.656 (97.674)
[2021-04-28 22:44:48 train_lshot.py:257] INFO Epoch: [60][140/150] Time 0.284 (0.340) Data 0.000 (0.044) Loss 0.3877 (0.4138) Prec@1 92.578 (90.714) Prec@5 97.656 (97.687)
[2021-04-28 22:44:58 train_lshot.py:257] INFO Epoch: [61][0/150] Time 6.920 (6.920) Data 6.475 (6.475) Loss 0.4130 (0.4130) Prec@1 91.406 (91.406) Prec@5 96.484 (96.484)
[2021-04-28 22:45:02 train_lshot.py:257] INFO Epoch: [61][10/150] Time 0.292 (0.943) Data 0.000 (0.589) Loss 0.3964 (0.4005) Prec@1 90.625 (91.087) Prec@5 98.047 (97.869)
[2021-04-28 22:45:05 train_lshot.py:257] INFO Epoch: [61][20/150] Time 0.285 (0.630) Data 0.000 (0.309) Loss 0.3738 (0.3983) Prec@1 92.578 (91.127) Prec@5 98.047 (97.879)
[2021-04-28 22:45:07 train_lshot.py:257] INFO Epoch: [61][30/150] Time 0.282 (0.520) Data 0.000 (0.209) Loss 0.3984 (0.4001) Prec@1 90.625 (91.116) Prec@5 97.656 (97.858)
[2021-04-28 22:45:10 train_lshot.py:257] INFO Epoch: [61][40/150] Time 0.283 (0.462) Data 0.001 (0.158) Loss 0.3706 (0.4054) Prec@1 92.969 (90.844) Prec@5 98.438 (97.752)
[2021-04-28 22:45:13 train_lshot.py:257] INFO Epoch: [61][50/150] Time 0.281 (0.427) Data 0.000 (0.127) Loss 0.4492 (0.4093) Prec@1 90.234 (90.748) Prec@5 97.266 (97.695)
[2021-04-28 22:45:16 train_lshot.py:257] INFO Epoch: [61][60/150] Time 0.279 (0.403) Data 0.000 (0.107) Loss 0.4326 (0.4072) Prec@1 91.797 (90.747) Prec@5 97.656 (97.829)
[2021-04-28 22:45:19 train_lshot.py:257] INFO Epoch: [61][70/150] Time 0.301 (0.386) Data 0.001 (0.092) Loss 0.3838 (0.4071) Prec@1 92.188 (90.790) Prec@5 98.828 (97.882)
[2021-04-28 22:45:23 train_lshot.py:257] INFO Epoch: [61][80/150] Time 0.291 (0.388) Data 0.001 (0.080) Loss 0.4404 (0.4102) Prec@1 90.625 (90.726) Prec@5 97.656 (97.811)
[2021-04-28 22:45:26 train_lshot.py:257] INFO Epoch: [61][90/150] Time 0.273 (0.377) Data 0.000 (0.072) Loss 0.4430 (0.4099) Prec@1 91.016 (90.719) Prec@5 97.266 (97.802)
[2021-04-28 22:45:28 train_lshot.py:257] INFO Epoch: [61][100/150] Time 0.289 (0.367) Data 0.000 (0.065) Loss 0.4105 (0.4094) Prec@1 89.844 (90.718) Prec@5 98.438 (97.780)
[2021-04-28 22:45:31 train_lshot.py:257] INFO Epoch: [61][110/150] Time 0.279 (0.359) Data 0.000 (0.059) Loss 0.4644 (0.4107) Prec@1 89.062 (90.741) Prec@5 94.531 (97.769)
[2021-04-28 22:45:34 train_lshot.py:257] INFO Epoch: [61][120/150] Time 0.304 (0.353) Data 0.000 (0.054) Loss 0.2749 (0.4104) Prec@1 95.312 (90.780) Prec@5 99.609 (97.792)
[2021-04-28 22:45:37 train_lshot.py:257] INFO Epoch: [61][130/150] Time 0.290 (0.348) Data 0.000 (0.050) Loss 0.4269 (0.4109) Prec@1 89.844 (90.810) Prec@5 97.656 (97.805)
[2021-04-28 22:45:40 train_lshot.py:257] INFO Epoch: [61][140/150] Time 0.347 (0.347) Data 0.000 (0.046) Loss 0.4147 (0.4112) Prec@1 89.453 (90.811) Prec@5 97.266 (97.781)
[2021-04-28 22:45:49 train_lshot.py:257] INFO Epoch: [62][0/150] Time 5.494 (5.494) Data 5.054 (5.054) Loss 0.3506 (0.3506) Prec@1 94.141 (94.141) Prec@5 98.047 (98.047)
[2021-04-28 22:45:55 train_lshot.py:257] INFO Epoch: [62][10/150] Time 0.280 (0.999) Data 0.000 (0.688) Loss 0.3299 (0.3985) Prec@1 93.359 (91.193) Prec@5 99.219 (97.869)
[2021-04-28 22:45:57 train_lshot.py:257] INFO Epoch: [62][20/150] Time 0.276 (0.657) Data 0.001 (0.361) Loss 0.4471 (0.4034) Prec@1 91.797 (91.109) Prec@5 96.484 (97.731)
[2021-04-28 22:46:00 train_lshot.py:257] INFO Epoch: [62][30/150] Time 0.275 (0.537) Data 0.000 (0.244) Loss 0.3437 (0.4064) Prec@1 95.703 (91.053) Prec@5 97.656 (97.606)
[2021-04-28 22:46:03 train_lshot.py:257] INFO Epoch: [62][40/150] Time 0.275 (0.475) Data 0.001 (0.185) Loss 0.3380 (0.4026) Prec@1 94.141 (91.149) Prec@5 98.828 (97.742)
[2021-04-28 22:46:06 train_lshot.py:257] INFO Epoch: [62][50/150] Time 0.285 (0.437) Data 0.000 (0.149) Loss 0.4256 (0.4052) Prec@1 89.844 (91.115) Prec@5 97.656 (97.771)
[2021-04-28 22:46:09 train_lshot.py:257] INFO Epoch: [62][60/150] Time 0.278 (0.411) Data 0.000 (0.124) Loss 0.4021 (0.4032) Prec@1 91.406 (91.144) Prec@5 98.047 (97.855)
[2021-04-28 22:46:11 train_lshot.py:257] INFO Epoch: [62][70/150] Time 0.281 (0.393) Data 0.001 (0.107) Loss 0.5027 (0.4075) Prec@1 86.328 (91.016) Prec@5 95.312 (97.755)
[2021-04-28 22:46:14 train_lshot.py:257] INFO Epoch: [62][80/150] Time 0.283 (0.380) Data 0.000 (0.094) Loss 0.4585 (0.4047) Prec@1 87.891 (91.131) Prec@5 96.875 (97.796)
[2021-04-28 22:46:17 train_lshot.py:257] INFO Epoch: [62][90/150] Time 0.284 (0.369) Data 0.000 (0.084) Loss 0.3494 (0.4070) Prec@1 93.359 (91.024) Prec@5 99.219 (97.802)
[2021-04-28 22:46:20 train_lshot.py:257] INFO Epoch: [62][100/150] Time 0.288 (0.361) Data 0.000 (0.075) Loss 0.4312 (0.4066) Prec@1 89.062 (90.969) Prec@5 96.875 (97.792)
[2021-04-28 22:46:23 train_lshot.py:257] INFO Epoch: [62][110/150] Time 0.294 (0.355) Data 0.000 (0.069) Loss 0.3878 (0.4047) Prec@1 91.797 (91.054) Prec@5 98.828 (97.793)
[2021-04-28 22:46:26 train_lshot.py:257] INFO Epoch: [62][120/150] Time 0.331 (0.352) Data 0.000 (0.063) Loss 0.4350 (0.4055) Prec@1 89.453 (91.025) Prec@5 98.047 (97.779)
[2021-04-28 22:46:29 train_lshot.py:257] INFO Epoch: [62][130/150] Time 0.275 (0.347) Data 0.000 (0.058) Loss 0.4509 (0.4075) Prec@1 89.453 (90.935) Prec@5 97.266 (97.761)
[2021-04-28 22:46:32 train_lshot.py:257] INFO Epoch: [62][140/150] Time 0.291 (0.347) Data 0.000 (0.054) Loss 0.3808 (0.4084) Prec@1 91.016 (90.891) Prec@5 98.047 (97.762)
[2021-04-28 22:46:41 train_lshot.py:257] INFO Epoch: [63][0/150] Time 5.851 (5.851) Data 5.364 (5.364) Loss 0.4751 (0.4751) Prec@1 87.891 (87.891) Prec@5 96.094 (96.094)
[2021-04-28 22:46:45 train_lshot.py:257] INFO Epoch: [63][10/150] Time 0.300 (0.890) Data 0.000 (0.530) Loss 0.3647 (0.3998) Prec@1 93.359 (91.229) Prec@5 98.438 (98.082)
[2021-04-28 22:46:48 train_lshot.py:257] INFO Epoch: [63][20/150] Time 0.280 (0.605) Data 0.000 (0.278) Loss 0.3248 (0.3871) Prec@1 92.578 (91.536) Prec@5 98.438 (97.954)
[2021-04-28 22:46:51 train_lshot.py:257] INFO Epoch: [63][30/150] Time 0.282 (0.500) Data 0.000 (0.188) Loss 0.3675 (0.3927) Prec@1 92.969 (91.356) Prec@5 98.438 (97.845)
[2021-04-28 22:46:54 train_lshot.py:257] INFO Epoch: [63][40/150] Time 0.287 (0.447) Data 0.000 (0.143) Loss 0.4181 (0.3987) Prec@1 91.016 (91.101) Prec@5 98.047 (97.780)
[2021-04-28 22:46:57 train_lshot.py:257] INFO Epoch: [63][50/150] Time 0.293 (0.414) Data 0.000 (0.115) Loss 0.3731 (0.3975) Prec@1 91.797 (91.169) Prec@5 98.047 (97.825)
[2021-04-28 22:46:59 train_lshot.py:257] INFO Epoch: [63][60/150] Time 0.281 (0.393) Data 0.000 (0.096) Loss 0.4329 (0.3993) Prec@1 87.891 (91.105) Prec@5 97.656 (97.810)
[2021-04-28 22:47:04 train_lshot.py:257] INFO Epoch: [63][70/150] Time 0.296 (0.396) Data 0.001 (0.082) Loss 0.3970 (0.4010) Prec@1 90.625 (91.082) Prec@5 98.047 (97.788)
[2021-04-28 22:47:06 train_lshot.py:257] INFO Epoch: [63][80/150] Time 0.273 (0.382) Data 0.000 (0.072) Loss 0.3911 (0.3993) Prec@1 90.625 (91.146) Prec@5 97.656 (97.815)
[2021-04-28 22:47:09 train_lshot.py:257] INFO Epoch: [63][90/150] Time 0.275 (0.371) Data 0.000 (0.064) Loss 0.4824 (0.4021) Prec@1 87.891 (91.050) Prec@5 96.484 (97.776)
[2021-04-28 22:47:12 train_lshot.py:257] INFO Epoch: [63][100/150] Time 0.298 (0.362) Data 0.000 (0.058) Loss 0.3795 (0.4019) Prec@1 93.359 (91.105) Prec@5 98.438 (97.776)
[2021-04-28 22:47:16 train_lshot.py:257] INFO Epoch: [63][110/150] Time 0.585 (0.365) Data 0.000 (0.053) Loss 0.3874 (0.4023) Prec@1 91.016 (91.100) Prec@5 99.609 (97.755)
[2021-04-28 22:47:19 train_lshot.py:257] INFO Epoch: [63][120/150] Time 0.284 (0.361) Data 0.000 (0.049) Loss 0.5249 (0.4020) Prec@1 85.547 (91.087) Prec@5 94.531 (97.785)
[2021-04-28 22:47:22 train_lshot.py:257] INFO Epoch: [63][130/150] Time 0.290 (0.354) Data 0.000 (0.045) Loss 0.3635 (0.4025) Prec@1 93.750 (91.102) Prec@5 98.047 (97.776)
[2021-04-28 22:47:25 train_lshot.py:257] INFO Epoch: [63][140/150] Time 0.276 (0.349) Data 0.000 (0.042) Loss 0.4322 (0.4030) Prec@1 89.453 (91.079) Prec@5 97.656 (97.778)
[2021-04-28 22:47:56 train_lshot.py:119] INFO Meta Val 63: 0.6058133470416069
[2021-04-28 22:48:04 train_lshot.py:257] INFO Epoch: [64][0/150] Time 7.423 (7.423) Data 7.021 (7.021) Loss 0.4279 (0.4279) Prec@1 92.188 (92.188) Prec@5 97.266 (97.266)
[2021-04-28 22:48:07 train_lshot.py:257] INFO Epoch: [64][10/150] Time 0.278 (0.961) Data 0.001 (0.639) Loss 0.3481 (0.4033) Prec@1 93.359 (91.335) Prec@5 98.438 (97.798)
[2021-04-28 22:48:10 train_lshot.py:257] INFO Epoch: [64][20/150] Time 0.277 (0.641) Data 0.000 (0.335) Loss 0.3382 (0.4000) Prec@1 94.922 (91.499) Prec@5 98.828 (97.786)
[2021-04-28 22:48:12 train_lshot.py:257] INFO Epoch: [64][30/150] Time 0.282 (0.524) Data 0.000 (0.227) Loss 0.3953 (0.3958) Prec@1 92.578 (91.469) Prec@5 98.047 (97.807)
[2021-04-28 22:48:15 train_lshot.py:257] INFO Epoch: [64][40/150] Time 0.285 (0.468) Data 0.001 (0.172) Loss 0.3395 (0.3986) Prec@1 91.797 (91.216) Prec@5 98.828 (97.837)
[2021-04-28 22:48:18 train_lshot.py:257] INFO Epoch: [64][50/150] Time 0.288 (0.431) Data 0.000 (0.138) Loss 0.4262 (0.3939) Prec@1 89.062 (91.337) Prec@5 97.656 (97.917)
[2021-04-28 22:48:21 train_lshot.py:257] INFO Epoch: [64][60/150] Time 0.277 (0.407) Data 0.000 (0.116) Loss 0.3739 (0.3947) Prec@1 92.188 (91.272) Prec@5 99.219 (97.951)
[2021-04-28 22:48:24 train_lshot.py:257] INFO Epoch: [64][70/150] Time 0.284 (0.389) Data 0.001 (0.099) Loss 0.3593 (0.3946) Prec@1 92.969 (91.351) Prec@5 98.438 (97.926)
[2021-04-28 22:48:27 train_lshot.py:257] INFO Epoch: [64][80/150] Time 0.275 (0.375) Data 0.000 (0.087) Loss 0.3447 (0.3952) Prec@1 92.578 (91.281) Prec@5 98.438 (97.868)
[2021-04-28 22:48:29 train_lshot.py:257] INFO Epoch: [64][90/150] Time 0.278 (0.365) Data 0.000 (0.078) Loss 0.4250 (0.3989) Prec@1 89.453 (91.153) Prec@5 98.047 (97.819)
[2021-04-28 22:48:32 train_lshot.py:257] INFO Epoch: [64][100/150] Time 0.286 (0.357) Data 0.000 (0.070) Loss 0.4073 (0.4011) Prec@1 91.016 (91.035) Prec@5 98.828 (97.815)
[2021-04-28 22:48:35 train_lshot.py:257] INFO Epoch: [64][110/150] Time 0.285 (0.350) Data 0.000 (0.064) Loss 0.4054 (0.4005) Prec@1 89.844 (91.082) Prec@5 96.484 (97.818)
[2021-04-28 22:48:38 train_lshot.py:257] INFO Epoch: [64][120/150] Time 0.287 (0.345) Data 0.000 (0.058) Loss 0.3505 (0.3996) Prec@1 92.578 (91.145) Prec@5 100.000 (97.856)
[2021-04-28 22:48:41 train_lshot.py:257] INFO Epoch: [64][130/150] Time 0.286 (0.341) Data 0.000 (0.054) Loss 0.4074 (0.3999) Prec@1 91.016 (91.120) Prec@5 98.047 (97.850)
[2021-04-28 22:48:44 train_lshot.py:257] INFO Epoch: [64][140/150] Time 0.286 (0.337) Data 0.000 (0.050) Loss 0.3902 (0.3996) Prec@1 92.188 (91.138) Prec@5 98.438 (97.892)
[2021-04-28 22:48:54 train_lshot.py:257] INFO Epoch: [65][0/150] Time 6.927 (6.927) Data 6.510 (6.510) Loss 0.3751 (0.3751) Prec@1 91.016 (91.016) Prec@5 98.438 (98.438)
[2021-04-28 22:48:57 train_lshot.py:257] INFO Epoch: [65][10/150] Time 0.286 (0.946) Data 0.000 (0.593) Loss 0.4530 (0.3931) Prec@1 90.234 (91.229) Prec@5 97.266 (97.905)
[2021-04-28 22:49:00 train_lshot.py:257] INFO Epoch: [65][20/150] Time 0.275 (0.631) Data 0.000 (0.311) Loss 0.4473 (0.3957) Prec@1 89.453 (91.295) Prec@5 97.266 (97.842)
[2021-04-28 22:49:03 train_lshot.py:257] INFO Epoch: [65][30/150] Time 0.277 (0.523) Data 0.000 (0.211) Loss 0.4252 (0.3987) Prec@1 88.281 (91.154) Prec@5 98.438 (97.921)
[2021-04-28 22:49:06 train_lshot.py:257] INFO Epoch: [65][40/150] Time 0.281 (0.464) Data 0.000 (0.159) Loss 0.4010 (0.4004) Prec@1 89.453 (91.063) Prec@5 98.438 (97.904)
[2021-04-28 22:49:09 train_lshot.py:257] INFO Epoch: [65][50/150] Time 0.277 (0.428) Data 0.000 (0.128) Loss 0.4240 (0.3952) Prec@1 91.016 (91.238) Prec@5 96.094 (97.947)
[2021-04-28 22:49:11 train_lshot.py:257] INFO Epoch: [65][60/150] Time 0.287 (0.404) Data 0.000 (0.107) Loss 0.3694 (0.3945) Prec@1 93.359 (91.310) Prec@5 98.047 (97.983)
[2021-04-28 22:49:14 train_lshot.py:257] INFO Epoch: [65][70/150] Time 0.292 (0.388) Data 0.001 (0.092) Loss 0.4285 (0.3968) Prec@1 91.016 (91.324) Prec@5 98.438 (97.931)
[2021-04-28 22:49:17 train_lshot.py:257] INFO Epoch: [65][80/150] Time 0.282 (0.375) Data 0.000 (0.081) Loss 0.3120 (0.3976) Prec@1 95.703 (91.233) Prec@5 99.609 (98.008)
[2021-04-28 22:49:20 train_lshot.py:257] INFO Epoch: [65][90/150] Time 0.289 (0.368) Data 0.000 (0.072) Loss 0.4138 (0.3974) Prec@1 89.062 (91.170) Prec@5 98.438 (97.987)
[2021-04-28 22:49:23 train_lshot.py:257] INFO Epoch: [65][100/150] Time 0.283 (0.360) Data 0.000 (0.065) Loss 0.3852 (0.3963) Prec@1 94.141 (91.275) Prec@5 99.609 (98.004)
[2021-04-28 22:49:26 train_lshot.py:257] INFO Epoch: [65][110/150] Time 0.289 (0.353) Data 0.000 (0.059) Loss 0.3150 (0.3964) Prec@1 94.922 (91.318) Prec@5 99.219 (98.019)
[2021-04-28 22:49:29 train_lshot.py:257] INFO Epoch: [65][120/150] Time 0.284 (0.348) Data 0.000 (0.054) Loss 0.3853 (0.3974) Prec@1 89.844 (91.209) Prec@5 99.219 (97.986)
[2021-04-28 22:49:32 train_lshot.py:257] INFO Epoch: [65][130/150] Time 0.289 (0.343) Data 0.000 (0.050) Loss 0.3919 (0.3992) Prec@1 91.406 (91.117) Prec@5 98.047 (97.966)
[2021-04-28 22:49:35 train_lshot.py:257] INFO Epoch: [65][140/150] Time 0.300 (0.339) Data 0.000 (0.047) Loss 0.3694 (0.3999) Prec@1 93.359 (91.110) Prec@5 98.828 (97.939)
[2021-04-28 22:49:46 train_lshot.py:257] INFO Epoch: [66][0/150] Time 6.626 (6.626) Data 6.213 (6.213) Loss 0.4031 (0.4031) Prec@1 90.625 (90.625) Prec@5 98.438 (98.438)
[2021-04-28 22:49:49 train_lshot.py:257] INFO Epoch: [66][10/150] Time 0.276 (0.924) Data 0.000 (0.567) Loss 0.4257 (0.3897) Prec@1 89.844 (91.939) Prec@5 97.266 (97.976)
[2021-04-28 22:49:52 train_lshot.py:257] INFO Epoch: [66][20/150] Time 0.280 (0.618) Data 0.000 (0.297) Loss 0.3962 (0.3819) Prec@1 92.969 (92.001) Prec@5 98.438 (98.196)
[2021-04-28 22:49:55 train_lshot.py:257] INFO Epoch: [66][30/150] Time 0.278 (0.512) Data 0.000 (0.201) Loss 0.3423 (0.3895) Prec@1 93.359 (91.671) Prec@5 97.656 (97.996)
[2021-04-28 22:49:58 train_lshot.py:257] INFO Epoch: [66][40/150] Time 0.283 (0.455) Data 0.000 (0.152) Loss 0.3945 (0.3941) Prec@1 89.453 (91.378) Prec@5 97.266 (97.952)
[2021-04-28 22:50:01 train_lshot.py:257] INFO Epoch: [66][50/150] Time 0.281 (0.421) Data 0.000 (0.123) Loss 0.4088 (0.3941) Prec@1 90.234 (91.368) Prec@5 97.656 (97.947)
[2021-04-28 22:50:03 train_lshot.py:257] INFO Epoch: [66][60/150] Time 0.281 (0.398) Data 0.000 (0.102) Loss 0.3588 (0.3912) Prec@1 92.188 (91.477) Prec@5 97.656 (97.996)
[2021-04-28 22:50:06 train_lshot.py:257] INFO Epoch: [66][70/150] Time 0.281 (0.382) Data 0.001 (0.088) Loss 0.3907 (0.3911) Prec@1 92.188 (91.439) Prec@5 98.047 (98.036)
[2021-04-28 22:50:09 train_lshot.py:257] INFO Epoch: [66][80/150] Time 0.285 (0.369) Data 0.000 (0.077) Loss 0.3551 (0.3911) Prec@1 94.141 (91.430) Prec@5 98.438 (98.013)
[2021-04-28 22:50:12 train_lshot.py:257] INFO Epoch: [66][90/150] Time 0.285 (0.359) Data 0.000 (0.069) Loss 0.3855 (0.3941) Prec@1 93.750 (91.415) Prec@5 97.656 (97.935)
[2021-04-28 22:50:15 train_lshot.py:257] INFO Epoch: [66][100/150] Time 0.293 (0.352) Data 0.000 (0.062) Loss 0.3836 (0.3935) Prec@1 91.016 (91.426) Prec@5 98.047 (97.919)
[2021-04-28 22:50:18 train_lshot.py:257] INFO Epoch: [66][110/150] Time 0.283 (0.346) Data 0.000 (0.056) Loss 0.4117 (0.3947) Prec@1 90.234 (91.392) Prec@5 97.656 (97.885)
[2021-04-28 22:50:21 train_lshot.py:257] INFO Epoch: [66][120/150] Time 1.235 (0.349) Data 0.000 (0.052) Loss 0.4092 (0.3957) Prec@1 90.234 (91.387) Prec@5 96.875 (97.860)
[2021-04-28 22:50:25 train_lshot.py:257] INFO Epoch: [66][130/150] Time 0.285 (0.348) Data 0.000 (0.048) Loss 0.4143 (0.3969) Prec@1 89.453 (91.365) Prec@5 98.438 (97.832)
[2021-04-28 22:50:28 train_lshot.py:257] INFO Epoch: [66][140/150] Time 0.278 (0.343) Data 0.000 (0.044) Loss 0.4419 (0.3977) Prec@1 90.625 (91.290) Prec@5 96.484 (97.834)
[2021-04-28 22:50:36 train_lshot.py:257] INFO Epoch: [67][0/150] Time 5.479 (5.479) Data 5.086 (5.086) Loss 0.4355 (0.4355) Prec@1 90.625 (90.625) Prec@5 97.266 (97.266)
[2021-04-28 22:50:40 train_lshot.py:257] INFO Epoch: [67][10/150] Time 0.358 (0.846) Data 0.001 (0.463) Loss 0.3519 (0.3840) Prec@1 92.969 (92.152) Prec@5 98.438 (97.976)
[2021-04-28 22:50:43 train_lshot.py:257] INFO Epoch: [67][20/150] Time 0.286 (0.589) Data 0.000 (0.243) Loss 0.3917 (0.3844) Prec@1 89.062 (92.020) Prec@5 98.828 (98.177)
[2021-04-28 22:50:46 train_lshot.py:257] INFO Epoch: [67][30/150] Time 0.275 (0.492) Data 0.000 (0.165) Loss 0.4341 (0.3901) Prec@1 87.891 (91.759) Prec@5 96.875 (97.984)
[2021-04-28 22:50:49 train_lshot.py:257] INFO Epoch: [67][40/150] Time 0.287 (0.441) Data 0.000 (0.125) Loss 0.4015 (0.3841) Prec@1 90.234 (91.835) Prec@5 96.875 (97.999)
[2021-04-28 22:50:51 train_lshot.py:257] INFO Epoch: [67][50/150] Time 0.294 (0.410) Data 0.000 (0.100) Loss 0.4254 (0.3886) Prec@1 90.234 (91.621) Prec@5 98.047 (97.970)
[2021-04-28 22:50:54 train_lshot.py:257] INFO Epoch: [67][60/150] Time 0.290 (0.389) Data 0.000 (0.084) Loss 0.3634 (0.3896) Prec@1 92.188 (91.586) Prec@5 99.609 (98.047)
[2021-04-28 22:50:57 train_lshot.py:257] INFO Epoch: [67][70/150] Time 0.281 (0.374) Data 0.001 (0.072) Loss 0.3558 (0.3890) Prec@1 91.016 (91.571) Prec@5 99.219 (98.025)
[2021-04-28 22:51:00 train_lshot.py:257] INFO Epoch: [67][80/150] Time 0.281 (0.363) Data 0.000 (0.063) Loss 0.4075 (0.3912) Prec@1 92.578 (91.517) Prec@5 98.047 (97.960)
[2021-04-28 22:51:03 train_lshot.py:257] INFO Epoch: [67][90/150] Time 0.293 (0.357) Data 0.000 (0.056) Loss 0.3984 (0.3921) Prec@1 91.406 (91.509) Prec@5 96.875 (97.944)
[2021-04-28 22:51:06 train_lshot.py:257] INFO Epoch: [67][100/150] Time 0.289 (0.349) Data 0.000 (0.051) Loss 0.4100 (0.3933) Prec@1 91.406 (91.511) Prec@5 97.656 (97.904)
[2021-04-28 22:51:09 train_lshot.py:257] INFO Epoch: [67][110/150] Time 0.278 (0.343) Data 0.000 (0.046) Loss 0.3841 (0.3935) Prec@1 91.016 (91.519) Prec@5 98.438 (97.899)
[2021-04-28 22:51:12 train_lshot.py:257] INFO Epoch: [67][120/150] Time 0.281 (0.339) Data 0.000 (0.042) Loss 0.3420 (0.3921) Prec@1 91.406 (91.584) Prec@5 99.219 (97.911)
[2021-04-28 22:51:15 train_lshot.py:257] INFO Epoch: [67][130/150] Time 0.377 (0.341) Data 0.000 (0.039) Loss 0.4123 (0.3924) Prec@1 90.234 (91.537) Prec@5 99.219 (97.925)
[2021-04-28 22:51:18 train_lshot.py:257] INFO Epoch: [67][140/150] Time 0.279 (0.338) Data 0.000 (0.036) Loss 0.3962 (0.3936) Prec@1 90.625 (91.478) Prec@5 97.656 (97.906)
[2021-04-28 22:51:49 train_lshot.py:119] INFO Meta Val 67: 0.595360013127327
[2021-04-28 22:51:56 train_lshot.py:257] INFO Epoch: [68][0/150] Time 6.266 (6.266) Data 5.823 (5.823) Loss 0.4528 (0.4528) Prec@1 90.234 (90.234) Prec@5 98.438 (98.438)
[2021-04-28 22:51:59 train_lshot.py:257] INFO Epoch: [68][10/150] Time 0.324 (0.892) Data 0.001 (0.531) Loss 0.4069 (0.4277) Prec@1 91.016 (90.518) Prec@5 97.656 (97.869)
[2021-04-28 22:52:02 train_lshot.py:257] INFO Epoch: [68][20/150] Time 0.283 (0.602) Data 0.000 (0.278) Loss 0.3929 (0.4192) Prec@1 92.188 (90.644) Prec@5 98.828 (97.991)
[2021-04-28 22:52:05 train_lshot.py:257] INFO Epoch: [68][30/150] Time 0.275 (0.498) Data 0.000 (0.189) Loss 0.3633 (0.4081) Prec@1 92.188 (91.205) Prec@5 99.219 (98.022)
[2021-04-28 22:52:08 train_lshot.py:257] INFO Epoch: [68][40/150] Time 0.273 (0.447) Data 0.000 (0.143) Loss 0.3048 (0.4023) Prec@1 94.531 (91.387) Prec@5 99.609 (97.990)
[2021-04-28 22:52:11 train_lshot.py:257] INFO Epoch: [68][50/150] Time 0.282 (0.414) Data 0.000 (0.115) Loss 0.4302 (0.3998) Prec@1 88.672 (91.368) Prec@5 96.875 (98.047)
[2021-04-28 22:52:13 train_lshot.py:257] INFO Epoch: [68][60/150] Time 0.286 (0.393) Data 0.000 (0.096) Loss 0.3123 (0.3958) Prec@1 93.750 (91.509) Prec@5 99.609 (98.053)
[2021-04-28 22:52:16 train_lshot.py:257] INFO Epoch: [68][70/150] Time 0.289 (0.378) Data 0.001 (0.083) Loss 0.4393 (0.3980) Prec@1 90.234 (91.445) Prec@5 97.656 (97.970)
[2021-04-28 22:52:19 train_lshot.py:257] INFO Epoch: [68][80/150] Time 0.285 (0.366) Data 0.000 (0.072) Loss 0.3701 (0.3944) Prec@1 92.969 (91.541) Prec@5 98.047 (97.979)
[2021-04-28 22:52:22 train_lshot.py:257] INFO Epoch: [68][90/150] Time 0.276 (0.356) Data 0.000 (0.064) Loss 0.4089 (0.3941) Prec@1 91.797 (91.539) Prec@5 97.656 (97.991)
[2021-04-28 22:52:25 train_lshot.py:257] INFO Epoch: [68][100/150] Time 0.287 (0.349) Data 0.000 (0.058) Loss 0.3485 (0.3926) Prec@1 92.188 (91.611) Prec@5 99.219 (97.997)
[2021-04-28 22:52:28 train_lshot.py:257] INFO Epoch: [68][110/150] Time 0.286 (0.343) Data 0.000 (0.053) Loss 0.3608 (0.3924) Prec@1 92.188 (91.596) Prec@5 98.047 (98.015)
[2021-04-28 22:52:32 train_lshot.py:257] INFO Epoch: [68][120/150] Time 0.296 (0.349) Data 0.000 (0.049) Loss 0.4365 (0.3914) Prec@1 90.234 (91.639) Prec@5 97.656 (98.028)
[2021-04-28 22:52:35 train_lshot.py:257] INFO Epoch: [68][130/150] Time 0.273 (0.344) Data 0.000 (0.045) Loss 0.3781 (0.3895) Prec@1 91.016 (91.681) Prec@5 97.656 (98.029)
[2021-04-28 22:52:37 train_lshot.py:257] INFO Epoch: [68][140/150] Time 0.287 (0.340) Data 0.000 (0.042) Loss 0.3681 (0.3884) Prec@1 92.578 (91.717) Prec@5 98.438 (98.036)
[2021-04-28 22:52:47 train_lshot.py:257] INFO Epoch: [69][0/150] Time 6.404 (6.404) Data 5.955 (5.955) Loss 0.3368 (0.3368) Prec@1 93.750 (93.750) Prec@5 98.438 (98.438)
[2021-04-28 22:52:50 train_lshot.py:257] INFO Epoch: [69][10/150] Time 0.300 (0.908) Data 0.000 (0.543) Loss 0.3518 (0.3819) Prec@1 92.969 (91.655) Prec@5 98.828 (97.869)
[2021-04-28 22:52:53 train_lshot.py:257] INFO Epoch: [69][20/150] Time 0.283 (0.609) Data 0.000 (0.284) Loss 0.4060 (0.3864) Prec@1 90.234 (91.406) Prec@5 97.656 (97.898)
[2021-04-28 22:52:56 train_lshot.py:257] INFO Epoch: [69][30/150] Time 0.281 (0.508) Data 0.001 (0.193) Loss 0.3703 (0.3889) Prec@1 92.188 (91.394) Prec@5 98.438 (97.971)
[2021-04-28 22:52:59 train_lshot.py:257] INFO Epoch: [69][40/150] Time 0.281 (0.453) Data 0.000 (0.146) Loss 0.4442 (0.3854) Prec@1 88.672 (91.492) Prec@5 97.266 (97.980)
[2021-04-28 22:53:02 train_lshot.py:257] INFO Epoch: [69][50/150] Time 0.278 (0.420) Data 0.000 (0.118) Loss 0.4080 (0.3845) Prec@1 90.625 (91.468) Prec@5 98.438 (97.963)
[2021-04-28 22:53:05 train_lshot.py:257] INFO Epoch: [69][60/150] Time 0.281 (0.397) Data 0.000 (0.098) Loss 0.3511 (0.3831) Prec@1 91.797 (91.522) Prec@5 97.656 (97.938)
[2021-04-28 22:53:08 train_lshot.py:257] INFO Epoch: [69][70/150] Time 0.293 (0.382) Data 0.001 (0.085) Loss 0.3924 (0.3828) Prec@1 91.016 (91.549) Prec@5 97.266 (97.926)
[2021-04-28 22:53:11 train_lshot.py:257] INFO Epoch: [69][80/150] Time 0.296 (0.374) Data 0.000 (0.074) Loss 0.4114 (0.3827) Prec@1 89.844 (91.575) Prec@5 97.266 (97.907)
[2021-04-28 22:53:14 train_lshot.py:257] INFO Epoch: [69][90/150] Time 0.510 (0.369) Data 0.000 (0.066) Loss 0.3978 (0.3836) Prec@1 92.188 (91.518) Prec@5 98.438 (97.901)
[2021-04-28 22:53:17 train_lshot.py:257] INFO Epoch: [69][100/150] Time 0.285 (0.363) Data 0.000 (0.059) Loss 0.4111 (0.3834) Prec@1 91.016 (91.538) Prec@5 97.656 (97.931)
[2021-04-28 22:53:20 train_lshot.py:257] INFO Epoch: [69][110/150] Time 0.279 (0.356) Data 0.000 (0.054) Loss 0.3383 (0.3823) Prec@1 94.141 (91.610) Prec@5 98.047 (97.955)
[2021-04-28 22:53:23 train_lshot.py:257] INFO Epoch: [69][120/150] Time 0.291 (0.350) Data 0.000 (0.050) Loss 0.4127 (0.3831) Prec@1 89.062 (91.600) Prec@5 97.656 (97.953)
[2021-04-28 22:53:26 train_lshot.py:257] INFO Epoch: [69][130/150] Time 0.292 (0.345) Data 0.000 (0.046) Loss 0.4039 (0.3842) Prec@1 90.625 (91.558) Prec@5 98.047 (97.975)
[2021-04-28 22:53:29 train_lshot.py:257] INFO Epoch: [69][140/150] Time 0.288 (0.341) Data 0.000 (0.043) Loss 0.3914 (0.3855) Prec@1 90.625 (91.514) Prec@5 98.047 (97.964)
[2021-04-28 22:53:36 train_lshot.py:257] INFO Epoch: [70][0/150] Time 4.093 (4.093) Data 3.658 (3.658) Loss 0.3714 (0.3714) Prec@1 92.969 (92.969) Prec@5 97.266 (97.266)
[2021-04-28 22:53:41 train_lshot.py:257] INFO Epoch: [70][10/150] Time 0.299 (0.894) Data 0.000 (0.529) Loss 0.3637 (0.3691) Prec@1 91.797 (92.436) Prec@5 98.828 (98.295)
[2021-04-28 22:53:44 train_lshot.py:257] INFO Epoch: [70][20/150] Time 0.277 (0.610) Data 0.000 (0.277) Loss 0.3962 (0.3713) Prec@1 91.016 (92.020) Prec@5 97.656 (98.158)
[2021-04-28 22:53:47 train_lshot.py:257] INFO Epoch: [70][30/150] Time 0.286 (0.504) Data 0.000 (0.188) Loss 0.3839 (0.3762) Prec@1 90.625 (91.923) Prec@5 98.047 (98.085)
[2021-04-28 22:53:50 train_lshot.py:257] INFO Epoch: [70][40/150] Time 0.284 (0.450) Data 0.000 (0.142) Loss 0.3643 (0.3721) Prec@1 93.750 (91.873) Prec@5 97.656 (98.075)
[2021-04-28 22:53:53 train_lshot.py:257] INFO Epoch: [70][50/150] Time 0.278 (0.417) Data 0.001 (0.114) Loss 0.3190 (0.3717) Prec@1 92.969 (91.858) Prec@5 98.828 (98.131)
[2021-04-28 22:53:56 train_lshot.py:257] INFO Epoch: [70][60/150] Time 0.276 (0.395) Data 0.000 (0.096) Loss 0.3667 (0.3734) Prec@1 91.797 (91.778) Prec@5 99.219 (98.169)
[2021-04-28 22:53:59 train_lshot.py:257] INFO Epoch: [70][70/150] Time 0.290 (0.380) Data 0.001 (0.082) Loss 0.3914 (0.3763) Prec@1 91.406 (91.698) Prec@5 98.438 (98.113)
[2021-04-28 22:54:02 train_lshot.py:257] INFO Epoch: [70][80/150] Time 0.510 (0.371) Data 0.000 (0.072) Loss 0.3353 (0.3749) Prec@1 95.703 (91.860) Prec@5 98.438 (98.119)
[2021-04-28 22:54:05 train_lshot.py:257] INFO Epoch: [70][90/150] Time 0.283 (0.366) Data 0.000 (0.064) Loss 0.3392 (0.3729) Prec@1 94.531 (91.934) Prec@5 98.047 (98.154)
[2021-04-28 22:54:08 train_lshot.py:257] INFO Epoch: [70][100/150] Time 0.286 (0.357) Data 0.000 (0.058) Loss 0.4608 (0.3734) Prec@1 89.062 (91.963) Prec@5 95.312 (98.163)
[2021-04-28 22:54:11 train_lshot.py:257] INFO Epoch: [70][110/150] Time 0.296 (0.352) Data 0.000 (0.053) Loss 0.3272 (0.3741) Prec@1 95.312 (91.976) Prec@5 98.828 (98.131)
[2021-04-28 22:54:15 train_lshot.py:257] INFO Epoch: [70][120/150] Time 0.530 (0.356) Data 0.000 (0.048) Loss 0.3689 (0.3740) Prec@1 91.797 (91.939) Prec@5 97.656 (98.160)
[2021-04-28 22:54:18 train_lshot.py:257] INFO Epoch: [70][130/150] Time 0.280 (0.353) Data 0.000 (0.045) Loss 0.4191 (0.3748) Prec@1 91.016 (91.922) Prec@5 96.484 (98.124)
[2021-04-28 22:54:21 train_lshot.py:257] INFO Epoch: [70][140/150] Time 0.285 (0.348) Data 0.000 (0.042) Loss 0.4283 (0.3750) Prec@1 90.234 (91.958) Prec@5 97.266 (98.122)
[2021-04-28 22:54:30 train_lshot.py:257] INFO Epoch: [71][0/150] Time 6.610 (6.610) Data 6.195 (6.195) Loss 0.4174 (0.4174) Prec@1 92.188 (92.188) Prec@5 97.656 (97.656)
[2021-04-28 22:54:34 train_lshot.py:257] INFO Epoch: [71][10/150] Time 0.284 (0.914) Data 0.000 (0.565) Loss 0.4267 (0.3810) Prec@1 90.234 (92.045) Prec@5 97.266 (97.869)
[2021-04-28 22:54:37 train_lshot.py:257] INFO Epoch: [71][20/150] Time 0.278 (0.617) Data 0.000 (0.296) Loss 0.3894 (0.3749) Prec@1 93.359 (92.299) Prec@5 98.047 (97.954)
[2021-04-28 22:54:39 train_lshot.py:257] INFO Epoch: [71][30/150] Time 0.286 (0.511) Data 0.000 (0.201) Loss 0.3933 (0.3788) Prec@1 91.406 (91.973) Prec@5 98.438 (97.984)
[2021-04-28 22:54:42 train_lshot.py:257] INFO Epoch: [71][40/150] Time 0.281 (0.455) Data 0.001 (0.152) Loss 0.4131 (0.3816) Prec@1 89.844 (91.902) Prec@5 97.266 (98.018)
[2021-04-28 22:54:45 train_lshot.py:257] INFO Epoch: [71][50/150] Time 0.277 (0.421) Data 0.000 (0.122) Loss 0.4064 (0.3782) Prec@1 90.625 (91.950) Prec@5 97.266 (98.085)
[2021-04-28 22:54:48 train_lshot.py:257] INFO Epoch: [71][60/150] Time 0.281 (0.399) Data 0.000 (0.102) Loss 0.3831 (0.3792) Prec@1 90.625 (91.880) Prec@5 99.219 (98.066)
[2021-04-28 22:54:51 train_lshot.py:257] INFO Epoch: [71][70/150] Time 0.295 (0.382) Data 0.001 (0.088) Loss 0.3712 (0.3822) Prec@1 92.188 (91.808) Prec@5 98.047 (98.014)
[2021-04-28 22:54:54 train_lshot.py:257] INFO Epoch: [71][80/150] Time 0.284 (0.370) Data 0.000 (0.077) Loss 0.4105 (0.3821) Prec@1 91.406 (91.792) Prec@5 98.828 (98.032)
[2021-04-28 22:54:57 train_lshot.py:257] INFO Epoch: [71][90/150] Time 0.357 (0.364) Data 0.000 (0.069) Loss 0.4023 (0.3814) Prec@1 91.016 (91.767) Prec@5 98.047 (98.004)
[2021-04-28 22:55:00 train_lshot.py:257] INFO Epoch: [71][100/150] Time 0.274 (0.357) Data 0.000 (0.062) Loss 0.3551 (0.3799) Prec@1 91.406 (91.805) Prec@5 99.219 (98.078)
[2021-04-28 22:55:04 train_lshot.py:257] INFO Epoch: [71][110/150] Time 0.327 (0.362) Data 0.000 (0.056) Loss 0.4034 (0.3796) Prec@1 91.797 (91.839) Prec@5 97.656 (98.064)
[2021-04-28 22:55:07 train_lshot.py:257] INFO Epoch: [71][120/150] Time 0.278 (0.356) Data 0.000 (0.052) Loss 0.3940 (0.3797) Prec@1 91.016 (91.842) Prec@5 97.266 (98.066)
[2021-04-28 22:55:10 train_lshot.py:257] INFO Epoch: [71][130/150] Time 0.275 (0.350) Data 0.000 (0.048) Loss 0.3379 (0.3810) Prec@1 93.359 (91.788) Prec@5 99.219 (98.083)
[2021-04-28 22:55:12 train_lshot.py:257] INFO Epoch: [71][140/150] Time 0.280 (0.346) Data 0.000 (0.044) Loss 0.3722 (0.3807) Prec@1 89.844 (91.772) Prec@5 99.219 (98.097)
[2021-04-28 22:55:43 train_lshot.py:119] INFO Meta Val 71: 0.6085066797733307
[2021-04-28 22:55:49 train_lshot.py:257] INFO Epoch: [72][0/150] Time 6.066 (6.066) Data 5.640 (5.640) Loss 0.4083 (0.4083) Prec@1 91.406 (91.406) Prec@5 99.219 (99.219)
[2021-04-28 22:55:53 train_lshot.py:257] INFO Epoch: [72][10/150] Time 0.340 (0.903) Data 0.003 (0.542) Loss 0.3598 (0.3623) Prec@1 91.016 (92.223) Prec@5 99.609 (98.402)
[2021-04-28 22:55:56 train_lshot.py:257] INFO Epoch: [72][20/150] Time 0.291 (0.613) Data 0.000 (0.284) Loss 0.3809 (0.3808) Prec@1 92.578 (91.815) Prec@5 97.656 (98.084)
[2021-04-28 22:55:59 train_lshot.py:257] INFO Epoch: [72][30/150] Time 0.286 (0.507) Data 0.000 (0.193) Loss 0.4143 (0.3850) Prec@1 91.016 (91.620) Prec@5 96.484 (97.959)
[2021-04-28 22:56:02 train_lshot.py:257] INFO Epoch: [72][40/150] Time 0.276 (0.453) Data 0.001 (0.146) Loss 0.3986 (0.3805) Prec@1 89.062 (91.597) Prec@5 98.047 (98.075)
[2021-04-28 22:56:05 train_lshot.py:257] INFO Epoch: [72][50/150] Time 0.298 (0.420) Data 0.000 (0.117) Loss 0.4167 (0.3813) Prec@1 89.062 (91.636) Prec@5 96.484 (98.047)
[2021-04-28 22:56:08 train_lshot.py:257] INFO Epoch: [72][60/150] Time 0.277 (0.397) Data 0.000 (0.098) Loss 0.3327 (0.3785) Prec@1 93.750 (91.810) Prec@5 98.438 (98.137)
[2021-04-28 22:56:10 train_lshot.py:257] INFO Epoch: [72][70/150] Time 0.295 (0.381) Data 0.002 (0.084) Loss 0.3349 (0.3775) Prec@1 93.750 (91.951) Prec@5 98.047 (98.107)
[2021-04-28 22:56:13 train_lshot.py:257] INFO Epoch: [72][80/150] Time 0.275 (0.369) Data 0.000 (0.074) Loss 0.3707 (0.3770) Prec@1 93.359 (91.956) Prec@5 98.047 (98.119)
[2021-04-28 22:56:16 train_lshot.py:257] INFO Epoch: [72][90/150] Time 0.283 (0.359) Data 0.000 (0.066) Loss 0.3563 (0.3788) Prec@1 91.016 (91.939) Prec@5 98.828 (98.081)
[2021-04-28 22:56:19 train_lshot.py:257] INFO Epoch: [72][100/150] Time 0.287 (0.352) Data 0.000 (0.060) Loss 0.3660 (0.3780) Prec@1 91.016 (91.921) Prec@5 98.828 (98.124)
[2021-04-28 22:56:22 train_lshot.py:257] INFO Epoch: [72][110/150] Time 0.277 (0.346) Data 0.000 (0.054) Loss 0.3661 (0.3785) Prec@1 92.969 (91.917) Prec@5 98.047 (98.107)
[2021-04-28 22:56:26 train_lshot.py:257] INFO Epoch: [72][120/150] Time 0.290 (0.350) Data 0.000 (0.050) Loss 0.3438 (0.3787) Prec@1 94.141 (91.920) Prec@5 98.828 (98.099)
[2021-04-28 22:56:28 train_lshot.py:257] INFO Epoch: [72][130/150] Time 0.278 (0.345) Data 0.001 (0.046) Loss 0.3572 (0.3789) Prec@1 93.359 (91.925) Prec@5 97.266 (98.118)
[2021-04-28 22:56:32 train_lshot.py:257] INFO Epoch: [72][140/150] Time 0.298 (0.347) Data 0.000 (0.043) Loss 0.3979 (0.3790) Prec@1 91.016 (91.927) Prec@5 96.484 (98.102)
[2021-04-28 22:56:41 train_lshot.py:257] INFO Epoch: [73][0/150] Time 5.827 (5.827) Data 5.432 (5.432) Loss 0.3683 (0.3683) Prec@1 91.016 (91.016) Prec@5 97.266 (97.266)
[2021-04-28 22:56:45 train_lshot.py:257] INFO Epoch: [73][10/150] Time 0.387 (0.891) Data 0.000 (0.507) Loss 0.3516 (0.3804) Prec@1 91.797 (91.797) Prec@5 97.656 (98.153)
[2021-04-28 22:56:48 train_lshot.py:257] INFO Epoch: [73][20/150] Time 0.278 (0.602) Data 0.000 (0.266) Loss 0.3876 (0.3724) Prec@1 89.844 (92.039) Prec@5 98.047 (98.251)
[2021-04-28 22:56:51 train_lshot.py:257] INFO Epoch: [73][30/150] Time 0.275 (0.504) Data 0.000 (0.180) Loss 0.4453 (0.3793) Prec@1 90.625 (91.923) Prec@5 96.094 (98.059)
[2021-04-28 22:56:54 train_lshot.py:257] INFO Epoch: [73][40/150] Time 0.280 (0.450) Data 0.000 (0.136) Loss 0.3692 (0.3756) Prec@1 91.016 (91.873) Prec@5 98.828 (98.161)
[2021-04-28 22:56:57 train_lshot.py:257] INFO Epoch: [73][50/150] Time 0.295 (0.417) Data 0.000 (0.110) Loss 0.3867 (0.3786) Prec@1 92.188 (91.805) Prec@5 96.875 (98.100)
[2021-04-28 22:57:00 train_lshot.py:257] INFO Epoch: [73][60/150] Time 0.278 (0.395) Data 0.000 (0.092) Loss 0.3289 (0.3768) Prec@1 94.141 (91.931) Prec@5 99.219 (98.137)
[2021-04-28 22:57:02 train_lshot.py:257] INFO Epoch: [73][70/150] Time 0.288 (0.379) Data 0.001 (0.079) Loss 0.3484 (0.3765) Prec@1 92.969 (91.912) Prec@5 99.219 (98.151)
[2021-04-28 22:57:05 train_lshot.py:257] INFO Epoch: [73][80/150] Time 0.303 (0.370) Data 0.000 (0.069) Loss 0.3815 (0.3792) Prec@1 92.578 (91.826) Prec@5 96.875 (98.057)
[2021-04-28 22:57:08 train_lshot.py:257] INFO Epoch: [73][90/150] Time 0.285 (0.361) Data 0.000 (0.062) Loss 0.4446 (0.3810) Prec@1 89.062 (91.780) Prec@5 96.484 (98.000)
[2021-04-28 22:57:12 train_lshot.py:257] INFO Epoch: [73][100/150] Time 0.350 (0.360) Data 0.000 (0.056) Loss 0.3700 (0.3800) Prec@1 92.969 (91.774) Prec@5 98.828 (98.008)
[2021-04-28 22:57:15 train_lshot.py:257] INFO Epoch: [73][110/150] Time 0.275 (0.354) Data 0.000 (0.051) Loss 0.3602 (0.3803) Prec@1 93.359 (91.776) Prec@5 98.438 (98.026)
[2021-04-28 22:57:18 train_lshot.py:257] INFO Epoch: [73][120/150] Time 0.282 (0.348) Data 0.000 (0.046) Loss 0.4378 (0.3810) Prec@1 89.062 (91.758) Prec@5 97.656 (97.998)
[2021-04-28 22:57:20 train_lshot.py:257] INFO Epoch: [73][130/150] Time 0.285 (0.344) Data 0.000 (0.043) Loss 0.3027 (0.3809) Prec@1 95.312 (91.770) Prec@5 98.438 (97.981)
[2021-04-28 22:57:23 train_lshot.py:257] INFO Epoch: [73][140/150] Time 0.285 (0.340) Data 0.000 (0.040) Loss 0.4774 (0.3809) Prec@1 89.062 (91.805) Prec@5 97.656 (97.997)
[2021-04-28 22:57:33 train_lshot.py:257] INFO Epoch: [74][0/150] Time 6.950 (6.950) Data 6.498 (6.498) Loss 0.3885 (0.3885) Prec@1 91.016 (91.016) Prec@5 97.266 (97.266)
[2021-04-28 22:57:37 train_lshot.py:257] INFO Epoch: [74][10/150] Time 0.282 (0.932) Data 0.000 (0.591) Loss 0.4298 (0.3775) Prec@1 91.797 (91.584) Prec@5 96.484 (98.082)
[2021-04-28 22:57:39 train_lshot.py:257] INFO Epoch: [74][20/150] Time 0.284 (0.622) Data 0.000 (0.310) Loss 0.3762 (0.3666) Prec@1 91.406 (92.076) Prec@5 98.438 (98.233)
[2021-04-28 22:57:42 train_lshot.py:257] INFO Epoch: [74][30/150] Time 0.283 (0.515) Data 0.000 (0.210) Loss 0.3513 (0.3689) Prec@1 93.750 (91.973) Prec@5 98.828 (98.160)
[2021-04-28 22:57:45 train_lshot.py:257] INFO Epoch: [74][40/150] Time 0.278 (0.458) Data 0.001 (0.159) Loss 0.4182 (0.3768) Prec@1 87.891 (91.673) Prec@5 96.875 (98.085)
[2021-04-28 22:57:48 train_lshot.py:257] INFO Epoch: [74][50/150] Time 0.288 (0.423) Data 0.000 (0.128) Loss 0.3429 (0.3783) Prec@1 92.578 (91.644) Prec@5 98.047 (98.085)
[2021-04-28 22:57:51 train_lshot.py:257] INFO Epoch: [74][60/150] Time 0.287 (0.400) Data 0.000 (0.107) Loss 0.3836 (0.3772) Prec@1 91.797 (91.746) Prec@5 97.266 (98.104)
[2021-04-28 22:57:54 train_lshot.py:257] INFO Epoch: [74][70/150] Time 0.284 (0.384) Data 0.001 (0.092) Loss 0.4279 (0.3776) Prec@1 92.188 (91.775) Prec@5 96.484 (98.058)
[2021-04-28 22:57:56 train_lshot.py:257] INFO Epoch: [74][80/150] Time 0.283 (0.371) Data 0.000 (0.081) Loss 0.3683 (0.3784) Prec@1 90.625 (91.734) Prec@5 98.828 (98.003)
[2021-04-28 22:57:59 train_lshot.py:257] INFO Epoch: [74][90/150] Time 0.290 (0.362) Data 0.000 (0.072) Loss 0.3812 (0.3783) Prec@1 91.797 (91.728) Prec@5 98.828 (98.004)
[2021-04-28 22:58:03 train_lshot.py:257] INFO Epoch: [74][100/150] Time 0.359 (0.358) Data 0.001 (0.065) Loss 0.3882 (0.3772) Prec@1 92.188 (91.727) Prec@5 98.438 (98.058)
[2021-04-28 22:58:06 train_lshot.py:257] INFO Epoch: [74][110/150] Time 0.278 (0.353) Data 0.000 (0.059) Loss 0.3152 (0.3763) Prec@1 93.359 (91.790) Prec@5 97.656 (98.075)
[2021-04-28 22:58:09 train_lshot.py:257] INFO Epoch: [74][120/150] Time 0.332 (0.354) Data 0.000 (0.054) Loss 0.4758 (0.3780) Prec@1 89.453 (91.716) Prec@5 97.266 (98.063)
[2021-04-28 22:58:12 train_lshot.py:257] INFO Epoch: [74][130/150] Time 0.280 (0.349) Data 0.000 (0.050) Loss 0.3652 (0.3784) Prec@1 89.453 (91.693) Prec@5 98.438 (98.056)
[2021-04-28 22:58:15 train_lshot.py:257] INFO Epoch: [74][140/150] Time 0.276 (0.345) Data 0.000 (0.046) Loss 0.3584 (0.3784) Prec@1 91.406 (91.683) Prec@5 98.047 (98.063)
[2021-04-28 22:58:23 train_lshot.py:257] INFO Epoch: [75][0/150] Time 4.210 (4.210) Data 3.809 (3.809) Loss 0.3834 (0.3834) Prec@1 92.969 (92.969) Prec@5 97.266 (97.266)
[2021-04-28 22:58:28 train_lshot.py:257] INFO Epoch: [75][10/150] Time 0.295 (0.872) Data 0.001 (0.518) Loss 0.4188 (0.3605) Prec@1 89.844 (92.330) Prec@5 97.656 (98.295)
[2021-04-28 22:58:31 train_lshot.py:257] INFO Epoch: [75][20/150] Time 0.298 (0.598) Data 0.001 (0.272) Loss 0.3107 (0.3731) Prec@1 93.750 (91.890) Prec@5 99.609 (98.084)
[2021-04-28 22:58:34 train_lshot.py:257] INFO Epoch: [75][30/150] Time 0.285 (0.496) Data 0.000 (0.184) Loss 0.3495 (0.3705) Prec@1 92.188 (91.973) Prec@5 98.438 (98.135)
[2021-04-28 22:58:37 train_lshot.py:257] INFO Epoch: [75][40/150] Time 0.275 (0.443) Data 0.000 (0.139) Loss 0.4051 (0.3783) Prec@1 92.969 (91.978) Prec@5 97.656 (97.971)
[2021-04-28 22:58:40 train_lshot.py:257] INFO Epoch: [75][50/150] Time 0.282 (0.412) Data 0.000 (0.112) Loss 0.3928 (0.3793) Prec@1 91.406 (91.927) Prec@5 97.656 (97.878)
[2021-04-28 22:58:42 train_lshot.py:257] INFO Epoch: [75][60/150] Time 0.282 (0.391) Data 0.000 (0.094) Loss 0.3032 (0.3804) Prec@1 94.531 (91.867) Prec@5 98.438 (97.893)
[2021-04-28 22:58:45 train_lshot.py:257] INFO Epoch: [75][70/150] Time 0.283 (0.375) Data 0.001 (0.081) Loss 0.3838 (0.3807) Prec@1 91.406 (91.879) Prec@5 96.875 (97.860)
[2021-04-28 22:58:48 train_lshot.py:257] INFO Epoch: [75][80/150] Time 0.287 (0.364) Data 0.000 (0.071) Loss 0.3246 (0.3805) Prec@1 93.359 (91.850) Prec@5 99.219 (97.849)
[2021-04-28 22:58:51 train_lshot.py:257] INFO Epoch: [75][90/150] Time 0.284 (0.355) Data 0.000 (0.063) Loss 0.3752 (0.3827) Prec@1 94.141 (91.797) Prec@5 98.828 (97.841)
[2021-04-28 22:58:54 train_lshot.py:257] INFO Epoch: [75][100/150] Time 0.296 (0.348) Data 0.000 (0.057) Loss 0.3691 (0.3788) Prec@1 91.406 (91.936) Prec@5 98.438 (97.915)
[2021-04-28 22:58:57 train_lshot.py:257] INFO Epoch: [75][110/150] Time 0.284 (0.342) Data 0.000 (0.052) Loss 0.4212 (0.3801) Prec@1 90.625 (91.892) Prec@5 98.438 (97.920)
[2021-04-28 22:58:59 train_lshot.py:257] INFO Epoch: [75][120/150] Time 0.285 (0.338) Data 0.000 (0.047) Loss 0.3825 (0.3795) Prec@1 91.797 (91.926) Prec@5 98.047 (97.950)
[2021-04-28 22:59:02 train_lshot.py:257] INFO Epoch: [75][130/150] Time 0.280 (0.334) Data 0.000 (0.044) Loss 0.3783 (0.3806) Prec@1 91.797 (91.868) Prec@5 97.266 (97.934)
[2021-04-28 22:59:05 train_lshot.py:257] INFO Epoch: [75][140/150] Time 0.484 (0.332) Data 0.000 (0.041) Loss 0.3598 (0.3803) Prec@1 93.359 (91.888) Prec@5 98.047 (97.961)
[2021-04-28 22:59:37 train_lshot.py:119] INFO Meta Val 75: 0.5889066801071167
[2021-04-28 22:59:42 train_lshot.py:257] INFO Epoch: [76][0/150] Time 4.968 (4.968) Data 4.566 (4.566) Loss 0.3375 (0.3375) Prec@1 92.578 (92.578) Prec@5 98.828 (98.828)
[2021-04-28 22:59:46 train_lshot.py:257] INFO Epoch: [76][10/150] Time 0.357 (0.867) Data 0.000 (0.493) Loss 0.3513 (0.3720) Prec@1 92.188 (91.513) Prec@5 98.047 (98.153)
[2021-04-28 22:59:49 train_lshot.py:257] INFO Epoch: [76][20/150] Time 0.275 (0.593) Data 0.000 (0.259) Loss 0.3906 (0.3726) Prec@1 91.797 (91.574) Prec@5 98.047 (98.270)
[2021-04-28 22:59:52 train_lshot.py:257] INFO Epoch: [76][30/150] Time 0.284 (0.493) Data 0.000 (0.175) Loss 0.3211 (0.3647) Prec@1 92.969 (91.872) Prec@5 98.438 (98.400)
[2021-04-28 22:59:55 train_lshot.py:257] INFO Epoch: [76][40/150] Time 0.286 (0.443) Data 0.000 (0.133) Loss 0.3953 (0.3663) Prec@1 88.672 (91.787) Prec@5 98.438 (98.428)
[2021-04-28 22:59:58 train_lshot.py:257] INFO Epoch: [76][50/150] Time 0.279 (0.411) Data 0.000 (0.107) Loss 0.3569 (0.3685) Prec@1 94.141 (91.789) Prec@5 98.047 (98.338)
[2021-04-28 23:00:01 train_lshot.py:257] INFO Epoch: [76][60/150] Time 0.281 (0.390) Data 0.000 (0.089) Loss 0.4291 (0.3717) Prec@1 89.453 (91.726) Prec@5 97.656 (98.316)
[2021-04-28 23:00:03 train_lshot.py:257] INFO Epoch: [76][70/150] Time 0.276 (0.375) Data 0.001 (0.077) Loss 0.4466 (0.3741) Prec@1 90.234 (91.681) Prec@5 97.266 (98.234)
[2021-04-28 23:00:06 train_lshot.py:257] INFO Epoch: [76][80/150] Time 0.277 (0.363) Data 0.000 (0.067) Loss 0.3499 (0.3732) Prec@1 91.797 (91.734) Prec@5 98.828 (98.245)
[2021-04-28 23:00:09 train_lshot.py:257] INFO Epoch: [76][90/150] Time 0.275 (0.354) Data 0.000 (0.060) Loss 0.4484 (0.3747) Prec@1 90.625 (91.732) Prec@5 94.922 (98.154)
[2021-04-28 23:00:12 train_lshot.py:257] INFO Epoch: [76][100/150] Time 0.290 (0.346) Data 0.000 (0.054) Loss 0.3520 (0.3752) Prec@1 93.750 (91.731) Prec@5 98.047 (98.147)
[2021-04-28 23:00:15 train_lshot.py:257] INFO Epoch: [76][110/150] Time 0.284 (0.341) Data 0.000 (0.049) Loss 0.3682 (0.3750) Prec@1 92.578 (91.776) Prec@5 97.656 (98.100)
[2021-04-28 23:00:17 train_lshot.py:257] INFO Epoch: [76][120/150] Time 0.303 (0.337) Data 0.000 (0.045) Loss 0.3168 (0.3723) Prec@1 94.531 (91.890) Prec@5 98.438 (98.134)
[2021-04-28 23:00:20 train_lshot.py:257] INFO Epoch: [76][130/150] Time 0.294 (0.333) Data 0.000 (0.042) Loss 0.3259 (0.3729) Prec@1 93.359 (91.877) Prec@5 99.609 (98.130)
[2021-04-28 23:00:23 train_lshot.py:257] INFO Epoch: [76][140/150] Time 0.282 (0.330) Data 0.000 (0.039) Loss 0.4264 (0.3742) Prec@1 89.062 (91.855) Prec@5 97.656 (98.127)
[2021-04-28 23:00:30 train_lshot.py:257] INFO Epoch: [77][0/150] Time 4.188 (4.188) Data 3.758 (3.758) Loss 0.3001 (0.3001) Prec@1 94.922 (94.922) Prec@5 99.219 (99.219)
[2021-04-28 23:00:36 train_lshot.py:257] INFO Epoch: [77][10/150] Time 0.309 (0.909) Data 0.001 (0.515) Loss 0.3826 (0.3722) Prec@1 92.188 (92.188) Prec@5 98.828 (98.189)
[2021-04-28 23:00:39 train_lshot.py:257] INFO Epoch: [77][20/150] Time 0.277 (0.612) Data 0.000 (0.270) Loss 0.3863 (0.3742) Prec@1 92.188 (92.001) Prec@5 97.266 (98.103)
[2021-04-28 23:00:42 train_lshot.py:257] INFO Epoch: [77][30/150] Time 0.280 (0.511) Data 0.000 (0.183) Loss 0.3684 (0.3736) Prec@1 92.188 (91.986) Prec@5 99.609 (98.160)
[2021-04-28 23:00:45 train_lshot.py:257] INFO Epoch: [77][40/150] Time 0.282 (0.455) Data 0.000 (0.139) Loss 0.4887 (0.3765) Prec@1 87.891 (91.854) Prec@5 96.094 (98.218)
[2021-04-28 23:00:48 train_lshot.py:257] INFO Epoch: [77][50/150] Time 0.276 (0.420) Data 0.000 (0.112) Loss 0.3209 (0.3757) Prec@1 93.750 (91.896) Prec@5 98.828 (98.208)
[2021-04-28 23:00:51 train_lshot.py:257] INFO Epoch: [77][60/150] Time 0.288 (0.398) Data 0.000 (0.093) Loss 0.4422 (0.3769) Prec@1 88.672 (91.848) Prec@5 96.484 (98.156)
[2021-04-28 23:00:53 train_lshot.py:257] INFO Epoch: [77][70/150] Time 0.279 (0.382) Data 0.001 (0.080) Loss 0.3626 (0.3763) Prec@1 92.578 (91.907) Prec@5 98.047 (98.118)
[2021-04-28 23:00:56 train_lshot.py:257] INFO Epoch: [77][80/150] Time 0.280 (0.371) Data 0.000 (0.070) Loss 0.3994 (0.3781) Prec@1 90.625 (91.855) Prec@5 97.656 (98.047)
[2021-04-28 23:00:59 train_lshot.py:257] INFO Epoch: [77][90/150] Time 0.287 (0.361) Data 0.000 (0.063) Loss 0.3587 (0.3757) Prec@1 93.750 (91.930) Prec@5 98.828 (98.107)
[2021-04-28 23:01:03 train_lshot.py:257] INFO Epoch: [77][100/150] Time 0.292 (0.366) Data 0.000 (0.057) Loss 0.3009 (0.3750) Prec@1 94.141 (91.944) Prec@5 99.609 (98.101)
[2021-04-28 23:01:06 train_lshot.py:257] INFO Epoch: [77][110/150] Time 0.276 (0.358) Data 0.000 (0.051) Loss 0.3922 (0.3752) Prec@1 90.625 (91.895) Prec@5 97.266 (98.103)
[2021-04-28 23:01:09 train_lshot.py:257] INFO Epoch: [77][120/150] Time 0.277 (0.352) Data 0.000 (0.047) Loss 0.3560 (0.3746) Prec@1 91.797 (91.903) Prec@5 98.047 (98.124)
[2021-04-28 23:01:13 train_lshot.py:257] INFO Epoch: [77][130/150] Time 0.290 (0.356) Data 0.000 (0.044) Loss 0.3673 (0.3742) Prec@1 92.578 (91.898) Prec@5 96.875 (98.118)
[2021-04-28 23:01:16 train_lshot.py:257] INFO Epoch: [77][140/150] Time 0.283 (0.350) Data 0.000 (0.041) Loss 0.3259 (0.3738) Prec@1 92.188 (91.946) Prec@5 98.438 (98.111)
[2021-04-28 23:01:25 train_lshot.py:257] INFO Epoch: [78][0/150] Time 5.885 (5.885) Data 5.437 (5.437) Loss 0.3731 (0.3731) Prec@1 92.188 (92.188) Prec@5 98.047 (98.047)
[2021-04-28 23:01:28 train_lshot.py:257] INFO Epoch: [78][10/150] Time 0.352 (0.871) Data 0.001 (0.496) Loss 0.3286 (0.3829) Prec@1 93.750 (91.229) Prec@5 99.219 (97.976)
[2021-04-28 23:01:31 train_lshot.py:257] INFO Epoch: [78][20/150] Time 0.276 (0.595) Data 0.000 (0.260) Loss 0.3272 (0.3874) Prec@1 92.578 (91.127) Prec@5 98.828 (97.954)
[2021-04-28 23:01:34 train_lshot.py:257] INFO Epoch: [78][30/150] Time 0.283 (0.496) Data 0.000 (0.176) Loss 0.3286 (0.3757) Prec@1 94.141 (91.671) Prec@5 98.047 (98.122)
[2021-04-28 23:01:37 train_lshot.py:257] INFO Epoch: [78][40/150] Time 0.291 (0.445) Data 0.000 (0.134) Loss 0.2832 (0.3730) Prec@1 95.703 (91.854) Prec@5 99.609 (98.104)
[2021-04-28 23:01:40 train_lshot.py:257] INFO Epoch: [78][50/150] Time 0.276 (0.413) Data 0.000 (0.107) Loss 0.4140 (0.3743) Prec@1 92.578 (91.942) Prec@5 97.656 (98.078)
[2021-04-28 23:01:43 train_lshot.py:257] INFO Epoch: [78][60/150] Time 0.291 (0.391) Data 0.000 (0.090) Loss 0.3372 (0.3714) Prec@1 93.750 (92.098) Prec@5 97.266 (98.092)
[2021-04-28 23:01:45 train_lshot.py:257] INFO Epoch: [78][70/150] Time 0.280 (0.376) Data 0.001 (0.077) Loss 0.4144 (0.3728) Prec@1 90.625 (92.033) Prec@5 97.656 (98.058)
[2021-04-28 23:01:49 train_lshot.py:257] INFO Epoch: [78][80/150] Time 0.322 (0.377) Data 0.000 (0.068) Loss 0.3243 (0.3734) Prec@1 94.141 (92.048) Prec@5 99.609 (98.105)
[2021-04-28 23:01:52 train_lshot.py:257] INFO Epoch: [78][90/150] Time 0.275 (0.367) Data 0.000 (0.060) Loss 0.3347 (0.3724) Prec@1 92.578 (92.106) Prec@5 98.828 (98.086)
[2021-04-28 23:01:55 train_lshot.py:257] INFO Epoch: [78][100/150] Time 0.280 (0.359) Data 0.000 (0.054) Loss 0.3703 (0.3733) Prec@1 93.750 (92.048) Prec@5 97.266 (98.086)
[2021-04-28 23:01:58 train_lshot.py:257] INFO Epoch: [78][110/150] Time 0.283 (0.352) Data 0.000 (0.050) Loss 0.4243 (0.3747) Prec@1 90.625 (92.012) Prec@5 98.047 (98.068)
[2021-04-28 23:02:01 train_lshot.py:257] INFO Epoch: [78][120/150] Time 0.292 (0.346) Data 0.000 (0.045) Loss 0.3642 (0.3744) Prec@1 93.359 (92.087) Prec@5 97.266 (98.057)
[2021-04-28 23:02:04 train_lshot.py:257] INFO Epoch: [78][130/150] Time 0.369 (0.345) Data 0.000 (0.042) Loss 0.3412 (0.3742) Prec@1 92.188 (92.098) Prec@5 98.438 (98.062)
[2021-04-28 23:02:07 train_lshot.py:257] INFO Epoch: [78][140/150] Time 0.280 (0.341) Data 0.000 (0.039) Loss 0.3885 (0.3731) Prec@1 92.188 (92.154) Prec@5 97.656 (98.063)
[2021-04-28 23:02:15 train_lshot.py:257] INFO Epoch: [79][0/150] Time 5.047 (5.047) Data 4.610 (4.610) Loss 0.3922 (0.3922) Prec@1 90.234 (90.234) Prec@5 97.656 (97.656)
[2021-04-28 23:02:20 train_lshot.py:257] INFO Epoch: [79][10/150] Time 0.292 (0.911) Data 0.000 (0.542) Loss 0.3334 (0.3695) Prec@1 94.141 (92.081) Prec@5 99.219 (98.189)
[2021-04-28 23:02:23 train_lshot.py:257] INFO Epoch: [79][20/150] Time 0.281 (0.615) Data 0.000 (0.284) Loss 0.4095 (0.3772) Prec@1 90.234 (91.685) Prec@5 97.266 (98.177)
[2021-04-28 23:02:26 train_lshot.py:257] INFO Epoch: [79][30/150] Time 0.280 (0.511) Data 0.000 (0.193) Loss 0.3740 (0.3806) Prec@1 93.750 (91.822) Prec@5 98.828 (98.085)
[2021-04-28 23:02:29 train_lshot.py:257] INFO Epoch: [79][40/150] Time 0.280 (0.455) Data 0.000 (0.146) Loss 0.4134 (0.3775) Prec@1 89.844 (91.845) Prec@5 97.656 (98.180)
[2021-04-28 23:02:31 train_lshot.py:257] INFO Epoch: [79][50/150] Time 0.279 (0.421) Data 0.000 (0.117) Loss 0.4058 (0.3761) Prec@1 91.016 (92.034) Prec@5 97.656 (98.146)
[2021-04-28 23:02:34 train_lshot.py:257] INFO Epoch: [79][60/150] Time 0.287 (0.398) Data 0.000 (0.098) Loss 0.3447 (0.3749) Prec@1 93.359 (92.021) Prec@5 98.438 (98.175)
[2021-04-28 23:02:37 train_lshot.py:257] INFO Epoch: [79][70/150] Time 0.283 (0.382) Data 0.001 (0.084) Loss 0.4019 (0.3753) Prec@1 90.625 (91.989) Prec@5 97.656 (98.157)
[2021-04-28 23:02:40 train_lshot.py:257] INFO Epoch: [79][80/150] Time 0.281 (0.369) Data 0.000 (0.074) Loss 0.3695 (0.3749) Prec@1 90.625 (91.985) Prec@5 98.438 (98.139)
[2021-04-28 23:02:43 train_lshot.py:257] INFO Epoch: [79][90/150] Time 0.286 (0.360) Data 0.000 (0.066) Loss 0.3816 (0.3758) Prec@1 93.359 (91.951) Prec@5 98.047 (98.120)
[2021-04-28 23:02:47 train_lshot.py:257] INFO Epoch: [79][100/150] Time 0.356 (0.365) Data 0.000 (0.059) Loss 0.4031 (0.3789) Prec@1 89.844 (91.839) Prec@5 98.828 (98.082)
[2021-04-28 23:02:50 train_lshot.py:257] INFO Epoch: [79][110/150] Time 0.282 (0.359) Data 0.000 (0.054) Loss 0.3653 (0.3794) Prec@1 92.188 (91.758) Prec@5 98.828 (98.075)
[2021-04-28 23:02:53 train_lshot.py:257] INFO Epoch: [79][120/150] Time 0.276 (0.353) Data 0.000 (0.050) Loss 0.3434 (0.3783) Prec@1 92.578 (91.790) Prec@5 99.219 (98.076)
[2021-04-28 23:02:55 train_lshot.py:257] INFO Epoch: [79][130/150] Time 0.280 (0.347) Data 0.000 (0.046) Loss 0.4298 (0.3792) Prec@1 90.234 (91.794) Prec@5 97.266 (98.080)
[2021-04-28 23:02:58 train_lshot.py:257] INFO Epoch: [79][140/150] Time 0.287 (0.343) Data 0.000 (0.043) Loss 0.4077 (0.3811) Prec@1 91.016 (91.725) Prec@5 97.266 (98.022)
[2021-04-28 23:03:29 train_lshot.py:119] INFO Meta Val 79: 0.6036000137329102
[2021-04-28 23:03:35 train_lshot.py:257] INFO Epoch: [80][0/150] Time 5.677 (5.677) Data 5.276 (5.276) Loss 0.3741 (0.3741) Prec@1 92.188 (92.188) Prec@5 98.047 (98.047)
[2021-04-28 23:03:39 train_lshot.py:257] INFO Epoch: [80][10/150] Time 0.300 (0.847) Data 0.000 (0.480) Loss 0.3843 (0.3742) Prec@1 91.406 (92.330) Prec@5 98.438 (97.834)
[2021-04-28 23:03:42 train_lshot.py:257] INFO Epoch: [80][20/150] Time 0.283 (0.582) Data 0.000 (0.252) Loss 0.3876 (0.3709) Prec@1 92.969 (92.299) Prec@5 98.828 (97.972)
[2021-04-28 23:03:44 train_lshot.py:257] INFO Epoch: [80][30/150] Time 0.274 (0.485) Data 0.000 (0.171) Loss 0.3157 (0.3686) Prec@1 93.750 (92.276) Prec@5 99.219 (98.072)
[2021-04-28 23:03:47 train_lshot.py:257] INFO Epoch: [80][40/150] Time 0.277 (0.435) Data 0.001 (0.129) Loss 0.3888 (0.3697) Prec@1 89.844 (92.188) Prec@5 98.438 (98.047)
[2021-04-28 23:03:50 train_lshot.py:257] INFO Epoch: [80][50/150] Time 0.276 (0.407) Data 0.000 (0.104) Loss 0.3838 (0.3748) Prec@1 92.188 (92.027) Prec@5 96.875 (97.978)
[2021-04-28 23:03:53 train_lshot.py:257] INFO Epoch: [80][60/150] Time 0.282 (0.387) Data 0.000 (0.087) Loss 0.4009 (0.3725) Prec@1 92.188 (92.059) Prec@5 97.656 (98.021)
[2021-04-28 23:03:56 train_lshot.py:257] INFO Epoch: [80][70/150] Time 0.289 (0.372) Data 0.002 (0.075) Loss 0.4546 (0.3719) Prec@1 89.453 (92.143) Prec@5 94.922 (97.986)
[2021-04-28 23:03:59 train_lshot.py:257] INFO Epoch: [80][80/150] Time 0.276 (0.361) Data 0.000 (0.066) Loss 0.3314 (0.3726) Prec@1 92.969 (92.134) Prec@5 98.438 (97.975)
[2021-04-28 23:04:02 train_lshot.py:257] INFO Epoch: [80][90/150] Time 0.277 (0.352) Data 0.000 (0.058) Loss 0.3633 (0.3749) Prec@1 92.188 (92.097) Prec@5 99.219 (97.961)
[2021-04-28 23:04:06 train_lshot.py:257] INFO Epoch: [80][100/150] Time 0.306 (0.360) Data 0.000 (0.053) Loss 0.4313 (0.3739) Prec@1 91.797 (92.149) Prec@5 97.656 (98.004)
[2021-04-28 23:04:09 train_lshot.py:257] INFO Epoch: [80][110/150] Time 0.277 (0.352) Data 0.000 (0.048) Loss 0.4087 (0.3746) Prec@1 89.453 (92.114) Prec@5 97.656 (98.005)
[2021-04-28 23:04:11 train_lshot.py:257] INFO Epoch: [80][120/150] Time 0.293 (0.347) Data 0.000 (0.044) Loss 0.3153 (0.3726) Prec@1 94.922 (92.204) Prec@5 99.609 (98.060)
[2021-04-28 23:04:14 train_lshot.py:257] INFO Epoch: [80][130/150] Time 0.283 (0.342) Data 0.000 (0.041) Loss 0.4287 (0.3725) Prec@1 89.062 (92.193) Prec@5 97.266 (98.065)
[2021-04-28 23:04:17 train_lshot.py:257] INFO Epoch: [80][140/150] Time 0.284 (0.338) Data 0.000 (0.038) Loss 0.3853 (0.3738) Prec@1 92.188 (92.157) Prec@5 96.484 (98.011)
[2021-04-28 23:04:25 train_lshot.py:257] INFO Epoch: [81][0/150] Time 4.683 (4.683) Data 4.295 (4.295) Loss 0.3676 (0.3676) Prec@1 91.797 (91.797) Prec@5 98.438 (98.438)
[2021-04-28 23:04:30 train_lshot.py:257] INFO Epoch: [81][10/150] Time 0.376 (0.866) Data 0.000 (0.477) Loss 0.3872 (0.3740) Prec@1 91.016 (92.010) Prec@5 96.875 (97.905)
[2021-04-28 23:04:33 train_lshot.py:257] INFO Epoch: [81][20/150] Time 0.279 (0.592) Data 0.000 (0.250) Loss 0.4237 (0.3737) Prec@1 91.406 (92.094) Prec@5 95.703 (98.084)
[2021-04-28 23:04:36 train_lshot.py:257] INFO Epoch: [81][30/150] Time 0.282 (0.494) Data 0.000 (0.169) Loss 0.4742 (0.3760) Prec@1 87.500 (91.721) Prec@5 96.094 (98.148)
[2021-04-28 23:04:38 train_lshot.py:257] INFO Epoch: [81][40/150] Time 0.283 (0.443) Data 0.000 (0.128) Loss 0.3859 (0.3796) Prec@1 90.625 (91.663) Prec@5 97.656 (98.056)
[2021-04-28 23:04:41 train_lshot.py:257] INFO Epoch: [81][50/150] Time 0.278 (0.411) Data 0.000 (0.103) Loss 0.3398 (0.3770) Prec@1 92.969 (91.759) Prec@5 98.438 (98.009)
[2021-04-28 23:04:44 train_lshot.py:257] INFO Epoch: [81][60/150] Time 0.284 (0.390) Data 0.000 (0.086) Loss 0.4167 (0.3770) Prec@1 89.844 (91.803) Prec@5 98.047 (97.970)
[2021-04-28 23:04:47 train_lshot.py:257] INFO Epoch: [81][70/150] Time 0.285 (0.375) Data 0.001 (0.074) Loss 0.4044 (0.3802) Prec@1 91.797 (91.643) Prec@5 96.875 (97.953)
[2021-04-28 23:04:50 train_lshot.py:257] INFO Epoch: [81][80/150] Time 0.287 (0.364) Data 0.000 (0.065) Loss 0.4325 (0.3797) Prec@1 91.016 (91.657) Prec@5 97.266 (97.965)
[2021-04-28 23:04:53 train_lshot.py:257] INFO Epoch: [81][90/150] Time 0.276 (0.355) Data 0.000 (0.058) Loss 0.3335 (0.3793) Prec@1 94.531 (91.681) Prec@5 97.266 (97.944)
[2021-04-28 23:04:55 train_lshot.py:257] INFO Epoch: [81][100/150] Time 0.287 (0.348) Data 0.000 (0.052) Loss 0.4844 (0.3808) Prec@1 87.500 (91.665) Prec@5 96.484 (97.900)
[2021-04-28 23:04:59 train_lshot.py:257] INFO Epoch: [81][110/150] Time 0.301 (0.347) Data 0.000 (0.048) Loss 0.3801 (0.3814) Prec@1 93.359 (91.660) Prec@5 98.047 (97.892)
[2021-04-28 23:05:02 train_lshot.py:257] INFO Epoch: [81][120/150] Time 0.283 (0.342) Data 0.000 (0.044) Loss 0.3958 (0.3822) Prec@1 90.625 (91.668) Prec@5 96.484 (97.860)
[2021-04-28 23:05:04 train_lshot.py:257] INFO Epoch: [81][130/150] Time 0.284 (0.337) Data 0.000 (0.040) Loss 0.4036 (0.3815) Prec@1 91.016 (91.654) Prec@5 96.484 (97.862)
[2021-04-28 23:05:07 train_lshot.py:257] INFO Epoch: [81][140/150] Time 0.285 (0.334) Data 0.000 (0.037) Loss 0.3920 (0.3819) Prec@1 90.234 (91.656) Prec@5 97.656 (97.864)
[2021-04-28 23:05:16 train_lshot.py:257] INFO Epoch: [82][0/150] Time 6.005 (6.005) Data 5.554 (5.554) Loss 0.3800 (0.3800) Prec@1 92.578 (92.578) Prec@5 97.656 (97.656)
[2021-04-28 23:05:20 train_lshot.py:257] INFO Epoch: [82][10/150] Time 0.280 (0.877) Data 0.001 (0.509) Loss 0.3498 (0.3594) Prec@1 91.797 (92.472) Prec@5 98.047 (98.047)
[2021-04-28 23:05:23 train_lshot.py:257] INFO Epoch: [82][20/150] Time 0.284 (0.598) Data 0.000 (0.267) Loss 0.3216 (0.3626) Prec@1 93.359 (92.374) Prec@5 98.828 (98.103)
[2021-04-28 23:05:26 train_lshot.py:257] INFO Epoch: [82][30/150] Time 0.279 (0.496) Data 0.000 (0.181) Loss 0.4088 (0.3683) Prec@1 90.234 (92.099) Prec@5 97.266 (98.173)
[2021-04-28 23:05:29 train_lshot.py:257] INFO Epoch: [82][40/150] Time 0.277 (0.444) Data 0.000 (0.137) Loss 0.4454 (0.3738) Prec@1 91.406 (91.978) Prec@5 97.656 (98.095)
[2021-04-28 23:05:31 train_lshot.py:257] INFO Epoch: [82][50/150] Time 0.280 (0.413) Data 0.000 (0.110) Loss 0.3955 (0.3728) Prec@1 91.016 (92.103) Prec@5 97.266 (98.108)
[2021-04-28 23:05:34 train_lshot.py:257] INFO Epoch: [82][60/150] Time 0.281 (0.391) Data 0.000 (0.092) Loss 0.3586 (0.3746) Prec@1 92.188 (92.021) Prec@5 98.047 (98.034)
[2021-04-28 23:05:37 train_lshot.py:257] INFO Epoch: [82][70/150] Time 0.289 (0.376) Data 0.001 (0.079) Loss 0.4070 (0.3751) Prec@1 88.672 (91.984) Prec@5 98.438 (98.058)
[2021-04-28 23:05:40 train_lshot.py:257] INFO Epoch: [82][80/150] Time 0.289 (0.365) Data 0.000 (0.069) Loss 0.3349 (0.3743) Prec@1 93.359 (92.019) Prec@5 98.438 (98.066)
[2021-04-28 23:05:43 train_lshot.py:257] INFO Epoch: [82][90/150] Time 0.286 (0.356) Data 0.000 (0.062) Loss 0.3029 (0.3724) Prec@1 94.141 (92.033) Prec@5 99.609 (98.060)
[2021-04-28 23:05:46 train_lshot.py:257] INFO Epoch: [82][100/150] Time 0.285 (0.349) Data 0.000 (0.056) Loss 0.3533 (0.3748) Prec@1 92.969 (91.967) Prec@5 98.438 (97.997)
[2021-04-28 23:05:48 train_lshot.py:257] INFO Epoch: [82][110/150] Time 0.293 (0.344) Data 0.000 (0.051) Loss 0.3220 (0.3748) Prec@1 93.359 (91.973) Prec@5 98.828 (97.980)
[2021-04-28 23:05:51 train_lshot.py:257] INFO Epoch: [82][120/150] Time 0.282 (0.339) Data 0.000 (0.047) Loss 0.4333 (0.3761) Prec@1 89.453 (91.913) Prec@5 96.484 (97.953)
[2021-04-28 23:05:54 train_lshot.py:257] INFO Epoch: [82][130/150] Time 0.289 (0.335) Data 0.000 (0.043) Loss 0.3947 (0.3771) Prec@1 91.406 (91.889) Prec@5 97.266 (97.948)
[2021-04-28 23:05:57 train_lshot.py:257] INFO Epoch: [82][140/150] Time 0.369 (0.333) Data 0.000 (0.040) Loss 0.3854 (0.3779) Prec@1 90.234 (91.836) Prec@5 97.266 (97.925)
[2021-04-28 23:06:07 train_lshot.py:257] INFO Epoch: [83][0/150] Time 6.236 (6.236) Data 5.803 (5.803) Loss 0.4267 (0.4267) Prec@1 90.625 (90.625) Prec@5 96.875 (96.875)
[2021-04-28 23:06:10 train_lshot.py:257] INFO Epoch: [83][10/150] Time 0.292 (0.881) Data 0.000 (0.528) Loss 0.4923 (0.3574) Prec@1 89.844 (92.401) Prec@5 96.484 (98.260)
[2021-04-28 23:06:13 train_lshot.py:257] INFO Epoch: [83][20/150] Time 0.286 (0.598) Data 0.000 (0.277) Loss 0.4611 (0.3619) Prec@1 88.281 (92.169) Prec@5 96.875 (98.196)
[2021-04-28 23:06:16 train_lshot.py:257] INFO Epoch: [83][30/150] Time 0.285 (0.497) Data 0.000 (0.188) Loss 0.3588 (0.3570) Prec@1 93.750 (92.414) Prec@5 98.438 (98.223)
[2021-04-28 23:06:19 train_lshot.py:257] INFO Epoch: [83][40/150] Time 0.284 (0.445) Data 0.001 (0.142) Loss 0.4493 (0.3599) Prec@1 87.891 (92.397) Prec@5 96.875 (98.190)
[2021-04-28 23:06:21 train_lshot.py:257] INFO Epoch: [83][50/150] Time 0.279 (0.413) Data 0.000 (0.114) Loss 0.3608 (0.3680) Prec@1 92.188 (92.134) Prec@5 98.438 (98.032)
[2021-04-28 23:06:24 train_lshot.py:257] INFO Epoch: [83][60/150] Time 0.284 (0.391) Data 0.000 (0.096) Loss 0.3459 (0.3665) Prec@1 91.016 (92.226) Prec@5 98.047 (98.079)
[2021-04-28 23:06:27 train_lshot.py:257] INFO Epoch: [83][70/150] Time 0.292 (0.376) Data 0.001 (0.082) Loss 0.3730 (0.3690) Prec@1 94.141 (92.171) Prec@5 98.047 (98.030)
[2021-04-28 23:06:30 train_lshot.py:257] INFO Epoch: [83][80/150] Time 0.284 (0.364) Data 0.000 (0.072) Loss 0.4687 (0.3709) Prec@1 88.672 (92.081) Prec@5 96.094 (98.052)
[2021-04-28 23:06:34 train_lshot.py:257] INFO Epoch: [83][90/150] Time 0.300 (0.364) Data 0.000 (0.064) Loss 0.3419 (0.3711) Prec@1 93.750 (92.050) Prec@5 98.047 (98.038)
[2021-04-28 23:06:36 train_lshot.py:257] INFO Epoch: [83][100/150] Time 0.273 (0.356) Data 0.000 (0.058) Loss 0.4184 (0.3715) Prec@1 91.797 (92.091) Prec@5 96.875 (98.000)
[2021-04-28 23:06:39 train_lshot.py:257] INFO Epoch: [83][110/150] Time 0.277 (0.349) Data 0.000 (0.053) Loss 0.3275 (0.3706) Prec@1 93.750 (92.145) Prec@5 98.828 (97.987)
[2021-04-28 23:06:42 train_lshot.py:257] INFO Epoch: [83][120/150] Time 0.276 (0.344) Data 0.000 (0.048) Loss 0.3842 (0.3722) Prec@1 92.188 (92.058) Prec@5 97.266 (97.953)
[2021-04-28 23:06:45 train_lshot.py:257] INFO Epoch: [83][130/150] Time 0.281 (0.339) Data 0.000 (0.045) Loss 0.4182 (0.3728) Prec@1 90.625 (92.044) Prec@5 97.266 (97.945)
[2021-04-28 23:06:48 train_lshot.py:257] INFO Epoch: [83][140/150] Time 0.307 (0.336) Data 0.000 (0.041) Loss 0.3783 (0.3739) Prec@1 91.016 (91.966) Prec@5 99.219 (97.953)
[2021-04-28 23:07:19 train_lshot.py:119] INFO Meta Val 83: 0.5997866780161858
[2021-04-28 23:07:27 train_lshot.py:257] INFO Epoch: [84][0/150] Time 7.591 (7.591) Data 7.281 (7.281) Loss 0.4146 (0.4146) Prec@1 91.406 (91.406) Prec@5 97.266 (97.266)
[2021-04-28 23:07:30 train_lshot.py:257] INFO Epoch: [84][10/150] Time 0.275 (0.949) Data 0.001 (0.662) Loss 0.3121 (0.3563) Prec@1 94.531 (92.720) Prec@5 99.219 (98.438)
[2021-04-28 23:07:33 train_lshot.py:257] INFO Epoch: [84][20/150] Time 0.275 (0.630) Data 0.000 (0.347) Loss 0.3803 (0.3594) Prec@1 91.406 (92.634) Prec@5 98.438 (98.158)
[2021-04-28 23:07:35 train_lshot.py:257] INFO Epoch: [84][30/150] Time 0.282 (0.518) Data 0.000 (0.235) Loss 0.2926 (0.3642) Prec@1 95.312 (92.553) Prec@5 99.609 (98.160)
[2021-04-28 23:07:38 train_lshot.py:257] INFO Epoch: [84][40/150] Time 0.286 (0.462) Data 0.001 (0.178) Loss 0.3345 (0.3675) Prec@1 94.141 (92.435) Prec@5 98.047 (98.199)
[2021-04-28 23:07:41 train_lshot.py:257] INFO Epoch: [84][50/150] Time 0.300 (0.427) Data 0.000 (0.143) Loss 0.3820 (0.3743) Prec@1 89.844 (92.157) Prec@5 98.438 (98.047)
[2021-04-28 23:07:44 train_lshot.py:257] INFO Epoch: [84][60/150] Time 0.287 (0.404) Data 0.000 (0.120) Loss 0.3059 (0.3706) Prec@1 94.141 (92.284) Prec@5 99.609 (98.072)
[2021-04-28 23:07:47 train_lshot.py:257] INFO Epoch: [84][70/150] Time 0.275 (0.387) Data 0.001 (0.103) Loss 0.3466 (0.3716) Prec@1 93.359 (92.193) Prec@5 97.656 (98.025)
[2021-04-28 23:07:50 train_lshot.py:257] INFO Epoch: [84][80/150] Time 0.277 (0.374) Data 0.000 (0.090) Loss 0.4067 (0.3743) Prec@1 91.016 (92.130) Prec@5 97.656 (98.003)
[2021-04-28 23:07:52 train_lshot.py:257] INFO Epoch: [84][90/150] Time 0.278 (0.363) Data 0.000 (0.080) Loss 0.3641 (0.3739) Prec@1 93.750 (92.157) Prec@5 97.656 (97.991)
[2021-04-28 23:07:55 train_lshot.py:257] INFO Epoch: [84][100/150] Time 0.277 (0.355) Data 0.000 (0.073) Loss 0.3802 (0.3727) Prec@1 91.406 (92.184) Prec@5 98.047 (98.024)
[2021-04-28 23:07:58 train_lshot.py:257] INFO Epoch: [84][110/150] Time 0.287 (0.349) Data 0.000 (0.066) Loss 0.3977 (0.3736) Prec@1 90.625 (92.159) Prec@5 97.656 (98.040)
[2021-04-28 23:08:01 train_lshot.py:257] INFO Epoch: [84][120/150] Time 0.280 (0.344) Data 0.000 (0.061) Loss 0.3507 (0.3727) Prec@1 92.188 (92.168) Prec@5 98.438 (98.060)
[2021-04-28 23:08:05 train_lshot.py:257] INFO Epoch: [84][130/150] Time 0.323 (0.350) Data 0.000 (0.056) Loss 0.3183 (0.3714) Prec@1 92.188 (92.185) Prec@5 99.609 (98.095)
[2021-04-28 23:08:08 train_lshot.py:257] INFO Epoch: [84][140/150] Time 0.277 (0.346) Data 0.000 (0.052) Loss 0.4295 (0.3715) Prec@1 92.188 (92.204) Prec@5 96.484 (98.080)
[2021-04-28 23:08:18 train_lshot.py:257] INFO Epoch: [85][0/150] Time 6.831 (6.831) Data 6.445 (6.445) Loss 0.4315 (0.4315) Prec@1 90.625 (90.625) Prec@5 96.875 (96.875)
[2021-04-28 23:08:21 train_lshot.py:257] INFO Epoch: [85][10/150] Time 0.286 (0.932) Data 0.000 (0.586) Loss 0.4353 (0.3855) Prec@1 89.062 (91.832) Prec@5 97.266 (97.763)
[2021-04-28 23:08:24 train_lshot.py:257] INFO Epoch: [85][20/150] Time 0.282 (0.625) Data 0.000 (0.307) Loss 0.4205 (0.3825) Prec@1 91.406 (91.704) Prec@5 96.484 (97.879)
[2021-04-28 23:08:27 train_lshot.py:257] INFO Epoch: [85][30/150] Time 0.282 (0.521) Data 0.000 (0.208) Loss 0.3237 (0.3733) Prec@1 93.750 (92.087) Prec@5 99.219 (97.984)
[2021-04-28 23:08:30 train_lshot.py:257] INFO Epoch: [85][40/150] Time 0.283 (0.463) Data 0.000 (0.158) Loss 0.3939 (0.3701) Prec@1 92.578 (92.207) Prec@5 97.656 (98.104)
[2021-04-28 23:08:33 train_lshot.py:257] INFO Epoch: [85][50/150] Time 0.287 (0.428) Data 0.000 (0.127) Loss 0.3995 (0.3776) Prec@1 91.016 (91.942) Prec@5 96.484 (97.993)
[2021-04-28 23:08:36 train_lshot.py:257] INFO Epoch: [85][60/150] Time 0.279 (0.404) Data 0.000 (0.106) Loss 0.3317 (0.3749) Prec@1 92.578 (91.976) Prec@5 98.047 (97.989)
[2021-04-28 23:08:39 train_lshot.py:257] INFO Epoch: [85][70/150] Time 0.293 (0.387) Data 0.001 (0.091) Loss 0.3614 (0.3751) Prec@1 92.188 (91.989) Prec@5 99.219 (98.019)
[2021-04-28 23:08:42 train_lshot.py:257] INFO Epoch: [85][80/150] Time 0.295 (0.375) Data 0.001 (0.080) Loss 0.3725 (0.3768) Prec@1 91.797 (91.942) Prec@5 97.266 (98.013)
[2021-04-28 23:08:44 train_lshot.py:257] INFO Epoch: [85][90/150] Time 0.282 (0.365) Data 0.000 (0.071) Loss 0.3299 (0.3750) Prec@1 94.141 (92.024) Prec@5 98.047 (98.021)
[2021-04-28 23:08:47 train_lshot.py:257] INFO Epoch: [85][100/150] Time 0.298 (0.358) Data 0.000 (0.064) Loss 0.3180 (0.3763) Prec@1 92.188 (91.975) Prec@5 98.828 (97.993)
[2021-04-28 23:08:50 train_lshot.py:257] INFO Epoch: [85][110/150] Time 0.288 (0.351) Data 0.000 (0.058) Loss 0.3868 (0.3769) Prec@1 92.188 (91.966) Prec@5 96.875 (97.948)
[2021-04-28 23:08:54 train_lshot.py:257] INFO Epoch: [85][120/150] Time 0.328 (0.351) Data 0.000 (0.054) Loss 0.4033 (0.3753) Prec@1 92.969 (92.042) Prec@5 97.656 (97.976)
[2021-04-28 23:08:57 train_lshot.py:257] INFO Epoch: [85][130/150] Time 0.276 (0.346) Data 0.000 (0.050) Loss 0.3191 (0.3729) Prec@1 92.969 (92.089) Prec@5 98.438 (98.017)
[2021-04-28 23:08:59 train_lshot.py:257] INFO Epoch: [85][140/150] Time 0.291 (0.342) Data 0.000 (0.046) Loss 0.3241 (0.3723) Prec@1 94.141 (92.115) Prec@5 98.438 (98.011)
[2021-04-28 23:09:07 train_lshot.py:257] INFO Epoch: [86][0/150] Time 4.429 (4.429) Data 3.999 (3.999) Loss 0.3583 (0.3583) Prec@1 93.359 (93.359) Prec@5 97.656 (97.656)
[2021-04-28 23:09:12 train_lshot.py:257] INFO Epoch: [86][10/150] Time 0.357 (0.882) Data 0.005 (0.486) Loss 0.4053 (0.3856) Prec@1 89.453 (91.193) Prec@5 97.266 (97.585)
[2021-04-28 23:09:15 train_lshot.py:257] INFO Epoch: [86][20/150] Time 0.281 (0.599) Data 0.000 (0.255) Loss 0.2947 (0.3727) Prec@1 94.922 (91.648) Prec@5 98.828 (97.917)
[2021-04-28 23:09:18 train_lshot.py:257] INFO Epoch: [86][30/150] Time 0.290 (0.505) Data 0.000 (0.173) Loss 0.3656 (0.3717) Prec@1 91.797 (91.721) Prec@5 98.047 (97.883)
[2021-04-28 23:09:21 train_lshot.py:257] INFO Epoch: [86][40/150] Time 0.286 (0.450) Data 0.000 (0.131) Loss 0.4364 (0.3736) Prec@1 90.234 (91.644) Prec@5 97.656 (97.942)
[2021-04-28 23:09:24 train_lshot.py:257] INFO Epoch: [86][50/150] Time 0.282 (0.418) Data 0.000 (0.105) Loss 0.3741 (0.3705) Prec@1 92.188 (91.789) Prec@5 97.656 (98.024)
[2021-04-28 23:09:27 train_lshot.py:257] INFO Epoch: [86][60/150] Time 0.277 (0.395) Data 0.000 (0.088) Loss 0.3229 (0.3691) Prec@1 92.578 (91.912) Prec@5 98.047 (98.104)
[2021-04-28 23:09:29 train_lshot.py:257] INFO Epoch: [86][70/150] Time 0.282 (0.379) Data 0.001 (0.076) Loss 0.3572 (0.3695) Prec@1 91.797 (91.885) Prec@5 97.656 (98.074)
[2021-04-28 23:09:32 train_lshot.py:257] INFO Epoch: [86][80/150] Time 0.284 (0.368) Data 0.000 (0.066) Loss 0.3415 (0.3707) Prec@1 94.531 (91.956) Prec@5 98.438 (98.057)
[2021-04-28 23:09:35 train_lshot.py:257] INFO Epoch: [86][90/150] Time 0.282 (0.358) Data 0.000 (0.059) Loss 0.4288 (0.3699) Prec@1 89.453 (92.033) Prec@5 98.047 (98.073)
[2021-04-28 23:09:39 train_lshot.py:257] INFO Epoch: [86][100/150] Time 0.289 (0.363) Data 0.000 (0.053) Loss 0.3819 (0.3702) Prec@1 92.188 (92.048) Prec@5 97.266 (98.097)
[2021-04-28 23:09:42 train_lshot.py:257] INFO Epoch: [86][110/150] Time 0.275 (0.356) Data 0.000 (0.048) Loss 0.3077 (0.3715) Prec@1 94.531 (92.026) Prec@5 99.219 (98.086)
[2021-04-28 23:09:45 train_lshot.py:257] INFO Epoch: [86][120/150] Time 0.285 (0.350) Data 0.000 (0.044) Loss 0.3981 (0.3726) Prec@1 90.625 (91.965) Prec@5 98.047 (98.092)
[2021-04-28 23:09:48 train_lshot.py:257] INFO Epoch: [86][130/150] Time 0.291 (0.348) Data 0.000 (0.041) Loss 0.3517 (0.3715) Prec@1 91.797 (92.012) Prec@5 98.047 (98.107)
[2021-04-28 23:09:51 train_lshot.py:257] INFO Epoch: [86][140/150] Time 0.282 (0.344) Data 0.000 (0.038) Loss 0.3706 (0.3712) Prec@1 91.406 (91.999) Prec@5 98.828 (98.133)
[2021-04-28 23:09:59 train_lshot.py:257] INFO Epoch: [87][0/150] Time 4.936 (4.936) Data 4.510 (4.510) Loss 0.3745 (0.3745) Prec@1 92.578 (92.578) Prec@5 98.828 (98.828)
[2021-04-28 23:10:04 train_lshot.py:257] INFO Epoch: [87][10/150] Time 0.329 (0.866) Data 0.001 (0.482) Loss 0.3513 (0.3776) Prec@1 91.797 (91.903) Prec@5 98.438 (98.011)
[2021-04-28 23:10:07 train_lshot.py:257] INFO Epoch: [87][20/150] Time 0.282 (0.597) Data 0.000 (0.253) Loss 0.3701 (0.3743) Prec@1 92.578 (92.020) Prec@5 98.438 (98.140)
[2021-04-28 23:10:10 train_lshot.py:257] INFO Epoch: [87][30/150] Time 0.288 (0.496) Data 0.000 (0.171) Loss 0.3238 (0.3730) Prec@1 93.750 (92.049) Prec@5 98.047 (98.059)
[2021-04-28 23:10:12 train_lshot.py:257] INFO Epoch: [87][40/150] Time 0.276 (0.443) Data 0.000 (0.130) Loss 0.3789 (0.3720) Prec@1 92.188 (92.016) Prec@5 97.266 (98.047)
[2021-04-28 23:10:15 train_lshot.py:257] INFO Epoch: [87][50/150] Time 0.281 (0.412) Data 0.000 (0.104) Loss 0.3891 (0.3733) Prec@1 91.016 (91.942) Prec@5 98.438 (98.032)
[2021-04-28 23:10:18 train_lshot.py:257] INFO Epoch: [87][60/150] Time 0.287 (0.391) Data 0.000 (0.087) Loss 0.4257 (0.3748) Prec@1 88.672 (91.899) Prec@5 98.438 (98.079)
[2021-04-28 23:10:21 train_lshot.py:257] INFO Epoch: [87][70/150] Time 0.286 (0.376) Data 0.001 (0.075) Loss 0.4192 (0.3766) Prec@1 88.672 (91.802) Prec@5 97.266 (98.069)
[2021-04-28 23:10:24 train_lshot.py:257] INFO Epoch: [87][80/150] Time 0.992 (0.373) Data 0.000 (0.066) Loss 0.3495 (0.3745) Prec@1 92.188 (91.874) Prec@5 98.828 (98.100)
[2021-04-28 23:10:28 train_lshot.py:257] INFO Epoch: [87][90/150] Time 0.285 (0.369) Data 0.000 (0.059) Loss 0.3169 (0.3733) Prec@1 94.531 (91.939) Prec@5 98.438 (98.107)
[2021-04-28 23:10:31 train_lshot.py:257] INFO Epoch: [87][100/150] Time 0.277 (0.360) Data 0.000 (0.053) Loss 0.3875 (0.3725) Prec@1 90.625 (91.948) Prec@5 98.438 (98.151)
[2021-04-28 23:10:33 train_lshot.py:257] INFO Epoch: [87][110/150] Time 0.280 (0.353) Data 0.000 (0.048) Loss 0.3826 (0.3740) Prec@1 92.578 (91.987) Prec@5 97.656 (98.124)
[2021-04-28 23:10:36 train_lshot.py:257] INFO Epoch: [87][120/150] Time 0.283 (0.347) Data 0.000 (0.044) Loss 0.3744 (0.3743) Prec@1 92.188 (92.003) Prec@5 96.484 (98.105)
[2021-04-28 23:10:39 train_lshot.py:257] INFO Epoch: [87][130/150] Time 0.390 (0.346) Data 0.001 (0.041) Loss 0.3968 (0.3736) Prec@1 90.625 (92.018) Prec@5 98.828 (98.130)
[2021-04-28 23:10:42 train_lshot.py:257] INFO Epoch: [87][140/150] Time 0.283 (0.343) Data 0.000 (0.038) Loss 0.3610 (0.3734) Prec@1 91.797 (91.994) Prec@5 98.438 (98.127)
[2021-04-28 23:11:14 train_lshot.py:119] INFO Meta Val 87: 0.6050666811466217
[2021-04-28 23:11:20 train_lshot.py:257] INFO Epoch: [88][0/150] Time 5.580 (5.580) Data 5.161 (5.161) Loss 0.3559 (0.3559) Prec@1 92.969 (92.969) Prec@5 96.875 (96.875)
[2021-04-28 23:11:23 train_lshot.py:257] INFO Epoch: [88][10/150] Time 0.341 (0.827) Data 0.000 (0.470) Loss 0.3580 (0.3797) Prec@1 92.578 (92.045) Prec@5 98.047 (97.656)
[2021-04-28 23:11:26 train_lshot.py:257] INFO Epoch: [88][20/150] Time 0.287 (0.574) Data 0.001 (0.246) Loss 0.3543 (0.3692) Prec@1 92.188 (92.243) Prec@5 98.047 (97.935)
[2021-04-28 23:11:29 train_lshot.py:257] INFO Epoch: [88][30/150] Time 0.273 (0.480) Data 0.000 (0.167) Loss 0.3506 (0.3706) Prec@1 92.969 (92.175) Prec@5 97.656 (98.009)
[2021-04-28 23:11:32 train_lshot.py:257] INFO Epoch: [88][40/150] Time 0.278 (0.432) Data 0.000 (0.126) Loss 0.3561 (0.3703) Prec@1 91.406 (92.111) Prec@5 99.219 (98.056)
[2021-04-28 23:11:35 train_lshot.py:257] INFO Epoch: [88][50/150] Time 0.275 (0.402) Data 0.000 (0.102) Loss 0.3419 (0.3697) Prec@1 93.750 (92.218) Prec@5 98.438 (98.047)
[2021-04-28 23:11:37 train_lshot.py:257] INFO Epoch: [88][60/150] Time 0.285 (0.383) Data 0.000 (0.085) Loss 0.3876 (0.3693) Prec@1 90.234 (92.149) Prec@5 98.828 (98.053)
[2021-04-28 23:11:40 train_lshot.py:257] INFO Epoch: [88][70/150] Time 0.290 (0.369) Data 0.003 (0.073) Loss 0.3989 (0.3727) Prec@1 91.797 (91.984) Prec@5 98.047 (98.014)
[2021-04-28 23:11:43 train_lshot.py:257] INFO Epoch: [88][80/150] Time 0.275 (0.358) Data 0.000 (0.064) Loss 0.3552 (0.3717) Prec@1 91.797 (91.995) Prec@5 98.438 (98.013)
[2021-04-28 23:11:46 train_lshot.py:257] INFO Epoch: [88][90/150] Time 0.279 (0.349) Data 0.000 (0.057) Loss 0.4434 (0.3732) Prec@1 89.453 (91.956) Prec@5 96.484 (97.974)
[2021-04-28 23:11:49 train_lshot.py:257] INFO Epoch: [88][100/150] Time 0.285 (0.343) Data 0.000 (0.052) Loss 0.4169 (0.3726) Prec@1 89.453 (91.963) Prec@5 98.438 (98.012)
[2021-04-28 23:11:51 train_lshot.py:257] INFO Epoch: [88][110/150] Time 0.281 (0.338) Data 0.000 (0.047) Loss 0.3970 (0.3728) Prec@1 90.625 (91.976) Prec@5 98.438 (98.033)
[2021-04-28 23:11:54 train_lshot.py:257] INFO Epoch: [88][120/150] Time 0.282 (0.333) Data 0.000 (0.043) Loss 0.3796 (0.3726) Prec@1 92.188 (92.033) Prec@5 97.656 (98.047)
[2021-04-28 23:11:57 train_lshot.py:257] INFO Epoch: [88][130/150] Time 0.306 (0.330) Data 0.000 (0.040) Loss 0.3667 (0.3722) Prec@1 92.188 (92.047) Prec@5 98.047 (98.062)
[2021-04-28 23:12:00 train_lshot.py:257] INFO Epoch: [88][140/150] Time 0.280 (0.327) Data 0.000 (0.037) Loss 0.3400 (0.3725) Prec@1 94.141 (92.046) Prec@5 98.438 (98.061)
[2021-04-28 23:12:10 train_lshot.py:257] INFO Epoch: [89][0/150] Time 6.799 (6.799) Data 6.342 (6.342) Loss 0.2952 (0.2952) Prec@1 94.531 (94.531) Prec@5 98.438 (98.438)
[2021-04-28 23:12:13 train_lshot.py:257] INFO Epoch: [89][10/150] Time 0.279 (0.927) Data 0.000 (0.578) Loss 0.3724 (0.3537) Prec@1 90.625 (92.685) Prec@5 98.047 (98.118)
[2021-04-28 23:12:16 train_lshot.py:257] INFO Epoch: [89][20/150] Time 0.277 (0.622) Data 0.000 (0.303) Loss 0.3968 (0.3602) Prec@1 89.844 (92.485) Prec@5 96.875 (97.954)
[2021-04-28 23:12:19 train_lshot.py:257] INFO Epoch: [89][30/150] Time 0.275 (0.516) Data 0.000 (0.205) Loss 0.3905 (0.3640) Prec@1 90.625 (92.301) Prec@5 98.047 (97.984)
[2021-04-28 23:12:22 train_lshot.py:257] INFO Epoch: [89][40/150] Time 0.284 (0.460) Data 0.000 (0.155) Loss 0.4120 (0.3641) Prec@1 91.016 (92.311) Prec@5 98.047 (97.990)
[2021-04-28 23:12:25 train_lshot.py:257] INFO Epoch: [89][50/150] Time 0.287 (0.425) Data 0.000 (0.125) Loss 0.3586 (0.3592) Prec@1 92.969 (92.502) Prec@5 98.047 (98.093)
[2021-04-28 23:12:28 train_lshot.py:257] INFO Epoch: [89][60/150] Time 0.278 (0.402) Data 0.000 (0.104) Loss 0.3878 (0.3603) Prec@1 91.016 (92.456) Prec@5 97.656 (98.124)
[2021-04-28 23:12:31 train_lshot.py:257] INFO Epoch: [89][70/150] Time 1.058 (0.396) Data 0.001 (0.090) Loss 0.3714 (0.3629) Prec@1 92.188 (92.435) Prec@5 98.438 (98.091)
[2021-04-28 23:12:35 train_lshot.py:257] INFO Epoch: [89][80/150] Time 0.287 (0.390) Data 0.000 (0.079) Loss 0.3840 (0.3627) Prec@1 90.234 (92.424) Prec@5 98.438 (98.081)
[2021-04-28 23:12:38 train_lshot.py:257] INFO Epoch: [89][90/150] Time 0.279 (0.378) Data 0.000 (0.070) Loss 0.4060 (0.3657) Prec@1 91.406 (92.295) Prec@5 96.875 (98.077)
[2021-04-28 23:12:40 train_lshot.py:257] INFO Epoch: [89][100/150] Time 0.294 (0.368) Data 0.000 (0.063) Loss 0.4274 (0.3683) Prec@1 90.625 (92.199) Prec@5 96.484 (98.051)
[2021-04-28 23:12:43 train_lshot.py:257] INFO Epoch: [89][110/150] Time 0.281 (0.361) Data 0.000 (0.058) Loss 0.3897 (0.3679) Prec@1 91.016 (92.230) Prec@5 99.219 (98.082)
[2021-04-28 23:12:46 train_lshot.py:257] INFO Epoch: [89][120/150] Time 0.284 (0.355) Data 0.000 (0.053) Loss 0.4003 (0.3680) Prec@1 91.016 (92.246) Prec@5 97.656 (98.076)
[2021-04-28 23:12:49 train_lshot.py:257] INFO Epoch: [89][130/150] Time 0.286 (0.349) Data 0.000 (0.049) Loss 0.4100 (0.3668) Prec@1 89.453 (92.262) Prec@5 97.656 (98.118)
[2021-04-28 23:12:53 train_lshot.py:257] INFO Epoch: [89][140/150] Time 0.291 (0.353) Data 0.000 (0.045) Loss 0.3668 (0.3673) Prec@1 90.625 (92.212) Prec@5 98.047 (98.116)
[2021-04-28 23:13:45 train_lshot.py:570] INFO validation lmd=0.10: Best
feature CL2N
GVP 1Shot 0.7197(0.0088)
GVP_5Shot 0.8135(0.0069))
[2021-04-28 23:14:00 train_lshot.py:570] INFO validation lmd=0.30: Best
feature CL2N
GVP 1Shot 0.7239(0.0089)
GVP_5Shot 0.8155(0.0066))
[2021-04-28 23:14:15 train_lshot.py:570] INFO validation lmd=0.50: Best
feature CL2N
GVP 1Shot 0.7207(0.0092)
GVP_5Shot 0.8087(0.0064))
[2021-04-28 23:14:30 train_lshot.py:570] INFO validation lmd=0.70: Best
feature CL2N
GVP 1Shot 0.7237(0.0089)
GVP_5Shot 0.8051(0.0067))
[2021-04-28 23:14:46 train_lshot.py:570] INFO validation lmd=0.80: Best
feature CL2N
GVP 1Shot 0.7161(0.0091)
GVP_5Shot 0.8033(0.0064))
[2021-04-28 23:15:03 train_lshot.py:570] INFO validation lmd=1.00: Best
feature CL2N
GVP 1Shot 0.7178(0.0087)
GVP_5Shot 0.7901(0.0067))
[2021-04-28 23:15:20 train_lshot.py:570] INFO validation lmd=1.20: Best
feature CL2N
GVP 1Shot 0.7081(0.0089)
GVP_5Shot 0.7650(0.0072))
[2021-04-28 23:15:37 train_lshot.py:570] INFO validation lmd=1.50: Best
feature CL2N
GVP 1Shot 0.6825(0.0093)
GVP_5Shot 0.7309(0.0079))
[2021-04-28 23:15:37 train_lshot.py:580] INFO Best lambda on validation:
0.30 with 1 shot acc 0.7239
0.30 with 5 shot acc 0.8155
[2021-04-28 23:15:37 train_lshot.py:707] INFO Proto-rectification = True in Evaluation
[2021-04-28 23:16:12 train_lshot.py:713] INFO Run with lambda 0.3 for 1 shot
[2021-04-28 23:23:13 train_lshot.py:717] INFO Run with lambda 0.3 for 5 shot
[2021-04-28 23:30:12 train_lshot.py:724] INFO Meta Test: LAST
feature UN L2N CL2N
GVP 1Shot 0.6433(0.0020) 0.6531(0.0020) 0.7008(0.0020)
GVP_5Shot 0.7397(0.0020) 0.7305(0.0020) 0.8100(0.0015)
[2021-04-28 23:30:22 train_lshot.py:730] INFO Run with lambda 0.3 for 1 shot
[2021-04-28 23:37:23 train_lshot.py:734] INFO Run with lambda 0.3 for 5 shot
[2021-04-28 23:44:24 train_lshot.py:741] INFO Meta Test: BEST
feature UN L2N CL2N
GVP 1Shot 0.6443(0.0019) 0.6598(0.0019) 0.6886(0.0019)
GVP_5Shot 0.7421(0.0018) 0.7490(0.0017) 0.7957(0.0015)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment