Skip to content

Instantly share code, notes, and snippets.

@shwangtangjun

shwangtangjun/LaplacianShot.log Secret

Created May 1, 2021 04:55
Show Gist options
  • Save shwangtangjun/2718637a326be36651cc8fa2d2e12e89 to your computer and use it in GitHub Desktop.
Save shwangtangjun/2718637a326be36651cc8fa2d2e12e89 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
LaplacianShot.log
[2021-05-01 08:52:56 train_lshot.py:38] INFO arch: resnet18
[2021-05-01 08:52:56 train_lshot.py:38] INFO batch_size: 256
[2021-05-01 08:52:56 train_lshot.py:38] INFO beta: -1.0
[2021-05-01 08:52:56 train_lshot.py:38] INFO config: ./configs/mini/softmax/resnet18.config
[2021-05-01 08:52:56 train_lshot.py:38] INFO cutmix_prob: 0
[2021-05-01 08:52:56 train_lshot.py:38] INFO data: ./data/images
[2021-05-01 08:52:56 train_lshot.py:38] INFO disable_random_resize: False
[2021-05-01 08:52:56 train_lshot.py:38] INFO disable_tqdm: False
[2021-05-01 08:52:56 train_lshot.py:38] INFO disable_train_augment: False
[2021-05-01 08:52:56 train_lshot.py:38] INFO do_meta_train: False
[2021-05-01 08:52:56 train_lshot.py:38] INFO enlarge: True
[2021-05-01 08:52:56 train_lshot.py:38] INFO epochs: 90
[2021-05-01 08:52:56 train_lshot.py:38] INFO eval_fc: False
[2021-05-01 08:52:56 train_lshot.py:38] INFO evaluate: False
[2021-05-01 08:52:56 train_lshot.py:38] INFO jitter: False
[2021-05-01 08:52:56 train_lshot.py:38] INFO knn: 3
[2021-05-01 08:52:56 train_lshot.py:38] INFO label_smooth: 0.0
[2021-05-01 08:52:56 train_lshot.py:38] INFO lmd: 1.0
[2021-05-01 08:52:56 train_lshot.py:38] INFO log_file: /LaplacianShot.log
[2021-05-01 08:52:56 train_lshot.py:38] INFO lr: 0.1
[2021-05-01 08:52:56 train_lshot.py:38] INFO lr_gamma: 0.1
[2021-05-01 08:52:56 train_lshot.py:38] INFO lr_stepsize: 30
[2021-05-01 08:52:56 train_lshot.py:38] INFO lshot: True
[2021-05-01 08:52:56 train_lshot.py:38] INFO meta_test_iter: 10000
[2021-05-01 08:52:56 train_lshot.py:38] INFO meta_train_iter: 100
[2021-05-01 08:52:56 train_lshot.py:38] INFO meta_train_metric: euclidean
[2021-05-01 08:52:56 train_lshot.py:38] INFO meta_train_query: 15
[2021-05-01 08:52:56 train_lshot.py:38] INFO meta_train_shot: 1
[2021-05-01 08:52:56 train_lshot.py:38] INFO meta_train_way: 30
[2021-05-01 08:52:56 train_lshot.py:38] INFO meta_val_interval: 4
[2021-05-01 08:52:56 train_lshot.py:38] INFO meta_val_iter: 500
[2021-05-01 08:52:56 train_lshot.py:38] INFO meta_val_metric: cosine
[2021-05-01 08:52:56 train_lshot.py:38] INFO meta_val_query: 15
[2021-05-01 08:52:56 train_lshot.py:38] INFO meta_val_shot: 1
[2021-05-01 08:52:56 train_lshot.py:38] INFO meta_val_way: 5
[2021-05-01 08:52:56 train_lshot.py:38] INFO nesterov: False
[2021-05-01 08:52:56 train_lshot.py:38] INFO num_NN: 1
[2021-05-01 08:52:56 train_lshot.py:38] INFO num_classes: 64
[2021-05-01 08:52:56 train_lshot.py:38] INFO optimizer: SGD
[2021-05-01 08:52:56 train_lshot.py:38] INFO plot_converge: False
[2021-05-01 08:52:56 train_lshot.py:38] INFO pretrain: None
[2021-05-01 08:52:56 train_lshot.py:38] INFO print_freq: 10
[2021-05-01 08:52:56 train_lshot.py:38] INFO proto_rect: True
[2021-05-01 08:52:56 train_lshot.py:38] INFO resume:
[2021-05-01 08:52:56 train_lshot.py:38] INFO save_path: ./results/mini/softmax/resnet18
[2021-05-01 08:52:56 train_lshot.py:38] INFO scheduler: multi_step
[2021-05-01 08:52:56 train_lshot.py:38] INFO seed: None
[2021-05-01 08:52:56 train_lshot.py:38] INFO split_dir: ./split/mini/
[2021-05-01 08:52:56 train_lshot.py:38] INFO start_epoch: 0
[2021-05-01 08:52:56 train_lshot.py:38] INFO tune_lmd: True
[2021-05-01 08:52:56 train_lshot.py:38] INFO weight_decay: 0.0001
[2021-05-01 08:52:56 train_lshot.py:38] INFO workers: 40
[2021-05-01 08:52:56 train_lshot.py:46] INFO => creating model 'resnet18'
[2021-05-01 08:52:56 train_lshot.py:49] INFO Number of model parameters: 11201664
[2021-05-01 08:53:14 train_lshot.py:257] INFO Epoch: [0][0/150] Time 13.823 (13.823) Data 3.486 (3.486) Loss 4.2086 (4.2086) Prec@1 2.734 (2.734) Prec@5 7.812 (7.812)
[2021-05-01 08:53:17 train_lshot.py:257] INFO Epoch: [0][10/150] Time 0.283 (1.519) Data 0.004 (0.318) Loss 4.4522 (4.2762) Prec@1 5.078 (3.800) Prec@5 12.891 (13.246)
[2021-05-01 08:53:20 train_lshot.py:257] INFO Epoch: [0][20/150] Time 0.264 (0.928) Data 0.000 (0.168) Loss 4.0276 (4.2141) Prec@1 5.469 (4.836) Prec@5 21.875 (16.406)
[2021-05-01 08:53:22 train_lshot.py:257] INFO Epoch: [0][30/150] Time 0.267 (0.714) Data 0.000 (0.114) Loss 3.9023 (4.1037) Prec@1 5.078 (5.607) Prec@5 20.703 (19.115)
[2021-05-01 08:53:25 train_lshot.py:257] INFO Epoch: [0][40/150] Time 0.267 (0.605) Data 0.000 (0.086) Loss 3.8853 (4.0417) Prec@1 6.250 (6.183) Prec@5 25.391 (20.741)
[2021-05-01 08:53:28 train_lshot.py:257] INFO Epoch: [0][50/150] Time 0.271 (0.539) Data 0.000 (0.069) Loss 3.7516 (3.9957) Prec@1 7.031 (6.579) Prec@5 28.516 (21.975)
[2021-05-01 08:53:30 train_lshot.py:257] INFO Epoch: [0][60/150] Time 0.270 (0.494) Data 0.000 (0.058) Loss 3.6544 (3.9509) Prec@1 11.719 (7.114) Prec@5 31.250 (23.393)
[2021-05-01 08:53:33 train_lshot.py:257] INFO Epoch: [0][70/150] Time 0.267 (0.463) Data 0.002 (0.050) Loss 3.5877 (3.9100) Prec@1 10.938 (7.702) Prec@5 32.812 (24.626)
[2021-05-01 08:53:36 train_lshot.py:257] INFO Epoch: [0][80/150] Time 0.269 (0.438) Data 0.000 (0.044) Loss 3.7506 (3.8805) Prec@1 11.719 (8.155) Prec@5 28.516 (25.579)
[2021-05-01 08:53:38 train_lshot.py:257] INFO Epoch: [0][90/150] Time 0.267 (0.420) Data 0.000 (0.039) Loss 3.6412 (3.8499) Prec@1 10.547 (8.448) Prec@5 30.078 (26.429)
[2021-05-01 08:53:41 train_lshot.py:257] INFO Epoch: [0][100/150] Time 0.270 (0.404) Data 0.000 (0.035) Loss 3.5806 (3.8273) Prec@1 11.719 (8.636) Prec@5 31.641 (27.046)
[2021-05-01 08:53:44 train_lshot.py:257] INFO Epoch: [0][110/150] Time 0.265 (0.392) Data 0.000 (0.032) Loss 3.5520 (3.8089) Prec@1 10.547 (8.928) Prec@5 37.500 (27.646)
[2021-05-01 08:53:46 train_lshot.py:257] INFO Epoch: [0][120/150] Time 0.268 (0.382) Data 0.000 (0.029) Loss 3.4885 (3.7882) Prec@1 10.938 (9.172) Prec@5 37.109 (28.293)
[2021-05-01 08:53:49 train_lshot.py:257] INFO Epoch: [0][130/150] Time 0.267 (0.373) Data 0.000 (0.027) Loss 3.6727 (3.7719) Prec@1 8.594 (9.375) Prec@5 32.031 (28.811)
[2021-05-01 08:53:52 train_lshot.py:257] INFO Epoch: [0][140/150] Time 0.267 (0.366) Data 0.000 (0.025) Loss 3.5191 (3.7554) Prec@1 9.766 (9.583) Prec@5 35.547 (29.322)
[2021-05-01 08:54:00 train_lshot.py:257] INFO Epoch: [1][0/150] Time 6.095 (6.095) Data 5.631 (5.631) Loss 3.5415 (3.5415) Prec@1 12.891 (12.891) Prec@5 39.453 (39.453)
[2021-05-01 08:54:04 train_lshot.py:257] INFO Epoch: [1][10/150] Time 0.270 (0.915) Data 0.000 (0.566) Loss 3.4110 (3.4835) Prec@1 13.281 (12.926) Prec@5 39.453 (38.636)
[2021-05-01 08:54:07 train_lshot.py:257] INFO Epoch: [1][20/150] Time 0.273 (0.615) Data 0.000 (0.297) Loss 3.4186 (3.4589) Prec@1 14.844 (13.449) Prec@5 38.281 (39.435)
[2021-05-01 08:54:10 train_lshot.py:257] INFO Epoch: [1][30/150] Time 0.280 (0.505) Data 0.000 (0.201) Loss 3.3557 (3.4548) Prec@1 18.359 (14.214) Prec@5 44.141 (39.844)
[2021-05-01 08:54:13 train_lshot.py:257] INFO Epoch: [1][40/150] Time 0.274 (0.449) Data 0.000 (0.152) Loss 3.3209 (3.4492) Prec@1 17.578 (14.310) Prec@5 41.406 (40.015)
[2021-05-01 08:54:15 train_lshot.py:257] INFO Epoch: [1][50/150] Time 0.271 (0.414) Data 0.000 (0.123) Loss 3.4180 (3.4402) Prec@1 17.969 (14.668) Prec@5 42.969 (40.227)
[2021-05-01 08:54:18 train_lshot.py:257] INFO Epoch: [1][60/150] Time 0.272 (0.391) Data 0.000 (0.103) Loss 3.4198 (3.4269) Prec@1 13.672 (14.831) Prec@5 42.188 (40.587)
[2021-05-01 08:54:21 train_lshot.py:257] INFO Epoch: [1][70/150] Time 0.271 (0.374) Data 0.001 (0.088) Loss 3.3868 (3.4237) Prec@1 16.797 (15.003) Prec@5 43.359 (40.597)
[2021-05-01 08:54:24 train_lshot.py:257] INFO Epoch: [1][80/150] Time 0.278 (0.362) Data 0.001 (0.077) Loss 3.3058 (3.4180) Prec@1 17.188 (15.143) Prec@5 44.922 (40.789)
[2021-05-01 08:54:26 train_lshot.py:257] INFO Epoch: [1][90/150] Time 0.280 (0.352) Data 0.001 (0.069) Loss 3.2777 (3.4082) Prec@1 15.625 (15.312) Prec@5 44.922 (41.157)
[2021-05-01 08:54:29 train_lshot.py:257] INFO Epoch: [1][100/150] Time 0.271 (0.344) Data 0.000 (0.062) Loss 3.4229 (3.3948) Prec@1 14.453 (15.633) Prec@5 41.016 (41.646)
[2021-05-01 08:54:32 train_lshot.py:257] INFO Epoch: [1][110/150] Time 0.283 (0.338) Data 0.000 (0.057) Loss 3.0827 (3.3809) Prec@1 20.312 (15.917) Prec@5 48.828 (42.124)
[2021-05-01 08:54:35 train_lshot.py:257] INFO Epoch: [1][120/150] Time 0.271 (0.333) Data 0.000 (0.052) Loss 3.1645 (3.3717) Prec@1 21.875 (16.116) Prec@5 47.266 (42.323)
[2021-05-01 08:54:37 train_lshot.py:257] INFO Epoch: [1][130/150] Time 0.275 (0.329) Data 0.000 (0.048) Loss 3.3068 (3.3596) Prec@1 14.844 (16.317) Prec@5 42.188 (42.677)
[2021-05-01 08:54:40 train_lshot.py:257] INFO Epoch: [1][140/150] Time 0.273 (0.325) Data 0.000 (0.045) Loss 3.3164 (3.3496) Prec@1 16.016 (16.608) Prec@5 43.359 (43.035)
[2021-05-01 08:54:50 train_lshot.py:257] INFO Epoch: [2][0/150] Time 6.850 (6.850) Data 6.374 (6.374) Loss 2.9556 (2.9556) Prec@1 25.781 (25.781) Prec@5 52.734 (52.734)
[2021-05-01 08:54:53 train_lshot.py:257] INFO Epoch: [2][10/150] Time 0.276 (0.928) Data 0.000 (0.582) Loss 3.1037 (3.1408) Prec@1 23.047 (20.632) Prec@5 48.828 (50.426)
[2021-05-01 08:54:56 train_lshot.py:257] INFO Epoch: [2][20/150] Time 0.274 (0.621) Data 0.000 (0.305) Loss 3.1259 (3.1639) Prec@1 23.047 (20.610) Prec@5 51.953 (49.442)
[2021-05-01 08:54:59 train_lshot.py:257] INFO Epoch: [2][30/150] Time 0.287 (0.513) Data 0.000 (0.207) Loss 3.0660 (3.1648) Prec@1 22.656 (20.728) Prec@5 51.953 (49.206)
[2021-05-01 08:55:02 train_lshot.py:257] INFO Epoch: [2][40/150] Time 0.278 (0.455) Data 0.000 (0.156) Loss 3.0522 (3.1492) Prec@1 23.828 (20.941) Prec@5 49.609 (49.381)
[2021-05-01 08:55:05 train_lshot.py:257] INFO Epoch: [2][50/150] Time 0.271 (0.420) Data 0.000 (0.126) Loss 2.9924 (3.1330) Prec@1 22.656 (21.224) Prec@5 57.422 (49.862)
[2021-05-01 08:55:07 train_lshot.py:257] INFO Epoch: [2][60/150] Time 0.286 (0.396) Data 0.000 (0.105) Loss 3.0397 (3.1307) Prec@1 22.656 (21.395) Prec@5 52.734 (50.013)
[2021-05-01 08:55:10 train_lshot.py:257] INFO Epoch: [2][70/150] Time 0.281 (0.380) Data 0.002 (0.091) Loss 2.9762 (3.1206) Prec@1 19.141 (21.407) Prec@5 55.469 (50.303)
[2021-05-01 08:55:13 train_lshot.py:257] INFO Epoch: [2][80/150] Time 0.273 (0.367) Data 0.000 (0.079) Loss 2.9654 (3.1111) Prec@1 23.047 (21.402) Prec@5 57.422 (50.540)
[2021-05-01 08:55:16 train_lshot.py:257] INFO Epoch: [2][90/150] Time 0.277 (0.357) Data 0.001 (0.071) Loss 3.1842 (3.1035) Prec@1 21.484 (21.592) Prec@5 50.391 (50.768)
[2021-05-01 08:55:18 train_lshot.py:257] INFO Epoch: [2][100/150] Time 0.282 (0.349) Data 0.000 (0.064) Loss 2.8054 (3.0921) Prec@1 26.562 (21.716) Prec@5 58.594 (51.087)
[2021-05-01 08:55:21 train_lshot.py:257] INFO Epoch: [2][110/150] Time 0.274 (0.342) Data 0.000 (0.058) Loss 2.9238 (3.0830) Prec@1 23.438 (21.822) Prec@5 57.812 (51.348)
[2021-05-01 08:55:24 train_lshot.py:257] INFO Epoch: [2][120/150] Time 0.280 (0.336) Data 0.000 (0.053) Loss 3.0430 (3.0740) Prec@1 22.656 (21.978) Prec@5 51.172 (51.634)
[2021-05-01 08:55:27 train_lshot.py:257] INFO Epoch: [2][130/150] Time 0.271 (0.332) Data 0.000 (0.049) Loss 2.8617 (3.0630) Prec@1 22.656 (22.182) Prec@5 55.469 (51.899)
[2021-05-01 08:55:29 train_lshot.py:257] INFO Epoch: [2][140/150] Time 0.272 (0.328) Data 0.000 (0.046) Loss 2.7034 (3.0560) Prec@1 27.734 (22.282) Prec@5 65.234 (52.108)
[2021-05-01 08:55:38 train_lshot.py:257] INFO Epoch: [3][0/150] Time 5.518 (5.518) Data 5.077 (5.077) Loss 3.0266 (3.0266) Prec@1 24.219 (24.219) Prec@5 54.688 (54.688)
[2021-05-01 08:55:42 train_lshot.py:257] INFO Epoch: [3][10/150] Time 0.346 (0.837) Data 0.001 (0.463) Loss 2.8953 (2.9003) Prec@1 24.609 (25.000) Prec@5 57.422 (56.783)
[2021-05-01 08:55:45 train_lshot.py:257] INFO Epoch: [3][20/150] Time 0.280 (0.582) Data 0.000 (0.243) Loss 3.0606 (2.8756) Prec@1 24.219 (26.246) Prec@5 53.125 (57.124)
[2021-05-01 08:55:47 train_lshot.py:257] INFO Epoch: [3][30/150] Time 0.273 (0.482) Data 0.000 (0.165) Loss 2.7924 (2.8590) Prec@1 28.125 (26.777) Prec@5 59.375 (57.586)
[2021-05-01 08:55:50 train_lshot.py:257] INFO Epoch: [3][40/150] Time 0.275 (0.433) Data 0.000 (0.125) Loss 2.9047 (2.8558) Prec@1 27.344 (26.496) Prec@5 55.469 (57.479)
[2021-05-01 08:55:53 train_lshot.py:257] INFO Epoch: [3][50/150] Time 0.279 (0.402) Data 0.000 (0.100) Loss 2.7816 (2.8391) Prec@1 29.297 (26.984) Prec@5 62.500 (57.973)
[2021-05-01 08:55:56 train_lshot.py:257] INFO Epoch: [3][60/150] Time 0.285 (0.381) Data 0.000 (0.084) Loss 2.7825 (2.8304) Prec@1 30.078 (27.350) Prec@5 58.203 (58.306)
[2021-05-01 08:55:58 train_lshot.py:257] INFO Epoch: [3][70/150] Time 0.273 (0.367) Data 0.001 (0.072) Loss 2.5916 (2.8201) Prec@1 32.422 (27.575) Prec@5 65.625 (58.605)
[2021-05-01 08:56:01 train_lshot.py:257] INFO Epoch: [3][80/150] Time 0.273 (0.356) Data 0.001 (0.063) Loss 2.8614 (2.8185) Prec@1 25.000 (27.508) Prec@5 57.422 (58.637)
[2021-05-01 08:56:04 train_lshot.py:257] INFO Epoch: [3][90/150] Time 0.287 (0.347) Data 0.000 (0.056) Loss 2.9062 (2.8142) Prec@1 28.516 (27.597) Prec@5 57.031 (58.697)
[2021-05-01 08:56:07 train_lshot.py:257] INFO Epoch: [3][100/150] Time 0.274 (0.340) Data 0.000 (0.051) Loss 2.5942 (2.8052) Prec@1 33.984 (27.765) Prec@5 63.672 (58.977)
[2021-05-01 08:56:09 train_lshot.py:257] INFO Epoch: [3][110/150] Time 0.273 (0.335) Data 0.000 (0.046) Loss 2.5377 (2.7978) Prec@1 29.688 (27.903) Prec@5 64.062 (59.164)
[2021-05-01 08:56:12 train_lshot.py:257] INFO Epoch: [3][120/150] Time 0.286 (0.330) Data 0.000 (0.042) Loss 2.8120 (2.7931) Prec@1 29.297 (28.083) Prec@5 57.812 (59.256)
[2021-05-01 08:56:15 train_lshot.py:257] INFO Epoch: [3][130/150] Time 0.275 (0.326) Data 0.000 (0.039) Loss 2.8032 (2.7888) Prec@1 30.469 (28.146) Prec@5 58.984 (59.408)
[2021-05-01 08:56:19 train_lshot.py:257] INFO Epoch: [3][140/150] Time 0.401 (0.331) Data 0.000 (0.036) Loss 2.8928 (2.7856) Prec@1 27.734 (28.297) Prec@5 57.031 (59.444)
[2021-05-01 08:56:50 train_lshot.py:119] INFO Meta Val 3: 0.4369333430826664
[2021-05-01 08:56:56 train_lshot.py:257] INFO Epoch: [4][0/150] Time 6.019 (6.019) Data 5.595 (5.595) Loss 2.6627 (2.6627) Prec@1 35.547 (35.547) Prec@5 63.281 (63.281)
[2021-05-01 08:57:00 train_lshot.py:257] INFO Epoch: [4][10/150] Time 0.383 (0.864) Data 0.001 (0.514) Loss 2.7946 (2.6374) Prec@1 29.297 (31.321) Prec@5 60.156 (63.352)
[2021-05-01 08:57:03 train_lshot.py:257] INFO Epoch: [4][20/150] Time 0.271 (0.588) Data 0.000 (0.270) Loss 2.8406 (2.6576) Prec@1 24.219 (30.227) Prec@5 56.250 (62.333)
[2021-05-01 08:57:06 train_lshot.py:257] INFO Epoch: [4][30/150] Time 0.280 (0.490) Data 0.000 (0.183) Loss 2.5414 (2.6453) Prec@1 33.203 (30.771) Prec@5 64.062 (62.424)
[2021-05-01 08:57:08 train_lshot.py:257] INFO Epoch: [4][40/150] Time 0.282 (0.439) Data 0.001 (0.138) Loss 2.5902 (2.6351) Prec@1 37.891 (31.431) Prec@5 61.719 (62.595)
[2021-05-01 08:57:11 train_lshot.py:257] INFO Epoch: [4][50/150] Time 0.273 (0.407) Data 0.001 (0.111) Loss 2.4623 (2.6244) Prec@1 32.422 (31.702) Prec@5 67.188 (63.074)
[2021-05-01 08:57:14 train_lshot.py:257] INFO Epoch: [4][60/150] Time 0.283 (0.387) Data 0.001 (0.093) Loss 2.6291 (2.6170) Prec@1 32.031 (31.942) Prec@5 61.719 (63.486)
[2021-05-01 08:57:17 train_lshot.py:257] INFO Epoch: [4][70/150] Time 0.281 (0.371) Data 0.001 (0.080) Loss 2.6243 (2.6147) Prec@1 35.547 (32.026) Prec@5 63.281 (63.727)
[2021-05-01 08:57:19 train_lshot.py:257] INFO Epoch: [4][80/150] Time 0.271 (0.359) Data 0.000 (0.070) Loss 2.5952 (2.6092) Prec@1 30.469 (32.012) Prec@5 67.188 (63.913)
[2021-05-01 08:57:22 train_lshot.py:257] INFO Epoch: [4][90/150] Time 0.280 (0.350) Data 0.000 (0.063) Loss 2.5929 (2.6026) Prec@1 36.328 (32.203) Prec@5 65.234 (64.157)
[2021-05-01 08:57:25 train_lshot.py:257] INFO Epoch: [4][100/150] Time 0.281 (0.343) Data 0.000 (0.056) Loss 2.5021 (2.5985) Prec@1 34.375 (32.298) Prec@5 64.062 (64.136)
[2021-05-01 08:57:28 train_lshot.py:257] INFO Epoch: [4][110/150] Time 0.286 (0.337) Data 0.000 (0.051) Loss 2.6732 (2.5925) Prec@1 32.812 (32.373) Prec@5 64.453 (64.397)
[2021-05-01 08:57:31 train_lshot.py:257] INFO Epoch: [4][120/150] Time 0.281 (0.332) Data 0.000 (0.047) Loss 2.6731 (2.5893) Prec@1 32.031 (32.528) Prec@5 64.062 (64.492)
[2021-05-01 08:57:33 train_lshot.py:257] INFO Epoch: [4][130/150] Time 0.282 (0.329) Data 0.000 (0.044) Loss 2.6869 (2.5801) Prec@1 31.250 (32.729) Prec@5 58.984 (64.742)
[2021-05-01 08:57:37 train_lshot.py:257] INFO Epoch: [4][140/150] Time 0.300 (0.333) Data 0.000 (0.040) Loss 2.4363 (2.5717) Prec@1 35.547 (32.932) Prec@5 69.922 (64.924)
[2021-05-01 08:57:47 train_lshot.py:257] INFO Epoch: [5][0/150] Time 6.084 (6.084) Data 5.675 (5.675) Loss 2.3837 (2.3837) Prec@1 38.281 (38.281) Prec@5 69.531 (69.531)
[2021-05-01 08:57:50 train_lshot.py:257] INFO Epoch: [5][10/150] Time 0.302 (0.883) Data 0.001 (0.518) Loss 2.5513 (2.4460) Prec@1 35.938 (35.724) Prec@5 64.844 (67.223)
[2021-05-01 08:57:53 train_lshot.py:257] INFO Epoch: [5][20/150] Time 0.279 (0.603) Data 0.000 (0.271) Loss 2.5328 (2.4327) Prec@1 32.031 (35.640) Prec@5 66.016 (67.857)
[2021-05-01 08:57:56 train_lshot.py:257] INFO Epoch: [5][30/150] Time 0.282 (0.499) Data 0.000 (0.184) Loss 2.3377 (2.4210) Prec@1 43.359 (36.265) Prec@5 71.875 (68.498)
[2021-05-01 08:57:59 train_lshot.py:257] INFO Epoch: [5][40/150] Time 0.277 (0.446) Data 0.000 (0.139) Loss 2.1876 (2.4130) Prec@1 39.453 (36.452) Prec@5 73.828 (68.502)
[2021-05-01 08:58:01 train_lshot.py:257] INFO Epoch: [5][50/150] Time 0.275 (0.413) Data 0.001 (0.112) Loss 2.3613 (2.4128) Prec@1 38.672 (36.275) Prec@5 68.750 (68.696)
[2021-05-01 08:58:04 train_lshot.py:257] INFO Epoch: [5][60/150] Time 0.275 (0.391) Data 0.000 (0.094) Loss 2.3209 (2.4115) Prec@1 35.547 (36.418) Prec@5 71.875 (68.763)
[2021-05-01 08:58:07 train_lshot.py:257] INFO Epoch: [5][70/150] Time 0.281 (0.375) Data 0.001 (0.081) Loss 2.2785 (2.4026) Prec@1 41.406 (36.548) Prec@5 72.656 (68.948)
[2021-05-01 08:58:10 train_lshot.py:257] INFO Epoch: [5][80/150] Time 0.285 (0.363) Data 0.000 (0.071) Loss 2.4486 (2.4068) Prec@1 30.859 (36.386) Prec@5 66.797 (68.875)
[2021-05-01 08:58:13 train_lshot.py:257] INFO Epoch: [5][90/150] Time 0.286 (0.354) Data 0.000 (0.063) Loss 2.3406 (2.4055) Prec@1 36.328 (36.427) Prec@5 69.141 (68.905)
[2021-05-01 08:58:16 train_lshot.py:257] INFO Epoch: [5][100/150] Time 0.283 (0.347) Data 0.000 (0.057) Loss 2.5739 (2.4083) Prec@1 30.469 (36.344) Prec@5 66.406 (68.916)
[2021-05-01 08:58:18 train_lshot.py:257] INFO Epoch: [5][110/150] Time 0.283 (0.342) Data 0.000 (0.052) Loss 2.4553 (2.4083) Prec@1 34.766 (36.328) Prec@5 67.578 (68.898)
[2021-05-01 08:58:22 train_lshot.py:257] INFO Epoch: [5][120/150] Time 0.291 (0.344) Data 0.000 (0.047) Loss 2.3415 (2.4008) Prec@1 41.016 (36.522) Prec@5 68.750 (68.924)
[2021-05-01 08:58:25 train_lshot.py:257] INFO Epoch: [5][130/150] Time 0.276 (0.339) Data 0.000 (0.044) Loss 2.3286 (2.3937) Prec@1 37.891 (36.728) Prec@5 69.141 (69.081)
[2021-05-01 08:58:28 train_lshot.py:257] INFO Epoch: [5][140/150] Time 0.275 (0.335) Data 0.000 (0.041) Loss 2.2101 (2.3848) Prec@1 41.406 (36.996) Prec@5 72.656 (69.240)
[2021-05-01 08:58:35 train_lshot.py:257] INFO Epoch: [6][0/150] Time 4.320 (4.320) Data 3.889 (3.889) Loss 2.0400 (2.0400) Prec@1 46.484 (46.484) Prec@5 75.000 (75.000)
[2021-05-01 08:58:40 train_lshot.py:257] INFO Epoch: [6][10/150] Time 0.367 (0.847) Data 0.001 (0.470) Loss 2.2179 (2.2986) Prec@1 40.625 (40.021) Prec@5 75.391 (70.028)
[2021-05-01 08:58:43 train_lshot.py:257] INFO Epoch: [6][20/150] Time 0.277 (0.584) Data 0.000 (0.246) Loss 2.1363 (2.2944) Prec@1 41.406 (39.565) Prec@5 75.000 (70.796)
[2021-05-01 08:58:46 train_lshot.py:257] INFO Epoch: [6][30/150] Time 0.281 (0.488) Data 0.000 (0.167) Loss 2.0712 (2.2713) Prec@1 42.969 (39.894) Prec@5 75.391 (71.547)
[2021-05-01 08:58:49 train_lshot.py:257] INFO Epoch: [6][40/150] Time 0.276 (0.438) Data 0.000 (0.126) Loss 2.1852 (2.2722) Prec@1 42.969 (40.006) Prec@5 73.438 (71.475)
[2021-05-01 08:58:52 train_lshot.py:257] INFO Epoch: [6][50/150] Time 0.275 (0.407) Data 0.000 (0.102) Loss 2.2138 (2.2527) Prec@1 43.750 (40.357) Prec@5 74.609 (71.998)
[2021-05-01 08:58:54 train_lshot.py:257] INFO Epoch: [6][60/150] Time 0.283 (0.386) Data 0.000 (0.085) Loss 2.2102 (2.2468) Prec@1 40.234 (40.420) Prec@5 69.531 (72.099)
[2021-05-01 08:58:57 train_lshot.py:257] INFO Epoch: [6][70/150] Time 0.280 (0.371) Data 0.001 (0.073) Loss 2.3087 (2.2508) Prec@1 39.062 (40.427) Prec@5 71.875 (71.892)
[2021-05-01 08:59:00 train_lshot.py:257] INFO Epoch: [6][80/150] Time 0.280 (0.360) Data 0.000 (0.064) Loss 2.0493 (2.2465) Prec@1 45.703 (40.519) Prec@5 77.344 (72.063)
[2021-05-01 08:59:03 train_lshot.py:257] INFO Epoch: [6][90/150] Time 0.277 (0.353) Data 0.000 (0.057) Loss 2.1803 (2.2409) Prec@1 39.453 (40.668) Prec@5 74.609 (72.210)
[2021-05-01 08:59:06 train_lshot.py:257] INFO Epoch: [6][100/150] Time 0.290 (0.350) Data 0.000 (0.052) Loss 2.0863 (2.2406) Prec@1 46.094 (40.753) Prec@5 74.609 (72.262)
[2021-05-01 08:59:09 train_lshot.py:257] INFO Epoch: [6][110/150] Time 0.290 (0.344) Data 0.000 (0.047) Loss 2.0212 (2.2316) Prec@1 48.438 (40.991) Prec@5 75.781 (72.456)
[2021-05-01 08:59:12 train_lshot.py:257] INFO Epoch: [6][120/150] Time 0.288 (0.339) Data 0.001 (0.043) Loss 2.2153 (2.2302) Prec@1 42.578 (40.996) Prec@5 69.922 (72.566)
[2021-05-01 08:59:15 train_lshot.py:257] INFO Epoch: [6][130/150] Time 0.286 (0.338) Data 0.000 (0.040) Loss 2.1805 (2.2245) Prec@1 45.703 (41.144) Prec@5 72.266 (72.644)
[2021-05-01 08:59:18 train_lshot.py:257] INFO Epoch: [6][140/150] Time 0.281 (0.334) Data 0.000 (0.037) Loss 2.0696 (2.2148) Prec@1 42.188 (41.351) Prec@5 76.953 (72.870)
[2021-05-01 08:59:27 train_lshot.py:257] INFO Epoch: [7][0/150] Time 5.932 (5.932) Data 5.461 (5.461) Loss 2.2265 (2.2265) Prec@1 41.406 (41.406) Prec@5 73.047 (73.047)
[2021-05-01 08:59:31 train_lshot.py:257] INFO Epoch: [7][10/150] Time 0.355 (0.882) Data 0.000 (0.497) Loss 2.1959 (2.0988) Prec@1 42.578 (44.389) Prec@5 75.781 (74.822)
[2021-05-01 08:59:34 train_lshot.py:257] INFO Epoch: [7][20/150] Time 0.285 (0.602) Data 0.000 (0.261) Loss 2.1226 (2.1018) Prec@1 44.141 (44.550) Prec@5 75.000 (75.130)
[2021-05-01 08:59:36 train_lshot.py:257] INFO Epoch: [7][30/150] Time 0.279 (0.500) Data 0.000 (0.177) Loss 2.0467 (2.1080) Prec@1 46.484 (44.191) Prec@5 77.734 (75.239)
[2021-05-01 08:59:39 train_lshot.py:257] INFO Epoch: [7][40/150] Time 0.280 (0.446) Data 0.001 (0.134) Loss 2.1318 (2.1216) Prec@1 42.188 (44.083) Prec@5 73.828 (74.800)
[2021-05-01 08:59:42 train_lshot.py:257] INFO Epoch: [7][50/150] Time 0.284 (0.413) Data 0.001 (0.108) Loss 1.9807 (2.1144) Prec@1 44.141 (44.102) Prec@5 80.078 (74.824)
[2021-05-01 08:59:45 train_lshot.py:257] INFO Epoch: [7][60/150] Time 0.278 (0.391) Data 0.000 (0.090) Loss 2.1343 (2.1156) Prec@1 42.188 (43.878) Prec@5 76.562 (74.821)
[2021-05-01 08:59:48 train_lshot.py:257] INFO Epoch: [7][70/150] Time 0.286 (0.376) Data 0.001 (0.077) Loss 2.0249 (2.1069) Prec@1 45.703 (44.047) Prec@5 76.953 (74.945)
[2021-05-01 08:59:52 train_lshot.py:257] INFO Epoch: [7][80/150] Time 0.310 (0.381) Data 0.000 (0.068) Loss 1.9206 (2.0973) Prec@1 45.703 (44.117) Prec@5 79.297 (75.135)
[2021-05-01 08:59:55 train_lshot.py:257] INFO Epoch: [7][90/150] Time 0.276 (0.370) Data 0.000 (0.061) Loss 2.0917 (2.0902) Prec@1 45.312 (44.390) Prec@5 75.000 (75.258)
[2021-05-01 08:59:57 train_lshot.py:257] INFO Epoch: [7][100/150] Time 0.303 (0.362) Data 0.000 (0.055) Loss 2.0121 (2.0901) Prec@1 44.531 (44.311) Prec@5 79.297 (75.317)
[2021-05-01 09:00:00 train_lshot.py:257] INFO Epoch: [7][110/150] Time 0.279 (0.355) Data 0.000 (0.050) Loss 1.9969 (2.0823) Prec@1 48.438 (44.517) Prec@5 77.344 (75.422)
[2021-05-01 09:00:03 train_lshot.py:257] INFO Epoch: [7][120/150] Time 0.312 (0.351) Data 0.000 (0.046) Loss 2.0639 (2.0784) Prec@1 46.875 (44.641) Prec@5 73.828 (75.481)
[2021-05-01 09:00:06 train_lshot.py:257] INFO Epoch: [7][130/150] Time 0.281 (0.346) Data 0.000 (0.042) Loss 2.0393 (2.0738) Prec@1 47.656 (44.776) Prec@5 75.000 (75.531)
[2021-05-01 09:00:09 train_lshot.py:257] INFO Epoch: [7][140/150] Time 0.279 (0.342) Data 0.000 (0.039) Loss 2.3246 (2.0725) Prec@1 39.062 (44.742) Prec@5 68.359 (75.546)
[2021-05-01 09:00:40 train_lshot.py:119] INFO Meta Val 7: 0.46613334396481515
[2021-05-01 09:00:45 train_lshot.py:257] INFO Epoch: [8][0/150] Time 4.850 (4.850) Data 4.456 (4.456) Loss 2.1281 (2.1281) Prec@1 43.750 (43.750) Prec@5 72.266 (72.266)
[2021-05-01 09:00:50 train_lshot.py:257] INFO Epoch: [8][10/150] Time 0.292 (0.834) Data 0.001 (0.527) Loss 2.0285 (2.0046) Prec@1 46.875 (46.804) Prec@5 76.172 (76.456)
[2021-05-01 09:00:53 train_lshot.py:257] INFO Epoch: [8][20/150] Time 0.277 (0.576) Data 0.000 (0.277) Loss 1.9309 (1.9668) Prec@1 46.094 (47.712) Prec@5 78.516 (77.158)
[2021-05-01 09:00:55 train_lshot.py:257] INFO Epoch: [8][30/150] Time 0.274 (0.480) Data 0.000 (0.187) Loss 1.8604 (1.9586) Prec@1 46.094 (47.505) Prec@5 83.594 (77.508)
[2021-05-01 09:00:58 train_lshot.py:257] INFO Epoch: [8][40/150] Time 0.283 (0.433) Data 0.000 (0.142) Loss 1.8728 (1.9592) Prec@1 48.047 (47.428) Prec@5 78.906 (77.429)
[2021-05-01 09:01:01 train_lshot.py:257] INFO Epoch: [8][50/150] Time 0.288 (0.403) Data 0.001 (0.114) Loss 1.9357 (1.9566) Prec@1 49.609 (47.449) Prec@5 81.250 (77.619)
[2021-05-01 09:01:04 train_lshot.py:257] INFO Epoch: [8][60/150] Time 0.274 (0.383) Data 0.000 (0.096) Loss 1.9497 (1.9622) Prec@1 49.219 (47.374) Prec@5 76.953 (77.574)
[2021-05-01 09:01:07 train_lshot.py:257] INFO Epoch: [8][70/150] Time 0.273 (0.368) Data 0.001 (0.082) Loss 1.9586 (1.9631) Prec@1 46.484 (47.513) Prec@5 73.438 (77.437)
[2021-05-01 09:01:09 train_lshot.py:257] INFO Epoch: [8][80/150] Time 0.276 (0.357) Data 0.000 (0.072) Loss 1.9816 (1.9597) Prec@1 50.000 (47.618) Prec@5 79.297 (77.537)
[2021-05-01 09:01:12 train_lshot.py:257] INFO Epoch: [8][90/150] Time 0.279 (0.348) Data 0.000 (0.064) Loss 1.9261 (1.9540) Prec@1 49.609 (47.785) Prec@5 76.953 (77.618)
[2021-05-01 09:01:15 train_lshot.py:257] INFO Epoch: [8][100/150] Time 0.287 (0.342) Data 0.000 (0.058) Loss 2.1442 (1.9563) Prec@1 44.531 (47.710) Prec@5 72.656 (77.549)
[2021-05-01 09:01:18 train_lshot.py:257] INFO Epoch: [8][110/150] Time 0.333 (0.341) Data 0.000 (0.053) Loss 2.0878 (1.9588) Prec@1 47.656 (47.663) Prec@5 75.781 (77.488)
[2021-05-01 09:01:21 train_lshot.py:257] INFO Epoch: [8][120/150] Time 0.277 (0.337) Data 0.000 (0.048) Loss 1.7897 (1.9639) Prec@1 48.047 (47.482) Prec@5 80.859 (77.373)
[2021-05-01 09:01:24 train_lshot.py:257] INFO Epoch: [8][130/150] Time 0.283 (0.333) Data 0.000 (0.045) Loss 2.1693 (1.9661) Prec@1 43.750 (47.495) Prec@5 75.000 (77.308)
[2021-05-01 09:01:27 train_lshot.py:257] INFO Epoch: [8][140/150] Time 0.288 (0.329) Data 0.000 (0.042) Loss 1.9270 (1.9625) Prec@1 50.000 (47.581) Prec@5 75.000 (77.391)
[2021-05-01 09:01:36 train_lshot.py:257] INFO Epoch: [9][0/150] Time 6.485 (6.485) Data 6.026 (6.026) Loss 1.7174 (1.7174) Prec@1 48.438 (48.438) Prec@5 82.422 (82.422)
[2021-05-01 09:01:40 train_lshot.py:257] INFO Epoch: [9][10/150] Time 0.291 (0.910) Data 0.000 (0.548) Loss 1.8938 (1.8261) Prec@1 48.047 (50.284) Prec@5 78.516 (80.291)
[2021-05-01 09:01:43 train_lshot.py:257] INFO Epoch: [9][20/150] Time 0.279 (0.609) Data 0.000 (0.287) Loss 1.8166 (1.8263) Prec@1 48.438 (49.963) Prec@5 80.859 (79.948)
[2021-05-01 09:01:46 train_lshot.py:257] INFO Epoch: [9][30/150] Time 0.278 (0.507) Data 0.000 (0.195) Loss 1.9415 (1.8435) Prec@1 46.094 (49.975) Prec@5 81.250 (79.977)
[2021-05-01 09:01:48 train_lshot.py:257] INFO Epoch: [9][40/150] Time 0.287 (0.452) Data 0.000 (0.147) Loss 1.9535 (1.8577) Prec@1 49.609 (49.848) Prec@5 77.734 (79.697)
[2021-05-01 09:01:51 train_lshot.py:257] INFO Epoch: [9][50/150] Time 0.278 (0.418) Data 0.000 (0.119) Loss 1.7451 (1.8651) Prec@1 50.391 (49.900) Prec@5 80.859 (79.519)
[2021-05-01 09:01:54 train_lshot.py:257] INFO Epoch: [9][60/150] Time 0.274 (0.395) Data 0.000 (0.099) Loss 1.9980 (1.8607) Prec@1 51.953 (50.307) Prec@5 77.344 (79.515)
[2021-05-01 09:01:57 train_lshot.py:257] INFO Epoch: [9][70/150] Time 0.275 (0.380) Data 0.001 (0.085) Loss 1.8477 (1.8630) Prec@1 50.781 (50.182) Prec@5 77.734 (79.357)
[2021-05-01 09:02:00 train_lshot.py:257] INFO Epoch: [9][80/150] Time 0.299 (0.368) Data 0.000 (0.075) Loss 1.8106 (1.8623) Prec@1 51.953 (50.039) Prec@5 81.250 (79.475)
[2021-05-01 09:02:03 train_lshot.py:257] INFO Epoch: [9][90/150] Time 0.279 (0.359) Data 0.000 (0.067) Loss 1.9340 (1.8621) Prec@1 51.172 (50.146) Prec@5 75.781 (79.366)
[2021-05-01 09:02:05 train_lshot.py:257] INFO Epoch: [9][100/150] Time 0.285 (0.352) Data 0.000 (0.060) Loss 1.9956 (1.8595) Prec@1 48.828 (50.244) Prec@5 77.734 (79.281)
[2021-05-01 09:02:08 train_lshot.py:257] INFO Epoch: [9][110/150] Time 0.282 (0.345) Data 0.000 (0.055) Loss 1.8447 (1.8568) Prec@1 53.516 (50.348) Prec@5 78.906 (79.276)
[2021-05-01 09:02:11 train_lshot.py:257] INFO Epoch: [9][120/150] Time 0.290 (0.340) Data 0.005 (0.050) Loss 1.6606 (1.8529) Prec@1 55.469 (50.326) Prec@5 83.203 (79.361)
[2021-05-01 09:02:14 train_lshot.py:257] INFO Epoch: [9][130/150] Time 0.287 (0.336) Data 0.000 (0.046) Loss 1.9300 (1.8506) Prec@1 51.953 (50.394) Prec@5 76.953 (79.383)
[2021-05-01 09:02:17 train_lshot.py:257] INFO Epoch: [9][140/150] Time 0.320 (0.334) Data 0.000 (0.043) Loss 1.7982 (1.8501) Prec@1 51.562 (50.435) Prec@5 81.641 (79.416)
[2021-05-01 09:02:27 train_lshot.py:257] INFO Epoch: [10][0/150] Time 6.781 (6.781) Data 6.314 (6.314) Loss 1.6939 (1.6939) Prec@1 53.516 (53.516) Prec@5 83.594 (83.594)
[2021-05-01 09:02:30 train_lshot.py:257] INFO Epoch: [10][10/150] Time 0.295 (0.911) Data 0.002 (0.575) Loss 1.7599 (1.7712) Prec@1 48.828 (51.811) Prec@5 85.156 (81.108)
[2021-05-01 09:02:33 train_lshot.py:257] INFO Epoch: [10][20/150] Time 0.276 (0.617) Data 0.000 (0.302) Loss 2.0080 (1.7776) Prec@1 50.391 (51.581) Prec@5 77.734 (80.878)
[2021-05-01 09:02:36 train_lshot.py:257] INFO Epoch: [10][30/150] Time 0.273 (0.508) Data 0.000 (0.204) Loss 1.9863 (1.7852) Prec@1 47.266 (51.310) Prec@5 77.344 (80.607)
[2021-05-01 09:02:39 train_lshot.py:257] INFO Epoch: [10][40/150] Time 0.277 (0.453) Data 0.000 (0.155) Loss 1.8128 (1.7922) Prec@1 53.516 (51.296) Prec@5 79.688 (80.497)
[2021-05-01 09:02:41 train_lshot.py:257] INFO Epoch: [10][50/150] Time 0.284 (0.420) Data 0.000 (0.124) Loss 1.7988 (1.7846) Prec@1 53.125 (51.578) Prec@5 78.906 (80.584)
[2021-05-01 09:02:44 train_lshot.py:257] INFO Epoch: [10][60/150] Time 0.278 (0.396) Data 0.000 (0.104) Loss 1.7098 (1.7823) Prec@1 53.125 (51.601) Prec@5 80.469 (80.558)
[2021-05-01 09:02:47 train_lshot.py:257] INFO Epoch: [10][70/150] Time 0.278 (0.380) Data 0.001 (0.089) Loss 1.7637 (1.7771) Prec@1 47.656 (51.728) Prec@5 80.469 (80.584)
[2021-05-01 09:02:50 train_lshot.py:257] INFO Epoch: [10][80/150] Time 0.281 (0.368) Data 0.000 (0.078) Loss 1.4742 (1.7783) Prec@1 62.109 (51.736) Prec@5 86.719 (80.551)
[2021-05-01 09:02:53 train_lshot.py:257] INFO Epoch: [10][90/150] Time 0.285 (0.359) Data 0.000 (0.070) Loss 1.7430 (1.7825) Prec@1 51.562 (51.614) Prec@5 83.594 (80.434)
[2021-05-01 09:02:55 train_lshot.py:257] INFO Epoch: [10][100/150] Time 0.282 (0.351) Data 0.000 (0.063) Loss 1.8203 (1.7766) Prec@1 50.000 (51.795) Prec@5 80.469 (80.527)
[2021-05-01 09:02:58 train_lshot.py:257] INFO Epoch: [10][110/150] Time 0.277 (0.346) Data 0.000 (0.057) Loss 1.6045 (1.7737) Prec@1 58.594 (51.837) Prec@5 84.375 (80.634)
[2021-05-01 09:03:03 train_lshot.py:257] INFO Epoch: [10][120/150] Time 0.327 (0.351) Data 0.000 (0.053) Loss 1.5931 (1.7689) Prec@1 59.766 (52.050) Prec@5 83.203 (80.714)
[2021-05-01 09:03:05 train_lshot.py:257] INFO Epoch: [10][130/150] Time 0.276 (0.346) Data 0.000 (0.049) Loss 1.8242 (1.7679) Prec@1 50.781 (52.141) Prec@5 79.297 (80.782)
[2021-05-01 09:03:08 train_lshot.py:257] INFO Epoch: [10][140/150] Time 0.283 (0.342) Data 0.000 (0.045) Loss 1.8647 (1.7621) Prec@1 53.125 (52.258) Prec@5 80.469 (80.870)
[2021-05-01 09:03:17 train_lshot.py:257] INFO Epoch: [11][0/150] Time 5.863 (5.863) Data 5.427 (5.427) Loss 1.7186 (1.7186) Prec@1 53.125 (53.125) Prec@5 79.297 (79.297)
[2021-05-01 09:03:21 train_lshot.py:257] INFO Epoch: [11][10/150] Time 0.302 (0.870) Data 0.001 (0.495) Loss 1.8074 (1.6860) Prec@1 51.953 (54.581) Prec@5 80.859 (82.777)
[2021-05-01 09:03:24 train_lshot.py:257] INFO Epoch: [11][20/150] Time 0.285 (0.592) Data 0.000 (0.260) Loss 1.5343 (1.6626) Prec@1 53.906 (54.427) Prec@5 85.938 (83.333)
[2021-05-01 09:03:27 train_lshot.py:257] INFO Epoch: [11][30/150] Time 0.273 (0.494) Data 0.000 (0.176) Loss 1.7581 (1.6831) Prec@1 51.562 (54.020) Prec@5 82.812 (82.913)
[2021-05-01 09:03:29 train_lshot.py:257] INFO Epoch: [11][40/150] Time 0.279 (0.442) Data 0.000 (0.133) Loss 1.8801 (1.6751) Prec@1 50.391 (54.383) Prec@5 80.078 (82.927)
[2021-05-01 09:03:32 train_lshot.py:257] INFO Epoch: [11][50/150] Time 0.284 (0.410) Data 0.000 (0.107) Loss 1.7374 (1.6827) Prec@1 55.469 (54.373) Prec@5 81.641 (82.713)
[2021-05-01 09:03:35 train_lshot.py:257] INFO Epoch: [11][60/150] Time 0.277 (0.389) Data 0.000 (0.090) Loss 1.8377 (1.6925) Prec@1 51.953 (54.220) Prec@5 80.078 (82.518)
[2021-05-01 09:03:38 train_lshot.py:257] INFO Epoch: [11][70/150] Time 0.285 (0.374) Data 0.002 (0.077) Loss 1.5660 (1.6894) Prec@1 55.469 (54.396) Prec@5 84.375 (82.455)
[2021-05-01 09:03:41 train_lshot.py:257] INFO Epoch: [11][80/150] Time 0.281 (0.363) Data 0.000 (0.068) Loss 1.6035 (1.6832) Prec@1 62.109 (54.668) Prec@5 82.422 (82.489)
[2021-05-01 09:03:43 train_lshot.py:257] INFO Epoch: [11][90/150] Time 0.279 (0.354) Data 0.001 (0.060) Loss 1.6277 (1.6874) Prec@1 55.078 (54.481) Prec@5 81.641 (82.246)
[2021-05-01 09:03:46 train_lshot.py:257] INFO Epoch: [11][100/150] Time 0.282 (0.347) Data 0.000 (0.054) Loss 1.7626 (1.6942) Prec@1 55.078 (54.247) Prec@5 81.250 (82.128)
[2021-05-01 09:03:49 train_lshot.py:257] INFO Epoch: [11][110/150] Time 0.280 (0.341) Data 0.000 (0.049) Loss 1.7153 (1.6907) Prec@1 55.078 (54.364) Prec@5 80.469 (82.168)
[2021-05-01 09:03:52 train_lshot.py:257] INFO Epoch: [11][120/150] Time 0.280 (0.336) Data 0.000 (0.045) Loss 1.4470 (1.6847) Prec@1 59.766 (54.481) Prec@5 87.500 (82.254)
[2021-05-01 09:03:55 train_lshot.py:257] INFO Epoch: [11][130/150] Time 0.288 (0.334) Data 0.000 (0.042) Loss 1.6284 (1.6846) Prec@1 54.297 (54.515) Prec@5 83.594 (82.210)
[2021-05-01 09:03:58 train_lshot.py:257] INFO Epoch: [11][140/150] Time 0.275 (0.330) Data 0.000 (0.039) Loss 1.3849 (1.6825) Prec@1 57.031 (54.499) Prec@5 88.281 (82.231)
[2021-05-01 09:04:29 train_lshot.py:119] INFO Meta Val 11: 0.5156000116467476
[2021-05-01 09:04:34 train_lshot.py:257] INFO Epoch: [12][0/150] Time 4.341 (4.341) Data 3.920 (3.920) Loss 1.4463 (1.4463) Prec@1 60.156 (60.156) Prec@5 85.547 (85.547)
[2021-05-01 09:04:39 train_lshot.py:257] INFO Epoch: [12][10/150] Time 0.329 (0.872) Data 0.001 (0.516) Loss 1.7056 (1.6523) Prec@1 55.469 (55.114) Prec@5 82.422 (81.854)
[2021-05-01 09:04:42 train_lshot.py:257] INFO Epoch: [12][20/150] Time 0.281 (0.594) Data 0.000 (0.270) Loss 1.7962 (1.6468) Prec@1 54.688 (55.618) Prec@5 79.297 (82.254)
[2021-05-01 09:04:45 train_lshot.py:257] INFO Epoch: [12][30/150] Time 0.288 (0.493) Data 0.001 (0.183) Loss 1.5196 (1.6147) Prec@1 56.641 (56.540) Prec@5 84.375 (82.901)
[2021-05-01 09:04:48 train_lshot.py:257] INFO Epoch: [12][40/150] Time 0.274 (0.443) Data 0.000 (0.139) Loss 1.6068 (1.6144) Prec@1 55.469 (56.526) Prec@5 82.031 (83.013)
[2021-05-01 09:04:50 train_lshot.py:257] INFO Epoch: [12][50/150] Time 0.276 (0.411) Data 0.000 (0.112) Loss 1.6963 (1.6091) Prec@1 54.297 (56.602) Prec@5 81.641 (83.188)
[2021-05-01 09:04:53 train_lshot.py:257] INFO Epoch: [12][60/150] Time 0.287 (0.390) Data 0.000 (0.093) Loss 1.5363 (1.6086) Prec@1 57.031 (56.513) Prec@5 83.203 (83.229)
[2021-05-01 09:04:56 train_lshot.py:257] INFO Epoch: [12][70/150] Time 0.280 (0.374) Data 0.001 (0.080) Loss 1.5634 (1.6122) Prec@1 59.375 (56.564) Prec@5 81.641 (83.170)
[2021-05-01 09:04:59 train_lshot.py:257] INFO Epoch: [12][80/150] Time 0.275 (0.362) Data 0.000 (0.070) Loss 1.7915 (1.6172) Prec@1 49.609 (56.409) Prec@5 79.297 (83.039)
[2021-05-01 09:05:01 train_lshot.py:257] INFO Epoch: [12][90/150] Time 0.277 (0.353) Data 0.000 (0.063) Loss 1.4054 (1.6126) Prec@1 60.938 (56.439) Prec@5 85.938 (83.203)
[2021-05-01 09:05:04 train_lshot.py:257] INFO Epoch: [12][100/150] Time 0.273 (0.345) Data 0.000 (0.057) Loss 1.5660 (1.6158) Prec@1 60.156 (56.351) Prec@5 82.422 (83.172)
[2021-05-01 09:05:07 train_lshot.py:257] INFO Epoch: [12][110/150] Time 0.301 (0.340) Data 0.000 (0.051) Loss 1.4847 (1.6155) Prec@1 55.469 (56.313) Prec@5 86.719 (83.256)
[2021-05-01 09:05:10 train_lshot.py:257] INFO Epoch: [12][120/150] Time 0.277 (0.336) Data 0.001 (0.047) Loss 1.5079 (1.6120) Prec@1 58.984 (56.344) Prec@5 84.375 (83.316)
[2021-05-01 09:05:14 train_lshot.py:257] INFO Epoch: [12][130/150] Time 0.321 (0.338) Data 0.000 (0.044) Loss 1.7519 (1.6087) Prec@1 57.422 (56.515) Prec@5 78.516 (83.385)
[2021-05-01 09:05:17 train_lshot.py:257] INFO Epoch: [12][140/150] Time 0.279 (0.335) Data 0.000 (0.041) Loss 1.5737 (1.6088) Prec@1 55.859 (56.466) Prec@5 85.156 (83.428)
[2021-05-01 09:05:26 train_lshot.py:257] INFO Epoch: [13][0/150] Time 6.714 (6.714) Data 6.287 (6.287) Loss 1.4997 (1.4997) Prec@1 57.812 (57.812) Prec@5 86.719 (86.719)
[2021-05-01 09:05:30 train_lshot.py:257] INFO Epoch: [13][10/150] Time 0.280 (0.933) Data 0.000 (0.574) Loss 1.5338 (1.5381) Prec@1 58.984 (58.061) Prec@5 86.328 (84.339)
[2021-05-01 09:05:33 train_lshot.py:257] INFO Epoch: [13][20/150] Time 0.274 (0.623) Data 0.000 (0.301) Loss 1.4669 (1.5243) Prec@1 57.812 (57.664) Prec@5 88.281 (84.766)
[2021-05-01 09:05:36 train_lshot.py:257] INFO Epoch: [13][30/150] Time 0.281 (0.514) Data 0.000 (0.204) Loss 1.4821 (1.5156) Prec@1 62.109 (58.052) Prec@5 84.375 (85.068)
[2021-05-01 09:05:38 train_lshot.py:257] INFO Epoch: [13][40/150] Time 0.275 (0.457) Data 0.000 (0.154) Loss 1.7204 (1.5302) Prec@1 51.562 (57.927) Prec@5 79.688 (84.756)
[2021-05-01 09:05:41 train_lshot.py:257] INFO Epoch: [13][50/150] Time 0.276 (0.422) Data 0.000 (0.124) Loss 1.3414 (1.5354) Prec@1 60.938 (57.981) Prec@5 89.062 (84.819)
[2021-05-01 09:05:44 train_lshot.py:257] INFO Epoch: [13][60/150] Time 0.276 (0.399) Data 0.000 (0.104) Loss 1.5310 (1.5358) Prec@1 61.328 (58.126) Prec@5 82.031 (84.734)
[2021-05-01 09:05:47 train_lshot.py:257] INFO Epoch: [13][70/150] Time 0.300 (0.383) Data 0.001 (0.089) Loss 1.4584 (1.5400) Prec@1 57.812 (58.082) Prec@5 87.109 (84.639)
[2021-05-01 09:05:50 train_lshot.py:257] INFO Epoch: [13][80/150] Time 0.283 (0.370) Data 0.000 (0.078) Loss 1.4925 (1.5405) Prec@1 60.156 (58.039) Prec@5 85.547 (84.587)
[2021-05-01 09:05:52 train_lshot.py:257] INFO Epoch: [13][90/150] Time 0.288 (0.360) Data 0.000 (0.070) Loss 1.5632 (1.5386) Prec@1 59.375 (58.147) Prec@5 83.203 (84.530)
[2021-05-01 09:05:55 train_lshot.py:257] INFO Epoch: [13][100/150] Time 0.288 (0.353) Data 0.000 (0.063) Loss 1.5695 (1.5396) Prec@1 56.250 (58.052) Prec@5 83.594 (84.479)
[2021-05-01 09:05:58 train_lshot.py:257] INFO Epoch: [13][110/150] Time 0.286 (0.346) Data 0.000 (0.057) Loss 1.5236 (1.5398) Prec@1 58.984 (58.048) Prec@5 84.766 (84.495)
[2021-05-01 09:06:01 train_lshot.py:257] INFO Epoch: [13][120/150] Time 0.277 (0.342) Data 0.000 (0.053) Loss 1.3621 (1.5395) Prec@1 60.156 (57.951) Prec@5 87.500 (84.520)
[2021-05-01 09:06:04 train_lshot.py:257] INFO Epoch: [13][130/150] Time 0.294 (0.338) Data 0.000 (0.049) Loss 1.6227 (1.5410) Prec@1 60.156 (58.000) Prec@5 81.641 (84.411)
[2021-05-01 09:06:07 train_lshot.py:257] INFO Epoch: [13][140/150] Time 0.286 (0.334) Data 0.000 (0.045) Loss 1.4838 (1.5420) Prec@1 59.766 (57.968) Prec@5 84.766 (84.381)
[2021-05-01 09:06:17 train_lshot.py:257] INFO Epoch: [14][0/150] Time 6.836 (6.836) Data 6.372 (6.372) Loss 1.6109 (1.6109) Prec@1 57.812 (57.812) Prec@5 82.812 (82.812)
[2021-05-01 09:06:20 train_lshot.py:257] INFO Epoch: [14][10/150] Time 0.284 (0.921) Data 0.000 (0.587) Loss 1.2264 (1.4690) Prec@1 66.797 (60.085) Prec@5 90.234 (85.831)
[2021-05-01 09:06:23 train_lshot.py:257] INFO Epoch: [14][20/150] Time 0.279 (0.616) Data 0.000 (0.307) Loss 1.4193 (1.4877) Prec@1 62.109 (59.654) Prec@5 87.109 (85.510)
[2021-05-01 09:06:26 train_lshot.py:257] INFO Epoch: [14][30/150] Time 0.278 (0.509) Data 0.000 (0.208) Loss 1.6166 (1.4942) Prec@1 56.641 (59.791) Prec@5 84.766 (85.370)
[2021-05-01 09:06:28 train_lshot.py:257] INFO Epoch: [14][40/150] Time 0.275 (0.453) Data 0.001 (0.158) Loss 1.5497 (1.4788) Prec@1 56.250 (60.109) Prec@5 87.500 (85.547)
[2021-05-01 09:06:31 train_lshot.py:257] INFO Epoch: [14][50/150] Time 0.278 (0.419) Data 0.000 (0.127) Loss 1.5143 (1.4686) Prec@1 60.547 (60.524) Prec@5 84.766 (85.677)
[2021-05-01 09:06:34 train_lshot.py:257] INFO Epoch: [14][60/150] Time 0.277 (0.396) Data 0.000 (0.106) Loss 1.2465 (1.4579) Prec@1 66.406 (60.707) Prec@5 89.453 (85.752)
[2021-05-01 09:06:37 train_lshot.py:257] INFO Epoch: [14][70/150] Time 0.288 (0.380) Data 0.001 (0.091) Loss 1.6730 (1.4668) Prec@1 55.859 (60.332) Prec@5 80.078 (85.574)
[2021-05-01 09:06:40 train_lshot.py:257] INFO Epoch: [14][80/150] Time 0.282 (0.368) Data 0.000 (0.080) Loss 1.5810 (1.4693) Prec@1 53.125 (60.195) Prec@5 83.594 (85.465)
[2021-05-01 09:06:43 train_lshot.py:257] INFO Epoch: [14][90/150] Time 0.289 (0.362) Data 0.000 (0.071) Loss 1.2854 (1.4745) Prec@1 64.844 (59.976) Prec@5 87.500 (85.401)
[2021-05-01 09:06:46 train_lshot.py:257] INFO Epoch: [14][100/150] Time 0.285 (0.354) Data 0.000 (0.064) Loss 1.4187 (1.4747) Prec@1 58.203 (60.032) Prec@5 88.672 (85.326)
[2021-05-01 09:06:48 train_lshot.py:257] INFO Epoch: [14][110/150] Time 0.291 (0.348) Data 0.000 (0.058) Loss 1.5935 (1.4810) Prec@1 51.562 (59.780) Prec@5 83.594 (85.290)
[2021-05-01 09:06:52 train_lshot.py:257] INFO Epoch: [14][120/150] Time 0.359 (0.352) Data 0.000 (0.054) Loss 1.4123 (1.4870) Prec@1 58.594 (59.636) Prec@5 88.672 (85.172)
[2021-05-01 09:06:55 train_lshot.py:257] INFO Epoch: [14][130/150] Time 0.279 (0.347) Data 0.000 (0.050) Loss 1.3510 (1.4861) Prec@1 60.156 (59.608) Prec@5 89.453 (85.186)
[2021-05-01 09:06:58 train_lshot.py:257] INFO Epoch: [14][140/150] Time 0.273 (0.343) Data 0.000 (0.046) Loss 1.4360 (1.4830) Prec@1 59.766 (59.633) Prec@5 88.672 (85.273)
[2021-05-01 09:07:07 train_lshot.py:257] INFO Epoch: [15][0/150] Time 5.983 (5.983) Data 5.537 (5.537) Loss 1.5242 (1.5242) Prec@1 60.156 (60.156) Prec@5 83.203 (83.203)
[2021-05-01 09:07:11 train_lshot.py:257] INFO Epoch: [15][10/150] Time 0.310 (0.907) Data 0.000 (0.506) Loss 1.2324 (1.3953) Prec@1 66.797 (63.104) Prec@5 89.453 (85.582)
[2021-05-01 09:07:14 train_lshot.py:257] INFO Epoch: [15][20/150] Time 0.281 (0.613) Data 0.000 (0.265) Loss 1.3440 (1.3975) Prec@1 62.109 (62.333) Prec@5 86.719 (85.975)
[2021-05-01 09:07:17 train_lshot.py:257] INFO Epoch: [15][30/150] Time 0.273 (0.506) Data 0.000 (0.180) Loss 1.3549 (1.3882) Prec@1 64.453 (62.664) Prec@5 84.766 (86.152)
[2021-05-01 09:07:20 train_lshot.py:257] INFO Epoch: [15][40/150] Time 0.280 (0.451) Data 0.000 (0.136) Loss 1.4841 (1.3941) Prec@1 58.203 (62.176) Prec@5 83.594 (86.252)
[2021-05-01 09:07:23 train_lshot.py:257] INFO Epoch: [15][50/150] Time 0.294 (0.417) Data 0.000 (0.109) Loss 1.5155 (1.4086) Prec@1 57.422 (61.673) Prec@5 84.766 (86.114)
[2021-05-01 09:07:26 train_lshot.py:257] INFO Epoch: [15][60/150] Time 0.274 (0.394) Data 0.000 (0.091) Loss 1.5137 (1.4100) Prec@1 56.250 (61.360) Prec@5 82.422 (86.078)
[2021-05-01 09:07:28 train_lshot.py:257] INFO Epoch: [15][70/150] Time 0.280 (0.378) Data 0.001 (0.079) Loss 1.4552 (1.4114) Prec@1 64.453 (61.251) Prec@5 84.766 (86.119)
[2021-05-01 09:07:31 train_lshot.py:257] INFO Epoch: [15][80/150] Time 0.272 (0.366) Data 0.000 (0.069) Loss 1.3923 (1.4162) Prec@1 58.984 (61.068) Prec@5 86.719 (86.077)
[2021-05-01 09:07:34 train_lshot.py:257] INFO Epoch: [15][90/150] Time 0.283 (0.357) Data 0.000 (0.061) Loss 1.2863 (1.4179) Prec@1 64.453 (61.079) Prec@5 89.453 (86.002)
[2021-05-01 09:07:37 train_lshot.py:257] INFO Epoch: [15][100/150] Time 0.285 (0.349) Data 0.000 (0.055) Loss 1.3648 (1.4222) Prec@1 62.891 (61.026) Prec@5 89.453 (85.926)
[2021-05-01 09:07:40 train_lshot.py:257] INFO Epoch: [15][110/150] Time 0.288 (0.343) Data 0.000 (0.050) Loss 1.3309 (1.4233) Prec@1 63.672 (60.938) Prec@5 85.547 (85.888)
[2021-05-01 09:07:43 train_lshot.py:257] INFO Epoch: [15][120/150] Time 0.301 (0.342) Data 0.000 (0.046) Loss 1.5503 (1.4217) Prec@1 58.594 (61.009) Prec@5 82.812 (85.957)
[2021-05-01 09:07:46 train_lshot.py:257] INFO Epoch: [15][130/150] Time 0.276 (0.337) Data 0.000 (0.043) Loss 1.4097 (1.4234) Prec@1 62.500 (60.955) Prec@5 84.766 (85.890)
[2021-05-01 09:07:48 train_lshot.py:257] INFO Epoch: [15][140/150] Time 0.293 (0.334) Data 0.000 (0.040) Loss 1.3121 (1.4265) Prec@1 66.016 (60.957) Prec@5 86.328 (85.860)
[2021-05-01 09:08:20 train_lshot.py:119] INFO Meta Val 15: 0.5519200122952461
[2021-05-01 09:08:27 train_lshot.py:257] INFO Epoch: [16][0/150] Time 6.572 (6.572) Data 6.109 (6.109) Loss 1.4240 (1.4240) Prec@1 58.594 (58.594) Prec@5 87.109 (87.109)
[2021-05-01 09:08:30 train_lshot.py:257] INFO Epoch: [16][10/150] Time 0.279 (0.898) Data 0.001 (0.556) Loss 1.4762 (1.3504) Prec@1 59.766 (62.855) Prec@5 83.203 (87.322)
[2021-05-01 09:08:33 train_lshot.py:257] INFO Epoch: [16][20/150] Time 0.273 (0.604) Data 0.000 (0.291) Loss 1.1928 (1.3263) Prec@1 66.797 (63.374) Prec@5 91.016 (87.481)
[2021-05-01 09:08:36 train_lshot.py:257] INFO Epoch: [16][30/150] Time 0.281 (0.499) Data 0.000 (0.198) Loss 1.3194 (1.3468) Prec@1 62.109 (62.903) Prec@5 89.453 (87.399)
[2021-05-01 09:08:39 train_lshot.py:257] INFO Epoch: [16][40/150] Time 0.279 (0.448) Data 0.000 (0.149) Loss 1.3847 (1.3562) Prec@1 60.547 (63.005) Prec@5 85.547 (87.157)
[2021-05-01 09:08:41 train_lshot.py:257] INFO Epoch: [16][50/150] Time 0.284 (0.416) Data 0.000 (0.120) Loss 1.4487 (1.3534) Prec@1 61.719 (63.082) Prec@5 86.328 (87.270)
[2021-05-01 09:08:44 train_lshot.py:257] INFO Epoch: [16][60/150] Time 0.276 (0.394) Data 0.000 (0.101) Loss 1.2421 (1.3483) Prec@1 67.578 (63.134) Prec@5 89.844 (87.346)
[2021-05-01 09:08:47 train_lshot.py:257] INFO Epoch: [16][70/150] Time 0.275 (0.378) Data 0.001 (0.086) Loss 1.3790 (1.3583) Prec@1 63.281 (62.847) Prec@5 85.547 (87.065)
[2021-05-01 09:08:50 train_lshot.py:257] INFO Epoch: [16][80/150] Time 0.282 (0.365) Data 0.000 (0.076) Loss 1.4447 (1.3680) Prec@1 59.375 (62.625) Prec@5 86.328 (86.931)
[2021-05-01 09:08:53 train_lshot.py:257] INFO Epoch: [16][90/150] Time 0.296 (0.356) Data 0.000 (0.068) Loss 1.5876 (1.3734) Prec@1 57.031 (62.440) Prec@5 82.422 (86.852)
[2021-05-01 09:08:55 train_lshot.py:257] INFO Epoch: [16][100/150] Time 0.283 (0.348) Data 0.000 (0.061) Loss 1.2730 (1.3757) Prec@1 64.844 (62.264) Prec@5 88.281 (86.858)
[2021-05-01 09:08:58 train_lshot.py:257] INFO Epoch: [16][110/150] Time 0.283 (0.342) Data 0.000 (0.055) Loss 1.5241 (1.3770) Prec@1 57.812 (62.254) Prec@5 83.984 (86.898)
[2021-05-01 09:09:01 train_lshot.py:257] INFO Epoch: [16][120/150] Time 0.285 (0.337) Data 0.000 (0.051) Loss 1.4142 (1.3791) Prec@1 61.328 (62.239) Prec@5 85.547 (86.861)
[2021-05-01 09:09:04 train_lshot.py:257] INFO Epoch: [16][130/150] Time 0.276 (0.333) Data 0.000 (0.047) Loss 1.4244 (1.3790) Prec@1 64.453 (62.258) Prec@5 86.719 (86.883)
[2021-05-01 09:09:08 train_lshot.py:257] INFO Epoch: [16][140/150] Time 0.301 (0.338) Data 0.000 (0.044) Loss 1.5026 (1.3832) Prec@1 60.156 (62.229) Prec@5 84.375 (86.782)
[2021-05-01 09:09:17 train_lshot.py:257] INFO Epoch: [17][0/150] Time 6.146 (6.146) Data 5.734 (5.734) Loss 1.2414 (1.2414) Prec@1 65.625 (65.625) Prec@5 87.891 (87.891)
[2021-05-01 09:09:21 train_lshot.py:257] INFO Epoch: [17][10/150] Time 0.284 (0.885) Data 0.001 (0.523) Loss 1.2480 (1.2736) Prec@1 64.844 (65.447) Prec@5 87.891 (87.536)
[2021-05-01 09:09:23 train_lshot.py:257] INFO Epoch: [17][20/150] Time 0.281 (0.598) Data 0.000 (0.275) Loss 1.3724 (1.2919) Prec@1 62.109 (64.769) Prec@5 86.719 (87.500)
[2021-05-01 09:09:26 train_lshot.py:257] INFO Epoch: [17][30/150] Time 0.278 (0.497) Data 0.000 (0.186) Loss 1.1874 (1.3043) Prec@1 65.234 (64.264) Prec@5 91.016 (87.336)
[2021-05-01 09:09:29 train_lshot.py:257] INFO Epoch: [17][40/150] Time 0.280 (0.444) Data 0.000 (0.141) Loss 1.2116 (1.3052) Prec@1 64.453 (64.186) Prec@5 91.016 (87.529)
[2021-05-01 09:09:32 train_lshot.py:257] INFO Epoch: [17][50/150] Time 0.273 (0.412) Data 0.000 (0.113) Loss 1.4619 (1.3130) Prec@1 61.328 (63.917) Prec@5 86.719 (87.469)
[2021-05-01 09:09:35 train_lshot.py:257] INFO Epoch: [17][60/150] Time 0.282 (0.390) Data 0.000 (0.095) Loss 1.2812 (1.3149) Prec@1 62.109 (63.902) Prec@5 90.234 (87.500)
[2021-05-01 09:09:37 train_lshot.py:257] INFO Epoch: [17][70/150] Time 0.280 (0.375) Data 0.001 (0.081) Loss 1.1914 (1.3085) Prec@1 65.625 (64.112) Prec@5 89.062 (87.555)
[2021-05-01 09:09:41 train_lshot.py:257] INFO Epoch: [17][80/150] Time 0.308 (0.368) Data 0.000 (0.071) Loss 1.4717 (1.3145) Prec@1 59.375 (63.870) Prec@5 83.203 (87.457)
[2021-05-01 09:09:44 train_lshot.py:257] INFO Epoch: [17][90/150] Time 0.295 (0.359) Data 0.000 (0.064) Loss 1.2324 (1.3164) Prec@1 66.016 (63.749) Prec@5 87.891 (87.513)
[2021-05-01 09:09:46 train_lshot.py:257] INFO Epoch: [17][100/150] Time 0.283 (0.351) Data 0.000 (0.057) Loss 1.2199 (1.3100) Prec@1 63.672 (63.954) Prec@5 88.672 (87.620)
[2021-05-01 09:09:49 train_lshot.py:257] INFO Epoch: [17][110/150] Time 0.287 (0.345) Data 0.000 (0.052) Loss 1.2841 (1.3122) Prec@1 63.672 (63.915) Prec@5 87.500 (87.577)
[2021-05-01 09:09:52 train_lshot.py:257] INFO Epoch: [17][120/150] Time 0.273 (0.340) Data 0.000 (0.048) Loss 1.3328 (1.3095) Prec@1 63.672 (63.940) Prec@5 83.203 (87.581)
[2021-05-01 09:09:55 train_lshot.py:257] INFO Epoch: [17][130/150] Time 0.287 (0.336) Data 0.001 (0.044) Loss 1.3578 (1.3078) Prec@1 66.406 (63.976) Prec@5 87.109 (87.583)
[2021-05-01 09:09:58 train_lshot.py:257] INFO Epoch: [17][140/150] Time 0.283 (0.333) Data 0.000 (0.041) Loss 1.2643 (1.3052) Prec@1 64.453 (64.026) Prec@5 87.500 (87.669)
[2021-05-01 09:10:08 train_lshot.py:257] INFO Epoch: [18][0/150] Time 6.246 (6.246) Data 5.813 (5.813) Loss 1.3520 (1.3520) Prec@1 65.625 (65.625) Prec@5 87.109 (87.109)
[2021-05-01 09:10:12 train_lshot.py:257] INFO Epoch: [18][10/150] Time 0.307 (0.884) Data 0.001 (0.530) Loss 1.2910 (1.2736) Prec@1 65.625 (65.980) Prec@5 86.328 (87.713)
[2021-05-01 09:10:15 train_lshot.py:257] INFO Epoch: [18][20/150] Time 0.284 (0.599) Data 0.000 (0.278) Loss 1.2434 (1.2608) Prec@1 66.797 (65.625) Prec@5 90.625 (88.225)
[2021-05-01 09:10:17 train_lshot.py:257] INFO Epoch: [18][30/150] Time 0.276 (0.497) Data 0.000 (0.188) Loss 1.1166 (1.2563) Prec@1 66.406 (65.461) Prec@5 90.234 (88.243)
[2021-05-01 09:10:20 train_lshot.py:257] INFO Epoch: [18][40/150] Time 0.286 (0.445) Data 0.000 (0.142) Loss 1.1653 (1.2494) Prec@1 70.312 (65.682) Prec@5 89.844 (88.558)
[2021-05-01 09:10:23 train_lshot.py:257] INFO Epoch: [18][50/150] Time 0.278 (0.413) Data 0.001 (0.115) Loss 1.2633 (1.2583) Prec@1 64.844 (65.464) Prec@5 89.062 (88.343)
[2021-05-01 09:10:26 train_lshot.py:257] INFO Epoch: [18][60/150] Time 0.286 (0.392) Data 0.000 (0.096) Loss 1.3886 (1.2634) Prec@1 62.891 (65.273) Prec@5 85.156 (88.236)
[2021-05-01 09:10:29 train_lshot.py:257] INFO Epoch: [18][70/150] Time 0.289 (0.376) Data 0.001 (0.082) Loss 1.3109 (1.2692) Prec@1 66.016 (65.036) Prec@5 87.109 (88.111)
[2021-05-01 09:10:32 train_lshot.py:257] INFO Epoch: [18][80/150] Time 0.274 (0.364) Data 0.000 (0.072) Loss 1.2110 (1.2713) Prec@1 66.797 (65.114) Prec@5 89.453 (88.156)
[2021-05-01 09:10:34 train_lshot.py:257] INFO Epoch: [18][90/150] Time 0.289 (0.356) Data 0.000 (0.064) Loss 1.3925 (1.2758) Prec@1 62.500 (64.925) Prec@5 86.328 (88.071)
[2021-05-01 09:10:37 train_lshot.py:257] INFO Epoch: [18][100/150] Time 0.412 (0.351) Data 0.001 (0.058) Loss 1.1868 (1.2760) Prec@1 71.094 (64.952) Prec@5 89.062 (88.022)
[2021-05-01 09:10:41 train_lshot.py:257] INFO Epoch: [18][110/150] Time 0.278 (0.347) Data 0.000 (0.053) Loss 1.3956 (1.2810) Prec@1 63.281 (64.805) Prec@5 85.938 (88.000)
[2021-05-01 09:10:43 train_lshot.py:257] INFO Epoch: [18][120/150] Time 0.283 (0.341) Data 0.000 (0.049) Loss 1.2287 (1.2853) Prec@1 66.797 (64.640) Prec@5 89.453 (87.907)
[2021-05-01 09:10:47 train_lshot.py:257] INFO Epoch: [18][130/150] Time 0.350 (0.344) Data 0.000 (0.045) Loss 1.1951 (1.2858) Prec@1 65.625 (64.626) Prec@5 88.672 (87.891)
[2021-05-01 09:10:50 train_lshot.py:257] INFO Epoch: [18][140/150] Time 0.278 (0.341) Data 0.000 (0.042) Loss 1.2085 (1.2825) Prec@1 68.359 (64.697) Prec@5 89.062 (87.982)
[2021-05-01 09:11:01 train_lshot.py:257] INFO Epoch: [19][0/150] Time 7.655 (7.655) Data 7.272 (7.272) Loss 1.2007 (1.2007) Prec@1 65.234 (65.234) Prec@5 88.672 (88.672)
[2021-05-01 09:11:04 train_lshot.py:257] INFO Epoch: [19][10/150] Time 0.286 (0.990) Data 0.000 (0.662) Loss 1.2247 (1.1752) Prec@1 66.797 (68.395) Prec@5 89.062 (89.134)
[2021-05-01 09:11:07 train_lshot.py:257] INFO Epoch: [19][20/150] Time 0.281 (0.652) Data 0.000 (0.347) Loss 1.1370 (1.1991) Prec@1 67.969 (67.076) Prec@5 89.844 (89.044)
[2021-05-01 09:11:10 train_lshot.py:257] INFO Epoch: [19][30/150] Time 0.279 (0.534) Data 0.000 (0.235) Loss 1.1584 (1.2162) Prec@1 68.750 (66.381) Prec@5 90.625 (89.201)
[2021-05-01 09:11:12 train_lshot.py:257] INFO Epoch: [19][40/150] Time 0.275 (0.472) Data 0.001 (0.178) Loss 1.1675 (1.2197) Prec@1 66.406 (66.206) Prec@5 90.625 (89.024)
[2021-05-01 09:11:15 train_lshot.py:257] INFO Epoch: [19][50/150] Time 0.281 (0.434) Data 0.000 (0.143) Loss 1.2640 (1.2120) Prec@1 64.062 (66.322) Prec@5 87.109 (89.139)
[2021-05-01 09:11:18 train_lshot.py:257] INFO Epoch: [19][60/150] Time 0.280 (0.409) Data 0.000 (0.120) Loss 1.2935 (1.2232) Prec@1 67.188 (66.259) Prec@5 85.938 (88.864)
[2021-05-01 09:11:21 train_lshot.py:257] INFO Epoch: [19][70/150] Time 0.286 (0.390) Data 0.001 (0.103) Loss 1.1673 (1.2335) Prec@1 66.406 (65.950) Prec@5 91.797 (88.809)
[2021-05-01 09:11:24 train_lshot.py:257] INFO Epoch: [19][80/150] Time 0.273 (0.377) Data 0.000 (0.090) Loss 1.4379 (1.2348) Prec@1 58.984 (65.972) Prec@5 85.938 (88.802)
[2021-05-01 09:11:26 train_lshot.py:257] INFO Epoch: [19][90/150] Time 0.279 (0.366) Data 0.000 (0.080) Loss 1.2904 (1.2330) Prec@1 63.281 (66.007) Prec@5 92.188 (88.904)
[2021-05-01 09:11:29 train_lshot.py:257] INFO Epoch: [19][100/150] Time 0.274 (0.358) Data 0.000 (0.072) Loss 1.3056 (1.2373) Prec@1 63.672 (65.880) Prec@5 88.672 (88.830)
[2021-05-01 09:11:33 train_lshot.py:257] INFO Epoch: [19][110/150] Time 0.288 (0.364) Data 0.000 (0.066) Loss 1.3858 (1.2407) Prec@1 62.500 (65.731) Prec@5 85.156 (88.721)
[2021-05-01 09:11:36 train_lshot.py:257] INFO Epoch: [19][120/150] Time 0.282 (0.357) Data 0.000 (0.060) Loss 1.1689 (1.2402) Prec@1 66.406 (65.815) Prec@5 89.844 (88.717)
[2021-05-01 09:11:39 train_lshot.py:257] INFO Epoch: [19][130/150] Time 0.285 (0.351) Data 0.000 (0.056) Loss 1.3126 (1.2452) Prec@1 66.797 (65.706) Prec@5 88.281 (88.627)
[2021-05-01 09:11:42 train_lshot.py:257] INFO Epoch: [19][140/150] Time 0.283 (0.346) Data 0.000 (0.052) Loss 1.1568 (1.2450) Prec@1 67.188 (65.639) Prec@5 91.797 (88.614)
[2021-05-01 09:12:13 train_lshot.py:119] INFO Meta Val 19: 0.5529333457350731
[2021-05-01 09:12:19 train_lshot.py:257] INFO Epoch: [20][0/150] Time 6.153 (6.153) Data 5.725 (5.725) Loss 1.2546 (1.2546) Prec@1 66.797 (66.797) Prec@5 87.500 (87.500)
[2021-05-01 09:12:23 train_lshot.py:257] INFO Epoch: [20][10/150] Time 0.288 (0.879) Data 0.000 (0.521) Loss 1.0865 (1.2006) Prec@1 69.141 (66.513) Prec@5 90.625 (89.702)
[2021-05-01 09:12:26 train_lshot.py:257] INFO Epoch: [20][20/150] Time 0.273 (0.599) Data 0.000 (0.273) Loss 1.3188 (1.2089) Prec@1 63.281 (66.276) Prec@5 88.672 (89.490)
[2021-05-01 09:12:29 train_lshot.py:257] INFO Epoch: [20][30/150] Time 0.280 (0.496) Data 0.000 (0.185) Loss 1.2341 (1.2131) Prec@1 70.312 (66.520) Prec@5 83.594 (89.239)
[2021-05-01 09:12:31 train_lshot.py:257] INFO Epoch: [20][40/150] Time 0.282 (0.443) Data 0.000 (0.140) Loss 1.2208 (1.2088) Prec@1 66.406 (66.482) Prec@5 87.891 (89.082)
[2021-05-01 09:12:34 train_lshot.py:257] INFO Epoch: [20][50/150] Time 0.279 (0.412) Data 0.000 (0.113) Loss 1.2030 (1.2086) Prec@1 67.578 (66.491) Prec@5 89.453 (89.062)
[2021-05-01 09:12:37 train_lshot.py:257] INFO Epoch: [20][60/150] Time 0.278 (0.391) Data 0.000 (0.094) Loss 1.0953 (1.2047) Prec@1 69.531 (66.541) Prec@5 90.625 (89.030)
[2021-05-01 09:12:40 train_lshot.py:257] INFO Epoch: [20][70/150] Time 0.281 (0.375) Data 0.001 (0.081) Loss 1.1699 (1.2031) Prec@1 68.359 (66.648) Prec@5 89.844 (89.013)
[2021-05-01 09:12:43 train_lshot.py:257] INFO Epoch: [20][80/150] Time 0.279 (0.363) Data 0.000 (0.071) Loss 1.0226 (1.2077) Prec@1 71.094 (66.411) Prec@5 92.578 (89.009)
[2021-05-01 09:12:45 train_lshot.py:257] INFO Epoch: [20][90/150] Time 0.287 (0.354) Data 0.000 (0.063) Loss 1.1992 (1.2109) Prec@1 66.016 (66.329) Prec@5 89.062 (88.985)
[2021-05-01 09:12:48 train_lshot.py:257] INFO Epoch: [20][100/150] Time 0.282 (0.346) Data 0.000 (0.057) Loss 0.9768 (1.2014) Prec@1 71.094 (66.515) Prec@5 92.188 (89.144)
[2021-05-01 09:12:51 train_lshot.py:257] INFO Epoch: [20][110/150] Time 0.287 (0.341) Data 0.000 (0.052) Loss 1.2158 (1.2015) Prec@1 66.406 (66.540) Prec@5 88.672 (89.154)
[2021-05-01 09:12:54 train_lshot.py:257] INFO Epoch: [20][120/150] Time 0.282 (0.336) Data 0.000 (0.048) Loss 1.3069 (1.2017) Prec@1 62.891 (66.561) Prec@5 89.844 (89.166)
[2021-05-01 09:12:57 train_lshot.py:257] INFO Epoch: [20][130/150] Time 0.280 (0.332) Data 0.000 (0.044) Loss 1.1573 (1.2034) Prec@1 68.359 (66.558) Prec@5 90.625 (89.167)
[2021-05-01 09:13:01 train_lshot.py:257] INFO Epoch: [20][140/150] Time 0.511 (0.336) Data 0.000 (0.041) Loss 1.3129 (1.2059) Prec@1 63.281 (66.473) Prec@5 87.109 (89.148)
[2021-05-01 09:13:08 train_lshot.py:257] INFO Epoch: [21][0/150] Time 4.328 (4.328) Data 3.951 (3.951) Loss 1.2196 (1.2196) Prec@1 67.188 (67.188) Prec@5 88.672 (88.672)
[2021-05-01 09:13:12 train_lshot.py:257] INFO Epoch: [21][10/150] Time 0.416 (0.757) Data 0.003 (0.368) Loss 1.2165 (1.1412) Prec@1 66.406 (67.898) Prec@5 89.453 (90.909)
[2021-05-01 09:13:15 train_lshot.py:257] INFO Epoch: [21][20/150] Time 0.289 (0.555) Data 0.001 (0.194) Loss 1.1276 (1.1313) Prec@1 67.578 (68.285) Prec@5 91.406 (90.755)
[2021-05-01 09:13:18 train_lshot.py:257] INFO Epoch: [21][30/150] Time 0.284 (0.471) Data 0.000 (0.132) Loss 1.1864 (1.1319) Prec@1 67.578 (68.523) Prec@5 89.453 (90.562)
[2021-05-01 09:13:21 train_lshot.py:257] INFO Epoch: [21][40/150] Time 0.281 (0.425) Data 0.000 (0.100) Loss 1.2211 (1.1395) Prec@1 67.578 (68.436) Prec@5 89.844 (90.282)
[2021-05-01 09:13:24 train_lshot.py:257] INFO Epoch: [21][50/150] Time 0.276 (0.396) Data 0.000 (0.080) Loss 1.2267 (1.1491) Prec@1 67.578 (68.160) Prec@5 87.891 (90.112)
[2021-05-01 09:13:27 train_lshot.py:257] INFO Epoch: [21][60/150] Time 0.281 (0.377) Data 0.000 (0.067) Loss 1.2276 (1.1604) Prec@1 66.797 (68.078) Prec@5 90.234 (89.965)
[2021-05-01 09:13:30 train_lshot.py:257] INFO Epoch: [21][70/150] Time 0.276 (0.364) Data 0.001 (0.058) Loss 1.3359 (1.1647) Prec@1 64.453 (67.919) Prec@5 89.062 (89.833)
[2021-05-01 09:13:33 train_lshot.py:257] INFO Epoch: [21][80/150] Time 0.293 (0.356) Data 0.000 (0.051) Loss 1.1004 (1.1635) Prec@1 69.922 (67.998) Prec@5 91.016 (89.834)
[2021-05-01 09:13:36 train_lshot.py:257] INFO Epoch: [21][90/150] Time 0.513 (0.350) Data 0.000 (0.045) Loss 1.2705 (1.1713) Prec@1 69.531 (67.887) Prec@5 86.328 (89.633)
[2021-05-01 09:13:39 train_lshot.py:257] INFO Epoch: [21][100/150] Time 0.286 (0.349) Data 0.000 (0.041) Loss 1.1833 (1.1741) Prec@1 69.922 (67.741) Prec@5 89.062 (89.573)
[2021-05-01 09:13:42 train_lshot.py:257] INFO Epoch: [21][110/150] Time 0.823 (0.347) Data 0.000 (0.037) Loss 1.2401 (1.1727) Prec@1 67.578 (67.729) Prec@5 88.672 (89.604)
[2021-05-01 09:13:46 train_lshot.py:257] INFO Epoch: [21][120/150] Time 0.285 (0.346) Data 0.000 (0.034) Loss 1.2387 (1.1701) Prec@1 65.625 (67.788) Prec@5 88.281 (89.618)
[2021-05-01 09:13:48 train_lshot.py:257] INFO Epoch: [21][130/150] Time 0.282 (0.341) Data 0.000 (0.031) Loss 1.3877 (1.1715) Prec@1 61.328 (67.736) Prec@5 86.328 (89.575)
[2021-05-01 09:13:51 train_lshot.py:257] INFO Epoch: [21][140/150] Time 0.278 (0.336) Data 0.000 (0.029) Loss 1.2172 (1.1711) Prec@1 66.406 (67.742) Prec@5 89.062 (89.592)
[2021-05-01 09:14:02 train_lshot.py:257] INFO Epoch: [22][0/150] Time 6.251 (6.251) Data 5.811 (5.811) Loss 1.0947 (1.0947) Prec@1 69.141 (69.141) Prec@5 91.406 (91.406)
[2021-05-01 09:14:05 train_lshot.py:257] INFO Epoch: [22][10/150] Time 0.365 (0.893) Data 0.001 (0.533) Loss 1.3432 (1.1046) Prec@1 61.719 (69.922) Prec@5 90.234 (90.234)
[2021-05-01 09:14:08 train_lshot.py:257] INFO Epoch: [22][20/150] Time 0.283 (0.613) Data 0.000 (0.280) Loss 1.1073 (1.1246) Prec@1 70.312 (68.601) Prec@5 90.625 (90.420)
[2021-05-01 09:14:11 train_lshot.py:257] INFO Epoch: [22][30/150] Time 0.284 (0.507) Data 0.001 (0.190) Loss 0.9452 (1.1109) Prec@1 73.047 (69.027) Prec@5 92.969 (90.486)
[2021-05-01 09:14:14 train_lshot.py:257] INFO Epoch: [22][40/150] Time 0.285 (0.453) Data 0.001 (0.143) Loss 1.0007 (1.1026) Prec@1 67.578 (69.131) Prec@5 90.625 (90.654)
[2021-05-01 09:14:17 train_lshot.py:257] INFO Epoch: [22][50/150] Time 0.282 (0.419) Data 0.000 (0.115) Loss 1.0075 (1.0962) Prec@1 72.656 (69.393) Prec@5 91.797 (90.801)
[2021-05-01 09:14:20 train_lshot.py:257] INFO Epoch: [22][60/150] Time 0.277 (0.396) Data 0.000 (0.097) Loss 1.0764 (1.1025) Prec@1 69.141 (69.173) Prec@5 89.844 (90.727)
[2021-05-01 09:14:23 train_lshot.py:257] INFO Epoch: [22][70/150] Time 0.285 (0.381) Data 0.001 (0.083) Loss 1.0395 (1.0982) Prec@1 69.141 (69.014) Prec@5 92.188 (90.834)
[2021-05-01 09:14:25 train_lshot.py:257] INFO Epoch: [22][80/150] Time 0.281 (0.368) Data 0.000 (0.073) Loss 1.2377 (1.1059) Prec@1 64.062 (68.875) Prec@5 89.844 (90.726)
[2021-05-01 09:14:29 train_lshot.py:257] INFO Epoch: [22][90/150] Time 0.288 (0.371) Data 0.000 (0.065) Loss 1.0145 (1.1041) Prec@1 71.875 (69.020) Prec@5 92.969 (90.792)
[2021-05-01 09:14:32 train_lshot.py:257] INFO Epoch: [22][100/150] Time 0.275 (0.362) Data 0.000 (0.058) Loss 1.1873 (1.1047) Prec@1 67.188 (69.079) Prec@5 91.016 (90.629)
[2021-05-01 09:14:35 train_lshot.py:257] INFO Epoch: [22][110/150] Time 0.282 (0.355) Data 0.000 (0.053) Loss 1.0794 (1.1114) Prec@1 66.016 (68.852) Prec@5 91.016 (90.597)
[2021-05-01 09:14:38 train_lshot.py:257] INFO Epoch: [22][120/150] Time 0.295 (0.349) Data 0.000 (0.049) Loss 0.9972 (1.1173) Prec@1 70.312 (68.724) Prec@5 91.406 (90.431)
[2021-05-01 09:14:41 train_lshot.py:257] INFO Epoch: [22][130/150] Time 0.345 (0.346) Data 0.000 (0.045) Loss 1.1158 (1.1232) Prec@1 67.578 (68.553) Prec@5 91.797 (90.380)
[2021-05-01 09:14:44 train_lshot.py:257] INFO Epoch: [22][140/150] Time 0.277 (0.342) Data 0.000 (0.042) Loss 1.1653 (1.1243) Prec@1 69.531 (68.559) Prec@5 89.453 (90.320)
[2021-05-01 09:14:51 train_lshot.py:257] INFO Epoch: [23][0/150] Time 4.221 (4.221) Data 3.790 (3.790) Loss 1.1309 (1.1309) Prec@1 68.750 (68.750) Prec@5 89.453 (89.453)
[2021-05-01 09:14:55 train_lshot.py:257] INFO Epoch: [23][10/150] Time 0.405 (0.792) Data 0.001 (0.377) Loss 1.0452 (1.0539) Prec@1 68.359 (70.064) Prec@5 91.406 (90.909)
[2021-05-01 09:14:59 train_lshot.py:257] INFO Epoch: [23][20/150] Time 0.281 (0.570) Data 0.000 (0.198) Loss 1.1085 (1.0727) Prec@1 68.750 (70.071) Prec@5 90.234 (90.830)
[2021-05-01 09:15:02 train_lshot.py:257] INFO Epoch: [23][30/150] Time 0.285 (0.482) Data 0.000 (0.134) Loss 1.0390 (1.0837) Prec@1 70.703 (70.275) Prec@5 90.625 (90.285)
[2021-05-01 09:15:05 train_lshot.py:257] INFO Epoch: [23][40/150] Time 0.273 (0.433) Data 0.000 (0.102) Loss 1.0921 (1.0728) Prec@1 72.656 (70.541) Prec@5 88.672 (90.396)
[2021-05-01 09:15:07 train_lshot.py:257] INFO Epoch: [23][50/150] Time 0.285 (0.403) Data 0.000 (0.082) Loss 1.0724 (1.0805) Prec@1 70.703 (70.236) Prec@5 89.844 (90.288)
[2021-05-01 09:15:10 train_lshot.py:257] INFO Epoch: [23][60/150] Time 0.288 (0.383) Data 0.000 (0.068) Loss 0.9625 (1.0819) Prec@1 70.703 (69.992) Prec@5 93.750 (90.426)
[2021-05-01 09:15:13 train_lshot.py:257] INFO Epoch: [23][70/150] Time 0.279 (0.369) Data 0.001 (0.059) Loss 1.0831 (1.0814) Prec@1 73.438 (70.054) Prec@5 89.844 (90.498)
[2021-05-01 09:15:16 train_lshot.py:257] INFO Epoch: [23][80/150] Time 0.287 (0.358) Data 0.000 (0.052) Loss 1.0850 (1.0813) Prec@1 68.750 (70.004) Prec@5 92.188 (90.529)
[2021-05-01 09:15:19 train_lshot.py:257] INFO Epoch: [23][90/150] Time 0.278 (0.350) Data 0.000 (0.046) Loss 1.1219 (1.0792) Prec@1 69.531 (70.059) Prec@5 92.188 (90.569)
[2021-05-01 09:15:21 train_lshot.py:257] INFO Epoch: [23][100/150] Time 0.288 (0.343) Data 0.000 (0.041) Loss 1.1316 (1.0836) Prec@1 67.969 (69.868) Prec@5 90.234 (90.544)
[2021-05-01 09:15:24 train_lshot.py:257] INFO Epoch: [23][110/150] Time 0.282 (0.338) Data 0.000 (0.038) Loss 1.4005 (1.0849) Prec@1 63.672 (69.813) Prec@5 86.719 (90.569)
[2021-05-01 09:15:28 train_lshot.py:257] INFO Epoch: [23][120/150] Time 0.838 (0.338) Data 0.000 (0.035) Loss 1.0443 (1.0819) Prec@1 73.047 (69.873) Prec@5 90.625 (90.615)
[2021-05-01 09:15:31 train_lshot.py:257] INFO Epoch: [23][130/150] Time 0.281 (0.337) Data 0.000 (0.032) Loss 1.0600 (1.0816) Prec@1 72.656 (69.904) Prec@5 87.500 (90.601)
[2021-05-01 09:15:34 train_lshot.py:257] INFO Epoch: [23][140/150] Time 0.283 (0.333) Data 0.000 (0.030) Loss 1.0461 (1.0827) Prec@1 71.484 (69.875) Prec@5 92.969 (90.617)
[2021-05-01 09:16:04 train_lshot.py:119] INFO Meta Val 23: 0.5906133472621441
[2021-05-01 09:16:11 train_lshot.py:257] INFO Epoch: [24][0/150] Time 5.640 (5.640) Data 5.182 (5.182) Loss 1.1157 (1.1157) Prec@1 71.484 (71.484) Prec@5 90.234 (90.234)
[2021-05-01 09:16:15 train_lshot.py:257] INFO Epoch: [24][10/150] Time 0.301 (0.866) Data 0.000 (0.500) Loss 1.0963 (1.0799) Prec@1 66.797 (70.099) Prec@5 89.062 (90.945)
[2021-05-01 09:16:17 train_lshot.py:257] INFO Epoch: [24][20/150] Time 0.285 (0.591) Data 0.000 (0.262) Loss 1.1105 (1.0782) Prec@1 68.750 (69.922) Prec@5 91.406 (90.867)
[2021-05-01 09:16:20 train_lshot.py:257] INFO Epoch: [24][30/150] Time 0.279 (0.491) Data 0.000 (0.178) Loss 0.9562 (1.0620) Prec@1 74.219 (70.489) Prec@5 93.750 (91.154)
[2021-05-01 09:16:23 train_lshot.py:257] INFO Epoch: [24][40/150] Time 0.275 (0.442) Data 0.000 (0.134) Loss 1.0320 (1.0549) Prec@1 71.875 (70.741) Prec@5 90.625 (91.101)
[2021-05-01 09:16:26 train_lshot.py:257] INFO Epoch: [24][50/150] Time 0.291 (0.410) Data 0.000 (0.108) Loss 0.9236 (1.0515) Prec@1 75.000 (70.703) Prec@5 91.797 (91.146)
[2021-05-01 09:16:29 train_lshot.py:257] INFO Epoch: [24][60/150] Time 0.281 (0.388) Data 0.000 (0.090) Loss 1.2279 (1.0631) Prec@1 67.578 (70.460) Prec@5 90.234 (91.137)
[2021-05-01 09:16:32 train_lshot.py:257] INFO Epoch: [24][70/150] Time 0.275 (0.373) Data 0.001 (0.078) Loss 1.0148 (1.0564) Prec@1 72.656 (70.665) Prec@5 93.750 (91.203)
[2021-05-01 09:16:34 train_lshot.py:257] INFO Epoch: [24][80/150] Time 0.278 (0.361) Data 0.000 (0.068) Loss 1.0413 (1.0564) Prec@1 69.922 (70.645) Prec@5 91.797 (91.175)
[2021-05-01 09:16:37 train_lshot.py:257] INFO Epoch: [24][90/150] Time 0.273 (0.352) Data 0.000 (0.061) Loss 0.9002 (1.0588) Prec@1 74.219 (70.604) Prec@5 93.750 (91.183)
[2021-05-01 09:16:40 train_lshot.py:257] INFO Epoch: [24][100/150] Time 0.290 (0.345) Data 0.000 (0.055) Loss 1.0934 (1.0631) Prec@1 69.922 (70.452) Prec@5 91.406 (91.128)
[2021-05-01 09:16:43 train_lshot.py:257] INFO Epoch: [24][110/150] Time 0.285 (0.340) Data 0.000 (0.050) Loss 1.0310 (1.0630) Prec@1 70.312 (70.432) Prec@5 92.188 (91.107)
[2021-05-01 09:16:46 train_lshot.py:257] INFO Epoch: [24][120/150] Time 0.284 (0.335) Data 0.000 (0.046) Loss 1.0247 (1.0667) Prec@1 73.047 (70.303) Prec@5 91.406 (91.006)
[2021-05-01 09:16:48 train_lshot.py:257] INFO Epoch: [24][130/150] Time 0.281 (0.331) Data 0.000 (0.042) Loss 1.1544 (1.0691) Prec@1 66.016 (70.286) Prec@5 88.672 (90.908)
[2021-05-01 09:16:51 train_lshot.py:257] INFO Epoch: [24][140/150] Time 0.283 (0.327) Data 0.000 (0.039) Loss 1.0804 (1.0714) Prec@1 69.141 (70.149) Prec@5 90.234 (90.960)
[2021-05-01 09:16:59 train_lshot.py:257] INFO Epoch: [25][0/150] Time 4.667 (4.667) Data 4.268 (4.268) Loss 0.9636 (0.9636) Prec@1 73.438 (73.438) Prec@5 89.844 (89.844)
[2021-05-01 09:17:05 train_lshot.py:257] INFO Epoch: [25][10/150] Time 0.284 (0.940) Data 0.001 (0.595) Loss 1.0103 (1.0299) Prec@1 73.438 (71.697) Prec@5 91.016 (91.051)
[2021-05-01 09:17:07 train_lshot.py:257] INFO Epoch: [25][20/150] Time 0.278 (0.629) Data 0.000 (0.312) Loss 0.9644 (1.0087) Prec@1 73.438 (71.801) Prec@5 92.969 (91.629)
[2021-05-01 09:17:10 train_lshot.py:257] INFO Epoch: [25][30/150] Time 0.281 (0.519) Data 0.000 (0.211) Loss 1.0789 (1.0023) Prec@1 70.703 (71.749) Prec@5 90.234 (91.671)
[2021-05-01 09:17:13 train_lshot.py:257] INFO Epoch: [25][40/150] Time 0.279 (0.460) Data 0.000 (0.160) Loss 1.0721 (1.0077) Prec@1 71.875 (71.837) Prec@5 89.453 (91.644)
[2021-05-01 09:17:16 train_lshot.py:257] INFO Epoch: [25][50/150] Time 0.284 (0.425) Data 0.000 (0.129) Loss 0.9374 (1.0048) Prec@1 74.219 (71.998) Prec@5 90.234 (91.736)
[2021-05-01 09:17:19 train_lshot.py:257] INFO Epoch: [25][60/150] Time 0.279 (0.401) Data 0.000 (0.108) Loss 0.9643 (1.0196) Prec@1 74.609 (71.632) Prec@5 92.969 (91.547)
[2021-05-01 09:17:22 train_lshot.py:257] INFO Epoch: [25][70/150] Time 0.279 (0.384) Data 0.001 (0.093) Loss 0.8747 (1.0233) Prec@1 74.219 (71.539) Prec@5 94.141 (91.527)
[2021-05-01 09:17:24 train_lshot.py:257] INFO Epoch: [25][80/150] Time 0.279 (0.371) Data 0.000 (0.081) Loss 1.1507 (1.0268) Prec@1 66.797 (71.460) Prec@5 91.016 (91.411)
[2021-05-01 09:17:27 train_lshot.py:257] INFO Epoch: [25][90/150] Time 0.287 (0.362) Data 0.000 (0.072) Loss 0.9889 (1.0285) Prec@1 73.047 (71.377) Prec@5 93.750 (91.415)
[2021-05-01 09:17:31 train_lshot.py:257] INFO Epoch: [25][100/150] Time 0.349 (0.366) Data 0.000 (0.065) Loss 1.0499 (1.0315) Prec@1 70.703 (71.272) Prec@5 91.016 (91.383)
[2021-05-01 09:17:34 train_lshot.py:257] INFO Epoch: [25][110/150] Time 0.276 (0.359) Data 0.000 (0.059) Loss 0.9500 (1.0314) Prec@1 75.391 (71.301) Prec@5 90.234 (91.396)
[2021-05-01 09:17:37 train_lshot.py:257] INFO Epoch: [25][120/150] Time 0.274 (0.352) Data 0.000 (0.054) Loss 1.1477 (1.0356) Prec@1 67.578 (71.245) Prec@5 87.500 (91.316)
[2021-05-01 09:17:40 train_lshot.py:257] INFO Epoch: [25][130/150] Time 0.274 (0.347) Data 0.000 (0.050) Loss 1.0316 (1.0381) Prec@1 73.438 (71.124) Prec@5 90.625 (91.269)
[2021-05-01 09:17:42 train_lshot.py:257] INFO Epoch: [25][140/150] Time 0.290 (0.342) Data 0.000 (0.047) Loss 1.1117 (1.0380) Prec@1 66.797 (71.130) Prec@5 89.453 (91.257)
[2021-05-01 09:17:53 train_lshot.py:257] INFO Epoch: [26][0/150] Time 6.998 (6.998) Data 6.611 (6.611) Loss 1.0523 (1.0523) Prec@1 69.922 (69.922) Prec@5 90.234 (90.234)
[2021-05-01 09:17:56 train_lshot.py:257] INFO Epoch: [26][10/150] Time 0.277 (0.946) Data 0.001 (0.603) Loss 0.9874 (0.9415) Prec@1 70.703 (73.509) Prec@5 92.188 (92.223)
[2021-05-01 09:17:59 train_lshot.py:257] INFO Epoch: [26][20/150] Time 0.273 (0.631) Data 0.000 (0.316) Loss 0.9171 (0.9493) Prec@1 75.781 (73.735) Prec@5 94.141 (92.188)
[2021-05-01 09:18:02 train_lshot.py:257] INFO Epoch: [26][30/150] Time 0.274 (0.520) Data 0.000 (0.214) Loss 0.8977 (0.9745) Prec@1 75.391 (73.085) Prec@5 93.359 (91.910)
[2021-05-01 09:18:04 train_lshot.py:257] INFO Epoch: [26][40/150] Time 0.291 (0.462) Data 0.000 (0.162) Loss 1.0214 (0.9796) Prec@1 71.875 (72.647) Prec@5 91.016 (91.959)
[2021-05-01 09:18:07 train_lshot.py:257] INFO Epoch: [26][50/150] Time 0.281 (0.426) Data 0.000 (0.130) Loss 0.9722 (0.9803) Prec@1 73.438 (72.679) Prec@5 92.188 (91.950)
[2021-05-01 09:18:10 train_lshot.py:257] INFO Epoch: [26][60/150] Time 0.276 (0.402) Data 0.000 (0.109) Loss 1.0450 (0.9857) Prec@1 70.703 (72.432) Prec@5 92.969 (91.861)
[2021-05-01 09:18:13 train_lshot.py:257] INFO Epoch: [26][70/150] Time 0.294 (0.385) Data 0.001 (0.094) Loss 1.0933 (0.9952) Prec@1 70.312 (72.293) Prec@5 90.234 (91.731)
[2021-05-01 09:18:16 train_lshot.py:257] INFO Epoch: [26][80/150] Time 0.280 (0.372) Data 0.000 (0.082) Loss 1.0311 (0.9983) Prec@1 72.266 (72.184) Prec@5 90.625 (91.628)
[2021-05-01 09:18:19 train_lshot.py:257] INFO Epoch: [26][90/150] Time 0.283 (0.363) Data 0.000 (0.073) Loss 1.0790 (0.9983) Prec@1 70.703 (72.124) Prec@5 89.453 (91.685)
[2021-05-01 09:18:21 train_lshot.py:257] INFO Epoch: [26][100/150] Time 0.274 (0.354) Data 0.000 (0.066) Loss 0.9668 (1.0038) Prec@1 71.094 (71.983) Prec@5 94.922 (91.658)
[2021-05-01 09:18:25 train_lshot.py:257] INFO Epoch: [26][110/150] Time 0.296 (0.356) Data 0.000 (0.060) Loss 0.9383 (1.0057) Prec@1 72.656 (71.917) Prec@5 91.797 (91.642)
[2021-05-01 09:18:28 train_lshot.py:257] INFO Epoch: [26][120/150] Time 0.273 (0.350) Data 0.000 (0.055) Loss 1.1020 (1.0110) Prec@1 63.281 (71.752) Prec@5 92.578 (91.603)
[2021-05-01 09:18:31 train_lshot.py:257] INFO Epoch: [26][130/150] Time 0.283 (0.345) Data 0.000 (0.051) Loss 0.9781 (1.0156) Prec@1 71.875 (71.684) Prec@5 91.406 (91.555)
[2021-05-01 09:18:34 train_lshot.py:257] INFO Epoch: [26][140/150] Time 0.284 (0.341) Data 0.000 (0.047) Loss 1.0826 (1.0153) Prec@1 69.531 (71.656) Prec@5 92.188 (91.581)
[2021-05-01 09:18:43 train_lshot.py:257] INFO Epoch: [27][0/150] Time 6.195 (6.195) Data 5.741 (5.741) Loss 0.8428 (0.8428) Prec@1 71.094 (71.094) Prec@5 94.922 (94.922)
[2021-05-01 09:18:47 train_lshot.py:257] INFO Epoch: [27][10/150] Time 0.304 (0.937) Data 0.000 (0.589) Loss 0.9521 (0.9845) Prec@1 70.312 (71.804) Prec@5 92.969 (91.832)
[2021-05-01 09:18:50 train_lshot.py:257] INFO Epoch: [27][20/150] Time 0.281 (0.630) Data 0.000 (0.309) Loss 1.0789 (0.9909) Prec@1 70.703 (71.894) Prec@5 91.406 (91.611)
[2021-05-01 09:18:53 train_lshot.py:257] INFO Epoch: [27][30/150] Time 0.274 (0.517) Data 0.000 (0.209) Loss 0.8670 (0.9800) Prec@1 76.953 (72.354) Prec@5 94.141 (91.721)
[2021-05-01 09:18:55 train_lshot.py:257] INFO Epoch: [27][40/150] Time 0.291 (0.460) Data 0.000 (0.158) Loss 1.0214 (0.9769) Prec@1 69.141 (72.485) Prec@5 91.406 (91.845)
[2021-05-01 09:18:58 train_lshot.py:257] INFO Epoch: [27][50/150] Time 0.285 (0.425) Data 0.000 (0.127) Loss 1.0895 (0.9778) Prec@1 72.656 (72.541) Prec@5 88.672 (91.850)
[2021-05-01 09:19:01 train_lshot.py:257] INFO Epoch: [27][60/150] Time 0.280 (0.401) Data 0.000 (0.107) Loss 1.0517 (0.9773) Prec@1 73.047 (72.663) Prec@5 90.625 (91.970)
[2021-05-01 09:19:04 train_lshot.py:257] INFO Epoch: [27][70/150] Time 0.287 (0.384) Data 0.001 (0.092) Loss 0.8283 (0.9772) Prec@1 78.125 (72.645) Prec@5 92.188 (91.984)
[2021-05-01 09:19:07 train_lshot.py:257] INFO Epoch: [27][80/150] Time 0.283 (0.371) Data 0.000 (0.080) Loss 1.0494 (0.9844) Prec@1 74.609 (72.565) Prec@5 89.844 (91.879)
[2021-05-01 09:19:09 train_lshot.py:257] INFO Epoch: [27][90/150] Time 0.273 (0.361) Data 0.000 (0.072) Loss 1.0734 (0.9865) Prec@1 69.531 (72.463) Prec@5 90.625 (91.874)
[2021-05-01 09:19:14 train_lshot.py:257] INFO Epoch: [27][100/150] Time 0.290 (0.367) Data 0.000 (0.064) Loss 0.8499 (0.9861) Prec@1 77.734 (72.505) Prec@5 94.141 (91.874)
[2021-05-01 09:19:16 train_lshot.py:257] INFO Epoch: [27][110/150] Time 0.280 (0.359) Data 0.000 (0.059) Loss 1.0028 (0.9909) Prec@1 68.750 (72.336) Prec@5 91.406 (91.797)
[2021-05-01 09:19:19 train_lshot.py:257] INFO Epoch: [27][120/150] Time 0.281 (0.352) Data 0.000 (0.054) Loss 1.0288 (0.9896) Prec@1 71.484 (72.379) Prec@5 91.016 (91.823)
[2021-05-01 09:19:22 train_lshot.py:257] INFO Epoch: [27][130/150] Time 0.281 (0.347) Data 0.000 (0.050) Loss 0.9553 (0.9899) Prec@1 72.656 (72.316) Prec@5 94.531 (91.859)
[2021-05-01 09:19:25 train_lshot.py:257] INFO Epoch: [27][140/150] Time 0.275 (0.342) Data 0.000 (0.046) Loss 1.0598 (0.9929) Prec@1 73.047 (72.313) Prec@5 91.016 (91.813)
[2021-05-01 09:19:56 train_lshot.py:119] INFO Meta Val 27: 0.5649066797494888
[2021-05-01 09:20:03 train_lshot.py:257] INFO Epoch: [28][0/150] Time 6.885 (6.885) Data 6.472 (6.472) Loss 0.9150 (0.9150) Prec@1 69.531 (69.531) Prec@5 93.359 (93.359)
[2021-05-01 09:20:06 train_lshot.py:257] INFO Epoch: [28][10/150] Time 0.287 (0.920) Data 0.000 (0.589) Loss 0.8861 (0.9278) Prec@1 75.391 (73.295) Prec@5 93.750 (93.253)
[2021-05-01 09:20:09 train_lshot.py:257] INFO Epoch: [28][20/150] Time 0.284 (0.616) Data 0.000 (0.309) Loss 1.0025 (0.9100) Prec@1 72.266 (73.977) Prec@5 92.188 (93.359)
[2021-05-01 09:20:12 train_lshot.py:257] INFO Epoch: [28][30/150] Time 0.280 (0.508) Data 0.000 (0.209) Loss 0.8897 (0.9378) Prec@1 73.828 (73.715) Prec@5 93.750 (92.818)
[2021-05-01 09:20:15 train_lshot.py:257] INFO Epoch: [28][40/150] Time 0.275 (0.455) Data 0.001 (0.158) Loss 1.0193 (0.9558) Prec@1 72.656 (73.457) Prec@5 89.453 (92.359)
[2021-05-01 09:20:17 train_lshot.py:257] INFO Epoch: [28][50/150] Time 0.274 (0.421) Data 0.000 (0.127) Loss 0.9686 (0.9576) Prec@1 75.781 (73.453) Prec@5 92.188 (92.333)
[2021-05-01 09:20:20 train_lshot.py:257] INFO Epoch: [28][60/150] Time 0.275 (0.398) Data 0.000 (0.107) Loss 0.8494 (0.9612) Prec@1 74.219 (73.393) Prec@5 91.406 (92.130)
[2021-05-01 09:20:23 train_lshot.py:257] INFO Epoch: [28][70/150] Time 0.277 (0.381) Data 0.001 (0.092) Loss 0.9858 (0.9636) Prec@1 73.828 (73.344) Prec@5 91.797 (92.039)
[2021-05-01 09:20:26 train_lshot.py:257] INFO Epoch: [28][80/150] Time 0.272 (0.368) Data 0.000 (0.080) Loss 1.2490 (0.9666) Prec@1 69.531 (73.235) Prec@5 88.281 (92.014)
[2021-05-01 09:20:29 train_lshot.py:257] INFO Epoch: [28][90/150] Time 0.289 (0.359) Data 0.001 (0.072) Loss 1.0248 (0.9707) Prec@1 72.656 (73.081) Prec@5 91.016 (91.956)
[2021-05-01 09:20:31 train_lshot.py:257] INFO Epoch: [28][100/150] Time 0.276 (0.351) Data 0.000 (0.064) Loss 1.1198 (0.9767) Prec@1 71.094 (72.954) Prec@5 89.453 (91.936)
[2021-05-01 09:20:34 train_lshot.py:257] INFO Epoch: [28][110/150] Time 0.276 (0.345) Data 0.000 (0.059) Loss 1.0365 (0.9774) Prec@1 71.094 (72.797) Prec@5 91.797 (91.966)
[2021-05-01 09:20:38 train_lshot.py:257] INFO Epoch: [28][120/150] Time 0.299 (0.346) Data 0.000 (0.054) Loss 0.8383 (0.9755) Prec@1 75.000 (72.847) Prec@5 91.797 (91.987)
[2021-05-01 09:20:41 train_lshot.py:257] INFO Epoch: [28][130/150] Time 0.274 (0.342) Data 0.000 (0.050) Loss 0.7617 (0.9715) Prec@1 77.344 (72.975) Prec@5 93.750 (92.000)
[2021-05-01 09:20:44 train_lshot.py:257] INFO Epoch: [28][140/150] Time 0.316 (0.338) Data 0.000 (0.046) Loss 0.9754 (0.9712) Prec@1 72.266 (72.972) Prec@5 91.406 (91.991)
[2021-05-01 09:20:52 train_lshot.py:257] INFO Epoch: [29][0/150] Time 5.113 (5.113) Data 4.754 (4.754) Loss 0.8524 (0.8524) Prec@1 76.562 (76.562) Prec@5 92.578 (92.578)
[2021-05-01 09:20:56 train_lshot.py:257] INFO Epoch: [29][10/150] Time 0.338 (0.887) Data 0.001 (0.523) Loss 1.0457 (0.9330) Prec@1 73.438 (73.899) Prec@5 88.672 (91.903)
[2021-05-01 09:20:59 train_lshot.py:257] INFO Epoch: [29][20/150] Time 0.282 (0.600) Data 0.000 (0.274) Loss 0.7991 (0.9470) Prec@1 77.734 (73.624) Prec@5 91.406 (91.704)
[2021-05-01 09:21:02 train_lshot.py:257] INFO Epoch: [29][30/150] Time 0.292 (0.499) Data 0.000 (0.186) Loss 0.8849 (0.9361) Prec@1 75.781 (73.891) Prec@5 92.188 (92.074)
[2021-05-01 09:21:05 train_lshot.py:257] INFO Epoch: [29][40/150] Time 0.284 (0.445) Data 0.000 (0.141) Loss 0.9857 (0.9397) Prec@1 71.875 (73.771) Prec@5 92.969 (92.197)
[2021-05-01 09:21:08 train_lshot.py:257] INFO Epoch: [29][50/150] Time 0.283 (0.413) Data 0.000 (0.113) Loss 0.9597 (0.9430) Prec@1 76.953 (73.843) Prec@5 92.188 (92.157)
[2021-05-01 09:21:11 train_lshot.py:257] INFO Epoch: [29][60/150] Time 0.281 (0.392) Data 0.000 (0.095) Loss 0.9793 (0.9377) Prec@1 71.875 (73.860) Prec@5 93.359 (92.316)
[2021-05-01 09:21:13 train_lshot.py:257] INFO Epoch: [29][70/150] Time 0.289 (0.377) Data 0.001 (0.081) Loss 0.9654 (0.9416) Prec@1 71.094 (73.801) Prec@5 92.188 (92.243)
[2021-05-01 09:21:16 train_lshot.py:257] INFO Epoch: [29][80/150] Time 0.283 (0.365) Data 0.000 (0.071) Loss 0.9414 (0.9387) Prec@1 75.000 (73.925) Prec@5 92.188 (92.337)
[2021-05-01 09:21:19 train_lshot.py:257] INFO Epoch: [29][90/150] Time 0.281 (0.356) Data 0.000 (0.064) Loss 0.9052 (0.9434) Prec@1 75.781 (73.905) Prec@5 91.406 (92.222)
[2021-05-01 09:21:23 train_lshot.py:257] INFO Epoch: [29][100/150] Time 0.288 (0.360) Data 0.000 (0.057) Loss 0.9456 (0.9459) Prec@1 70.312 (73.759) Prec@5 92.578 (92.199)
[2021-05-01 09:21:26 train_lshot.py:257] INFO Epoch: [29][110/150] Time 0.272 (0.353) Data 0.000 (0.052) Loss 0.9132 (0.9471) Prec@1 75.000 (73.779) Prec@5 92.969 (92.177)
[2021-05-01 09:21:29 train_lshot.py:257] INFO Epoch: [29][120/150] Time 0.277 (0.347) Data 0.000 (0.048) Loss 1.0823 (0.9520) Prec@1 69.922 (73.605) Prec@5 91.016 (92.152)
[2021-05-01 09:21:32 train_lshot.py:257] INFO Epoch: [29][130/150] Time 0.292 (0.342) Data 0.000 (0.044) Loss 0.7847 (0.9508) Prec@1 76.953 (73.643) Prec@5 94.141 (92.143)
[2021-05-01 09:21:34 train_lshot.py:257] INFO Epoch: [29][140/150] Time 0.284 (0.339) Data 0.000 (0.041) Loss 0.8583 (0.9502) Prec@1 75.000 (73.662) Prec@5 94.141 (92.165)
[2021-05-01 09:21:43 train_lshot.py:257] INFO Epoch: [30][0/150] Time 5.588 (5.588) Data 5.174 (5.174) Loss 0.8299 (0.8299) Prec@1 76.953 (76.953) Prec@5 93.750 (93.750)
[2021-05-01 09:21:47 train_lshot.py:257] INFO Epoch: [30][10/150] Time 0.360 (0.849) Data 0.001 (0.474) Loss 0.7403 (0.9058) Prec@1 78.906 (73.793) Prec@5 94.922 (92.543)
[2021-05-01 09:21:50 train_lshot.py:257] INFO Epoch: [30][20/150] Time 0.273 (0.592) Data 0.000 (0.250) Loss 0.7964 (0.8811) Prec@1 76.562 (74.702) Prec@5 94.141 (92.913)
[2021-05-01 09:21:53 train_lshot.py:257] INFO Epoch: [30][30/150] Time 0.285 (0.493) Data 0.000 (0.169) Loss 0.9965 (0.8933) Prec@1 70.312 (74.559) Prec@5 91.797 (92.780)
[2021-05-01 09:21:56 train_lshot.py:257] INFO Epoch: [30][40/150] Time 0.278 (0.441) Data 0.001 (0.128) Loss 1.0158 (0.8981) Prec@1 74.609 (74.800) Prec@5 91.406 (92.578)
[2021-05-01 09:21:58 train_lshot.py:257] INFO Epoch: [30][50/150] Time 0.287 (0.409) Data 0.000 (0.103) Loss 0.8906 (0.8995) Prec@1 68.750 (74.709) Prec@5 96.094 (92.693)
[2021-05-01 09:22:01 train_lshot.py:257] INFO Epoch: [30][60/150] Time 0.278 (0.388) Data 0.000 (0.086) Loss 0.6840 (0.8965) Prec@1 81.641 (74.923) Prec@5 96.484 (92.719)
[2021-05-01 09:22:04 train_lshot.py:257] INFO Epoch: [30][70/150] Time 0.283 (0.372) Data 0.001 (0.074) Loss 0.8145 (0.9001) Prec@1 77.734 (74.774) Prec@5 94.922 (92.688)
[2021-05-01 09:22:07 train_lshot.py:257] INFO Epoch: [30][80/150] Time 0.276 (0.361) Data 0.000 (0.065) Loss 0.8108 (0.9075) Prec@1 78.125 (74.590) Prec@5 92.969 (92.607)
[2021-05-01 09:22:10 train_lshot.py:257] INFO Epoch: [30][90/150] Time 0.287 (0.352) Data 0.000 (0.058) Loss 0.9167 (0.9090) Prec@1 75.000 (74.451) Prec@5 93.359 (92.728)
[2021-05-01 09:22:13 train_lshot.py:257] INFO Epoch: [30][100/150] Time 0.276 (0.346) Data 0.000 (0.052) Loss 0.9120 (0.9120) Prec@1 75.391 (74.470) Prec@5 91.797 (92.652)
[2021-05-01 09:22:15 train_lshot.py:257] INFO Epoch: [30][110/150] Time 0.288 (0.340) Data 0.000 (0.047) Loss 1.0368 (0.9211) Prec@1 72.266 (74.162) Prec@5 91.016 (92.624)
[2021-05-01 09:22:18 train_lshot.py:257] INFO Epoch: [30][120/150] Time 0.280 (0.336) Data 0.000 (0.044) Loss 0.8808 (0.9214) Prec@1 76.172 (74.138) Prec@5 93.750 (92.585)
[2021-05-01 09:22:21 train_lshot.py:257] INFO Epoch: [30][130/150] Time 0.283 (0.332) Data 0.000 (0.040) Loss 1.0659 (0.9254) Prec@1 70.703 (74.067) Prec@5 92.578 (92.563)
[2021-05-01 09:22:24 train_lshot.py:257] INFO Epoch: [30][140/150] Time 0.285 (0.328) Data 0.000 (0.037) Loss 0.9444 (0.9289) Prec@1 75.000 (73.978) Prec@5 92.188 (92.487)
[2021-05-01 09:22:34 train_lshot.py:257] INFO Epoch: [31][0/150] Time 7.108 (7.108) Data 6.713 (6.713) Loss 0.6935 (0.6935) Prec@1 83.203 (83.203) Prec@5 95.312 (95.312)
[2021-05-01 09:22:38 train_lshot.py:257] INFO Epoch: [31][10/150] Time 0.278 (0.944) Data 0.000 (0.612) Loss 0.7854 (0.8905) Prec@1 77.734 (75.426) Prec@5 93.750 (92.223)
[2021-05-01 09:22:40 train_lshot.py:257] INFO Epoch: [31][20/150] Time 0.274 (0.629) Data 0.000 (0.321) Loss 0.8156 (0.8869) Prec@1 79.297 (75.521) Prec@5 93.359 (92.708)
[2021-05-01 09:22:43 train_lshot.py:257] INFO Epoch: [31][30/150] Time 0.274 (0.518) Data 0.000 (0.217) Loss 0.7486 (0.8799) Prec@1 78.125 (75.756) Prec@5 94.141 (92.969)
[2021-05-01 09:22:46 train_lshot.py:257] INFO Epoch: [31][40/150] Time 0.279 (0.460) Data 0.001 (0.165) Loss 1.0372 (0.8851) Prec@1 70.703 (75.419) Prec@5 91.797 (92.940)
[2021-05-01 09:22:49 train_lshot.py:257] INFO Epoch: [31][50/150] Time 0.277 (0.425) Data 0.000 (0.132) Loss 0.8205 (0.8825) Prec@1 76.953 (75.490) Prec@5 93.750 (93.022)
[2021-05-01 09:22:52 train_lshot.py:257] INFO Epoch: [31][60/150] Time 0.274 (0.401) Data 0.000 (0.111) Loss 0.8846 (0.8821) Prec@1 76.562 (75.435) Prec@5 92.188 (93.065)
[2021-05-01 09:22:54 train_lshot.py:257] INFO Epoch: [31][70/150] Time 0.287 (0.384) Data 0.001 (0.095) Loss 0.9184 (0.8911) Prec@1 74.219 (75.094) Prec@5 94.141 (92.947)
[2021-05-01 09:22:57 train_lshot.py:257] INFO Epoch: [31][80/150] Time 0.289 (0.372) Data 0.000 (0.083) Loss 0.9225 (0.8983) Prec@1 73.438 (74.875) Prec@5 93.750 (92.906)
[2021-05-01 09:23:00 train_lshot.py:257] INFO Epoch: [31][90/150] Time 0.293 (0.362) Data 0.000 (0.074) Loss 1.0318 (0.8982) Prec@1 75.000 (74.910) Prec@5 89.062 (92.879)
[2021-05-01 09:23:03 train_lshot.py:257] INFO Epoch: [31][100/150] Time 0.288 (0.354) Data 0.000 (0.067) Loss 0.9308 (0.9012) Prec@1 77.344 (74.899) Prec@5 91.797 (92.841)
[2021-05-01 09:23:06 train_lshot.py:257] INFO Epoch: [31][110/150] Time 0.276 (0.348) Data 0.000 (0.061) Loss 0.8140 (0.9045) Prec@1 78.906 (74.803) Prec@5 92.969 (92.772)
[2021-05-01 09:23:09 train_lshot.py:257] INFO Epoch: [31][120/150] Time 0.280 (0.343) Data 0.000 (0.056) Loss 0.9605 (0.9074) Prec@1 72.266 (74.742) Prec@5 91.797 (92.704)
[2021-05-01 09:23:12 train_lshot.py:257] INFO Epoch: [31][130/150] Time 0.275 (0.339) Data 0.000 (0.052) Loss 0.8990 (0.9042) Prec@1 75.000 (74.741) Prec@5 93.359 (92.766)
[2021-05-01 09:23:16 train_lshot.py:257] INFO Epoch: [31][140/150] Time 0.286 (0.343) Data 0.000 (0.048) Loss 0.9063 (0.9018) Prec@1 72.656 (74.801) Prec@5 94.922 (92.830)
[2021-05-01 09:23:46 train_lshot.py:119] INFO Meta Val 31: 0.5799733449816704
[2021-05-01 09:23:52 train_lshot.py:257] INFO Epoch: [32][0/150] Time 5.473 (5.473) Data 5.076 (5.076) Loss 0.9252 (0.9252) Prec@1 75.781 (75.781) Prec@5 91.406 (91.406)
[2021-05-01 09:23:57 train_lshot.py:257] INFO Epoch: [32][10/150] Time 0.274 (0.954) Data 0.000 (0.614) Loss 0.8098 (0.8672) Prec@1 78.516 (75.391) Prec@5 91.797 (92.969)
[2021-05-01 09:24:00 train_lshot.py:257] INFO Epoch: [32][20/150] Time 0.276 (0.632) Data 0.000 (0.322) Loss 0.9433 (0.8740) Prec@1 73.047 (75.223) Prec@5 92.969 (93.118)
[2021-05-01 09:24:03 train_lshot.py:257] INFO Epoch: [32][30/150] Time 0.279 (0.517) Data 0.001 (0.218) Loss 0.8859 (0.8670) Prec@1 73.828 (75.542) Prec@5 93.750 (93.233)
[2021-05-01 09:24:06 train_lshot.py:257] INFO Epoch: [32][40/150] Time 0.278 (0.459) Data 0.000 (0.165) Loss 0.8028 (0.8704) Prec@1 77.734 (75.343) Prec@5 93.359 (93.188)
[2021-05-01 09:24:08 train_lshot.py:257] INFO Epoch: [32][50/150] Time 0.273 (0.427) Data 0.000 (0.133) Loss 0.8990 (0.8701) Prec@1 73.047 (75.383) Prec@5 92.578 (93.237)
[2021-05-01 09:24:11 train_lshot.py:257] INFO Epoch: [32][60/150] Time 0.280 (0.403) Data 0.000 (0.111) Loss 0.8930 (0.8716) Prec@1 75.391 (75.474) Prec@5 92.969 (93.276)
[2021-05-01 09:24:14 train_lshot.py:257] INFO Epoch: [32][70/150] Time 0.284 (0.386) Data 0.002 (0.096) Loss 0.9189 (0.8734) Prec@1 77.344 (75.583) Prec@5 91.406 (93.238)
[2021-05-01 09:24:17 train_lshot.py:257] INFO Epoch: [32][80/150] Time 0.279 (0.373) Data 0.000 (0.084) Loss 0.8928 (0.8734) Prec@1 76.953 (75.627) Prec@5 90.625 (93.157)
[2021-05-01 09:24:20 train_lshot.py:257] INFO Epoch: [32][90/150] Time 0.275 (0.362) Data 0.000 (0.075) Loss 0.8104 (0.8735) Prec@1 77.344 (75.708) Prec@5 92.578 (93.029)
[2021-05-01 09:24:22 train_lshot.py:257] INFO Epoch: [32][100/150] Time 0.285 (0.354) Data 0.000 (0.067) Loss 0.8880 (0.8698) Prec@1 75.391 (75.777) Prec@5 93.359 (93.112)
[2021-05-01 09:24:25 train_lshot.py:257] INFO Epoch: [32][110/150] Time 0.279 (0.348) Data 0.000 (0.061) Loss 0.7667 (0.8698) Prec@1 78.906 (75.739) Prec@5 95.312 (93.110)
[2021-05-01 09:24:28 train_lshot.py:257] INFO Epoch: [32][120/150] Time 0.280 (0.343) Data 0.000 (0.056) Loss 0.9818 (0.8748) Prec@1 75.391 (75.584) Prec@5 93.750 (93.033)
[2021-05-01 09:24:31 train_lshot.py:257] INFO Epoch: [32][130/150] Time 0.284 (0.338) Data 0.000 (0.052) Loss 0.9165 (0.8790) Prec@1 77.734 (75.447) Prec@5 90.625 (93.002)
[2021-05-01 09:24:35 train_lshot.py:257] INFO Epoch: [32][140/150] Time 0.292 (0.343) Data 0.000 (0.048) Loss 0.8787 (0.8811) Prec@1 73.438 (75.366) Prec@5 91.406 (92.999)
[2021-05-01 09:24:44 train_lshot.py:257] INFO Epoch: [33][0/150] Time 5.663 (5.663) Data 5.222 (5.222) Loss 0.8581 (0.8581) Prec@1 73.828 (73.828) Prec@5 94.531 (94.531)
[2021-05-01 09:24:48 train_lshot.py:257] INFO Epoch: [33][10/150] Time 0.350 (0.869) Data 0.001 (0.476) Loss 0.7820 (0.8585) Prec@1 77.734 (75.462) Prec@5 92.969 (93.572)
[2021-05-01 09:24:51 train_lshot.py:257] INFO Epoch: [33][20/150] Time 0.273 (0.592) Data 0.000 (0.250) Loss 0.7610 (0.8382) Prec@1 77.344 (75.725) Prec@5 94.531 (93.787)
[2021-05-01 09:24:54 train_lshot.py:257] INFO Epoch: [33][30/150] Time 0.276 (0.493) Data 0.000 (0.169) Loss 0.8876 (0.8257) Prec@1 76.562 (76.323) Prec@5 91.797 (93.813)
[2021-05-01 09:24:57 train_lshot.py:257] INFO Epoch: [33][40/150] Time 0.280 (0.442) Data 0.001 (0.128) Loss 0.7331 (0.8311) Prec@1 79.688 (76.200) Prec@5 94.531 (93.731)
[2021-05-01 09:24:59 train_lshot.py:257] INFO Epoch: [33][50/150] Time 0.278 (0.410) Data 0.000 (0.103) Loss 0.9953 (0.8345) Prec@1 70.703 (76.118) Prec@5 92.969 (93.727)
[2021-05-01 09:25:02 train_lshot.py:257] INFO Epoch: [33][60/150] Time 0.275 (0.389) Data 0.000 (0.086) Loss 0.8979 (0.8404) Prec@1 78.125 (75.961) Prec@5 91.797 (93.635)
[2021-05-01 09:25:05 train_lshot.py:257] INFO Epoch: [33][70/150] Time 0.281 (0.374) Data 0.001 (0.074) Loss 0.8347 (0.8481) Prec@1 76.562 (75.836) Prec@5 92.188 (93.447)
[2021-05-01 09:25:08 train_lshot.py:257] INFO Epoch: [33][80/150] Time 0.521 (0.365) Data 0.000 (0.065) Loss 0.9904 (0.8539) Prec@1 74.219 (75.714) Prec@5 92.578 (93.451)
[2021-05-01 09:25:11 train_lshot.py:257] INFO Epoch: [33][90/150] Time 0.287 (0.361) Data 0.000 (0.058) Loss 0.8119 (0.8566) Prec@1 75.781 (75.717) Prec@5 94.922 (93.475)
[2021-05-01 09:25:14 train_lshot.py:257] INFO Epoch: [33][100/150] Time 0.278 (0.353) Data 0.000 (0.052) Loss 0.8340 (0.8622) Prec@1 76.562 (75.545) Prec@5 95.703 (93.417)
[2021-05-01 09:25:18 train_lshot.py:257] INFO Epoch: [33][110/150] Time 0.293 (0.353) Data 0.000 (0.048) Loss 0.8610 (0.8632) Prec@1 74.609 (75.475) Prec@5 93.750 (93.391)
[2021-05-01 09:25:20 train_lshot.py:257] INFO Epoch: [33][120/150] Time 0.278 (0.347) Data 0.000 (0.044) Loss 0.8744 (0.8637) Prec@1 75.781 (75.491) Prec@5 94.141 (93.437)
[2021-05-01 09:25:23 train_lshot.py:257] INFO Epoch: [33][130/150] Time 0.287 (0.342) Data 0.000 (0.040) Loss 0.9957 (0.8691) Prec@1 73.438 (75.397) Prec@5 91.406 (93.368)
[2021-05-01 09:25:26 train_lshot.py:257] INFO Epoch: [33][140/150] Time 0.292 (0.338) Data 0.000 (0.037) Loss 0.8860 (0.8695) Prec@1 73.438 (75.416) Prec@5 92.578 (93.337)
[2021-05-01 09:25:37 train_lshot.py:257] INFO Epoch: [34][0/150] Time 7.797 (7.797) Data 7.433 (7.433) Loss 0.6675 (0.6675) Prec@1 80.469 (80.469) Prec@5 96.484 (96.484)
[2021-05-01 09:25:40 train_lshot.py:257] INFO Epoch: [34][10/150] Time 0.290 (1.001) Data 0.000 (0.677) Loss 0.6252 (0.8247) Prec@1 83.203 (77.095) Prec@5 95.703 (93.466)
[2021-05-01 09:25:43 train_lshot.py:257] INFO Epoch: [34][20/150] Time 0.276 (0.665) Data 0.000 (0.355) Loss 0.7657 (0.8065) Prec@1 78.906 (77.846) Prec@5 93.359 (93.638)
[2021-05-01 09:25:46 train_lshot.py:257] INFO Epoch: [34][30/150] Time 0.281 (0.541) Data 0.000 (0.240) Loss 0.8455 (0.8130) Prec@1 75.000 (77.306) Prec@5 94.531 (93.485)
[2021-05-01 09:25:49 train_lshot.py:257] INFO Epoch: [34][40/150] Time 0.276 (0.478) Data 0.001 (0.182) Loss 0.9756 (0.8193) Prec@1 75.781 (77.039) Prec@5 89.453 (93.350)
[2021-05-01 09:25:51 train_lshot.py:257] INFO Epoch: [34][50/150] Time 0.276 (0.439) Data 0.000 (0.146) Loss 0.8367 (0.8237) Prec@1 76.953 (76.945) Prec@5 94.531 (93.359)
[2021-05-01 09:25:54 train_lshot.py:257] INFO Epoch: [34][60/150] Time 0.281 (0.413) Data 0.000 (0.122) Loss 0.8936 (0.8297) Prec@1 74.609 (76.812) Prec@5 94.141 (93.302)
[2021-05-01 09:25:57 train_lshot.py:257] INFO Epoch: [34][70/150] Time 0.274 (0.394) Data 0.001 (0.105) Loss 0.9414 (0.8372) Prec@1 71.484 (76.568) Prec@5 93.750 (93.310)
[2021-05-01 09:26:00 train_lshot.py:257] INFO Epoch: [34][80/150] Time 0.290 (0.380) Data 0.000 (0.092) Loss 0.9073 (0.8375) Prec@1 74.219 (76.418) Prec@5 91.406 (93.388)
[2021-05-01 09:26:03 train_lshot.py:257] INFO Epoch: [34][90/150] Time 0.285 (0.369) Data 0.000 (0.082) Loss 0.8734 (0.8394) Prec@1 76.172 (76.425) Prec@5 94.531 (93.445)
[2021-05-01 09:26:06 train_lshot.py:257] INFO Epoch: [34][100/150] Time 0.283 (0.364) Data 0.000 (0.074) Loss 0.8385 (0.8431) Prec@1 77.344 (76.346) Prec@5 92.188 (93.394)
[2021-05-01 09:26:09 train_lshot.py:257] INFO Epoch: [34][110/150] Time 0.282 (0.356) Data 0.000 (0.067) Loss 0.8741 (0.8440) Prec@1 76.562 (76.362) Prec@5 93.359 (93.426)
[2021-05-01 09:26:11 train_lshot.py:257] INFO Epoch: [34][120/150] Time 0.278 (0.351) Data 0.000 (0.062) Loss 0.8295 (0.8459) Prec@1 78.516 (76.307) Prec@5 92.578 (93.434)
[2021-05-01 09:26:15 train_lshot.py:257] INFO Epoch: [34][130/150] Time 0.288 (0.349) Data 0.000 (0.057) Loss 0.7406 (0.8498) Prec@1 77.734 (76.202) Prec@5 95.703 (93.353)
[2021-05-01 09:26:18 train_lshot.py:257] INFO Epoch: [34][140/150] Time 0.277 (0.344) Data 0.000 (0.053) Loss 0.8342 (0.8544) Prec@1 80.078 (76.111) Prec@5 94.531 (93.332)
[2021-05-01 09:26:25 train_lshot.py:257] INFO Epoch: [35][0/150] Time 4.339 (4.339) Data 3.925 (3.925) Loss 0.8506 (0.8506) Prec@1 78.125 (78.125) Prec@5 92.188 (92.188)
[2021-05-01 09:26:31 train_lshot.py:257] INFO Epoch: [35][10/150] Time 0.285 (0.952) Data 0.000 (0.598) Loss 0.8960 (0.8328) Prec@1 77.734 (76.918) Prec@5 92.188 (93.821)
[2021-05-01 09:26:34 train_lshot.py:257] INFO Epoch: [35][20/150] Time 0.274 (0.634) Data 0.000 (0.314) Loss 0.9108 (0.8371) Prec@1 75.781 (77.009) Prec@5 92.578 (93.341)
[2021-05-01 09:26:37 train_lshot.py:257] INFO Epoch: [35][30/150] Time 0.292 (0.523) Data 0.000 (0.213) Loss 0.7551 (0.8268) Prec@1 79.297 (77.545) Prec@5 97.656 (93.624)
[2021-05-01 09:26:40 train_lshot.py:257] INFO Epoch: [35][40/150] Time 0.276 (0.464) Data 0.000 (0.161) Loss 0.8496 (0.8142) Prec@1 76.562 (77.534) Prec@5 92.188 (93.826)
[2021-05-01 09:26:42 train_lshot.py:257] INFO Epoch: [35][50/150] Time 0.277 (0.428) Data 0.000 (0.129) Loss 0.8252 (0.8098) Prec@1 77.344 (77.451) Prec@5 93.359 (93.865)
[2021-05-01 09:26:45 train_lshot.py:257] INFO Epoch: [35][60/150] Time 0.287 (0.405) Data 0.000 (0.108) Loss 0.7577 (0.8046) Prec@1 80.078 (77.504) Prec@5 94.531 (93.936)
[2021-05-01 09:26:48 train_lshot.py:257] INFO Epoch: [35][70/150] Time 0.287 (0.387) Data 0.001 (0.093) Loss 0.9511 (0.8129) Prec@1 75.781 (77.360) Prec@5 92.969 (93.816)
[2021-05-01 09:26:51 train_lshot.py:257] INFO Epoch: [35][80/150] Time 0.284 (0.374) Data 0.000 (0.082) Loss 0.7618 (0.8161) Prec@1 80.469 (77.334) Prec@5 94.531 (93.784)
[2021-05-01 09:26:54 train_lshot.py:257] INFO Epoch: [35][90/150] Time 0.278 (0.364) Data 0.000 (0.073) Loss 0.8023 (0.8179) Prec@1 76.953 (77.163) Prec@5 91.797 (93.698)
[2021-05-01 09:26:58 train_lshot.py:257] INFO Epoch: [35][100/150] Time 0.283 (0.365) Data 0.000 (0.065) Loss 0.7478 (0.8179) Prec@1 81.641 (77.181) Prec@5 93.750 (93.704)
[2021-05-01 09:27:00 train_lshot.py:257] INFO Epoch: [35][110/150] Time 0.275 (0.357) Data 0.000 (0.060) Loss 0.8741 (0.8189) Prec@1 77.344 (77.119) Prec@5 92.188 (93.701)
[2021-05-01 09:27:03 train_lshot.py:257] INFO Epoch: [35][120/150] Time 0.284 (0.351) Data 0.000 (0.055) Loss 1.0044 (0.8270) Prec@1 71.094 (76.882) Prec@5 91.797 (93.589)
[2021-05-01 09:27:06 train_lshot.py:257] INFO Epoch: [35][130/150] Time 0.285 (0.346) Data 0.000 (0.051) Loss 0.8089 (0.8252) Prec@1 78.125 (76.917) Prec@5 94.141 (93.607)
[2021-05-01 09:27:09 train_lshot.py:257] INFO Epoch: [35][140/150] Time 0.281 (0.341) Data 0.000 (0.047) Loss 0.7458 (0.8260) Prec@1 80.078 (76.920) Prec@5 94.531 (93.600)
[2021-05-01 09:27:40 train_lshot.py:119] INFO Meta Val 35: 0.5943200136721134
[2021-05-01 09:27:46 train_lshot.py:257] INFO Epoch: [36][0/150] Time 5.931 (5.931) Data 5.474 (5.474) Loss 0.9401 (0.9401) Prec@1 72.656 (72.656) Prec@5 91.016 (91.016)
[2021-05-01 09:27:50 train_lshot.py:257] INFO Epoch: [36][10/150] Time 0.282 (0.875) Data 0.001 (0.499) Loss 0.7825 (0.8128) Prec@1 78.516 (76.740) Prec@5 95.703 (93.892)
[2021-05-01 09:27:53 train_lshot.py:257] INFO Epoch: [36][20/150] Time 0.293 (0.600) Data 0.000 (0.262) Loss 0.7289 (0.8102) Prec@1 78.906 (76.972) Prec@5 95.312 (93.806)
[2021-05-01 09:27:56 train_lshot.py:257] INFO Epoch: [36][30/150] Time 0.277 (0.498) Data 0.000 (0.178) Loss 0.7646 (0.8120) Prec@1 80.078 (76.953) Prec@5 93.750 (93.712)
[2021-05-01 09:27:59 train_lshot.py:257] INFO Epoch: [36][40/150] Time 0.278 (0.446) Data 0.000 (0.134) Loss 0.7214 (0.8170) Prec@1 80.469 (76.839) Prec@5 93.359 (93.521)
[2021-05-01 09:28:01 train_lshot.py:257] INFO Epoch: [36][50/150] Time 0.274 (0.412) Data 0.000 (0.108) Loss 0.8084 (0.8181) Prec@1 75.781 (76.976) Prec@5 94.141 (93.520)
[2021-05-01 09:28:04 train_lshot.py:257] INFO Epoch: [36][60/150] Time 0.276 (0.391) Data 0.000 (0.090) Loss 0.7753 (0.8151) Prec@1 79.688 (77.043) Prec@5 93.359 (93.571)
[2021-05-01 09:28:07 train_lshot.py:257] INFO Epoch: [36][70/150] Time 0.281 (0.375) Data 0.001 (0.078) Loss 0.7068 (0.8119) Prec@1 79.297 (77.261) Prec@5 96.484 (93.634)
[2021-05-01 09:28:10 train_lshot.py:257] INFO Epoch: [36][80/150] Time 0.273 (0.363) Data 0.000 (0.068) Loss 0.7323 (0.8071) Prec@1 77.344 (77.276) Prec@5 95.312 (93.803)
[2021-05-01 09:28:12 train_lshot.py:257] INFO Epoch: [36][90/150] Time 0.283 (0.354) Data 0.000 (0.061) Loss 0.7871 (0.8085) Prec@1 79.688 (77.297) Prec@5 92.969 (93.823)
[2021-05-01 09:28:15 train_lshot.py:257] INFO Epoch: [36][100/150] Time 0.273 (0.346) Data 0.000 (0.055) Loss 0.8206 (0.8130) Prec@1 76.562 (77.228) Prec@5 93.750 (93.777)
[2021-05-01 09:28:18 train_lshot.py:257] INFO Epoch: [36][110/150] Time 0.284 (0.340) Data 0.000 (0.050) Loss 0.9354 (0.8192) Prec@1 73.828 (77.059) Prec@5 92.578 (93.676)
[2021-05-01 09:28:21 train_lshot.py:257] INFO Epoch: [36][120/150] Time 0.290 (0.339) Data 0.000 (0.046) Loss 0.8324 (0.8228) Prec@1 75.000 (76.901) Prec@5 94.141 (93.650)
[2021-05-01 09:28:24 train_lshot.py:257] INFO Epoch: [36][130/150] Time 0.287 (0.335) Data 0.000 (0.042) Loss 0.7823 (0.8250) Prec@1 77.344 (76.804) Prec@5 94.141 (93.646)
[2021-05-01 09:28:27 train_lshot.py:257] INFO Epoch: [36][140/150] Time 0.278 (0.331) Data 0.000 (0.039) Loss 0.9400 (0.8276) Prec@1 75.000 (76.751) Prec@5 93.359 (93.634)
[2021-05-01 09:28:35 train_lshot.py:257] INFO Epoch: [37][0/150] Time 4.710 (4.710) Data 4.353 (4.353) Loss 0.9108 (0.9108) Prec@1 75.000 (75.000) Prec@5 91.016 (91.016)
[2021-05-01 09:28:40 train_lshot.py:257] INFO Epoch: [37][10/150] Time 0.291 (0.944) Data 0.000 (0.602) Loss 0.6875 (0.7517) Prec@1 82.422 (79.652) Prec@5 94.922 (94.744)
[2021-05-01 09:28:43 train_lshot.py:257] INFO Epoch: [37][20/150] Time 0.286 (0.629) Data 0.000 (0.315) Loss 0.7494 (0.7790) Prec@1 76.562 (78.534) Prec@5 93.750 (94.401)
[2021-05-01 09:28:46 train_lshot.py:257] INFO Epoch: [37][30/150] Time 0.284 (0.521) Data 0.000 (0.214) Loss 0.8282 (0.7675) Prec@1 76.172 (78.642) Prec@5 95.312 (94.506)
[2021-05-01 09:28:49 train_lshot.py:257] INFO Epoch: [37][40/150] Time 0.282 (0.462) Data 0.000 (0.162) Loss 0.7392 (0.7650) Prec@1 80.078 (78.763) Prec@5 93.750 (94.284)
[2021-05-01 09:28:52 train_lshot.py:257] INFO Epoch: [37][50/150] Time 0.274 (0.427) Data 0.000 (0.130) Loss 0.8743 (0.7729) Prec@1 76.172 (78.569) Prec@5 93.750 (94.187)
[2021-05-01 09:28:55 train_lshot.py:257] INFO Epoch: [37][60/150] Time 0.277 (0.403) Data 0.000 (0.109) Loss 0.9891 (0.7771) Prec@1 71.484 (78.388) Prec@5 92.188 (94.185)
[2021-05-01 09:28:57 train_lshot.py:257] INFO Epoch: [37][70/150] Time 0.281 (0.386) Data 0.002 (0.094) Loss 0.7112 (0.7757) Prec@1 76.562 (78.389) Prec@5 96.484 (94.262)
[2021-05-01 09:29:00 train_lshot.py:257] INFO Epoch: [37][80/150] Time 0.290 (0.373) Data 0.000 (0.082) Loss 0.7461 (0.7820) Prec@1 78.906 (78.168) Prec@5 96.094 (94.198)
[2021-05-01 09:29:04 train_lshot.py:257] INFO Epoch: [37][90/150] Time 0.290 (0.371) Data 0.000 (0.073) Loss 0.9525 (0.7882) Prec@1 73.438 (77.863) Prec@5 90.625 (94.085)
[2021-05-01 09:29:07 train_lshot.py:257] INFO Epoch: [37][100/150] Time 0.283 (0.362) Data 0.000 (0.066) Loss 0.7753 (0.7922) Prec@1 76.953 (77.746) Prec@5 94.141 (94.017)
[2021-05-01 09:29:09 train_lshot.py:257] INFO Epoch: [37][110/150] Time 0.289 (0.355) Data 0.000 (0.060) Loss 0.7420 (0.7950) Prec@1 78.906 (77.639) Prec@5 95.312 (93.965)
[2021-05-01 09:29:12 train_lshot.py:257] INFO Epoch: [37][120/150] Time 0.278 (0.349) Data 0.000 (0.055) Loss 0.8601 (0.7982) Prec@1 74.219 (77.499) Prec@5 94.531 (93.950)
[2021-05-01 09:29:15 train_lshot.py:257] INFO Epoch: [37][130/150] Time 0.284 (0.347) Data 0.000 (0.051) Loss 0.9073 (0.8010) Prec@1 75.781 (77.388) Prec@5 92.188 (93.938)
[2021-05-01 09:29:18 train_lshot.py:257] INFO Epoch: [37][140/150] Time 0.280 (0.342) Data 0.000 (0.047) Loss 0.8254 (0.8039) Prec@1 78.125 (77.341) Prec@5 92.969 (93.866)
[2021-05-01 09:29:28 train_lshot.py:257] INFO Epoch: [38][0/150] Time 6.350 (6.350) Data 5.978 (5.978) Loss 0.6103 (0.6103) Prec@1 81.641 (81.641) Prec@5 96.484 (96.484)
[2021-05-01 09:29:32 train_lshot.py:257] INFO Epoch: [38][10/150] Time 0.307 (0.898) Data 0.001 (0.547) Loss 0.7328 (0.7705) Prec@1 79.688 (78.161) Prec@5 93.750 (94.318)
[2021-05-01 09:29:35 train_lshot.py:257] INFO Epoch: [38][20/150] Time 0.291 (0.612) Data 0.000 (0.287) Loss 0.7934 (0.7704) Prec@1 78.906 (78.423) Prec@5 94.141 (94.494)
[2021-05-01 09:29:37 train_lshot.py:257] INFO Epoch: [38][30/150] Time 0.276 (0.508) Data 0.000 (0.194) Loss 0.7360 (0.7626) Prec@1 78.516 (78.692) Prec@5 94.922 (94.531)
[2021-05-01 09:29:40 train_lshot.py:257] INFO Epoch: [38][40/150] Time 0.285 (0.453) Data 0.001 (0.147) Loss 0.7996 (0.7680) Prec@1 77.734 (78.563) Prec@5 94.922 (94.369)
[2021-05-01 09:29:43 train_lshot.py:257] INFO Epoch: [38][50/150] Time 0.283 (0.419) Data 0.000 (0.118) Loss 0.8127 (0.7697) Prec@1 73.828 (78.339) Prec@5 96.094 (94.386)
[2021-05-01 09:29:46 train_lshot.py:257] INFO Epoch: [38][60/150] Time 0.280 (0.397) Data 0.000 (0.099) Loss 0.8199 (0.7702) Prec@1 74.219 (78.330) Prec@5 94.922 (94.365)
[2021-05-01 09:29:49 train_lshot.py:257] INFO Epoch: [38][70/150] Time 0.281 (0.380) Data 0.001 (0.085) Loss 0.8536 (0.7789) Prec@1 76.953 (78.213) Prec@5 91.797 (94.185)
[2021-05-01 09:29:52 train_lshot.py:257] INFO Epoch: [38][80/150] Time 0.290 (0.369) Data 0.000 (0.075) Loss 0.6776 (0.7849) Prec@1 80.469 (77.990) Prec@5 95.312 (94.063)
[2021-05-01 09:29:54 train_lshot.py:257] INFO Epoch: [38][90/150] Time 0.276 (0.359) Data 0.000 (0.067) Loss 0.6883 (0.7851) Prec@1 80.078 (78.026) Prec@5 95.312 (94.033)
[2021-05-01 09:29:57 train_lshot.py:257] INFO Epoch: [38][100/150] Time 0.286 (0.352) Data 0.000 (0.060) Loss 0.7771 (0.7875) Prec@1 78.125 (77.939) Prec@5 94.531 (94.048)
[2021-05-01 09:30:00 train_lshot.py:257] INFO Epoch: [38][110/150] Time 0.283 (0.346) Data 0.000 (0.055) Loss 0.8309 (0.7908) Prec@1 75.781 (77.815) Prec@5 92.578 (93.989)
[2021-05-01 09:30:04 train_lshot.py:257] INFO Epoch: [38][120/150] Time 0.339 (0.348) Data 0.000 (0.050) Loss 0.8619 (0.7948) Prec@1 76.562 (77.728) Prec@5 94.531 (93.947)
[2021-05-01 09:30:07 train_lshot.py:257] INFO Epoch: [38][130/150] Time 0.283 (0.344) Data 0.000 (0.046) Loss 0.7838 (0.7981) Prec@1 81.641 (77.716) Prec@5 94.141 (93.920)
[2021-05-01 09:30:10 train_lshot.py:257] INFO Epoch: [38][140/150] Time 0.286 (0.339) Data 0.000 (0.043) Loss 0.7053 (0.7978) Prec@1 82.812 (77.751) Prec@5 92.969 (93.900)
[2021-05-01 09:30:19 train_lshot.py:257] INFO Epoch: [39][0/150] Time 6.764 (6.764) Data 6.291 (6.291) Loss 0.8889 (0.8889) Prec@1 79.297 (79.297) Prec@5 91.016 (91.016)
[2021-05-01 09:30:23 train_lshot.py:257] INFO Epoch: [39][10/150] Time 0.293 (0.939) Data 0.001 (0.574) Loss 0.8307 (0.7682) Prec@1 78.516 (78.977) Prec@5 92.969 (94.105)
[2021-05-01 09:30:26 train_lshot.py:257] INFO Epoch: [39][20/150] Time 0.279 (0.630) Data 0.000 (0.301) Loss 0.8546 (0.7804) Prec@1 75.391 (78.553) Prec@5 93.750 (94.141)
[2021-05-01 09:30:29 train_lshot.py:257] INFO Epoch: [39][30/150] Time 0.287 (0.517) Data 0.001 (0.204) Loss 0.8523 (0.7703) Prec@1 72.266 (78.566) Prec@5 92.578 (94.254)
[2021-05-01 09:30:31 train_lshot.py:257] INFO Epoch: [39][40/150] Time 0.279 (0.460) Data 0.001 (0.154) Loss 0.7645 (0.7608) Prec@1 79.297 (78.525) Prec@5 93.359 (94.312)
[2021-05-01 09:30:34 train_lshot.py:257] INFO Epoch: [39][50/150] Time 0.275 (0.425) Data 0.000 (0.124) Loss 0.7450 (0.7617) Prec@1 76.172 (78.324) Prec@5 94.141 (94.355)
[2021-05-01 09:30:37 train_lshot.py:257] INFO Epoch: [39][60/150] Time 0.278 (0.401) Data 0.000 (0.104) Loss 0.7467 (0.7647) Prec@1 78.906 (78.189) Prec@5 93.750 (94.403)
[2021-05-01 09:30:40 train_lshot.py:257] INFO Epoch: [39][70/150] Time 0.278 (0.385) Data 0.001 (0.089) Loss 0.8202 (0.7689) Prec@1 78.125 (78.235) Prec@5 94.141 (94.344)
[2021-05-01 09:30:43 train_lshot.py:257] INFO Epoch: [39][80/150] Time 0.278 (0.371) Data 0.001 (0.078) Loss 0.7522 (0.7737) Prec@1 78.516 (78.159) Prec@5 94.141 (94.305)
[2021-05-01 09:30:47 train_lshot.py:257] INFO Epoch: [39][90/150] Time 0.295 (0.376) Data 0.000 (0.070) Loss 0.9082 (0.7754) Prec@1 76.953 (78.172) Prec@5 92.578 (94.282)
[2021-05-01 09:30:50 train_lshot.py:257] INFO Epoch: [39][100/150] Time 0.276 (0.366) Data 0.000 (0.063) Loss 0.8383 (0.7751) Prec@1 76.172 (78.198) Prec@5 93.359 (94.284)
[2021-05-01 09:30:52 train_lshot.py:257] INFO Epoch: [39][110/150] Time 0.275 (0.358) Data 0.000 (0.057) Loss 0.7190 (0.7794) Prec@1 81.250 (78.107) Prec@5 94.922 (94.239)
[2021-05-01 09:30:55 train_lshot.py:257] INFO Epoch: [39][120/150] Time 0.274 (0.352) Data 0.000 (0.053) Loss 0.6905 (0.7781) Prec@1 78.125 (78.125) Prec@5 95.703 (94.231)
[2021-05-01 09:30:58 train_lshot.py:257] INFO Epoch: [39][130/150] Time 0.319 (0.348) Data 0.000 (0.049) Loss 0.5794 (0.7782) Prec@1 82.422 (78.110) Prec@5 96.094 (94.227)
[2021-05-01 09:31:01 train_lshot.py:257] INFO Epoch: [39][140/150] Time 0.274 (0.344) Data 0.000 (0.045) Loss 0.8879 (0.7800) Prec@1 73.438 (78.042) Prec@5 92.969 (94.210)
[2021-05-01 09:31:32 train_lshot.py:119] INFO Meta Val 39: 0.5716266791820526
[2021-05-01 09:31:38 train_lshot.py:257] INFO Epoch: [40][0/150] Time 5.778 (5.778) Data 5.378 (5.378) Loss 0.6522 (0.6522) Prec@1 82.031 (82.031) Prec@5 94.922 (94.922)
[2021-05-01 09:31:42 train_lshot.py:257] INFO Epoch: [40][10/150] Time 0.336 (0.859) Data 0.000 (0.490) Loss 0.8160 (0.7797) Prec@1 78.516 (78.516) Prec@5 92.969 (94.070)
[2021-05-01 09:31:45 train_lshot.py:257] INFO Epoch: [40][20/150] Time 0.288 (0.592) Data 0.000 (0.258) Loss 0.6766 (0.7378) Prec@1 80.469 (79.315) Prec@5 94.922 (94.457)
[2021-05-01 09:31:47 train_lshot.py:257] INFO Epoch: [40][30/150] Time 0.280 (0.492) Data 0.000 (0.175) Loss 0.7664 (0.7553) Prec@1 78.125 (78.856) Prec@5 95.312 (94.317)
[2021-05-01 09:31:50 train_lshot.py:257] INFO Epoch: [40][40/150] Time 0.286 (0.442) Data 0.000 (0.132) Loss 0.7274 (0.7548) Prec@1 79.297 (79.040) Prec@5 94.531 (94.284)
[2021-05-01 09:31:53 train_lshot.py:257] INFO Epoch: [40][50/150] Time 0.282 (0.410) Data 0.000 (0.106) Loss 0.6871 (0.7445) Prec@1 82.422 (79.197) Prec@5 93.750 (94.401)
[2021-05-01 09:31:56 train_lshot.py:257] INFO Epoch: [40][60/150] Time 0.284 (0.389) Data 0.000 (0.089) Loss 0.7591 (0.7420) Prec@1 74.219 (79.169) Prec@5 94.531 (94.467)
[2021-05-01 09:31:59 train_lshot.py:257] INFO Epoch: [40][70/150] Time 0.279 (0.373) Data 0.001 (0.077) Loss 0.8655 (0.7410) Prec@1 77.734 (79.264) Prec@5 93.359 (94.526)
[2021-05-01 09:32:01 train_lshot.py:257] INFO Epoch: [40][80/150] Time 0.273 (0.362) Data 0.000 (0.067) Loss 0.7353 (0.7473) Prec@1 78.125 (79.128) Prec@5 93.750 (94.464)
[2021-05-01 09:32:04 train_lshot.py:257] INFO Epoch: [40][90/150] Time 0.274 (0.353) Data 0.000 (0.060) Loss 0.8192 (0.7522) Prec@1 76.953 (79.039) Prec@5 93.750 (94.450)
[2021-05-01 09:32:07 train_lshot.py:257] INFO Epoch: [40][100/150] Time 0.282 (0.346) Data 0.000 (0.054) Loss 0.7959 (0.7532) Prec@1 76.953 (79.015) Prec@5 93.359 (94.431)
[2021-05-01 09:32:10 train_lshot.py:257] INFO Epoch: [40][110/150] Time 0.277 (0.340) Data 0.000 (0.049) Loss 0.7631 (0.7536) Prec@1 80.078 (79.012) Prec@5 94.141 (94.433)
[2021-05-01 09:32:14 train_lshot.py:257] INFO Epoch: [40][120/150] Time 0.319 (0.344) Data 0.000 (0.045) Loss 0.7996 (0.7567) Prec@1 76.562 (78.864) Prec@5 94.531 (94.386)
[2021-05-01 09:32:17 train_lshot.py:257] INFO Epoch: [40][130/150] Time 0.273 (0.340) Data 0.000 (0.042) Loss 0.8943 (0.7616) Prec@1 71.875 (78.712) Prec@5 94.922 (94.343)
[2021-05-01 09:32:19 train_lshot.py:257] INFO Epoch: [40][140/150] Time 0.274 (0.335) Data 0.000 (0.039) Loss 0.8306 (0.7644) Prec@1 78.125 (78.657) Prec@5 93.359 (94.326)
[2021-05-01 09:32:30 train_lshot.py:257] INFO Epoch: [41][0/150] Time 6.240 (6.240) Data 5.798 (5.798) Loss 0.7095 (0.7095) Prec@1 80.469 (80.469) Prec@5 95.312 (95.312)
[2021-05-01 09:32:33 train_lshot.py:257] INFO Epoch: [41][10/150] Time 0.293 (0.897) Data 0.001 (0.529) Loss 0.7001 (0.7506) Prec@1 81.641 (79.084) Prec@5 94.531 (94.105)
[2021-05-01 09:32:36 train_lshot.py:257] INFO Epoch: [41][20/150] Time 0.283 (0.607) Data 0.000 (0.277) Loss 0.6455 (0.7308) Prec@1 83.594 (79.464) Prec@5 96.875 (94.438)
[2021-05-01 09:32:39 train_lshot.py:257] INFO Epoch: [41][30/150] Time 0.280 (0.504) Data 0.000 (0.188) Loss 0.7755 (0.7382) Prec@1 82.031 (79.297) Prec@5 92.578 (94.254)
[2021-05-01 09:32:42 train_lshot.py:257] INFO Epoch: [41][40/150] Time 0.283 (0.450) Data 0.000 (0.142) Loss 0.6430 (0.7308) Prec@1 82.812 (79.402) Prec@5 94.531 (94.322)
[2021-05-01 09:32:45 train_lshot.py:257] INFO Epoch: [41][50/150] Time 0.281 (0.417) Data 0.000 (0.114) Loss 0.6941 (0.7306) Prec@1 79.688 (79.366) Prec@5 95.312 (94.409)
[2021-05-01 09:32:47 train_lshot.py:257] INFO Epoch: [41][60/150] Time 0.274 (0.394) Data 0.000 (0.096) Loss 0.7923 (0.7350) Prec@1 78.906 (79.265) Prec@5 94.531 (94.454)
[2021-05-01 09:32:50 train_lshot.py:257] INFO Epoch: [41][70/150] Time 0.282 (0.378) Data 0.001 (0.082) Loss 0.8134 (0.7421) Prec@1 75.391 (79.137) Prec@5 92.188 (94.350)
[2021-05-01 09:32:53 train_lshot.py:257] INFO Epoch: [41][80/150] Time 0.280 (0.366) Data 0.000 (0.072) Loss 0.6859 (0.7494) Prec@1 82.422 (78.983) Prec@5 94.531 (94.319)
[2021-05-01 09:32:56 train_lshot.py:257] INFO Epoch: [41][90/150] Time 0.277 (0.359) Data 0.000 (0.064) Loss 0.8760 (0.7451) Prec@1 76.172 (79.082) Prec@5 92.188 (94.394)
[2021-05-01 09:32:59 train_lshot.py:257] INFO Epoch: [41][100/150] Time 0.285 (0.351) Data 0.000 (0.058) Loss 0.6949 (0.7457) Prec@1 77.734 (79.038) Prec@5 95.312 (94.442)
[2021-05-01 09:33:02 train_lshot.py:257] INFO Epoch: [41][110/150] Time 0.285 (0.345) Data 0.000 (0.053) Loss 0.8463 (0.7531) Prec@1 78.516 (78.839) Prec@5 92.188 (94.362)
[2021-05-01 09:33:05 train_lshot.py:257] INFO Epoch: [41][120/150] Time 0.275 (0.340) Data 0.000 (0.048) Loss 0.8220 (0.7547) Prec@1 75.391 (78.806) Prec@5 94.141 (94.341)
[2021-05-01 09:33:09 train_lshot.py:257] INFO Epoch: [41][130/150] Time 0.303 (0.345) Data 0.000 (0.045) Loss 0.7430 (0.7558) Prec@1 78.516 (78.730) Prec@5 94.531 (94.284)
[2021-05-01 09:33:11 train_lshot.py:257] INFO Epoch: [41][140/150] Time 0.277 (0.341) Data 0.000 (0.042) Loss 0.7886 (0.7608) Prec@1 75.781 (78.596) Prec@5 94.531 (94.243)
[2021-05-01 09:33:21 train_lshot.py:257] INFO Epoch: [42][0/150] Time 6.743 (6.743) Data 6.340 (6.340) Loss 0.7254 (0.7254) Prec@1 80.859 (80.859) Prec@5 94.531 (94.531)
[2021-05-01 09:33:25 train_lshot.py:257] INFO Epoch: [42][10/150] Time 0.287 (0.946) Data 0.001 (0.578) Loss 0.7406 (0.7582) Prec@1 77.734 (78.622) Prec@5 94.922 (94.354)
[2021-05-01 09:33:28 train_lshot.py:257] INFO Epoch: [42][20/150] Time 0.293 (0.632) Data 0.000 (0.303) Loss 0.6318 (0.7501) Prec@1 83.594 (79.260) Prec@5 96.484 (94.420)
[2021-05-01 09:33:31 train_lshot.py:257] INFO Epoch: [42][30/150] Time 0.276 (0.521) Data 0.000 (0.205) Loss 0.6524 (0.7312) Prec@1 80.859 (79.650) Prec@5 95.703 (94.594)
[2021-05-01 09:33:33 train_lshot.py:257] INFO Epoch: [42][40/150] Time 0.283 (0.463) Data 0.000 (0.155) Loss 0.7729 (0.7205) Prec@1 78.516 (79.840) Prec@5 93.750 (94.665)
[2021-05-01 09:33:36 train_lshot.py:257] INFO Epoch: [42][50/150] Time 0.285 (0.428) Data 0.000 (0.125) Loss 0.7335 (0.7296) Prec@1 78.906 (79.634) Prec@5 96.094 (94.616)
[2021-05-01 09:33:39 train_lshot.py:257] INFO Epoch: [42][60/150] Time 0.286 (0.404) Data 0.001 (0.105) Loss 0.6311 (0.7305) Prec@1 82.422 (79.553) Prec@5 94.141 (94.582)
[2021-05-01 09:33:42 train_lshot.py:257] INFO Epoch: [42][70/150] Time 0.287 (0.387) Data 0.001 (0.090) Loss 0.7375 (0.7356) Prec@1 77.734 (79.330) Prec@5 95.312 (94.570)
[2021-05-01 09:33:45 train_lshot.py:257] INFO Epoch: [42][80/150] Time 0.282 (0.374) Data 0.000 (0.079) Loss 0.7562 (0.7404) Prec@1 78.125 (79.138) Prec@5 94.531 (94.488)
[2021-05-01 09:33:48 train_lshot.py:257] INFO Epoch: [42][90/150] Time 0.286 (0.364) Data 0.000 (0.070) Loss 0.7418 (0.7467) Prec@1 78.516 (78.945) Prec@5 94.531 (94.450)
[2021-05-01 09:33:50 train_lshot.py:257] INFO Epoch: [42][100/150] Time 0.285 (0.356) Data 0.000 (0.063) Loss 0.7417 (0.7472) Prec@1 81.250 (78.945) Prec@5 95.312 (94.489)
[2021-05-01 09:33:53 train_lshot.py:257] INFO Epoch: [42][110/150] Time 0.289 (0.350) Data 0.000 (0.058) Loss 0.7860 (0.7476) Prec@1 76.953 (79.015) Prec@5 96.484 (94.443)
[2021-05-01 09:33:56 train_lshot.py:257] INFO Epoch: [42][120/150] Time 0.286 (0.344) Data 0.000 (0.053) Loss 0.7972 (0.7509) Prec@1 75.781 (78.922) Prec@5 93.359 (94.399)
[2021-05-01 09:33:59 train_lshot.py:257] INFO Epoch: [42][130/150] Time 0.294 (0.341) Data 0.000 (0.049) Loss 0.6963 (0.7530) Prec@1 80.859 (78.876) Prec@5 96.484 (94.394)
[2021-05-01 09:34:02 train_lshot.py:257] INFO Epoch: [42][140/150] Time 0.288 (0.337) Data 0.000 (0.045) Loss 0.8944 (0.7562) Prec@1 73.828 (78.831) Prec@5 92.578 (94.343)
[2021-05-01 09:34:11 train_lshot.py:257] INFO Epoch: [43][0/150] Time 5.676 (5.676) Data 5.222 (5.222) Loss 0.6616 (0.6616) Prec@1 79.688 (79.688) Prec@5 95.703 (95.703)
[2021-05-01 09:34:15 train_lshot.py:257] INFO Epoch: [43][10/150] Time 0.279 (0.927) Data 0.001 (0.566) Loss 0.6791 (0.6970) Prec@1 80.078 (79.972) Prec@5 96.094 (95.206)
[2021-05-01 09:34:18 train_lshot.py:257] INFO Epoch: [43][20/150] Time 0.276 (0.619) Data 0.000 (0.297) Loss 0.8152 (0.7022) Prec@1 76.953 (79.725) Prec@5 91.797 (95.089)
[2021-05-01 09:34:21 train_lshot.py:257] INFO Epoch: [43][30/150] Time 0.283 (0.513) Data 0.000 (0.201) Loss 0.7948 (0.7040) Prec@1 77.734 (79.738) Prec@5 94.141 (95.123)
[2021-05-01 09:34:24 train_lshot.py:257] INFO Epoch: [43][40/150] Time 0.277 (0.457) Data 0.000 (0.152) Loss 0.7909 (0.7120) Prec@1 80.078 (79.678) Prec@5 93.359 (94.950)
[2021-05-01 09:34:27 train_lshot.py:257] INFO Epoch: [43][50/150] Time 0.284 (0.422) Data 0.000 (0.122) Loss 0.7267 (0.7121) Prec@1 78.906 (79.680) Prec@5 93.750 (94.983)
[2021-05-01 09:34:29 train_lshot.py:257] INFO Epoch: [43][60/150] Time 0.284 (0.399) Data 0.000 (0.102) Loss 0.7635 (0.7240) Prec@1 79.297 (79.521) Prec@5 94.531 (94.832)
[2021-05-01 09:34:32 train_lshot.py:257] INFO Epoch: [43][70/150] Time 0.287 (0.382) Data 0.001 (0.088) Loss 0.7214 (0.7284) Prec@1 81.641 (79.588) Prec@5 93.359 (94.751)
[2021-05-01 09:34:35 train_lshot.py:257] INFO Epoch: [43][80/150] Time 0.281 (0.370) Data 0.000 (0.077) Loss 0.6582 (0.7284) Prec@1 80.859 (79.461) Prec@5 96.875 (94.792)
[2021-05-01 09:34:38 train_lshot.py:257] INFO Epoch: [43][90/150] Time 0.289 (0.363) Data 0.000 (0.069) Loss 0.8446 (0.7322) Prec@1 75.391 (79.318) Prec@5 94.141 (94.677)
[2021-05-01 09:34:41 train_lshot.py:257] INFO Epoch: [43][100/150] Time 0.275 (0.355) Data 0.000 (0.062) Loss 0.7064 (0.7348) Prec@1 80.859 (79.312) Prec@5 95.312 (94.636)
[2021-05-01 09:34:44 train_lshot.py:257] INFO Epoch: [43][110/150] Time 0.285 (0.349) Data 0.000 (0.056) Loss 0.5738 (0.7318) Prec@1 85.547 (79.441) Prec@5 96.875 (94.658)
[2021-05-01 09:34:48 train_lshot.py:257] INFO Epoch: [43][120/150] Time 0.287 (0.354) Data 0.000 (0.052) Loss 0.7096 (0.7341) Prec@1 82.422 (79.436) Prec@5 94.531 (94.564)
[2021-05-01 09:34:51 train_lshot.py:257] INFO Epoch: [43][130/150] Time 0.273 (0.348) Data 0.000 (0.048) Loss 0.7103 (0.7358) Prec@1 79.297 (79.425) Prec@5 94.531 (94.543)
[2021-05-01 09:34:53 train_lshot.py:257] INFO Epoch: [43][140/150] Time 0.293 (0.344) Data 0.000 (0.044) Loss 0.7133 (0.7378) Prec@1 78.516 (79.397) Prec@5 94.141 (94.542)
[2021-05-01 09:35:24 train_lshot.py:119] INFO Meta Val 43: 0.5810933464169502
[2021-05-01 09:35:30 train_lshot.py:257] INFO Epoch: [44][0/150] Time 5.323 (5.323) Data 4.880 (4.880) Loss 0.5059 (0.5059) Prec@1 85.938 (85.938) Prec@5 96.875 (96.875)
[2021-05-01 09:35:34 train_lshot.py:257] INFO Epoch: [44][10/150] Time 0.311 (0.807) Data 0.000 (0.458) Loss 0.6208 (0.6454) Prec@1 80.078 (80.966) Prec@5 96.094 (95.597)
[2021-05-01 09:35:37 train_lshot.py:257] INFO Epoch: [44][20/150] Time 0.285 (0.560) Data 0.000 (0.240) Loss 0.7117 (0.6679) Prec@1 79.688 (80.729) Prec@5 96.094 (95.201)
[2021-05-01 09:35:39 train_lshot.py:257] INFO Epoch: [44][30/150] Time 0.274 (0.470) Data 0.000 (0.163) Loss 0.4897 (0.6763) Prec@1 85.547 (80.771) Prec@5 97.656 (95.073)
[2021-05-01 09:35:42 train_lshot.py:257] INFO Epoch: [44][40/150] Time 0.275 (0.425) Data 0.000 (0.123) Loss 0.7161 (0.6819) Prec@1 80.469 (80.793) Prec@5 94.141 (95.084)
[2021-05-01 09:35:45 train_lshot.py:257] INFO Epoch: [44][50/150] Time 0.277 (0.397) Data 0.000 (0.099) Loss 0.8175 (0.6912) Prec@1 74.219 (80.446) Prec@5 93.750 (94.991)
[2021-05-01 09:35:48 train_lshot.py:257] INFO Epoch: [44][60/150] Time 0.275 (0.378) Data 0.001 (0.083) Loss 0.6772 (0.6956) Prec@1 80.859 (80.373) Prec@5 93.359 (94.935)
[2021-05-01 09:35:51 train_lshot.py:257] INFO Epoch: [44][70/150] Time 0.284 (0.365) Data 0.003 (0.071) Loss 0.7962 (0.6991) Prec@1 76.953 (80.298) Prec@5 92.969 (94.867)
[2021-05-01 09:35:54 train_lshot.py:257] INFO Epoch: [44][80/150] Time 0.280 (0.354) Data 0.000 (0.063) Loss 0.8245 (0.7036) Prec@1 74.219 (80.247) Prec@5 92.188 (94.816)
[2021-05-01 09:35:56 train_lshot.py:257] INFO Epoch: [44][90/150] Time 0.280 (0.346) Data 0.000 (0.056) Loss 0.8199 (0.7092) Prec@1 79.297 (80.087) Prec@5 92.188 (94.767)
[2021-05-01 09:35:59 train_lshot.py:257] INFO Epoch: [44][100/150] Time 0.279 (0.340) Data 0.000 (0.050) Loss 0.8171 (0.7140) Prec@1 75.000 (79.896) Prec@5 95.312 (94.752)
[2021-05-01 09:36:02 train_lshot.py:257] INFO Epoch: [44][110/150] Time 0.281 (0.335) Data 0.000 (0.046) Loss 0.6815 (0.7160) Prec@1 78.516 (79.835) Prec@5 95.703 (94.753)
[2021-05-01 09:36:05 train_lshot.py:257] INFO Epoch: [44][120/150] Time 0.291 (0.330) Data 0.001 (0.042) Loss 0.7478 (0.7200) Prec@1 78.125 (79.733) Prec@5 94.141 (94.667)
[2021-05-01 09:36:08 train_lshot.py:257] INFO Epoch: [44][130/150] Time 0.287 (0.327) Data 0.000 (0.039) Loss 0.6833 (0.7184) Prec@1 82.812 (79.801) Prec@5 94.922 (94.668)
[2021-05-01 09:36:10 train_lshot.py:257] INFO Epoch: [44][140/150] Time 0.278 (0.324) Data 0.000 (0.036) Loss 0.6723 (0.7190) Prec@1 79.688 (79.812) Prec@5 96.484 (94.667)
[2021-05-01 09:36:21 train_lshot.py:257] INFO Epoch: [45][0/150] Time 7.027 (7.027) Data 6.626 (6.626) Loss 0.7513 (0.7513) Prec@1 75.781 (75.781) Prec@5 92.969 (92.969)
[2021-05-01 09:36:24 train_lshot.py:257] INFO Epoch: [45][10/150] Time 0.289 (0.962) Data 0.000 (0.604) Loss 0.5880 (0.6610) Prec@1 84.375 (80.682) Prec@5 96.094 (95.384)
[2021-05-01 09:36:27 train_lshot.py:257] INFO Epoch: [45][20/150] Time 0.285 (0.637) Data 0.000 (0.316) Loss 0.6886 (0.6656) Prec@1 82.812 (81.120) Prec@5 95.703 (95.201)
[2021-05-01 09:36:30 train_lshot.py:257] INFO Epoch: [45][30/150] Time 0.306 (0.528) Data 0.000 (0.214) Loss 0.7184 (0.6700) Prec@1 75.781 (81.086) Prec@5 94.141 (95.161)
[2021-05-01 09:36:33 train_lshot.py:257] INFO Epoch: [45][40/150] Time 0.282 (0.468) Data 0.000 (0.162) Loss 0.7560 (0.6744) Prec@1 81.250 (81.117) Prec@5 94.141 (95.179)
[2021-05-01 09:36:35 train_lshot.py:257] INFO Epoch: [45][50/150] Time 0.279 (0.431) Data 0.000 (0.130) Loss 0.7655 (0.6797) Prec@1 78.906 (80.959) Prec@5 94.531 (95.083)
[2021-05-01 09:36:38 train_lshot.py:257] INFO Epoch: [45][60/150] Time 0.290 (0.407) Data 0.000 (0.109) Loss 0.6571 (0.6872) Prec@1 82.422 (80.629) Prec@5 96.875 (95.140)
[2021-05-01 09:36:41 train_lshot.py:257] INFO Epoch: [45][70/150] Time 0.295 (0.389) Data 0.001 (0.094) Loss 0.6168 (0.6937) Prec@1 80.859 (80.392) Prec@5 95.703 (95.026)
[2021-05-01 09:36:45 train_lshot.py:257] INFO Epoch: [45][80/150] Time 0.317 (0.386) Data 0.000 (0.082) Loss 0.8093 (0.6945) Prec@1 78.125 (80.483) Prec@5 94.531 (95.028)
[2021-05-01 09:36:48 train_lshot.py:257] INFO Epoch: [45][90/150] Time 0.281 (0.376) Data 0.001 (0.073) Loss 0.7329 (0.6981) Prec@1 81.250 (80.404) Prec@5 93.359 (94.991)
[2021-05-01 09:36:50 train_lshot.py:257] INFO Epoch: [45][100/150] Time 0.287 (0.366) Data 0.000 (0.066) Loss 0.5091 (0.6983) Prec@1 84.766 (80.418) Prec@5 98.047 (95.007)
[2021-05-01 09:36:54 train_lshot.py:257] INFO Epoch: [45][110/150] Time 0.487 (0.360) Data 0.000 (0.060) Loss 0.5984 (0.7061) Prec@1 84.766 (80.149) Prec@5 97.266 (94.925)
[2021-05-01 09:36:57 train_lshot.py:257] INFO Epoch: [45][120/150] Time 0.285 (0.357) Data 0.000 (0.055) Loss 0.7448 (0.7086) Prec@1 78.125 (80.039) Prec@5 94.141 (94.928)
[2021-05-01 09:37:00 train_lshot.py:257] INFO Epoch: [45][130/150] Time 0.274 (0.351) Data 0.000 (0.051) Loss 0.7453 (0.7096) Prec@1 78.125 (80.004) Prec@5 94.531 (94.940)
[2021-05-01 09:37:02 train_lshot.py:257] INFO Epoch: [45][140/150] Time 0.284 (0.346) Data 0.000 (0.047) Loss 0.6749 (0.7146) Prec@1 80.859 (79.848) Prec@5 95.312 (94.911)
[2021-05-01 09:37:09 train_lshot.py:257] INFO Epoch: [46][0/150] Time 4.113 (4.113) Data 3.708 (3.708) Loss 0.7655 (0.7655) Prec@1 77.734 (77.734) Prec@5 93.359 (93.359)
[2021-05-01 09:37:16 train_lshot.py:257] INFO Epoch: [46][10/150] Time 0.288 (0.934) Data 0.000 (0.586) Loss 0.6742 (0.6719) Prec@1 83.203 (81.641) Prec@5 94.531 (94.993)
[2021-05-01 09:37:19 train_lshot.py:257] INFO Epoch: [46][20/150] Time 0.289 (0.628) Data 0.000 (0.307) Loss 0.7304 (0.6514) Prec@1 80.469 (81.957) Prec@5 95.312 (95.592)
[2021-05-01 09:37:21 train_lshot.py:257] INFO Epoch: [46][30/150] Time 0.281 (0.517) Data 0.000 (0.208) Loss 0.4781 (0.6280) Prec@1 86.719 (82.535) Prec@5 97.266 (95.842)
[2021-05-01 09:37:24 train_lshot.py:257] INFO Epoch: [46][40/150] Time 0.304 (0.460) Data 0.004 (0.158) Loss 0.5411 (0.6073) Prec@1 83.984 (83.098) Prec@5 97.656 (95.960)
[2021-05-01 09:37:27 train_lshot.py:257] INFO Epoch: [46][50/150] Time 0.280 (0.425) Data 0.000 (0.127) Loss 0.5226 (0.5961) Prec@1 84.766 (83.456) Prec@5 95.703 (95.910)
[2021-05-01 09:37:30 train_lshot.py:257] INFO Epoch: [46][60/150] Time 0.275 (0.401) Data 0.000 (0.106) Loss 0.4079 (0.5867) Prec@1 88.672 (83.683) Prec@5 97.266 (96.036)
[2021-05-01 09:37:33 train_lshot.py:257] INFO Epoch: [46][70/150] Time 0.285 (0.385) Data 0.001 (0.091) Loss 0.5163 (0.5784) Prec@1 83.984 (83.869) Prec@5 96.875 (96.132)
[2021-05-01 09:37:36 train_lshot.py:257] INFO Epoch: [46][80/150] Time 0.348 (0.383) Data 0.000 (0.080) Loss 0.4991 (0.5680) Prec@1 86.328 (84.163) Prec@5 98.047 (96.229)
[2021-05-01 09:37:39 train_lshot.py:257] INFO Epoch: [46][90/150] Time 0.273 (0.373) Data 0.000 (0.071) Loss 0.4175 (0.5604) Prec@1 89.453 (84.418) Prec@5 96.484 (96.274)
[2021-05-01 09:37:42 train_lshot.py:257] INFO Epoch: [46][100/150] Time 0.283 (0.363) Data 0.000 (0.064) Loss 0.5183 (0.5592) Prec@1 85.547 (84.518) Prec@5 98.047 (96.241)
[2021-05-01 09:37:45 train_lshot.py:257] INFO Epoch: [46][110/150] Time 0.276 (0.356) Data 0.000 (0.058) Loss 0.6352 (0.5571) Prec@1 82.812 (84.597) Prec@5 94.531 (96.252)
[2021-05-01 09:37:48 train_lshot.py:257] INFO Epoch: [46][120/150] Time 0.276 (0.350) Data 0.000 (0.054) Loss 0.6147 (0.5533) Prec@1 84.766 (84.737) Prec@5 94.141 (96.275)
[2021-05-01 09:37:51 train_lshot.py:257] INFO Epoch: [46][130/150] Time 0.325 (0.349) Data 0.000 (0.050) Loss 0.4816 (0.5497) Prec@1 87.109 (84.876) Prec@5 96.484 (96.314)
[2021-05-01 09:37:54 train_lshot.py:257] INFO Epoch: [46][140/150] Time 0.284 (0.345) Data 0.000 (0.046) Loss 0.4350 (0.5481) Prec@1 88.281 (84.929) Prec@5 98.828 (96.329)
[2021-05-01 09:38:02 train_lshot.py:257] INFO Epoch: [47][0/150] Time 4.884 (4.884) Data 4.422 (4.422) Loss 0.4368 (0.4368) Prec@1 87.891 (87.891) Prec@5 98.047 (98.047)
[2021-05-01 09:38:07 train_lshot.py:257] INFO Epoch: [47][10/150] Time 0.341 (0.878) Data 0.003 (0.491) Loss 0.5517 (0.5122) Prec@1 84.375 (85.795) Prec@5 95.312 (96.378)
[2021-05-01 09:38:10 train_lshot.py:257] INFO Epoch: [47][20/150] Time 0.278 (0.599) Data 0.000 (0.258) Loss 0.4871 (0.4995) Prec@1 86.719 (86.365) Prec@5 95.312 (96.466)
[2021-05-01 09:38:12 train_lshot.py:257] INFO Epoch: [47][30/150] Time 0.286 (0.500) Data 0.001 (0.175) Loss 0.4357 (0.4949) Prec@1 87.891 (86.568) Prec@5 97.656 (96.560)
[2021-05-01 09:38:15 train_lshot.py:257] INFO Epoch: [47][40/150] Time 0.282 (0.446) Data 0.000 (0.132) Loss 0.4279 (0.4915) Prec@1 88.281 (86.614) Prec@5 98.047 (96.561)
[2021-05-01 09:38:18 train_lshot.py:257] INFO Epoch: [47][50/150] Time 0.280 (0.414) Data 0.001 (0.106) Loss 0.5094 (0.4916) Prec@1 87.891 (86.726) Prec@5 96.094 (96.561)
[2021-05-01 09:38:21 train_lshot.py:257] INFO Epoch: [47][60/150] Time 0.275 (0.392) Data 0.000 (0.089) Loss 0.4881 (0.4952) Prec@1 87.891 (86.584) Prec@5 96.484 (96.523)
[2021-05-01 09:38:24 train_lshot.py:257] INFO Epoch: [47][70/150] Time 0.284 (0.376) Data 0.001 (0.077) Loss 0.4999 (0.4916) Prec@1 87.891 (86.757) Prec@5 94.922 (96.550)
[2021-05-01 09:38:27 train_lshot.py:257] INFO Epoch: [47][80/150] Time 0.286 (0.365) Data 0.000 (0.067) Loss 0.5115 (0.4922) Prec@1 86.328 (86.709) Prec@5 96.875 (96.624)
[2021-05-01 09:38:30 train_lshot.py:257] INFO Epoch: [47][90/150] Time 0.284 (0.359) Data 0.000 (0.060) Loss 0.5355 (0.4922) Prec@1 86.328 (86.710) Prec@5 96.094 (96.605)
[2021-05-01 09:38:32 train_lshot.py:257] INFO Epoch: [47][100/150] Time 0.288 (0.351) Data 0.000 (0.054) Loss 0.4885 (0.4932) Prec@1 87.891 (86.676) Prec@5 96.484 (96.569)
[2021-05-01 09:38:35 train_lshot.py:257] INFO Epoch: [47][110/150] Time 0.290 (0.345) Data 0.000 (0.049) Loss 0.4449 (0.4903) Prec@1 88.281 (86.719) Prec@5 96.875 (96.604)
[2021-05-01 09:38:38 train_lshot.py:257] INFO Epoch: [47][120/150] Time 0.537 (0.342) Data 0.000 (0.045) Loss 0.4527 (0.4886) Prec@1 89.062 (86.777) Prec@5 96.484 (96.594)
[2021-05-01 09:38:42 train_lshot.py:257] INFO Epoch: [47][130/150] Time 0.284 (0.341) Data 0.000 (0.042) Loss 0.3656 (0.4874) Prec@1 92.188 (86.787) Prec@5 97.266 (96.610)
[2021-05-01 09:38:45 train_lshot.py:257] INFO Epoch: [47][140/150] Time 0.288 (0.337) Data 0.000 (0.039) Loss 0.4051 (0.4874) Prec@1 89.062 (86.777) Prec@5 98.438 (96.595)
[2021-05-01 09:39:16 train_lshot.py:119] INFO Meta Val 47: 0.6016533468365669
[2021-05-01 09:39:21 train_lshot.py:257] INFO Epoch: [48][0/150] Time 4.965 (4.965) Data 4.567 (4.567) Loss 0.5015 (0.5015) Prec@1 84.766 (84.766) Prec@5 97.266 (97.266)
[2021-05-01 09:39:25 train_lshot.py:257] INFO Epoch: [48][10/150] Time 0.387 (0.808) Data 0.001 (0.428) Loss 0.4510 (0.4788) Prec@1 87.500 (86.364) Prec@5 97.266 (96.626)
[2021-05-01 09:39:28 train_lshot.py:257] INFO Epoch: [48][20/150] Time 0.278 (0.565) Data 0.000 (0.224) Loss 0.4091 (0.4515) Prec@1 90.234 (87.853) Prec@5 98.047 (97.061)
[2021-05-01 09:39:31 train_lshot.py:257] INFO Epoch: [48][30/150] Time 0.274 (0.473) Data 0.000 (0.152) Loss 0.4231 (0.4553) Prec@1 87.891 (87.802) Prec@5 97.266 (96.976)
[2021-05-01 09:39:34 train_lshot.py:257] INFO Epoch: [48][40/150] Time 0.279 (0.429) Data 0.000 (0.115) Loss 0.4275 (0.4635) Prec@1 87.891 (87.595) Prec@5 97.656 (96.856)
[2021-05-01 09:39:37 train_lshot.py:257] INFO Epoch: [48][50/150] Time 0.296 (0.400) Data 0.000 (0.093) Loss 0.4600 (0.4560) Prec@1 88.281 (87.776) Prec@5 98.047 (96.990)
[2021-05-01 09:39:40 train_lshot.py:257] INFO Epoch: [48][60/150] Time 0.293 (0.380) Data 0.000 (0.077) Loss 0.5286 (0.4538) Prec@1 85.938 (87.756) Prec@5 96.484 (97.035)
[2021-05-01 09:39:42 train_lshot.py:257] INFO Epoch: [48][70/150] Time 0.277 (0.367) Data 0.001 (0.067) Loss 0.3995 (0.4555) Prec@1 88.672 (87.682) Prec@5 97.656 (97.018)
[2021-05-01 09:39:45 train_lshot.py:257] INFO Epoch: [48][80/150] Time 0.271 (0.356) Data 0.000 (0.058) Loss 0.5395 (0.4573) Prec@1 85.938 (87.568) Prec@5 95.312 (97.015)
[2021-05-01 09:39:48 train_lshot.py:257] INFO Epoch: [48][90/150] Time 0.280 (0.347) Data 0.000 (0.052) Loss 0.3603 (0.4620) Prec@1 89.453 (87.414) Prec@5 97.656 (96.935)
[2021-05-01 09:39:52 train_lshot.py:257] INFO Epoch: [48][100/150] Time 0.319 (0.353) Data 0.000 (0.047) Loss 0.5094 (0.4613) Prec@1 87.109 (87.423) Prec@5 95.703 (96.925)
[2021-05-01 09:39:55 train_lshot.py:257] INFO Epoch: [48][110/150] Time 0.279 (0.347) Data 0.000 (0.043) Loss 0.4622 (0.4628) Prec@1 85.938 (87.363) Prec@5 97.656 (96.959)
[2021-05-01 09:39:58 train_lshot.py:257] INFO Epoch: [48][120/150] Time 0.423 (0.344) Data 0.000 (0.039) Loss 0.3745 (0.4601) Prec@1 89.453 (87.442) Prec@5 98.047 (97.011)
[2021-05-01 09:40:01 train_lshot.py:257] INFO Epoch: [48][130/150] Time 0.282 (0.341) Data 0.000 (0.036) Loss 0.5540 (0.4623) Prec@1 84.766 (87.402) Prec@5 95.312 (96.988)
[2021-05-01 09:40:04 train_lshot.py:257] INFO Epoch: [48][140/150] Time 0.281 (0.337) Data 0.000 (0.034) Loss 0.4393 (0.4619) Prec@1 88.672 (87.422) Prec@5 97.656 (96.994)
[2021-05-01 09:40:13 train_lshot.py:257] INFO Epoch: [49][0/150] Time 5.680 (5.680) Data 5.267 (5.267) Loss 0.4256 (0.4256) Prec@1 89.062 (89.062) Prec@5 97.266 (97.266)
[2021-05-01 09:40:16 train_lshot.py:257] INFO Epoch: [49][10/150] Time 0.339 (0.867) Data 0.001 (0.480) Loss 0.4560 (0.4652) Prec@1 89.844 (87.287) Prec@5 96.484 (97.053)
[2021-05-01 09:40:19 train_lshot.py:257] INFO Epoch: [49][20/150] Time 0.283 (0.592) Data 0.000 (0.252) Loss 0.3994 (0.4435) Prec@1 89.844 (87.946) Prec@5 96.484 (97.098)
[2021-05-01 09:40:22 train_lshot.py:257] INFO Epoch: [49][30/150] Time 0.286 (0.493) Data 0.000 (0.171) Loss 0.3675 (0.4498) Prec@1 89.844 (87.714) Prec@5 98.438 (97.039)
[2021-05-01 09:40:25 train_lshot.py:257] INFO Epoch: [49][40/150] Time 0.280 (0.441) Data 0.000 (0.129) Loss 0.4518 (0.4448) Prec@1 87.500 (88.081) Prec@5 98.047 (97.104)
[2021-05-01 09:40:28 train_lshot.py:257] INFO Epoch: [49][50/150] Time 0.293 (0.409) Data 0.000 (0.104) Loss 0.4476 (0.4498) Prec@1 90.234 (87.975) Prec@5 96.484 (97.005)
[2021-05-01 09:40:31 train_lshot.py:257] INFO Epoch: [49][60/150] Time 0.277 (0.389) Data 0.000 (0.087) Loss 0.3955 (0.4507) Prec@1 89.062 (87.961) Prec@5 98.047 (96.990)
[2021-05-01 09:40:34 train_lshot.py:257] INFO Epoch: [49][70/150] Time 0.500 (0.377) Data 0.001 (0.075) Loss 0.5689 (0.4533) Prec@1 87.109 (87.935) Prec@5 94.922 (96.903)
[2021-05-01 09:40:37 train_lshot.py:257] INFO Epoch: [49][80/150] Time 0.284 (0.371) Data 0.000 (0.065) Loss 0.4937 (0.4584) Prec@1 87.891 (87.794) Prec@5 96.875 (96.832)
[2021-05-01 09:40:40 train_lshot.py:257] INFO Epoch: [49][90/150] Time 0.282 (0.361) Data 0.000 (0.058) Loss 0.5228 (0.4567) Prec@1 85.938 (87.822) Prec@5 96.094 (96.905)
[2021-05-01 09:40:43 train_lshot.py:257] INFO Epoch: [49][100/150] Time 0.296 (0.360) Data 0.000 (0.053) Loss 0.4429 (0.4537) Prec@1 87.500 (87.929) Prec@5 96.875 (96.902)
[2021-05-01 09:40:46 train_lshot.py:257] INFO Epoch: [49][110/150] Time 0.280 (0.353) Data 0.000 (0.048) Loss 0.5245 (0.4507) Prec@1 85.547 (87.979) Prec@5 96.094 (96.945)
[2021-05-01 09:40:49 train_lshot.py:257] INFO Epoch: [49][120/150] Time 0.278 (0.347) Data 0.000 (0.044) Loss 0.4957 (0.4521) Prec@1 87.109 (87.881) Prec@5 95.312 (96.940)
[2021-05-01 09:40:52 train_lshot.py:257] INFO Epoch: [49][130/150] Time 0.279 (0.342) Data 0.000 (0.041) Loss 0.5030 (0.4517) Prec@1 87.109 (87.888) Prec@5 97.266 (96.967)
[2021-05-01 09:40:55 train_lshot.py:257] INFO Epoch: [49][140/150] Time 0.285 (0.338) Data 0.000 (0.038) Loss 0.4571 (0.4518) Prec@1 86.719 (87.844) Prec@5 97.656 (96.964)
[2021-05-01 09:41:04 train_lshot.py:257] INFO Epoch: [50][0/150] Time 5.892 (5.892) Data 5.398 (5.398) Loss 0.4576 (0.4576) Prec@1 87.109 (87.109) Prec@5 96.484 (96.484)
[2021-05-01 09:41:07 train_lshot.py:257] INFO Epoch: [50][10/150] Time 0.289 (0.886) Data 0.000 (0.509) Loss 0.3641 (0.4372) Prec@1 89.844 (87.820) Prec@5 99.219 (97.124)
[2021-05-01 09:41:10 train_lshot.py:257] INFO Epoch: [50][20/150] Time 0.277 (0.600) Data 0.000 (0.267) Loss 0.4380 (0.4385) Prec@1 89.844 (88.021) Prec@5 96.484 (97.135)
[2021-05-01 09:41:13 train_lshot.py:257] INFO Epoch: [50][30/150] Time 0.282 (0.500) Data 0.000 (0.181) Loss 0.3774 (0.4345) Prec@1 89.844 (88.407) Prec@5 97.266 (97.001)
[2021-05-01 09:41:16 train_lshot.py:257] INFO Epoch: [50][40/150] Time 0.289 (0.447) Data 0.001 (0.137) Loss 0.4161 (0.4378) Prec@1 90.234 (88.367) Prec@5 96.484 (96.980)
[2021-05-01 09:41:19 train_lshot.py:257] INFO Epoch: [50][50/150] Time 0.283 (0.414) Data 0.000 (0.110) Loss 0.5051 (0.4378) Prec@1 85.938 (88.304) Prec@5 96.484 (96.952)
[2021-05-01 09:41:22 train_lshot.py:257] INFO Epoch: [50][60/150] Time 0.284 (0.393) Data 0.000 (0.092) Loss 0.3237 (0.4320) Prec@1 92.969 (88.505) Prec@5 98.828 (97.048)
[2021-05-01 09:41:25 train_lshot.py:257] INFO Epoch: [50][70/150] Time 0.290 (0.377) Data 0.001 (0.079) Loss 0.4910 (0.4325) Prec@1 88.281 (88.518) Prec@5 96.094 (97.073)
[2021-05-01 09:41:29 train_lshot.py:257] INFO Epoch: [50][80/150] Time 0.349 (0.386) Data 0.000 (0.070) Loss 0.4593 (0.4322) Prec@1 86.719 (88.479) Prec@5 96.484 (97.049)
[2021-05-01 09:41:32 train_lshot.py:257] INFO Epoch: [50][90/150] Time 0.277 (0.376) Data 0.000 (0.062) Loss 0.5285 (0.4349) Prec@1 87.109 (88.389) Prec@5 94.531 (96.999)
[2021-05-01 09:41:35 train_lshot.py:257] INFO Epoch: [50][100/150] Time 0.273 (0.366) Data 0.000 (0.056) Loss 0.4817 (0.4358) Prec@1 87.109 (88.374) Prec@5 97.656 (97.026)
[2021-05-01 09:41:38 train_lshot.py:257] INFO Epoch: [50][110/150] Time 0.278 (0.358) Data 0.000 (0.051) Loss 0.5426 (0.4388) Prec@1 84.375 (88.260) Prec@5 96.875 (97.037)
[2021-05-01 09:41:40 train_lshot.py:257] INFO Epoch: [50][120/150] Time 0.285 (0.352) Data 0.000 (0.047) Loss 0.4994 (0.4339) Prec@1 87.500 (88.414) Prec@5 96.094 (97.091)
[2021-05-01 09:41:43 train_lshot.py:257] INFO Epoch: [50][130/150] Time 0.292 (0.347) Data 0.000 (0.043) Loss 0.4629 (0.4351) Prec@1 85.938 (88.314) Prec@5 97.266 (97.120)
[2021-05-01 09:41:46 train_lshot.py:257] INFO Epoch: [50][140/150] Time 0.283 (0.343) Data 0.000 (0.040) Loss 0.4433 (0.4350) Prec@1 85.938 (88.251) Prec@5 97.266 (97.127)
[2021-05-01 09:41:54 train_lshot.py:257] INFO Epoch: [51][0/150] Time 4.428 (4.428) Data 3.992 (3.992) Loss 0.3120 (0.3120) Prec@1 92.578 (92.578) Prec@5 98.047 (98.047)
[2021-05-01 09:42:00 train_lshot.py:257] INFO Epoch: [51][10/150] Time 0.288 (0.966) Data 0.000 (0.633) Loss 0.4006 (0.3969) Prec@1 85.156 (88.956) Prec@5 98.438 (97.656)
[2021-05-01 09:42:03 train_lshot.py:257] INFO Epoch: [51][20/150] Time 0.281 (0.644) Data 0.000 (0.332) Loss 0.3404 (0.4064) Prec@1 91.016 (88.690) Prec@5 97.656 (97.340)
[2021-05-01 09:42:06 train_lshot.py:257] INFO Epoch: [51][30/150] Time 0.281 (0.527) Data 0.000 (0.225) Loss 0.3460 (0.4050) Prec@1 89.453 (88.558) Prec@5 98.047 (97.392)
[2021-05-01 09:42:08 train_lshot.py:257] INFO Epoch: [51][40/150] Time 0.284 (0.467) Data 0.000 (0.170) Loss 0.3493 (0.4145) Prec@1 90.234 (88.348) Prec@5 97.656 (97.266)
[2021-05-01 09:42:11 train_lshot.py:257] INFO Epoch: [51][50/150] Time 0.281 (0.431) Data 0.000 (0.137) Loss 0.4383 (0.4125) Prec@1 87.109 (88.511) Prec@5 97.656 (97.304)
[2021-05-01 09:42:14 train_lshot.py:257] INFO Epoch: [51][60/150] Time 0.282 (0.406) Data 0.000 (0.115) Loss 0.4222 (0.4170) Prec@1 89.062 (88.569) Prec@5 98.438 (97.202)
[2021-05-01 09:42:17 train_lshot.py:257] INFO Epoch: [51][70/150] Time 0.286 (0.389) Data 0.003 (0.099) Loss 0.4921 (0.4154) Prec@1 86.328 (88.661) Prec@5 96.094 (97.249)
[2021-05-01 09:42:20 train_lshot.py:257] INFO Epoch: [51][80/150] Time 0.284 (0.376) Data 0.000 (0.086) Loss 0.4104 (0.4187) Prec@1 89.844 (88.643) Prec@5 97.656 (97.174)
[2021-05-01 09:42:22 train_lshot.py:257] INFO Epoch: [51][90/150] Time 0.280 (0.366) Data 0.000 (0.077) Loss 0.3789 (0.4185) Prec@1 91.016 (88.676) Prec@5 96.484 (97.214)
[2021-05-01 09:42:26 train_lshot.py:257] INFO Epoch: [51][100/150] Time 0.289 (0.364) Data 0.000 (0.069) Loss 0.5669 (0.4207) Prec@1 83.984 (88.595) Prec@5 93.750 (97.177)
[2021-05-01 09:42:29 train_lshot.py:257] INFO Epoch: [51][110/150] Time 0.279 (0.357) Data 0.000 (0.063) Loss 0.3678 (0.4198) Prec@1 91.406 (88.654) Prec@5 98.438 (97.181)
[2021-05-01 09:42:32 train_lshot.py:257] INFO Epoch: [51][120/150] Time 0.287 (0.351) Data 0.000 (0.058) Loss 0.4431 (0.4195) Prec@1 87.500 (88.633) Prec@5 97.656 (97.217)
[2021-05-01 09:42:34 train_lshot.py:257] INFO Epoch: [51][130/150] Time 0.280 (0.345) Data 0.000 (0.054) Loss 0.4091 (0.4219) Prec@1 89.844 (88.606) Prec@5 97.656 (97.170)
[2021-05-01 09:42:37 train_lshot.py:257] INFO Epoch: [51][140/150] Time 0.286 (0.341) Data 0.000 (0.050) Loss 0.4765 (0.4231) Prec@1 87.891 (88.561) Prec@5 95.703 (97.155)
[2021-05-01 09:43:08 train_lshot.py:119] INFO Meta Val 51: 0.6187466788291931
[2021-05-01 09:43:15 train_lshot.py:257] INFO Epoch: [52][0/150] Time 6.042 (6.042) Data 5.557 (5.557) Loss 0.3922 (0.3922) Prec@1 89.453 (89.453) Prec@5 98.047 (98.047)
[2021-05-01 09:43:19 train_lshot.py:257] INFO Epoch: [52][10/150] Time 0.291 (0.877) Data 0.000 (0.565) Loss 0.4293 (0.4335) Prec@1 88.672 (87.784) Prec@5 96.484 (97.372)
[2021-05-01 09:43:21 train_lshot.py:257] INFO Epoch: [52][20/150] Time 0.285 (0.593) Data 0.001 (0.296) Loss 0.3689 (0.4346) Prec@1 90.625 (88.188) Prec@5 97.656 (97.173)
[2021-05-01 09:43:24 train_lshot.py:257] INFO Epoch: [52][30/150] Time 0.275 (0.492) Data 0.000 (0.201) Loss 0.4709 (0.4279) Prec@1 89.844 (88.558) Prec@5 97.656 (97.152)
[2021-05-01 09:43:27 train_lshot.py:257] INFO Epoch: [52][40/150] Time 0.279 (0.444) Data 0.000 (0.152) Loss 0.4124 (0.4200) Prec@1 90.234 (88.777) Prec@5 97.266 (97.228)
[2021-05-01 09:43:30 train_lshot.py:257] INFO Epoch: [52][50/150] Time 0.281 (0.412) Data 0.000 (0.122) Loss 0.3880 (0.4234) Prec@1 88.672 (88.588) Prec@5 97.656 (97.212)
[2021-05-01 09:43:33 train_lshot.py:257] INFO Epoch: [52][60/150] Time 0.279 (0.391) Data 0.000 (0.102) Loss 0.4673 (0.4213) Prec@1 86.719 (88.697) Prec@5 98.047 (97.227)
[2021-05-01 09:43:36 train_lshot.py:257] INFO Epoch: [52][70/150] Time 0.291 (0.375) Data 0.001 (0.088) Loss 0.5014 (0.4226) Prec@1 84.375 (88.639) Prec@5 97.266 (97.249)
[2021-05-01 09:43:38 train_lshot.py:257] INFO Epoch: [52][80/150] Time 0.278 (0.363) Data 0.000 (0.077) Loss 0.4714 (0.4251) Prec@1 87.109 (88.551) Prec@5 96.094 (97.208)
[2021-05-01 09:43:41 train_lshot.py:257] INFO Epoch: [52][90/150] Time 0.283 (0.354) Data 0.000 (0.069) Loss 0.4125 (0.4242) Prec@1 89.453 (88.590) Prec@5 96.484 (97.223)
[2021-05-01 09:43:44 train_lshot.py:257] INFO Epoch: [52][100/150] Time 0.284 (0.347) Data 0.000 (0.062) Loss 0.5591 (0.4263) Prec@1 84.375 (88.506) Prec@5 95.312 (97.188)
[2021-05-01 09:43:47 train_lshot.py:257] INFO Epoch: [52][110/150] Time 0.278 (0.341) Data 0.000 (0.056) Loss 0.3862 (0.4259) Prec@1 87.891 (88.482) Prec@5 98.828 (97.213)
[2021-05-01 09:43:50 train_lshot.py:257] INFO Epoch: [52][120/150] Time 0.282 (0.336) Data 0.001 (0.052) Loss 0.5079 (0.4245) Prec@1 86.719 (88.517) Prec@5 95.703 (97.220)
[2021-05-01 09:43:52 train_lshot.py:257] INFO Epoch: [52][130/150] Time 0.286 (0.333) Data 0.000 (0.048) Loss 0.4152 (0.4266) Prec@1 89.453 (88.451) Prec@5 96.875 (97.215)
[2021-05-01 09:43:55 train_lshot.py:257] INFO Epoch: [52][140/150] Time 0.382 (0.330) Data 0.001 (0.044) Loss 0.4711 (0.4273) Prec@1 87.109 (88.406) Prec@5 97.266 (97.191)
[2021-05-01 09:44:04 train_lshot.py:257] INFO Epoch: [53][0/150] Time 4.858 (4.858) Data 4.431 (4.431) Loss 0.4060 (0.4060) Prec@1 89.062 (89.062) Prec@5 98.047 (98.047)
[2021-05-01 09:44:09 train_lshot.py:257] INFO Epoch: [53][10/150] Time 0.281 (0.958) Data 0.000 (0.616) Loss 0.4499 (0.4044) Prec@1 88.281 (89.489) Prec@5 96.875 (97.301)
[2021-05-01 09:44:12 train_lshot.py:257] INFO Epoch: [53][20/150] Time 0.291 (0.636) Data 0.000 (0.323) Loss 0.3675 (0.4028) Prec@1 89.453 (89.156) Prec@5 98.438 (97.173)
[2021-05-01 09:44:15 train_lshot.py:257] INFO Epoch: [53][30/150] Time 0.281 (0.527) Data 0.000 (0.219) Loss 0.3440 (0.3971) Prec@1 88.281 (89.214) Prec@5 97.656 (97.253)
[2021-05-01 09:44:18 train_lshot.py:257] INFO Epoch: [53][40/150] Time 0.288 (0.467) Data 0.000 (0.166) Loss 0.4273 (0.4029) Prec@1 89.062 (89.186) Prec@5 94.922 (97.218)
[2021-05-01 09:44:21 train_lshot.py:257] INFO Epoch: [53][50/150] Time 0.284 (0.431) Data 0.000 (0.133) Loss 0.3684 (0.3991) Prec@1 89.844 (89.269) Prec@5 98.047 (97.327)
[2021-05-01 09:44:23 train_lshot.py:257] INFO Epoch: [53][60/150] Time 0.287 (0.406) Data 0.000 (0.111) Loss 0.4673 (0.4000) Prec@1 86.719 (89.229) Prec@5 96.875 (97.368)
[2021-05-01 09:44:26 train_lshot.py:257] INFO Epoch: [53][70/150] Time 0.286 (0.389) Data 0.001 (0.096) Loss 0.4300 (0.4027) Prec@1 89.844 (89.129) Prec@5 97.266 (97.370)
[2021-05-01 09:44:29 train_lshot.py:257] INFO Epoch: [53][80/150] Time 0.285 (0.376) Data 0.000 (0.084) Loss 0.4636 (0.4048) Prec@1 88.281 (89.101) Prec@5 95.703 (97.328)
[2021-05-01 09:44:32 train_lshot.py:257] INFO Epoch: [53][90/150] Time 0.287 (0.366) Data 0.000 (0.075) Loss 0.4776 (0.4057) Prec@1 86.719 (89.058) Prec@5 97.266 (97.356)
[2021-05-01 09:44:36 train_lshot.py:257] INFO Epoch: [53][100/150] Time 0.549 (0.368) Data 0.000 (0.067) Loss 0.4256 (0.4083) Prec@1 88.672 (88.985) Prec@5 98.047 (97.382)
[2021-05-01 09:44:39 train_lshot.py:257] INFO Epoch: [53][110/150] Time 0.278 (0.363) Data 0.000 (0.061) Loss 0.3878 (0.4068) Prec@1 89.062 (89.062) Prec@5 96.094 (97.340)
[2021-05-01 09:44:42 train_lshot.py:257] INFO Epoch: [53][120/150] Time 0.272 (0.356) Data 0.000 (0.056) Loss 0.4618 (0.4062) Prec@1 87.500 (89.114) Prec@5 96.484 (97.372)
[2021-05-01 09:44:46 train_lshot.py:257] INFO Epoch: [53][130/150] Time 0.351 (0.357) Data 0.000 (0.052) Loss 0.4837 (0.4059) Prec@1 85.938 (89.128) Prec@5 97.266 (97.349)
[2021-05-01 09:44:48 train_lshot.py:257] INFO Epoch: [53][140/150] Time 0.276 (0.353) Data 0.000 (0.048) Loss 0.3721 (0.4055) Prec@1 90.234 (89.151) Prec@5 98.047 (97.354)
[2021-05-01 09:44:57 train_lshot.py:257] INFO Epoch: [54][0/150] Time 5.529 (5.529) Data 5.094 (5.094) Loss 0.5003 (0.5003) Prec@1 85.938 (85.938) Prec@5 96.875 (96.875)
[2021-05-01 09:45:01 train_lshot.py:257] INFO Epoch: [54][10/150] Time 0.408 (0.850) Data 0.006 (0.484) Loss 0.4048 (0.4067) Prec@1 89.453 (88.920) Prec@5 96.484 (97.301)
[2021-05-01 09:45:04 train_lshot.py:257] INFO Epoch: [54][20/150] Time 0.289 (0.585) Data 0.000 (0.254) Loss 0.4185 (0.4060) Prec@1 87.500 (88.765) Prec@5 98.438 (97.489)
[2021-05-01 09:45:07 train_lshot.py:257] INFO Epoch: [54][30/150] Time 0.278 (0.488) Data 0.000 (0.172) Loss 0.3028 (0.4016) Prec@1 91.797 (88.899) Prec@5 98.828 (97.543)
[2021-05-01 09:45:09 train_lshot.py:257] INFO Epoch: [54][40/150] Time 0.276 (0.436) Data 0.000 (0.130) Loss 0.3075 (0.3988) Prec@1 93.750 (89.205) Prec@5 98.438 (97.485)
[2021-05-01 09:45:12 train_lshot.py:257] INFO Epoch: [54][50/150] Time 0.275 (0.406) Data 0.000 (0.105) Loss 0.4292 (0.3979) Prec@1 88.672 (89.193) Prec@5 97.656 (97.541)
[2021-05-01 09:45:15 train_lshot.py:257] INFO Epoch: [54][60/150] Time 0.274 (0.385) Data 0.000 (0.088) Loss 0.3970 (0.3999) Prec@1 88.672 (89.152) Prec@5 96.875 (97.522)
[2021-05-01 09:45:18 train_lshot.py:257] INFO Epoch: [54][70/150] Time 0.283 (0.371) Data 0.001 (0.075) Loss 0.4758 (0.4035) Prec@1 87.500 (89.079) Prec@5 96.094 (97.447)
[2021-05-01 09:45:21 train_lshot.py:257] INFO Epoch: [54][80/150] Time 0.284 (0.360) Data 0.000 (0.066) Loss 0.3211 (0.4047) Prec@1 91.016 (88.985) Prec@5 98.438 (97.430)
[2021-05-01 09:45:23 train_lshot.py:257] INFO Epoch: [54][90/150] Time 0.287 (0.352) Data 0.000 (0.059) Loss 0.4117 (0.4031) Prec@1 87.891 (89.024) Prec@5 98.438 (97.476)
[2021-05-01 09:45:27 train_lshot.py:257] INFO Epoch: [54][100/150] Time 0.295 (0.351) Data 0.000 (0.053) Loss 0.2617 (0.4019) Prec@1 93.359 (89.066) Prec@5 99.609 (97.490)
[2021-05-01 09:45:30 train_lshot.py:257] INFO Epoch: [54][110/150] Time 0.283 (0.345) Data 0.000 (0.048) Loss 0.3830 (0.4018) Prec@1 89.453 (89.087) Prec@5 97.266 (97.477)
[2021-05-01 09:45:33 train_lshot.py:257] INFO Epoch: [54][120/150] Time 0.294 (0.340) Data 0.000 (0.044) Loss 0.3869 (0.4022) Prec@1 89.453 (89.130) Prec@5 98.047 (97.479)
[2021-05-01 09:45:35 train_lshot.py:257] INFO Epoch: [54][130/150] Time 0.312 (0.335) Data 0.000 (0.041) Loss 0.2807 (0.3999) Prec@1 92.578 (89.185) Prec@5 98.438 (97.528)
[2021-05-01 09:45:38 train_lshot.py:257] INFO Epoch: [54][140/150] Time 0.293 (0.332) Data 0.000 (0.038) Loss 0.4151 (0.4005) Prec@1 87.500 (89.132) Prec@5 97.656 (97.498)
[2021-05-01 09:45:48 train_lshot.py:257] INFO Epoch: [55][0/150] Time 6.821 (6.821) Data 6.397 (6.397) Loss 0.4299 (0.4299) Prec@1 87.500 (87.500) Prec@5 98.047 (98.047)
[2021-05-01 09:45:52 train_lshot.py:257] INFO Epoch: [55][10/150] Time 0.284 (0.929) Data 0.001 (0.582) Loss 0.3807 (0.4048) Prec@1 88.281 (89.098) Prec@5 97.656 (97.550)
[2021-05-01 09:45:54 train_lshot.py:257] INFO Epoch: [55][20/150] Time 0.273 (0.622) Data 0.000 (0.305) Loss 0.3990 (0.3951) Prec@1 89.453 (89.528) Prec@5 98.047 (97.619)
[2021-05-01 09:45:57 train_lshot.py:257] INFO Epoch: [55][30/150] Time 0.275 (0.513) Data 0.000 (0.207) Loss 0.3835 (0.3945) Prec@1 87.891 (89.478) Prec@5 98.438 (97.568)
[2021-05-01 09:46:00 train_lshot.py:257] INFO Epoch: [55][40/150] Time 0.281 (0.456) Data 0.001 (0.156) Loss 0.5391 (0.4028) Prec@1 83.984 (89.186) Prec@5 96.484 (97.370)
[2021-05-01 09:46:03 train_lshot.py:257] INFO Epoch: [55][50/150] Time 0.275 (0.422) Data 0.000 (0.126) Loss 0.3933 (0.4038) Prec@1 89.062 (89.208) Prec@5 96.875 (97.327)
[2021-05-01 09:46:06 train_lshot.py:257] INFO Epoch: [55][60/150] Time 0.280 (0.400) Data 0.000 (0.105) Loss 0.3352 (0.4038) Prec@1 90.625 (89.139) Prec@5 98.047 (97.355)
[2021-05-01 09:46:09 train_lshot.py:257] INFO Epoch: [55][70/150] Time 0.299 (0.383) Data 0.001 (0.091) Loss 0.4179 (0.4089) Prec@1 90.234 (89.018) Prec@5 97.266 (97.299)
[2021-05-01 09:46:11 train_lshot.py:257] INFO Epoch: [55][80/150] Time 0.285 (0.371) Data 0.000 (0.079) Loss 0.5018 (0.4095) Prec@1 86.719 (88.932) Prec@5 96.875 (97.280)
[2021-05-01 09:46:14 train_lshot.py:257] INFO Epoch: [55][90/150] Time 0.287 (0.361) Data 0.000 (0.071) Loss 0.4211 (0.4091) Prec@1 90.234 (88.951) Prec@5 97.656 (97.244)
[2021-05-01 09:46:18 train_lshot.py:257] INFO Epoch: [55][100/150] Time 0.316 (0.361) Data 0.000 (0.064) Loss 0.3500 (0.4105) Prec@1 90.234 (88.912) Prec@5 98.828 (97.273)
[2021-05-01 09:46:21 train_lshot.py:257] INFO Epoch: [55][110/150] Time 0.274 (0.354) Data 0.000 (0.058) Loss 0.5291 (0.4101) Prec@1 85.938 (88.887) Prec@5 95.703 (97.283)
[2021-05-01 09:46:24 train_lshot.py:257] INFO Epoch: [55][120/150] Time 0.278 (0.348) Data 0.001 (0.053) Loss 0.3651 (0.4080) Prec@1 88.672 (88.924) Prec@5 98.828 (97.324)
[2021-05-01 09:46:26 train_lshot.py:257] INFO Epoch: [55][130/150] Time 0.279 (0.343) Data 0.000 (0.049) Loss 0.4311 (0.4069) Prec@1 88.672 (88.991) Prec@5 97.266 (97.340)
[2021-05-01 09:46:29 train_lshot.py:257] INFO Epoch: [55][140/150] Time 0.281 (0.339) Data 0.000 (0.046) Loss 0.3937 (0.4052) Prec@1 90.234 (89.046) Prec@5 97.656 (97.374)
[2021-05-01 09:47:00 train_lshot.py:119] INFO Meta Val 55: 0.6036266803145408
[2021-05-01 09:47:07 train_lshot.py:257] INFO Epoch: [56][0/150] Time 7.174 (7.174) Data 6.711 (6.711) Loss 0.3574 (0.3574) Prec@1 91.016 (91.016) Prec@5 97.266 (97.266)
[2021-05-01 09:47:11 train_lshot.py:257] INFO Epoch: [56][10/150] Time 0.279 (0.939) Data 0.000 (0.611) Loss 0.3820 (0.3796) Prec@1 88.672 (89.524) Prec@5 98.438 (97.621)
[2021-05-01 09:47:13 train_lshot.py:257] INFO Epoch: [56][20/150] Time 0.293 (0.626) Data 0.000 (0.320) Loss 0.4395 (0.3834) Prec@1 88.672 (89.862) Prec@5 96.875 (97.414)
[2021-05-01 09:47:16 train_lshot.py:257] INFO Epoch: [56][30/150] Time 0.273 (0.513) Data 0.000 (0.217) Loss 0.3694 (0.3789) Prec@1 89.453 (89.856) Prec@5 97.656 (97.455)
[2021-05-01 09:47:19 train_lshot.py:257] INFO Epoch: [56][40/150] Time 0.281 (0.457) Data 0.001 (0.164) Loss 0.3387 (0.3795) Prec@1 92.188 (89.825) Prec@5 97.656 (97.551)
[2021-05-01 09:47:22 train_lshot.py:257] INFO Epoch: [56][50/150] Time 0.283 (0.424) Data 0.000 (0.132) Loss 0.3801 (0.3869) Prec@1 88.672 (89.553) Prec@5 96.875 (97.396)
[2021-05-01 09:47:25 train_lshot.py:257] INFO Epoch: [56][60/150] Time 0.284 (0.400) Data 0.000 (0.110) Loss 0.3263 (0.3864) Prec@1 90.234 (89.524) Prec@5 97.656 (97.374)
[2021-05-01 09:47:28 train_lshot.py:257] INFO Epoch: [56][70/150] Time 0.275 (0.383) Data 0.001 (0.095) Loss 0.4581 (0.3904) Prec@1 86.328 (89.437) Prec@5 96.875 (97.376)
[2021-05-01 09:47:30 train_lshot.py:257] INFO Epoch: [56][80/150] Time 0.278 (0.371) Data 0.000 (0.083) Loss 0.5131 (0.3926) Prec@1 86.328 (89.434) Prec@5 95.703 (97.367)
[2021-05-01 09:47:33 train_lshot.py:257] INFO Epoch: [56][90/150] Time 0.283 (0.361) Data 0.001 (0.074) Loss 0.4120 (0.3930) Prec@1 89.453 (89.363) Prec@5 97.266 (97.386)
[2021-05-01 09:47:36 train_lshot.py:257] INFO Epoch: [56][100/150] Time 0.275 (0.353) Data 0.000 (0.067) Loss 0.3725 (0.3948) Prec@1 90.625 (89.345) Prec@5 98.047 (97.378)
[2021-05-01 09:47:39 train_lshot.py:257] INFO Epoch: [56][110/150] Time 0.278 (0.346) Data 0.000 (0.061) Loss 0.4364 (0.3941) Prec@1 87.109 (89.383) Prec@5 98.047 (97.403)
[2021-05-01 09:47:43 train_lshot.py:257] INFO Epoch: [56][120/150] Time 0.297 (0.350) Data 0.000 (0.056) Loss 0.3236 (0.3936) Prec@1 91.797 (89.434) Prec@5 98.828 (97.401)
[2021-05-01 09:47:46 train_lshot.py:257] INFO Epoch: [56][130/150] Time 0.274 (0.345) Data 0.000 (0.052) Loss 0.4382 (0.3930) Prec@1 88.672 (89.480) Prec@5 96.875 (97.409)
[2021-05-01 09:47:48 train_lshot.py:257] INFO Epoch: [56][140/150] Time 0.285 (0.341) Data 0.000 (0.048) Loss 0.3219 (0.3942) Prec@1 91.016 (89.461) Prec@5 98.047 (97.399)
[2021-05-01 09:47:57 train_lshot.py:257] INFO Epoch: [57][0/150] Time 5.217 (5.217) Data 4.765 (4.765) Loss 0.4070 (0.4070) Prec@1 87.891 (87.891) Prec@5 97.266 (97.266)
[2021-05-01 09:48:01 train_lshot.py:257] INFO Epoch: [57][10/150] Time 0.345 (0.828) Data 0.001 (0.435) Loss 0.3557 (0.3740) Prec@1 90.625 (89.879) Prec@5 98.828 (97.692)
[2021-05-01 09:48:04 train_lshot.py:257] INFO Epoch: [57][20/150] Time 0.281 (0.579) Data 0.000 (0.228) Loss 0.4139 (0.3810) Prec@1 91.016 (89.676) Prec@5 96.875 (97.563)
[2021-05-01 09:48:07 train_lshot.py:257] INFO Epoch: [57][30/150] Time 0.279 (0.486) Data 0.000 (0.155) Loss 0.4873 (0.3828) Prec@1 88.281 (89.579) Prec@5 95.703 (97.543)
[2021-05-01 09:48:10 train_lshot.py:257] INFO Epoch: [57][40/150] Time 0.282 (0.436) Data 0.000 (0.117) Loss 0.3709 (0.3868) Prec@1 90.625 (89.520) Prec@5 97.266 (97.466)
[2021-05-01 09:48:13 train_lshot.py:257] INFO Epoch: [57][50/150] Time 0.303 (0.407) Data 0.000 (0.094) Loss 0.3774 (0.3869) Prec@1 88.281 (89.576) Prec@5 97.266 (97.426)
[2021-05-01 09:48:15 train_lshot.py:257] INFO Epoch: [57][60/150] Time 0.279 (0.386) Data 0.000 (0.079) Loss 0.3113 (0.3897) Prec@1 92.578 (89.530) Prec@5 98.828 (97.451)
[2021-05-01 09:48:18 train_lshot.py:257] INFO Epoch: [57][70/150] Time 0.277 (0.371) Data 0.001 (0.068) Loss 0.3950 (0.3835) Prec@1 89.062 (89.734) Prec@5 97.266 (97.568)
[2021-05-01 09:48:21 train_lshot.py:257] INFO Epoch: [57][80/150] Time 0.293 (0.361) Data 0.000 (0.059) Loss 0.3383 (0.3855) Prec@1 89.062 (89.704) Prec@5 98.438 (97.502)
[2021-05-01 09:48:24 train_lshot.py:257] INFO Epoch: [57][90/150] Time 0.284 (0.352) Data 0.000 (0.053) Loss 0.4346 (0.3862) Prec@1 88.281 (89.689) Prec@5 98.047 (97.519)
[2021-05-01 09:48:27 train_lshot.py:257] INFO Epoch: [57][100/150] Time 0.284 (0.345) Data 0.000 (0.048) Loss 0.4006 (0.3856) Prec@1 91.406 (89.735) Prec@5 96.875 (97.502)
[2021-05-01 09:48:30 train_lshot.py:257] INFO Epoch: [57][110/150] Time 0.289 (0.340) Data 0.000 (0.043) Loss 0.3988 (0.3860) Prec@1 90.234 (89.703) Prec@5 97.656 (97.530)
[2021-05-01 09:48:33 train_lshot.py:257] INFO Epoch: [57][120/150] Time 0.278 (0.336) Data 0.000 (0.040) Loss 0.4283 (0.3876) Prec@1 89.844 (89.666) Prec@5 97.266 (97.534)
[2021-05-01 09:48:37 train_lshot.py:257] INFO Epoch: [57][130/150] Time 0.304 (0.341) Data 0.000 (0.037) Loss 0.3840 (0.3901) Prec@1 90.625 (89.596) Prec@5 96.875 (97.471)
[2021-05-01 09:48:39 train_lshot.py:257] INFO Epoch: [57][140/150] Time 0.277 (0.337) Data 0.000 (0.034) Loss 0.3524 (0.3889) Prec@1 90.625 (89.625) Prec@5 98.047 (97.496)
[2021-05-01 09:48:51 train_lshot.py:257] INFO Epoch: [58][0/150] Time 7.396 (7.396) Data 7.001 (7.001) Loss 0.3467 (0.3467) Prec@1 91.797 (91.797) Prec@5 98.047 (98.047)
[2021-05-01 09:48:54 train_lshot.py:257] INFO Epoch: [58][10/150] Time 0.285 (0.963) Data 0.000 (0.639) Loss 0.2961 (0.3692) Prec@1 92.188 (90.163) Prec@5 99.609 (97.550)
[2021-05-01 09:48:57 train_lshot.py:257] INFO Epoch: [58][20/150] Time 0.290 (0.644) Data 0.001 (0.335) Loss 0.4346 (0.3842) Prec@1 88.672 (89.769) Prec@5 96.875 (97.303)
[2021-05-01 09:49:00 train_lshot.py:257] INFO Epoch: [58][30/150] Time 0.280 (0.527) Data 0.000 (0.227) Loss 0.4411 (0.3793) Prec@1 90.625 (89.882) Prec@5 96.875 (97.442)
[2021-05-01 09:49:03 train_lshot.py:257] INFO Epoch: [58][40/150] Time 0.277 (0.467) Data 0.000 (0.172) Loss 0.3361 (0.3780) Prec@1 91.797 (89.958) Prec@5 96.875 (97.466)
[2021-05-01 09:49:05 train_lshot.py:257] INFO Epoch: [58][50/150] Time 0.282 (0.430) Data 0.000 (0.138) Loss 0.3633 (0.3844) Prec@1 89.453 (89.767) Prec@5 99.219 (97.511)
[2021-05-01 09:49:08 train_lshot.py:257] INFO Epoch: [58][60/150] Time 0.275 (0.406) Data 0.000 (0.115) Loss 0.4664 (0.3879) Prec@1 87.500 (89.677) Prec@5 97.656 (97.419)
[2021-05-01 09:49:11 train_lshot.py:257] INFO Epoch: [58][70/150] Time 0.278 (0.388) Data 0.001 (0.099) Loss 0.3929 (0.3860) Prec@1 89.062 (89.739) Prec@5 97.266 (97.420)
[2021-05-01 09:49:14 train_lshot.py:257] INFO Epoch: [58][80/150] Time 0.280 (0.374) Data 0.000 (0.087) Loss 0.3115 (0.3853) Prec@1 90.234 (89.723) Prec@5 98.828 (97.454)
[2021-05-01 09:49:18 train_lshot.py:257] INFO Epoch: [58][90/150] Time 0.577 (0.376) Data 0.000 (0.078) Loss 0.4489 (0.3811) Prec@1 87.109 (89.835) Prec@5 96.094 (97.476)
[2021-05-01 09:49:21 train_lshot.py:257] INFO Epoch: [58][100/150] Time 0.281 (0.370) Data 0.000 (0.070) Loss 0.4294 (0.3846) Prec@1 88.672 (89.720) Prec@5 97.266 (97.444)
[2021-05-01 09:49:24 train_lshot.py:257] INFO Epoch: [58][110/150] Time 0.272 (0.362) Data 0.000 (0.064) Loss 0.4445 (0.3825) Prec@1 87.109 (89.773) Prec@5 95.703 (97.456)
[2021-05-01 09:49:26 train_lshot.py:257] INFO Epoch: [58][120/150] Time 0.286 (0.355) Data 0.000 (0.058) Loss 0.4039 (0.3842) Prec@1 89.062 (89.740) Prec@5 97.656 (97.440)
[2021-05-01 09:49:29 train_lshot.py:257] INFO Epoch: [58][130/150] Time 0.285 (0.350) Data 0.000 (0.054) Loss 0.2676 (0.3843) Prec@1 94.922 (89.713) Prec@5 98.438 (97.468)
[2021-05-01 09:49:32 train_lshot.py:257] INFO Epoch: [58][140/150] Time 0.277 (0.345) Data 0.000 (0.050) Loss 0.4205 (0.3842) Prec@1 87.500 (89.678) Prec@5 98.438 (97.504)
[2021-05-01 09:49:41 train_lshot.py:257] INFO Epoch: [59][0/150] Time 5.973 (5.973) Data 5.584 (5.584) Loss 0.3492 (0.3492) Prec@1 91.016 (91.016) Prec@5 98.047 (98.047)
[2021-05-01 09:49:45 train_lshot.py:257] INFO Epoch: [59][10/150] Time 0.306 (0.907) Data 0.000 (0.535) Loss 0.4444 (0.3835) Prec@1 90.234 (90.092) Prec@5 96.484 (97.443)
[2021-05-01 09:49:48 train_lshot.py:257] INFO Epoch: [59][20/150] Time 0.275 (0.612) Data 0.000 (0.280) Loss 0.3687 (0.3922) Prec@1 90.625 (89.955) Prec@5 96.875 (97.117)
[2021-05-01 09:49:51 train_lshot.py:257] INFO Epoch: [59][30/150] Time 0.276 (0.508) Data 0.000 (0.190) Loss 0.3504 (0.3843) Prec@1 90.234 (90.083) Prec@5 98.438 (97.316)
[2021-05-01 09:49:54 train_lshot.py:257] INFO Epoch: [59][40/150] Time 0.286 (0.452) Data 0.001 (0.144) Loss 0.2975 (0.3870) Prec@1 92.578 (89.891) Prec@5 98.438 (97.313)
[2021-05-01 09:49:57 train_lshot.py:257] INFO Epoch: [59][50/150] Time 0.282 (0.419) Data 0.000 (0.116) Loss 0.4118 (0.3834) Prec@1 89.453 (89.943) Prec@5 96.875 (97.449)
[2021-05-01 09:49:59 train_lshot.py:257] INFO Epoch: [59][60/150] Time 0.277 (0.397) Data 0.000 (0.097) Loss 0.3282 (0.3812) Prec@1 91.406 (89.965) Prec@5 99.219 (97.541)
[2021-05-01 09:50:02 train_lshot.py:257] INFO Epoch: [59][70/150] Time 0.291 (0.381) Data 0.001 (0.083) Loss 0.4485 (0.3849) Prec@1 87.109 (89.811) Prec@5 96.094 (97.442)
[2021-05-01 09:50:05 train_lshot.py:257] INFO Epoch: [59][80/150] Time 0.281 (0.368) Data 0.000 (0.073) Loss 0.4902 (0.3859) Prec@1 87.500 (89.718) Prec@5 96.094 (97.478)
[2021-05-01 09:50:08 train_lshot.py:257] INFO Epoch: [59][90/150] Time 0.282 (0.359) Data 0.000 (0.065) Loss 0.4075 (0.3834) Prec@1 90.234 (89.719) Prec@5 96.094 (97.519)
[2021-05-01 09:50:11 train_lshot.py:257] INFO Epoch: [59][100/150] Time 0.274 (0.352) Data 0.000 (0.059) Loss 0.4378 (0.3869) Prec@1 87.891 (89.635) Prec@5 98.047 (97.494)
[2021-05-01 09:50:14 train_lshot.py:257] INFO Epoch: [59][110/150] Time 0.287 (0.348) Data 0.000 (0.053) Loss 0.3408 (0.3892) Prec@1 92.188 (89.566) Prec@5 97.266 (97.463)
[2021-05-01 09:50:17 train_lshot.py:257] INFO Epoch: [59][120/150] Time 0.292 (0.343) Data 0.000 (0.049) Loss 0.5243 (0.3910) Prec@1 85.938 (89.589) Prec@5 95.703 (97.440)
[2021-05-01 09:50:20 train_lshot.py:257] INFO Epoch: [59][130/150] Time 0.286 (0.338) Data 0.000 (0.045) Loss 0.2803 (0.3924) Prec@1 92.578 (89.557) Prec@5 98.438 (97.397)
[2021-05-01 09:50:22 train_lshot.py:257] INFO Epoch: [59][140/150] Time 0.289 (0.334) Data 0.000 (0.042) Loss 0.3016 (0.3912) Prec@1 91.406 (89.589) Prec@5 98.828 (97.399)
[2021-05-01 09:50:55 train_lshot.py:119] INFO Meta Val 59: 0.6135733461380005
[2021-05-01 09:50:59 train_lshot.py:257] INFO Epoch: [60][0/150] Time 4.366 (4.366) Data 3.930 (3.930) Loss 0.4152 (0.4152) Prec@1 87.891 (87.891) Prec@5 98.047 (98.047)
[2021-05-01 09:51:03 train_lshot.py:257] INFO Epoch: [60][10/150] Time 0.383 (0.756) Data 0.000 (0.358) Loss 0.3604 (0.3923) Prec@1 89.453 (89.027) Prec@5 98.828 (97.230)
[2021-05-01 09:51:06 train_lshot.py:257] INFO Epoch: [60][20/150] Time 0.283 (0.549) Data 0.001 (0.189) Loss 0.4023 (0.3708) Prec@1 91.016 (89.974) Prec@5 97.656 (97.619)
[2021-05-01 09:51:09 train_lshot.py:257] INFO Epoch: [60][30/150] Time 0.279 (0.464) Data 0.000 (0.128) Loss 0.3131 (0.3663) Prec@1 91.797 (90.184) Prec@5 98.047 (97.555)
[2021-05-01 09:51:12 train_lshot.py:257] INFO Epoch: [60][40/150] Time 0.283 (0.422) Data 0.000 (0.097) Loss 0.3068 (0.3664) Prec@1 91.797 (90.149) Prec@5 98.438 (97.618)
[2021-05-01 09:51:15 train_lshot.py:257] INFO Epoch: [60][50/150] Time 0.284 (0.394) Data 0.000 (0.078) Loss 0.3252 (0.3728) Prec@1 91.406 (90.097) Prec@5 97.656 (97.580)
[2021-05-01 09:51:18 train_lshot.py:257] INFO Epoch: [60][60/150] Time 0.289 (0.377) Data 0.000 (0.065) Loss 0.4189 (0.3768) Prec@1 87.500 (89.876) Prec@5 97.656 (97.605)
[2021-05-01 09:51:21 train_lshot.py:257] INFO Epoch: [60][70/150] Time 0.295 (0.364) Data 0.001 (0.056) Loss 0.3696 (0.3742) Prec@1 88.281 (90.014) Prec@5 97.656 (97.612)
[2021-05-01 09:51:23 train_lshot.py:257] INFO Epoch: [60][80/150] Time 0.273 (0.353) Data 0.000 (0.049) Loss 0.3991 (0.3743) Prec@1 88.672 (89.935) Prec@5 97.656 (97.637)
[2021-05-01 09:51:26 train_lshot.py:257] INFO Epoch: [60][90/150] Time 0.278 (0.345) Data 0.000 (0.044) Loss 0.2246 (0.3694) Prec@1 94.531 (90.058) Prec@5 98.828 (97.708)
[2021-05-01 09:51:29 train_lshot.py:257] INFO Epoch: [60][100/150] Time 0.278 (0.339) Data 0.000 (0.040) Loss 0.4064 (0.3703) Prec@1 89.453 (90.084) Prec@5 96.484 (97.645)
[2021-05-01 09:51:32 train_lshot.py:257] INFO Epoch: [60][110/150] Time 0.281 (0.334) Data 0.000 (0.036) Loss 0.3469 (0.3695) Prec@1 92.578 (90.139) Prec@5 97.656 (97.656)
[2021-05-01 09:51:36 train_lshot.py:257] INFO Epoch: [60][120/150] Time 0.306 (0.342) Data 0.000 (0.033) Loss 0.2823 (0.3679) Prec@1 93.750 (90.205) Prec@5 98.047 (97.640)
[2021-05-01 09:51:39 train_lshot.py:257] INFO Epoch: [60][130/150] Time 0.278 (0.337) Data 0.000 (0.031) Loss 0.3391 (0.3685) Prec@1 89.844 (90.148) Prec@5 98.047 (97.606)
[2021-05-01 09:51:42 train_lshot.py:257] INFO Epoch: [60][140/150] Time 0.281 (0.333) Data 0.000 (0.028) Loss 0.4574 (0.3672) Prec@1 86.719 (90.204) Prec@5 96.094 (97.623)
[2021-05-01 09:51:51 train_lshot.py:257] INFO Epoch: [61][0/150] Time 5.862 (5.862) Data 5.468 (5.468) Loss 0.4182 (0.4182) Prec@1 88.672 (88.672) Prec@5 97.266 (97.266)
[2021-05-01 09:51:55 train_lshot.py:257] INFO Epoch: [61][10/150] Time 0.304 (0.889) Data 0.005 (0.533) Loss 0.4675 (0.3884) Prec@1 86.719 (89.524) Prec@5 97.266 (97.763)
[2021-05-01 09:51:57 train_lshot.py:257] INFO Epoch: [61][20/150] Time 0.280 (0.604) Data 0.000 (0.280) Loss 0.4050 (0.3826) Prec@1 89.062 (89.546) Prec@5 97.656 (97.824)
[2021-05-01 09:52:00 train_lshot.py:257] INFO Epoch: [61][30/150] Time 0.276 (0.502) Data 0.000 (0.190) Loss 0.2246 (0.3766) Prec@1 95.703 (89.970) Prec@5 99.609 (97.568)
[2021-05-01 09:52:03 train_lshot.py:257] INFO Epoch: [61][40/150] Time 0.276 (0.448) Data 0.000 (0.143) Loss 0.4281 (0.3679) Prec@1 87.109 (90.025) Prec@5 97.656 (97.675)
[2021-05-01 09:52:06 train_lshot.py:257] INFO Epoch: [61][50/150] Time 0.292 (0.416) Data 0.000 (0.115) Loss 0.4827 (0.3745) Prec@1 85.938 (89.798) Prec@5 96.875 (97.633)
[2021-05-01 09:52:09 train_lshot.py:257] INFO Epoch: [61][60/150] Time 0.281 (0.394) Data 0.000 (0.097) Loss 0.3442 (0.3731) Prec@1 91.016 (89.901) Prec@5 97.266 (97.586)
[2021-05-01 09:52:12 train_lshot.py:257] INFO Epoch: [61][70/150] Time 0.281 (0.379) Data 0.001 (0.083) Loss 0.4405 (0.3761) Prec@1 87.891 (89.844) Prec@5 96.094 (97.491)
[2021-05-01 09:52:14 train_lshot.py:257] INFO Epoch: [61][80/150] Time 0.281 (0.367) Data 0.000 (0.073) Loss 0.2981 (0.3724) Prec@1 91.016 (89.993) Prec@5 98.438 (97.526)
[2021-05-01 09:52:17 train_lshot.py:257] INFO Epoch: [61][90/150] Time 0.293 (0.357) Data 0.000 (0.065) Loss 0.4031 (0.3770) Prec@1 89.844 (89.865) Prec@5 96.875 (97.459)
[2021-05-01 09:52:20 train_lshot.py:257] INFO Epoch: [61][100/150] Time 0.286 (0.350) Data 0.001 (0.058) Loss 0.3973 (0.3761) Prec@1 89.453 (89.960) Prec@5 98.047 (97.447)
[2021-05-01 09:52:23 train_lshot.py:257] INFO Epoch: [61][110/150] Time 0.282 (0.344) Data 0.000 (0.053) Loss 0.4334 (0.3762) Prec@1 89.453 (89.985) Prec@5 96.875 (97.484)
[2021-05-01 09:52:26 train_lshot.py:257] INFO Epoch: [61][120/150] Time 0.284 (0.339) Data 0.000 (0.049) Loss 0.3763 (0.3760) Prec@1 89.062 (89.989) Prec@5 98.047 (97.511)
[2021-05-01 09:52:29 train_lshot.py:257] INFO Epoch: [61][130/150] Time 0.289 (0.335) Data 0.000 (0.045) Loss 0.3478 (0.3775) Prec@1 90.234 (89.966) Prec@5 97.656 (97.483)
[2021-05-01 09:52:31 train_lshot.py:257] INFO Epoch: [61][140/150] Time 0.285 (0.332) Data 0.000 (0.042) Loss 0.4613 (0.3777) Prec@1 87.109 (89.968) Prec@5 96.094 (97.457)
[2021-05-01 09:52:42 train_lshot.py:257] INFO Epoch: [62][0/150] Time 6.973 (6.973) Data 6.579 (6.579) Loss 0.2954 (0.2954) Prec@1 91.406 (91.406) Prec@5 98.438 (98.438)
[2021-05-01 09:52:45 train_lshot.py:257] INFO Epoch: [62][10/150] Time 0.297 (0.940) Data 0.001 (0.600) Loss 0.3336 (0.3566) Prec@1 91.406 (91.087) Prec@5 98.438 (97.621)
[2021-05-01 09:52:48 train_lshot.py:257] INFO Epoch: [62][20/150] Time 0.282 (0.629) Data 0.000 (0.315) Loss 0.3020 (0.3603) Prec@1 92.188 (90.644) Prec@5 98.438 (97.582)
[2021-05-01 09:52:51 train_lshot.py:257] INFO Epoch: [62][30/150] Time 0.284 (0.519) Data 0.000 (0.213) Loss 0.3868 (0.3649) Prec@1 88.281 (90.386) Prec@5 97.656 (97.681)
[2021-05-01 09:52:54 train_lshot.py:257] INFO Epoch: [62][40/150] Time 0.273 (0.460) Data 0.000 (0.161) Loss 0.3464 (0.3630) Prec@1 91.406 (90.196) Prec@5 96.875 (97.713)
[2021-05-01 09:52:57 train_lshot.py:257] INFO Epoch: [62][50/150] Time 0.275 (0.425) Data 0.000 (0.130) Loss 0.3739 (0.3625) Prec@1 88.672 (90.150) Prec@5 98.828 (97.771)
[2021-05-01 09:52:59 train_lshot.py:257] INFO Epoch: [62][60/150] Time 0.289 (0.401) Data 0.001 (0.109) Loss 0.4238 (0.3656) Prec@1 87.500 (90.087) Prec@5 96.875 (97.733)
[2021-05-01 09:53:02 train_lshot.py:257] INFO Epoch: [62][70/150] Time 0.276 (0.385) Data 0.001 (0.093) Loss 0.3168 (0.3672) Prec@1 92.188 (90.080) Prec@5 98.828 (97.728)
[2021-05-01 09:53:05 train_lshot.py:257] INFO Epoch: [62][80/150] Time 0.279 (0.372) Data 0.000 (0.082) Loss 0.4116 (0.3659) Prec@1 87.891 (90.138) Prec@5 96.484 (97.753)
[2021-05-01 09:53:08 train_lshot.py:257] INFO Epoch: [62][90/150] Time 0.281 (0.362) Data 0.000 (0.073) Loss 0.3759 (0.3666) Prec@1 90.234 (90.144) Prec@5 98.047 (97.746)
[2021-05-01 09:53:11 train_lshot.py:257] INFO Epoch: [62][100/150] Time 0.281 (0.355) Data 0.000 (0.066) Loss 0.4209 (0.3699) Prec@1 89.453 (90.045) Prec@5 96.875 (97.633)
[2021-05-01 09:53:15 train_lshot.py:257] INFO Epoch: [62][110/150] Time 0.291 (0.361) Data 0.000 (0.060) Loss 0.3590 (0.3696) Prec@1 87.891 (90.058) Prec@5 97.266 (97.628)
[2021-05-01 09:53:18 train_lshot.py:257] INFO Epoch: [62][120/150] Time 0.277 (0.354) Data 0.000 (0.055) Loss 0.3094 (0.3703) Prec@1 93.359 (90.096) Prec@5 97.266 (97.643)
[2021-05-01 09:53:21 train_lshot.py:257] INFO Epoch: [62][130/150] Time 0.290 (0.349) Data 0.000 (0.051) Loss 0.3680 (0.3697) Prec@1 91.797 (90.151) Prec@5 97.266 (97.623)
[2021-05-01 09:53:23 train_lshot.py:257] INFO Epoch: [62][140/150] Time 0.281 (0.344) Data 0.000 (0.047) Loss 0.3840 (0.3704) Prec@1 87.109 (90.110) Prec@5 98.438 (97.615)
[2021-05-01 09:53:33 train_lshot.py:257] INFO Epoch: [63][0/150] Time 6.380 (6.380) Data 5.950 (5.950) Loss 0.3849 (0.3849) Prec@1 89.453 (89.453) Prec@5 96.484 (96.484)
[2021-05-01 09:53:37 train_lshot.py:257] INFO Epoch: [63][10/150] Time 0.285 (0.927) Data 0.000 (0.580) Loss 0.3482 (0.3219) Prec@1 90.625 (90.909) Prec@5 98.828 (98.295)
[2021-05-01 09:53:40 train_lshot.py:257] INFO Epoch: [63][20/150] Time 0.287 (0.628) Data 0.000 (0.304) Loss 0.4061 (0.3446) Prec@1 88.672 (90.402) Prec@5 96.875 (97.824)
[2021-05-01 09:53:43 train_lshot.py:257] INFO Epoch: [63][30/150] Time 0.279 (0.516) Data 0.000 (0.206) Loss 0.3162 (0.3543) Prec@1 92.578 (90.197) Prec@5 97.656 (97.770)
[2021-05-01 09:53:46 train_lshot.py:257] INFO Epoch: [63][40/150] Time 0.282 (0.458) Data 0.000 (0.156) Loss 0.4063 (0.3613) Prec@1 87.891 (90.120) Prec@5 98.047 (97.675)
[2021-05-01 09:53:49 train_lshot.py:257] INFO Epoch: [63][50/150] Time 0.282 (0.423) Data 0.000 (0.125) Loss 0.3615 (0.3603) Prec@1 89.062 (90.257) Prec@5 97.266 (97.725)
[2021-05-01 09:53:52 train_lshot.py:257] INFO Epoch: [63][60/150] Time 0.274 (0.400) Data 0.000 (0.105) Loss 0.4221 (0.3614) Prec@1 88.281 (90.209) Prec@5 97.266 (97.675)
[2021-05-01 09:53:54 train_lshot.py:257] INFO Epoch: [63][70/150] Time 0.284 (0.384) Data 0.001 (0.090) Loss 0.3609 (0.3671) Prec@1 88.281 (90.102) Prec@5 98.047 (97.574)
[2021-05-01 09:53:57 train_lshot.py:257] INFO Epoch: [63][80/150] Time 0.279 (0.371) Data 0.000 (0.079) Loss 0.3123 (0.3704) Prec@1 91.406 (90.066) Prec@5 98.828 (97.545)
[2021-05-01 09:54:00 train_lshot.py:257] INFO Epoch: [63][90/150] Time 0.286 (0.361) Data 0.000 (0.070) Loss 0.3633 (0.3702) Prec@1 91.016 (90.071) Prec@5 97.266 (97.536)
[2021-05-01 09:54:03 train_lshot.py:257] INFO Epoch: [63][100/150] Time 0.290 (0.354) Data 0.000 (0.063) Loss 0.3543 (0.3735) Prec@1 90.625 (89.983) Prec@5 97.266 (97.494)
[2021-05-01 09:54:06 train_lshot.py:257] INFO Epoch: [63][110/150] Time 0.278 (0.348) Data 0.000 (0.058) Loss 0.4591 (0.3721) Prec@1 87.500 (89.981) Prec@5 97.266 (97.540)
[2021-05-01 09:54:09 train_lshot.py:257] INFO Epoch: [63][120/150] Time 0.280 (0.342) Data 0.000 (0.053) Loss 0.3373 (0.3710) Prec@1 91.016 (90.018) Prec@5 98.828 (97.582)
[2021-05-01 09:54:11 train_lshot.py:257] INFO Epoch: [63][130/150] Time 0.282 (0.338) Data 0.000 (0.049) Loss 0.2820 (0.3711) Prec@1 91.406 (90.017) Prec@5 98.438 (97.588)
[2021-05-01 09:54:14 train_lshot.py:257] INFO Epoch: [63][140/150] Time 0.291 (0.334) Data 0.000 (0.046) Loss 0.3090 (0.3696) Prec@1 92.578 (90.040) Prec@5 99.609 (97.642)
[2021-05-01 09:54:45 train_lshot.py:119] INFO Meta Val 63: 0.6070133473873138
[2021-05-01 09:54:52 train_lshot.py:257] INFO Epoch: [64][0/150] Time 6.280 (6.280) Data 5.843 (5.843) Loss 0.3352 (0.3352) Prec@1 92.188 (92.188) Prec@5 97.656 (97.656)
[2021-05-01 09:54:55 train_lshot.py:257] INFO Epoch: [64][10/150] Time 0.380 (0.891) Data 0.001 (0.532) Loss 0.3250 (0.3518) Prec@1 91.016 (90.803) Prec@5 97.266 (97.585)
[2021-05-01 09:54:58 train_lshot.py:257] INFO Epoch: [64][20/150] Time 0.282 (0.603) Data 0.000 (0.279) Loss 0.3029 (0.3602) Prec@1 91.797 (90.588) Prec@5 98.828 (97.731)
[2021-05-01 09:55:01 train_lshot.py:257] INFO Epoch: [64][30/150] Time 0.290 (0.502) Data 0.000 (0.189) Loss 0.3029 (0.3613) Prec@1 91.797 (90.512) Prec@5 98.047 (97.719)
[2021-05-01 09:55:04 train_lshot.py:257] INFO Epoch: [64][40/150] Time 0.284 (0.451) Data 0.000 (0.143) Loss 0.4366 (0.3587) Prec@1 88.672 (90.511) Prec@5 98.047 (97.771)
[2021-05-01 09:55:07 train_lshot.py:257] INFO Epoch: [64][50/150] Time 0.280 (0.418) Data 0.000 (0.115) Loss 0.4673 (0.3630) Prec@1 88.281 (90.380) Prec@5 96.094 (97.687)
[2021-05-01 09:55:10 train_lshot.py:257] INFO Epoch: [64][60/150] Time 0.273 (0.396) Data 0.000 (0.096) Loss 0.3791 (0.3614) Prec@1 91.016 (90.439) Prec@5 96.484 (97.637)
[2021-05-01 09:55:13 train_lshot.py:257] INFO Epoch: [64][70/150] Time 0.291 (0.380) Data 0.001 (0.083) Loss 0.4122 (0.3631) Prec@1 89.844 (90.449) Prec@5 96.094 (97.574)
[2021-05-01 09:55:15 train_lshot.py:257] INFO Epoch: [64][80/150] Time 0.277 (0.368) Data 0.000 (0.073) Loss 0.2886 (0.3631) Prec@1 92.969 (90.394) Prec@5 98.828 (97.594)
[2021-05-01 09:55:18 train_lshot.py:257] INFO Epoch: [64][90/150] Time 0.277 (0.358) Data 0.000 (0.065) Loss 0.3866 (0.3573) Prec@1 90.234 (90.513) Prec@5 97.656 (97.682)
[2021-05-01 09:55:21 train_lshot.py:257] INFO Epoch: [64][100/150] Time 0.280 (0.351) Data 0.000 (0.058) Loss 0.3508 (0.3585) Prec@1 90.234 (90.470) Prec@5 98.438 (97.683)
[2021-05-01 09:55:25 train_lshot.py:257] INFO Epoch: [64][110/150] Time 0.320 (0.353) Data 0.000 (0.053) Loss 0.4869 (0.3578) Prec@1 87.109 (90.470) Prec@5 96.094 (97.723)
[2021-05-01 09:55:28 train_lshot.py:257] INFO Epoch: [64][120/150] Time 0.272 (0.348) Data 0.000 (0.049) Loss 0.4051 (0.3590) Prec@1 86.719 (90.422) Prec@5 98.047 (97.730)
[2021-05-01 09:55:31 train_lshot.py:257] INFO Epoch: [64][130/150] Time 0.279 (0.343) Data 0.000 (0.045) Loss 0.2929 (0.3608) Prec@1 94.141 (90.372) Prec@5 98.828 (97.698)
[2021-05-01 09:55:34 train_lshot.py:257] INFO Epoch: [64][140/150] Time 0.384 (0.344) Data 0.000 (0.042) Loss 0.2758 (0.3615) Prec@1 92.188 (90.342) Prec@5 98.438 (97.692)
[2021-05-01 09:55:44 train_lshot.py:257] INFO Epoch: [65][0/150] Time 7.029 (7.029) Data 6.613 (6.613) Loss 0.2883 (0.2883) Prec@1 92.969 (92.969) Prec@5 98.438 (98.438)
[2021-05-01 09:55:48 train_lshot.py:257] INFO Epoch: [65][10/150] Time 0.295 (0.952) Data 0.000 (0.602) Loss 0.4384 (0.3590) Prec@1 86.719 (90.199) Prec@5 98.438 (97.656)
[2021-05-01 09:55:51 train_lshot.py:257] INFO Epoch: [65][20/150] Time 0.276 (0.633) Data 0.000 (0.316) Loss 0.3637 (0.3545) Prec@1 90.625 (90.234) Prec@5 98.047 (97.786)
[2021-05-01 09:55:54 train_lshot.py:257] INFO Epoch: [65][30/150] Time 0.279 (0.522) Data 0.000 (0.214) Loss 0.3248 (0.3540) Prec@1 91.797 (90.360) Prec@5 98.047 (97.681)
[2021-05-01 09:55:56 train_lshot.py:257] INFO Epoch: [65][40/150] Time 0.300 (0.464) Data 0.000 (0.162) Loss 0.3464 (0.3521) Prec@1 89.453 (90.444) Prec@5 98.828 (97.732)
[2021-05-01 09:55:59 train_lshot.py:257] INFO Epoch: [65][50/150] Time 0.285 (0.428) Data 0.000 (0.130) Loss 0.3057 (0.3572) Prec@1 93.359 (90.380) Prec@5 98.438 (97.672)
[2021-05-01 09:56:02 train_lshot.py:257] INFO Epoch: [65][60/150] Time 0.280 (0.404) Data 0.000 (0.109) Loss 0.3433 (0.3549) Prec@1 89.062 (90.394) Prec@5 98.438 (97.765)
[2021-05-01 09:56:05 train_lshot.py:257] INFO Epoch: [65][70/150] Time 0.286 (0.387) Data 0.001 (0.094) Loss 0.4343 (0.3577) Prec@1 89.453 (90.322) Prec@5 97.266 (97.788)
[2021-05-01 09:56:08 train_lshot.py:257] INFO Epoch: [65][80/150] Time 0.293 (0.374) Data 0.000 (0.082) Loss 0.3279 (0.3554) Prec@1 91.406 (90.312) Prec@5 98.047 (97.820)
[2021-05-01 09:56:11 train_lshot.py:257] INFO Epoch: [65][90/150] Time 0.284 (0.365) Data 0.000 (0.073) Loss 0.3227 (0.3556) Prec@1 91.406 (90.346) Prec@5 98.438 (97.815)
[2021-05-01 09:56:13 train_lshot.py:257] INFO Epoch: [65][100/150] Time 0.283 (0.357) Data 0.000 (0.066) Loss 0.3637 (0.3560) Prec@1 89.062 (90.347) Prec@5 97.656 (97.823)
[2021-05-01 09:56:16 train_lshot.py:257] INFO Epoch: [65][110/150] Time 0.294 (0.350) Data 0.000 (0.060) Loss 0.3764 (0.3574) Prec@1 89.844 (90.336) Prec@5 96.875 (97.758)
[2021-05-01 09:56:20 train_lshot.py:257] INFO Epoch: [65][120/150] Time 0.323 (0.351) Data 0.000 (0.055) Loss 0.3991 (0.3585) Prec@1 87.500 (90.328) Prec@5 98.438 (97.747)
[2021-05-01 09:56:23 train_lshot.py:257] INFO Epoch: [65][130/150] Time 0.280 (0.347) Data 0.000 (0.051) Loss 0.3712 (0.3576) Prec@1 89.453 (90.351) Prec@5 96.484 (97.752)
[2021-05-01 09:56:26 train_lshot.py:257] INFO Epoch: [65][140/150] Time 0.286 (0.342) Data 0.000 (0.047) Loss 0.3587 (0.3574) Prec@1 89.453 (90.345) Prec@5 98.438 (97.773)
[2021-05-01 09:56:35 train_lshot.py:257] INFO Epoch: [66][0/150] Time 6.359 (6.359) Data 5.962 (5.962) Loss 0.3415 (0.3415) Prec@1 89.844 (89.844) Prec@5 98.047 (98.047)
[2021-05-01 09:56:39 train_lshot.py:257] INFO Epoch: [66][10/150] Time 0.364 (0.911) Data 0.005 (0.544) Loss 0.2836 (0.3390) Prec@1 91.406 (90.980) Prec@5 98.828 (97.905)
[2021-05-01 09:56:42 train_lshot.py:257] INFO Epoch: [66][20/150] Time 0.284 (0.614) Data 0.000 (0.285) Loss 0.2582 (0.3359) Prec@1 92.188 (91.053) Prec@5 98.438 (97.786)
[2021-05-01 09:56:45 train_lshot.py:257] INFO Epoch: [66][30/150] Time 0.282 (0.510) Data 0.000 (0.193) Loss 0.4136 (0.3507) Prec@1 88.281 (90.474) Prec@5 97.266 (97.744)
[2021-05-01 09:56:47 train_lshot.py:257] INFO Epoch: [66][40/150] Time 0.281 (0.454) Data 0.001 (0.146) Loss 0.4003 (0.3516) Prec@1 88.281 (90.434) Prec@5 96.875 (97.732)
[2021-05-01 09:56:50 train_lshot.py:257] INFO Epoch: [66][50/150] Time 0.281 (0.420) Data 0.000 (0.118) Loss 0.3544 (0.3496) Prec@1 90.234 (90.456) Prec@5 98.047 (97.809)
[2021-05-01 09:56:53 train_lshot.py:257] INFO Epoch: [66][60/150] Time 0.290 (0.398) Data 0.000 (0.098) Loss 0.3585 (0.3473) Prec@1 91.016 (90.561) Prec@5 98.047 (97.874)
[2021-05-01 09:56:56 train_lshot.py:257] INFO Epoch: [66][70/150] Time 0.290 (0.381) Data 0.001 (0.085) Loss 0.3400 (0.3497) Prec@1 91.406 (90.553) Prec@5 97.656 (97.854)
[2021-05-01 09:56:59 train_lshot.py:257] INFO Epoch: [66][80/150] Time 0.295 (0.370) Data 0.001 (0.074) Loss 0.2780 (0.3507) Prec@1 94.141 (90.504) Prec@5 98.047 (97.840)
[2021-05-01 09:57:02 train_lshot.py:257] INFO Epoch: [66][90/150] Time 0.290 (0.361) Data 0.000 (0.066) Loss 0.5318 (0.3532) Prec@1 86.719 (90.453) Prec@5 95.703 (97.789)
[2021-05-01 09:57:04 train_lshot.py:257] INFO Epoch: [66][100/150] Time 0.284 (0.353) Data 0.000 (0.060) Loss 0.3184 (0.3514) Prec@1 91.406 (90.505) Prec@5 98.047 (97.795)
[2021-05-01 09:57:08 train_lshot.py:257] INFO Epoch: [66][110/150] Time 0.291 (0.358) Data 0.000 (0.054) Loss 0.2984 (0.3526) Prec@1 93.359 (90.460) Prec@5 99.219 (97.779)
[2021-05-01 09:57:11 train_lshot.py:257] INFO Epoch: [66][120/150] Time 0.282 (0.352) Data 0.000 (0.050) Loss 0.3646 (0.3537) Prec@1 90.625 (90.464) Prec@5 98.438 (97.747)
[2021-05-01 09:57:14 train_lshot.py:257] INFO Epoch: [66][130/150] Time 0.282 (0.346) Data 0.000 (0.046) Loss 0.3155 (0.3558) Prec@1 91.406 (90.404) Prec@5 98.828 (97.740)
[2021-05-01 09:57:18 train_lshot.py:257] INFO Epoch: [66][140/150] Time 0.395 (0.351) Data 0.000 (0.043) Loss 0.3658 (0.3560) Prec@1 90.625 (90.392) Prec@5 97.656 (97.742)
[2021-05-01 09:57:28 train_lshot.py:257] INFO Epoch: [67][0/150] Time 6.215 (6.215) Data 5.810 (5.810) Loss 0.3045 (0.3045) Prec@1 91.797 (91.797) Prec@5 99.219 (99.219)
[2021-05-01 09:57:31 train_lshot.py:257] INFO Epoch: [67][10/150] Time 0.320 (0.892) Data 0.001 (0.532) Loss 0.3914 (0.3755) Prec@1 89.062 (90.199) Prec@5 98.047 (97.266)
[2021-05-01 09:57:34 train_lshot.py:257] INFO Epoch: [67][20/150] Time 0.281 (0.604) Data 0.000 (0.279) Loss 0.3189 (0.3575) Prec@1 90.234 (90.662) Prec@5 98.828 (97.452)
[2021-05-01 09:57:37 train_lshot.py:257] INFO Epoch: [67][30/150] Time 0.279 (0.502) Data 0.000 (0.189) Loss 0.2791 (0.3548) Prec@1 91.797 (90.663) Prec@5 98.438 (97.568)
[2021-05-01 09:57:40 train_lshot.py:257] INFO Epoch: [67][40/150] Time 0.284 (0.448) Data 0.001 (0.143) Loss 0.3993 (0.3578) Prec@1 89.844 (90.444) Prec@5 97.656 (97.570)
[2021-05-01 09:57:43 train_lshot.py:257] INFO Epoch: [67][50/150] Time 0.289 (0.416) Data 0.000 (0.115) Loss 0.2968 (0.3551) Prec@1 92.188 (90.502) Prec@5 97.656 (97.618)
[2021-05-01 09:57:45 train_lshot.py:257] INFO Epoch: [67][60/150] Time 0.278 (0.394) Data 0.000 (0.096) Loss 0.4079 (0.3626) Prec@1 89.453 (90.337) Prec@5 97.266 (97.496)
[2021-05-01 09:57:48 train_lshot.py:257] INFO Epoch: [67][70/150] Time 0.276 (0.378) Data 0.001 (0.083) Loss 0.2635 (0.3574) Prec@1 94.922 (90.509) Prec@5 98.438 (97.585)
[2021-05-01 09:57:51 train_lshot.py:257] INFO Epoch: [67][80/150] Time 0.293 (0.366) Data 0.000 (0.073) Loss 0.3690 (0.3554) Prec@1 90.234 (90.553) Prec@5 98.047 (97.603)
[2021-05-01 09:57:54 train_lshot.py:257] INFO Epoch: [67][90/150] Time 0.288 (0.357) Data 0.000 (0.065) Loss 0.3493 (0.3542) Prec@1 89.062 (90.526) Prec@5 99.219 (97.639)
[2021-05-01 09:57:58 train_lshot.py:257] INFO Epoch: [67][100/150] Time 0.317 (0.364) Data 0.000 (0.058) Loss 0.3507 (0.3525) Prec@1 92.969 (90.582) Prec@5 98.438 (97.664)
[2021-05-01 09:58:01 train_lshot.py:257] INFO Epoch: [67][110/150] Time 0.281 (0.357) Data 0.000 (0.053) Loss 0.3585 (0.3535) Prec@1 91.016 (90.562) Prec@5 97.656 (97.642)
[2021-05-01 09:58:04 train_lshot.py:257] INFO Epoch: [67][120/150] Time 0.276 (0.351) Data 0.000 (0.049) Loss 0.3685 (0.3539) Prec@1 89.844 (90.525) Prec@5 98.047 (97.647)
[2021-05-01 09:58:07 train_lshot.py:257] INFO Epoch: [67][130/150] Time 0.425 (0.348) Data 0.000 (0.045) Loss 0.4499 (0.3544) Prec@1 87.109 (90.491) Prec@5 98.047 (97.674)
[2021-05-01 09:58:10 train_lshot.py:257] INFO Epoch: [67][140/150] Time 0.279 (0.345) Data 0.000 (0.042) Loss 0.3226 (0.3545) Prec@1 90.625 (90.492) Prec@5 98.438 (97.684)
[2021-05-01 09:58:41 train_lshot.py:119] INFO Meta Val 67: 0.6041066787242889
[2021-05-01 09:58:47 train_lshot.py:257] INFO Epoch: [68][0/150] Time 5.711 (5.711) Data 5.164 (5.164) Loss 0.2882 (0.2882) Prec@1 91.016 (91.016) Prec@5 98.438 (98.438)
[2021-05-01 09:58:51 train_lshot.py:257] INFO Epoch: [68][10/150] Time 0.291 (0.890) Data 0.000 (0.500) Loss 0.2994 (0.3372) Prec@1 92.188 (90.838) Prec@5 97.656 (97.976)
[2021-05-01 09:58:54 train_lshot.py:257] INFO Epoch: [68][20/150] Time 0.281 (0.602) Data 0.000 (0.262) Loss 0.3236 (0.3351) Prec@1 92.578 (90.867) Prec@5 97.656 (98.047)
[2021-05-01 09:58:57 train_lshot.py:257] INFO Epoch: [68][30/150] Time 0.283 (0.499) Data 0.000 (0.178) Loss 0.2685 (0.3350) Prec@1 92.969 (90.978) Prec@5 99.219 (97.984)
[2021-05-01 09:59:00 train_lshot.py:257] INFO Epoch: [68][40/150] Time 0.285 (0.447) Data 0.000 (0.135) Loss 0.3780 (0.3451) Prec@1 88.672 (90.749) Prec@5 98.047 (97.856)
[2021-05-01 09:59:03 train_lshot.py:257] INFO Epoch: [68][50/150] Time 0.282 (0.416) Data 0.000 (0.108) Loss 0.3084 (0.3457) Prec@1 91.797 (90.740) Prec@5 98.438 (97.855)
[2021-05-01 09:59:05 train_lshot.py:257] INFO Epoch: [68][60/150] Time 0.282 (0.394) Data 0.000 (0.091) Loss 0.4010 (0.3413) Prec@1 88.281 (90.817) Prec@5 96.094 (97.893)
[2021-05-01 09:59:08 train_lshot.py:257] INFO Epoch: [68][70/150] Time 0.283 (0.379) Data 0.001 (0.078) Loss 0.3243 (0.3400) Prec@1 89.453 (90.884) Prec@5 99.609 (97.904)
[2021-05-01 09:59:11 train_lshot.py:257] INFO Epoch: [68][80/150] Time 0.274 (0.367) Data 0.000 (0.068) Loss 0.3537 (0.3382) Prec@1 89.844 (90.967) Prec@5 98.047 (97.936)
[2021-05-01 09:59:14 train_lshot.py:257] INFO Epoch: [68][90/150] Time 0.279 (0.357) Data 0.000 (0.061) Loss 0.4079 (0.3409) Prec@1 91.016 (90.947) Prec@5 96.484 (97.862)
[2021-05-01 09:59:17 train_lshot.py:257] INFO Epoch: [68][100/150] Time 0.281 (0.350) Data 0.000 (0.055) Loss 0.2914 (0.3401) Prec@1 91.406 (90.950) Prec@5 98.438 (97.838)
[2021-05-01 09:59:20 train_lshot.py:257] INFO Epoch: [68][110/150] Time 0.282 (0.344) Data 0.000 (0.050) Loss 0.3344 (0.3400) Prec@1 90.234 (90.945) Prec@5 98.438 (97.846)
[2021-05-01 09:59:22 train_lshot.py:257] INFO Epoch: [68][120/150] Time 0.291 (0.340) Data 0.000 (0.046) Loss 0.4210 (0.3387) Prec@1 89.844 (91.019) Prec@5 97.656 (97.853)
[2021-05-01 09:59:25 train_lshot.py:257] INFO Epoch: [68][130/150] Time 0.285 (0.335) Data 0.000 (0.042) Loss 0.3596 (0.3389) Prec@1 91.797 (91.013) Prec@5 98.047 (97.841)
[2021-05-01 09:59:28 train_lshot.py:257] INFO Epoch: [68][140/150] Time 0.299 (0.332) Data 0.000 (0.039) Loss 0.3559 (0.3397) Prec@1 91.406 (91.002) Prec@5 98.828 (97.834)
[2021-05-01 09:59:37 train_lshot.py:257] INFO Epoch: [69][0/150] Time 5.961 (5.961) Data 5.549 (5.549) Loss 0.3291 (0.3291) Prec@1 91.016 (91.016) Prec@5 97.656 (97.656)
[2021-05-01 09:59:42 train_lshot.py:257] INFO Epoch: [69][10/150] Time 0.293 (0.992) Data 0.000 (0.670) Loss 0.3858 (0.3355) Prec@1 91.797 (91.051) Prec@5 95.703 (97.443)
[2021-05-01 09:59:45 train_lshot.py:257] INFO Epoch: [69][20/150] Time 0.282 (0.653) Data 0.000 (0.351) Loss 0.3178 (0.3328) Prec@1 91.016 (91.034) Prec@5 98.828 (97.563)
[2021-05-01 09:59:48 train_lshot.py:257] INFO Epoch: [69][30/150] Time 0.285 (0.535) Data 0.001 (0.238) Loss 0.3247 (0.3342) Prec@1 89.844 (90.990) Prec@5 98.047 (97.681)
[2021-05-01 09:59:51 train_lshot.py:257] INFO Epoch: [69][40/150] Time 0.278 (0.473) Data 0.000 (0.180) Loss 0.3181 (0.3307) Prec@1 90.625 (91.187) Prec@5 97.656 (97.752)
[2021-05-01 09:59:54 train_lshot.py:257] INFO Epoch: [69][50/150] Time 0.281 (0.435) Data 0.000 (0.145) Loss 0.3960 (0.3320) Prec@1 88.672 (91.161) Prec@5 98.047 (97.825)
[2021-05-01 09:59:56 train_lshot.py:257] INFO Epoch: [69][60/150] Time 0.287 (0.409) Data 0.000 (0.121) Loss 0.3458 (0.3304) Prec@1 90.234 (91.253) Prec@5 97.656 (97.836)
[2021-05-01 09:59:59 train_lshot.py:257] INFO Epoch: [69][70/150] Time 0.327 (0.395) Data 0.001 (0.104) Loss 0.3268 (0.3296) Prec@1 91.406 (91.159) Prec@5 98.047 (97.920)
[2021-05-01 10:00:02 train_lshot.py:257] INFO Epoch: [69][80/150] Time 0.278 (0.381) Data 0.000 (0.091) Loss 0.3199 (0.3334) Prec@1 92.188 (91.083) Prec@5 98.438 (97.883)
[2021-05-01 10:00:06 train_lshot.py:257] INFO Epoch: [69][90/150] Time 0.320 (0.378) Data 0.000 (0.081) Loss 0.2751 (0.3325) Prec@1 92.578 (91.114) Prec@5 98.828 (97.922)
[2021-05-01 10:00:09 train_lshot.py:257] INFO Epoch: [69][100/150] Time 0.279 (0.369) Data 0.000 (0.073) Loss 0.3103 (0.3317) Prec@1 92.578 (91.120) Prec@5 99.609 (97.966)
[2021-05-01 10:00:11 train_lshot.py:257] INFO Epoch: [69][110/150] Time 0.279 (0.361) Data 0.000 (0.067) Loss 0.3475 (0.3312) Prec@1 91.797 (91.146) Prec@5 97.656 (97.955)
[2021-05-01 10:00:14 train_lshot.py:257] INFO Epoch: [69][120/150] Time 0.286 (0.355) Data 0.000 (0.061) Loss 0.3578 (0.3305) Prec@1 91.406 (91.174) Prec@5 97.266 (97.950)
[2021-05-01 10:00:18 train_lshot.py:257] INFO Epoch: [69][130/150] Time 0.296 (0.356) Data 0.000 (0.057) Loss 0.3397 (0.3301) Prec@1 90.234 (91.177) Prec@5 97.656 (97.945)
[2021-05-01 10:00:21 train_lshot.py:257] INFO Epoch: [69][140/150] Time 0.273 (0.351) Data 0.000 (0.053) Loss 0.4447 (0.3327) Prec@1 89.062 (91.129) Prec@5 96.875 (97.908)
[2021-05-01 10:00:30 train_lshot.py:257] INFO Epoch: [70][0/150] Time 5.232 (5.232) Data 4.832 (4.832) Loss 0.4258 (0.4258) Prec@1 87.891 (87.891) Prec@5 98.438 (98.438)
[2021-05-01 10:00:34 train_lshot.py:257] INFO Epoch: [70][10/150] Time 0.320 (0.904) Data 0.001 (0.558) Loss 0.3230 (0.3496) Prec@1 92.188 (90.696) Prec@5 97.656 (97.869)
[2021-05-01 10:00:37 train_lshot.py:257] INFO Epoch: [70][20/150] Time 0.285 (0.616) Data 0.000 (0.293) Loss 0.3463 (0.3431) Prec@1 89.844 (90.904) Prec@5 98.047 (97.861)
[2021-05-01 10:00:40 train_lshot.py:257] INFO Epoch: [70][30/150] Time 0.278 (0.508) Data 0.001 (0.198) Loss 0.4122 (0.3523) Prec@1 89.844 (90.549) Prec@5 96.875 (97.681)
[2021-05-01 10:00:43 train_lshot.py:257] INFO Epoch: [70][40/150] Time 0.286 (0.454) Data 0.001 (0.150) Loss 0.3348 (0.3410) Prec@1 90.625 (90.835) Prec@5 97.266 (97.771)
[2021-05-01 10:00:46 train_lshot.py:257] INFO Epoch: [70][50/150] Time 0.281 (0.421) Data 0.000 (0.121) Loss 0.3390 (0.3406) Prec@1 92.188 (90.893) Prec@5 98.047 (97.809)
[2021-05-01 10:00:49 train_lshot.py:257] INFO Epoch: [70][60/150] Time 0.276 (0.398) Data 0.000 (0.101) Loss 0.4057 (0.3437) Prec@1 88.672 (90.824) Prec@5 98.047 (97.778)
[2021-05-01 10:00:51 train_lshot.py:257] INFO Epoch: [70][70/150] Time 0.286 (0.382) Data 0.001 (0.087) Loss 0.3847 (0.3388) Prec@1 88.672 (90.977) Prec@5 96.875 (97.810)
[2021-05-01 10:00:54 train_lshot.py:257] INFO Epoch: [70][80/150] Time 0.288 (0.370) Data 0.000 (0.076) Loss 0.3042 (0.3367) Prec@1 90.234 (91.035) Prec@5 98.828 (97.791)
[2021-05-01 10:00:57 train_lshot.py:257] INFO Epoch: [70][90/150] Time 0.282 (0.360) Data 0.000 (0.068) Loss 0.3217 (0.3350) Prec@1 89.062 (91.059) Prec@5 98.438 (97.785)
[2021-05-01 10:01:00 train_lshot.py:257] INFO Epoch: [70][100/150] Time 0.276 (0.353) Data 0.000 (0.061) Loss 0.3508 (0.3364) Prec@1 89.453 (91.031) Prec@5 98.047 (97.761)
[2021-05-01 10:01:03 train_lshot.py:257] INFO Epoch: [70][110/150] Time 0.280 (0.349) Data 0.000 (0.056) Loss 0.4097 (0.3357) Prec@1 88.672 (91.090) Prec@5 95.703 (97.762)
[2021-05-01 10:01:06 train_lshot.py:257] INFO Epoch: [70][120/150] Time 0.399 (0.345) Data 0.000 (0.051) Loss 0.4366 (0.3353) Prec@1 87.109 (91.080) Prec@5 96.094 (97.779)
[2021-05-01 10:01:09 train_lshot.py:257] INFO Epoch: [70][130/150] Time 0.277 (0.342) Data 0.000 (0.047) Loss 0.3151 (0.3346) Prec@1 91.406 (91.096) Prec@5 97.656 (97.793)
[2021-05-01 10:01:12 train_lshot.py:257] INFO Epoch: [70][140/150] Time 0.273 (0.338) Data 0.000 (0.044) Loss 0.3409 (0.3342) Prec@1 92.188 (91.074) Prec@5 97.266 (97.839)
[2021-05-01 10:01:22 train_lshot.py:257] INFO Epoch: [71][0/150] Time 5.280 (5.280) Data 4.852 (4.852) Loss 0.3447 (0.3447) Prec@1 90.625 (90.625) Prec@5 97.266 (97.266)
[2021-05-01 10:01:26 train_lshot.py:257] INFO Epoch: [71][10/150] Time 0.286 (0.888) Data 0.000 (0.537) Loss 0.4192 (0.3330) Prec@1 90.234 (91.158) Prec@5 96.875 (97.869)
[2021-05-01 10:01:29 train_lshot.py:257] INFO Epoch: [71][20/150] Time 0.288 (0.600) Data 0.000 (0.282) Loss 0.2555 (0.3204) Prec@1 93.359 (91.462) Prec@5 99.609 (98.028)
[2021-05-01 10:01:32 train_lshot.py:257] INFO Epoch: [71][30/150] Time 0.299 (0.500) Data 0.000 (0.191) Loss 0.2557 (0.3237) Prec@1 92.969 (91.557) Prec@5 98.438 (97.946)
[2021-05-01 10:01:35 train_lshot.py:257] INFO Epoch: [71][40/150] Time 0.278 (0.447) Data 0.000 (0.144) Loss 0.3051 (0.3207) Prec@1 91.797 (91.644) Prec@5 98.828 (97.980)
[2021-05-01 10:01:38 train_lshot.py:257] INFO Epoch: [71][50/150] Time 0.287 (0.415) Data 0.000 (0.116) Loss 0.3144 (0.3208) Prec@1 91.016 (91.544) Prec@5 98.047 (98.001)
[2021-05-01 10:01:40 train_lshot.py:257] INFO Epoch: [71][60/150] Time 0.277 (0.393) Data 0.000 (0.097) Loss 0.3912 (0.3287) Prec@1 89.453 (91.329) Prec@5 98.047 (97.938)
[2021-05-01 10:01:43 train_lshot.py:257] INFO Epoch: [71][70/150] Time 0.284 (0.377) Data 0.001 (0.084) Loss 0.2974 (0.3293) Prec@1 92.188 (91.269) Prec@5 96.875 (97.882)
[2021-05-01 10:01:46 train_lshot.py:257] INFO Epoch: [71][80/150] Time 0.279 (0.366) Data 0.000 (0.073) Loss 0.3935 (0.3287) Prec@1 90.625 (91.310) Prec@5 96.094 (97.907)
[2021-05-01 10:01:49 train_lshot.py:257] INFO Epoch: [71][90/150] Time 0.303 (0.362) Data 0.000 (0.065) Loss 0.3454 (0.3322) Prec@1 88.281 (91.196) Prec@5 98.438 (97.879)
[2021-05-01 10:01:52 train_lshot.py:257] INFO Epoch: [71][100/150] Time 0.289 (0.354) Data 0.000 (0.059) Loss 0.3271 (0.3339) Prec@1 91.406 (91.151) Prec@5 97.656 (97.826)
[2021-05-01 10:01:55 train_lshot.py:257] INFO Epoch: [71][110/150] Time 0.277 (0.348) Data 0.000 (0.054) Loss 0.2685 (0.3338) Prec@1 94.141 (91.174) Prec@5 99.219 (97.836)
[2021-05-01 10:01:58 train_lshot.py:257] INFO Epoch: [71][120/150] Time 0.280 (0.343) Data 0.000 (0.049) Loss 0.3265 (0.3329) Prec@1 91.406 (91.225) Prec@5 98.047 (97.811)
[2021-05-01 10:02:01 train_lshot.py:257] INFO Epoch: [71][130/150] Time 0.392 (0.342) Data 0.000 (0.045) Loss 0.3466 (0.3340) Prec@1 89.844 (91.162) Prec@5 98.047 (97.802)
[2021-05-01 10:02:04 train_lshot.py:257] INFO Epoch: [71][140/150] Time 0.277 (0.339) Data 0.000 (0.042) Loss 0.3241 (0.3331) Prec@1 91.016 (91.204) Prec@5 97.656 (97.809)
[2021-05-01 10:02:35 train_lshot.py:119] INFO Meta Val 71: 0.6157333469390869
[2021-05-01 10:02:42 train_lshot.py:257] INFO Epoch: [72][0/150] Time 6.614 (6.614) Data 6.132 (6.132) Loss 0.4906 (0.4906) Prec@1 86.719 (86.719) Prec@5 96.875 (96.875)
[2021-05-01 10:02:45 train_lshot.py:257] INFO Epoch: [72][10/150] Time 0.283 (0.899) Data 0.001 (0.558) Loss 0.3136 (0.3623) Prec@1 91.406 (90.057) Prec@5 97.266 (97.550)
[2021-05-01 10:02:48 train_lshot.py:257] INFO Epoch: [72][20/150] Time 0.290 (0.608) Data 0.000 (0.292) Loss 0.3199 (0.3527) Prec@1 91.406 (90.625) Prec@5 97.656 (97.452)
[2021-05-01 10:02:51 train_lshot.py:257] INFO Epoch: [72][30/150] Time 0.278 (0.504) Data 0.000 (0.198) Loss 0.3788 (0.3466) Prec@1 89.844 (90.990) Prec@5 97.266 (97.429)
[2021-05-01 10:02:54 train_lshot.py:257] INFO Epoch: [72][40/150] Time 0.283 (0.453) Data 0.000 (0.150) Loss 0.3217 (0.3472) Prec@1 91.797 (90.958) Prec@5 97.266 (97.466)
[2021-05-01 10:02:57 train_lshot.py:257] INFO Epoch: [72][50/150] Time 0.276 (0.419) Data 0.000 (0.121) Loss 0.3446 (0.3427) Prec@1 91.797 (91.123) Prec@5 98.047 (97.603)
[2021-05-01 10:02:59 train_lshot.py:257] INFO Epoch: [72][60/150] Time 0.280 (0.396) Data 0.000 (0.101) Loss 0.3068 (0.3387) Prec@1 91.406 (91.176) Prec@5 98.828 (97.707)
[2021-05-01 10:03:02 train_lshot.py:257] INFO Epoch: [72][70/150] Time 0.280 (0.380) Data 0.001 (0.087) Loss 0.3304 (0.3365) Prec@1 91.016 (91.175) Prec@5 97.656 (97.788)
[2021-05-01 10:03:05 train_lshot.py:257] INFO Epoch: [72][80/150] Time 0.279 (0.368) Data 0.000 (0.076) Loss 0.3122 (0.3348) Prec@1 92.578 (91.209) Prec@5 97.266 (97.777)
[2021-05-01 10:03:08 train_lshot.py:257] INFO Epoch: [72][90/150] Time 0.287 (0.358) Data 0.000 (0.068) Loss 0.3541 (0.3353) Prec@1 90.625 (91.136) Prec@5 99.219 (97.798)
[2021-05-01 10:03:11 train_lshot.py:257] INFO Epoch: [72][100/150] Time 0.274 (0.350) Data 0.000 (0.061) Loss 0.3361 (0.3388) Prec@1 91.406 (90.927) Prec@5 97.656 (97.795)
[2021-05-01 10:03:13 train_lshot.py:257] INFO Epoch: [72][110/150] Time 0.280 (0.345) Data 0.000 (0.056) Loss 0.3729 (0.3381) Prec@1 89.844 (90.991) Prec@5 98.047 (97.801)
[2021-05-01 10:03:16 train_lshot.py:257] INFO Epoch: [72][120/150] Time 0.285 (0.340) Data 0.000 (0.051) Loss 0.3862 (0.3404) Prec@1 88.281 (90.932) Prec@5 98.047 (97.769)
[2021-05-01 10:03:21 train_lshot.py:257] INFO Epoch: [72][130/150] Time 0.289 (0.347) Data 0.000 (0.047) Loss 0.3124 (0.3395) Prec@1 91.406 (90.977) Prec@5 96.875 (97.761)
[2021-05-01 10:03:23 train_lshot.py:257] INFO Epoch: [72][140/150] Time 0.271 (0.342) Data 0.000 (0.044) Loss 0.2452 (0.3390) Prec@1 92.969 (90.982) Prec@5 98.438 (97.784)
[2021-05-01 10:03:33 train_lshot.py:257] INFO Epoch: [73][0/150] Time 6.631 (6.631) Data 6.167 (6.167) Loss 0.4004 (0.4004) Prec@1 89.453 (89.453) Prec@5 98.047 (98.047)
[2021-05-01 10:03:37 train_lshot.py:257] INFO Epoch: [73][10/150] Time 0.297 (0.926) Data 0.000 (0.561) Loss 0.2835 (0.3199) Prec@1 92.578 (91.939) Prec@5 98.438 (98.047)
[2021-05-01 10:03:39 train_lshot.py:257] INFO Epoch: [73][20/150] Time 0.283 (0.621) Data 0.000 (0.294) Loss 0.2572 (0.3145) Prec@1 92.969 (92.094) Prec@5 98.828 (98.084)
[2021-05-01 10:03:42 train_lshot.py:257] INFO Epoch: [73][30/150] Time 0.285 (0.514) Data 0.000 (0.199) Loss 0.3613 (0.3160) Prec@1 90.625 (91.872) Prec@5 97.266 (98.135)
[2021-05-01 10:03:45 train_lshot.py:257] INFO Epoch: [73][40/150] Time 0.285 (0.457) Data 0.000 (0.151) Loss 0.3439 (0.3258) Prec@1 91.406 (91.530) Prec@5 96.875 (97.894)
[2021-05-01 10:03:48 train_lshot.py:257] INFO Epoch: [73][50/150] Time 0.292 (0.423) Data 0.001 (0.121) Loss 0.2806 (0.3275) Prec@1 93.359 (91.399) Prec@5 98.438 (97.932)
[2021-05-01 10:03:51 train_lshot.py:257] INFO Epoch: [73][60/150] Time 0.281 (0.400) Data 0.000 (0.102) Loss 0.2412 (0.3257) Prec@1 95.312 (91.509) Prec@5 97.656 (97.912)
[2021-05-01 10:03:54 train_lshot.py:257] INFO Epoch: [73][70/150] Time 0.283 (0.383) Data 0.001 (0.087) Loss 0.3051 (0.3249) Prec@1 89.844 (91.544) Prec@5 99.219 (97.937)
[2021-05-01 10:03:56 train_lshot.py:257] INFO Epoch: [73][80/150] Time 0.279 (0.370) Data 0.000 (0.077) Loss 0.3191 (0.3246) Prec@1 91.016 (91.546) Prec@5 97.656 (97.912)
[2021-05-01 10:03:59 train_lshot.py:257] INFO Epoch: [73][90/150] Time 0.287 (0.362) Data 0.000 (0.068) Loss 0.4254 (0.3259) Prec@1 87.500 (91.496) Prec@5 95.312 (97.867)
[2021-05-01 10:04:02 train_lshot.py:257] INFO Epoch: [73][100/150] Time 0.287 (0.354) Data 0.000 (0.062) Loss 0.2953 (0.3274) Prec@1 91.797 (91.387) Prec@5 98.438 (97.838)
[2021-05-01 10:04:05 train_lshot.py:257] INFO Epoch: [73][110/150] Time 0.286 (0.348) Data 0.000 (0.056) Loss 0.3128 (0.3262) Prec@1 92.188 (91.431) Prec@5 98.438 (97.836)
[2021-05-01 10:04:08 train_lshot.py:257] INFO Epoch: [73][120/150] Time 0.301 (0.343) Data 0.000 (0.051) Loss 0.3946 (0.3276) Prec@1 89.062 (91.374) Prec@5 97.656 (97.850)
[2021-05-01 10:04:11 train_lshot.py:257] INFO Epoch: [73][130/150] Time 0.364 (0.341) Data 0.000 (0.047) Loss 0.2935 (0.3267) Prec@1 91.406 (91.400) Prec@5 97.266 (97.844)
[2021-05-01 10:04:14 train_lshot.py:257] INFO Epoch: [73][140/150] Time 0.280 (0.338) Data 0.000 (0.044) Loss 0.3412 (0.3270) Prec@1 91.797 (91.359) Prec@5 97.266 (97.847)
[2021-05-01 10:04:23 train_lshot.py:257] INFO Epoch: [74][0/150] Time 6.316 (6.316) Data 5.850 (5.850) Loss 0.4115 (0.4115) Prec@1 88.281 (88.281) Prec@5 96.484 (96.484)
[2021-05-01 10:04:27 train_lshot.py:257] INFO Epoch: [74][10/150] Time 0.370 (0.905) Data 0.000 (0.532) Loss 0.3058 (0.3401) Prec@1 93.359 (90.945) Prec@5 97.656 (97.443)
[2021-05-01 10:04:30 train_lshot.py:257] INFO Epoch: [74][20/150] Time 0.275 (0.614) Data 0.000 (0.279) Loss 0.3593 (0.3480) Prec@1 90.625 (90.904) Prec@5 98.047 (97.433)
[2021-05-01 10:04:33 train_lshot.py:257] INFO Epoch: [74][30/150] Time 0.277 (0.509) Data 0.000 (0.189) Loss 0.3591 (0.3422) Prec@1 89.062 (91.079) Prec@5 98.047 (97.593)
[2021-05-01 10:04:36 train_lshot.py:257] INFO Epoch: [74][40/150] Time 0.297 (0.453) Data 0.001 (0.143) Loss 0.3453 (0.3394) Prec@1 90.234 (91.044) Prec@5 96.875 (97.742)
[2021-05-01 10:04:38 train_lshot.py:257] INFO Epoch: [74][50/150] Time 0.287 (0.420) Data 0.000 (0.115) Loss 0.3467 (0.3364) Prec@1 90.234 (91.062) Prec@5 98.047 (97.886)
[2021-05-01 10:04:41 train_lshot.py:257] INFO Epoch: [74][60/150] Time 0.287 (0.397) Data 0.000 (0.096) Loss 0.3110 (0.3341) Prec@1 92.188 (91.092) Prec@5 98.047 (97.900)
[2021-05-01 10:04:44 train_lshot.py:257] INFO Epoch: [74][70/150] Time 0.289 (0.381) Data 0.001 (0.083) Loss 0.3336 (0.3336) Prec@1 91.797 (91.203) Prec@5 97.266 (97.854)
[2021-05-01 10:04:47 train_lshot.py:257] INFO Epoch: [74][80/150] Time 0.451 (0.375) Data 0.000 (0.073) Loss 0.3761 (0.3328) Prec@1 91.406 (91.237) Prec@5 96.484 (97.840)
[2021-05-01 10:04:50 train_lshot.py:257] INFO Epoch: [74][90/150] Time 0.277 (0.367) Data 0.000 (0.065) Loss 0.2835 (0.3350) Prec@1 92.578 (91.132) Prec@5 98.828 (97.811)
[2021-05-01 10:04:53 train_lshot.py:257] INFO Epoch: [74][100/150] Time 0.277 (0.359) Data 0.000 (0.058) Loss 0.3508 (0.3338) Prec@1 91.016 (91.178) Prec@5 96.875 (97.834)
[2021-05-01 10:04:56 train_lshot.py:257] INFO Epoch: [74][110/150] Time 0.275 (0.352) Data 0.000 (0.053) Loss 0.3505 (0.3370) Prec@1 89.453 (91.107) Prec@5 97.266 (97.783)
[2021-05-01 10:04:59 train_lshot.py:257] INFO Epoch: [74][120/150] Time 0.296 (0.351) Data 0.000 (0.049) Loss 0.3183 (0.3372) Prec@1 91.016 (91.080) Prec@5 97.266 (97.779)
[2021-05-01 10:05:02 train_lshot.py:257] INFO Epoch: [74][130/150] Time 0.274 (0.345) Data 0.000 (0.045) Loss 0.3794 (0.3382) Prec@1 91.406 (91.075) Prec@5 96.484 (97.755)
[2021-05-01 10:05:06 train_lshot.py:257] INFO Epoch: [74][140/150] Time 0.296 (0.345) Data 0.000 (0.042) Loss 0.3671 (0.3378) Prec@1 89.062 (91.088) Prec@5 98.047 (97.764)
[2021-05-01 10:05:15 train_lshot.py:257] INFO Epoch: [75][0/150] Time 5.967 (5.967) Data 5.520 (5.520) Loss 0.3203 (0.3203) Prec@1 91.406 (91.406) Prec@5 98.828 (98.828)
[2021-05-01 10:05:18 train_lshot.py:257] INFO Epoch: [75][10/150] Time 0.384 (0.885) Data 0.000 (0.502) Loss 0.2850 (0.2953) Prec@1 91.016 (91.584) Prec@5 98.828 (98.509)
[2021-05-01 10:05:22 train_lshot.py:257] INFO Epoch: [75][20/150] Time 0.284 (0.613) Data 0.000 (0.264) Loss 0.2913 (0.3053) Prec@1 92.578 (91.964) Prec@5 98.438 (98.233)
[2021-05-01 10:05:24 train_lshot.py:257] INFO Epoch: [75][30/150] Time 0.285 (0.506) Data 0.000 (0.179) Loss 0.3452 (0.3074) Prec@1 89.062 (91.822) Prec@5 98.047 (98.211)
[2021-05-01 10:05:27 train_lshot.py:257] INFO Epoch: [75][40/150] Time 0.284 (0.451) Data 0.001 (0.135) Loss 0.3078 (0.3124) Prec@1 93.750 (91.711) Prec@5 98.047 (98.123)
[2021-05-01 10:05:30 train_lshot.py:257] INFO Epoch: [75][50/150] Time 0.291 (0.418) Data 0.000 (0.109) Loss 0.3131 (0.3146) Prec@1 92.969 (91.667) Prec@5 97.266 (98.162)
[2021-05-01 10:05:33 train_lshot.py:257] INFO Epoch: [75][60/150] Time 0.279 (0.396) Data 0.000 (0.091) Loss 0.4008 (0.3163) Prec@1 89.062 (91.656) Prec@5 96.484 (98.143)
[2021-05-01 10:05:36 train_lshot.py:257] INFO Epoch: [75][70/150] Time 0.282 (0.380) Data 0.001 (0.078) Loss 0.3922 (0.3164) Prec@1 89.062 (91.632) Prec@5 98.047 (98.162)
[2021-05-01 10:05:38 train_lshot.py:257] INFO Epoch: [75][80/150] Time 0.282 (0.368) Data 0.000 (0.069) Loss 0.3249 (0.3189) Prec@1 90.625 (91.527) Prec@5 98.047 (98.163)
[2021-05-01 10:05:43 train_lshot.py:257] INFO Epoch: [75][90/150] Time 0.303 (0.372) Data 0.000 (0.061) Loss 0.3511 (0.3210) Prec@1 91.016 (91.458) Prec@5 98.047 (98.158)
[2021-05-01 10:05:45 train_lshot.py:257] INFO Epoch: [75][100/150] Time 0.295 (0.363) Data 0.000 (0.055) Loss 0.2719 (0.3246) Prec@1 92.188 (91.348) Prec@5 98.438 (98.124)
[2021-05-01 10:05:48 train_lshot.py:257] INFO Epoch: [75][110/150] Time 0.281 (0.356) Data 0.000 (0.050) Loss 0.3127 (0.3248) Prec@1 90.234 (91.308) Prec@5 98.438 (98.086)
[2021-05-01 10:05:51 train_lshot.py:257] INFO Epoch: [75][120/150] Time 0.288 (0.350) Data 0.000 (0.046) Loss 0.4267 (0.3266) Prec@1 89.062 (91.255) Prec@5 96.484 (98.053)
[2021-05-01 10:05:54 train_lshot.py:257] INFO Epoch: [75][130/150] Time 0.290 (0.345) Data 0.000 (0.043) Loss 0.3780 (0.3261) Prec@1 88.672 (91.263) Prec@5 98.047 (98.083)
[2021-05-01 10:05:57 train_lshot.py:257] INFO Epoch: [75][140/150] Time 0.278 (0.341) Data 0.000 (0.040) Loss 0.4141 (0.3289) Prec@1 88.281 (91.234) Prec@5 97.656 (98.058)
[2021-05-01 10:06:27 train_lshot.py:119] INFO Meta Val 75: 0.6156266790628433
[2021-05-01 10:06:35 train_lshot.py:257] INFO Epoch: [76][0/150] Time 7.620 (7.620) Data 7.301 (7.301) Loss 0.3288 (0.3288) Prec@1 91.406 (91.406) Prec@5 98.047 (98.047)
[2021-05-01 10:06:38 train_lshot.py:257] INFO Epoch: [76][10/150] Time 0.274 (0.954) Data 0.000 (0.664) Loss 0.3311 (0.3493) Prec@1 91.406 (90.518) Prec@5 97.656 (97.479)
[2021-05-01 10:06:41 train_lshot.py:257] INFO Epoch: [76][20/150] Time 0.278 (0.632) Data 0.000 (0.348) Loss 0.2887 (0.3439) Prec@1 92.188 (90.885) Prec@5 98.047 (97.619)
[2021-05-01 10:06:44 train_lshot.py:257] INFO Epoch: [76][30/150] Time 0.280 (0.518) Data 0.000 (0.236) Loss 0.2657 (0.3280) Prec@1 93.359 (91.293) Prec@5 98.438 (97.833)
[2021-05-01 10:06:47 train_lshot.py:257] INFO Epoch: [76][40/150] Time 0.280 (0.463) Data 0.001 (0.179) Loss 0.3411 (0.3334) Prec@1 91.016 (91.120) Prec@5 97.266 (97.761)
[2021-05-01 10:06:49 train_lshot.py:257] INFO Epoch: [76][50/150] Time 0.281 (0.427) Data 0.000 (0.144) Loss 0.3397 (0.3362) Prec@1 90.234 (90.954) Prec@5 98.047 (97.756)
[2021-05-01 10:06:52 train_lshot.py:257] INFO Epoch: [76][60/150] Time 0.273 (0.403) Data 0.000 (0.120) Loss 0.3373 (0.3370) Prec@1 93.359 (90.939) Prec@5 97.656 (97.772)
[2021-05-01 10:06:55 train_lshot.py:257] INFO Epoch: [76][70/150] Time 0.297 (0.386) Data 0.002 (0.103) Loss 0.2768 (0.3350) Prec@1 92.969 (90.988) Prec@5 98.828 (97.799)
[2021-05-01 10:06:58 train_lshot.py:257] INFO Epoch: [76][80/150] Time 0.283 (0.373) Data 0.000 (0.091) Loss 0.3469 (0.3368) Prec@1 90.625 (90.977) Prec@5 97.266 (97.786)
[2021-05-01 10:07:01 train_lshot.py:257] INFO Epoch: [76][90/150] Time 0.291 (0.363) Data 0.000 (0.081) Loss 0.2773 (0.3346) Prec@1 92.188 (91.029) Prec@5 97.656 (97.837)
[2021-05-01 10:07:04 train_lshot.py:257] INFO Epoch: [76][100/150] Time 0.281 (0.355) Data 0.000 (0.073) Loss 0.3589 (0.3368) Prec@1 91.406 (90.907) Prec@5 97.656 (97.819)
[2021-05-01 10:07:06 train_lshot.py:257] INFO Epoch: [76][110/150] Time 0.280 (0.349) Data 0.000 (0.066) Loss 0.3822 (0.3373) Prec@1 91.016 (90.942) Prec@5 96.875 (97.818)
[2021-05-01 10:07:09 train_lshot.py:257] INFO Epoch: [76][120/150] Time 0.285 (0.344) Data 0.000 (0.061) Loss 0.2650 (0.3355) Prec@1 91.797 (91.022) Prec@5 99.609 (97.837)
[2021-05-01 10:07:12 train_lshot.py:257] INFO Epoch: [76][130/150] Time 0.284 (0.339) Data 0.001 (0.056) Loss 0.3244 (0.3347) Prec@1 91.797 (91.087) Prec@5 97.656 (97.832)
[2021-05-01 10:07:15 train_lshot.py:257] INFO Epoch: [76][140/150] Time 0.274 (0.335) Data 0.000 (0.052) Loss 0.2636 (0.3318) Prec@1 92.969 (91.185) Prec@5 98.438 (97.853)
[2021-05-01 10:07:25 train_lshot.py:257] INFO Epoch: [77][0/150] Time 7.113 (7.113) Data 6.716 (6.716) Loss 0.3269 (0.3269) Prec@1 91.797 (91.797) Prec@5 98.438 (98.438)
[2021-05-01 10:07:29 train_lshot.py:257] INFO Epoch: [77][10/150] Time 0.293 (0.945) Data 0.000 (0.612) Loss 0.3036 (0.3200) Prec@1 92.188 (91.371) Prec@5 98.438 (98.153)
[2021-05-01 10:07:31 train_lshot.py:257] INFO Epoch: [77][20/150] Time 0.275 (0.629) Data 0.000 (0.321) Loss 0.3186 (0.3244) Prec@1 92.188 (91.536) Prec@5 97.656 (97.842)
[2021-05-01 10:07:34 train_lshot.py:257] INFO Epoch: [77][30/150] Time 0.283 (0.522) Data 0.000 (0.217) Loss 0.2983 (0.3334) Prec@1 91.406 (91.079) Prec@5 99.609 (97.896)
[2021-05-01 10:07:37 train_lshot.py:257] INFO Epoch: [77][40/150] Time 0.278 (0.463) Data 0.001 (0.164) Loss 0.4356 (0.3300) Prec@1 89.062 (91.187) Prec@5 96.094 (97.923)
[2021-05-01 10:07:40 train_lshot.py:257] INFO Epoch: [77][50/150] Time 0.274 (0.427) Data 0.000 (0.132) Loss 0.3037 (0.3328) Prec@1 90.625 (91.169) Prec@5 98.438 (97.970)
[2021-05-01 10:07:43 train_lshot.py:257] INFO Epoch: [77][60/150] Time 0.277 (0.403) Data 0.000 (0.111) Loss 0.3328 (0.3296) Prec@1 91.797 (91.387) Prec@5 98.438 (97.989)
[2021-05-01 10:07:46 train_lshot.py:257] INFO Epoch: [77][70/150] Time 0.282 (0.386) Data 0.001 (0.095) Loss 0.2649 (0.3256) Prec@1 92.969 (91.423) Prec@5 99.219 (98.058)
[2021-05-01 10:07:48 train_lshot.py:257] INFO Epoch: [77][80/150] Time 0.279 (0.374) Data 0.000 (0.083) Loss 0.3526 (0.3259) Prec@1 90.625 (91.372) Prec@5 97.266 (98.066)
[2021-05-01 10:07:52 train_lshot.py:257] INFO Epoch: [77][90/150] Time 0.359 (0.367) Data 0.000 (0.074) Loss 0.2979 (0.3276) Prec@1 91.797 (91.312) Prec@5 98.047 (98.047)
[2021-05-01 10:07:54 train_lshot.py:257] INFO Epoch: [77][100/150] Time 0.272 (0.360) Data 0.000 (0.067) Loss 0.3190 (0.3291) Prec@1 91.406 (91.263) Prec@5 98.047 (98.051)
[2021-05-01 10:07:57 train_lshot.py:257] INFO Epoch: [77][110/150] Time 0.278 (0.353) Data 0.000 (0.061) Loss 0.3609 (0.3268) Prec@1 91.406 (91.294) Prec@5 97.656 (98.050)
[2021-05-01 10:08:01 train_lshot.py:257] INFO Epoch: [77][120/150] Time 0.354 (0.352) Data 0.000 (0.056) Loss 0.2786 (0.3227) Prec@1 89.844 (91.387) Prec@5 99.609 (98.089)
[2021-05-01 10:08:04 train_lshot.py:257] INFO Epoch: [77][130/150] Time 0.277 (0.347) Data 0.000 (0.052) Loss 0.4772 (0.3250) Prec@1 88.281 (91.323) Prec@5 95.703 (98.074)
[2021-05-01 10:08:06 train_lshot.py:257] INFO Epoch: [77][140/150] Time 0.282 (0.343) Data 0.000 (0.048) Loss 0.3903 (0.3283) Prec@1 91.016 (91.271) Prec@5 97.656 (98.022)
[2021-05-01 10:08:15 train_lshot.py:257] INFO Epoch: [78][0/150] Time 5.385 (5.385) Data 4.963 (4.963) Loss 0.3117 (0.3117) Prec@1 91.797 (91.797) Prec@5 98.828 (98.828)
[2021-05-01 10:08:20 train_lshot.py:257] INFO Epoch: [78][10/150] Time 0.290 (0.970) Data 0.000 (0.645) Loss 0.3207 (0.3434) Prec@1 91.797 (90.909) Prec@5 98.047 (97.550)
[2021-05-01 10:08:23 train_lshot.py:257] INFO Epoch: [78][20/150] Time 0.276 (0.642) Data 0.000 (0.338) Loss 0.3248 (0.3319) Prec@1 91.016 (91.109) Prec@5 98.438 (97.898)
[2021-05-01 10:08:26 train_lshot.py:257] INFO Epoch: [78][30/150] Time 0.279 (0.531) Data 0.000 (0.229) Loss 0.3751 (0.3278) Prec@1 90.625 (91.293) Prec@5 97.656 (97.908)
[2021-05-01 10:08:29 train_lshot.py:257] INFO Epoch: [78][40/150] Time 0.279 (0.470) Data 0.000 (0.173) Loss 0.3013 (0.3253) Prec@1 92.188 (91.425) Prec@5 97.656 (97.923)
[2021-05-01 10:08:32 train_lshot.py:257] INFO Epoch: [78][50/150] Time 0.279 (0.433) Data 0.000 (0.139) Loss 0.3280 (0.3233) Prec@1 91.797 (91.452) Prec@5 97.266 (97.940)
[2021-05-01 10:08:34 train_lshot.py:257] INFO Epoch: [78][60/150] Time 0.284 (0.408) Data 0.000 (0.117) Loss 0.3329 (0.3273) Prec@1 91.406 (91.361) Prec@5 97.656 (97.868)
[2021-05-01 10:08:37 train_lshot.py:257] INFO Epoch: [78][70/150] Time 0.278 (0.390) Data 0.001 (0.100) Loss 0.3390 (0.3258) Prec@1 92.188 (91.379) Prec@5 97.656 (97.893)
[2021-05-01 10:08:40 train_lshot.py:257] INFO Epoch: [78][80/150] Time 0.285 (0.377) Data 0.000 (0.088) Loss 0.3249 (0.3245) Prec@1 91.016 (91.392) Prec@5 98.438 (97.931)
[2021-05-01 10:08:43 train_lshot.py:257] INFO Epoch: [78][90/150] Time 0.281 (0.366) Data 0.000 (0.078) Loss 0.3247 (0.3238) Prec@1 91.406 (91.441) Prec@5 98.047 (97.948)
[2021-05-01 10:08:46 train_lshot.py:257] INFO Epoch: [78][100/150] Time 0.287 (0.358) Data 0.000 (0.071) Loss 0.3740 (0.3235) Prec@1 90.625 (91.445) Prec@5 96.094 (97.966)
[2021-05-01 10:08:50 train_lshot.py:257] INFO Epoch: [78][110/150] Time 0.306 (0.362) Data 0.000 (0.064) Loss 0.4073 (0.3250) Prec@1 87.500 (91.350) Prec@5 97.266 (97.948)
[2021-05-01 10:08:53 train_lshot.py:257] INFO Epoch: [78][120/150] Time 0.285 (0.356) Data 0.000 (0.059) Loss 0.3041 (0.3236) Prec@1 93.750 (91.393) Prec@5 98.047 (97.950)
[2021-05-01 10:08:55 train_lshot.py:257] INFO Epoch: [78][130/150] Time 0.325 (0.350) Data 0.000 (0.054) Loss 0.3174 (0.3237) Prec@1 90.234 (91.373) Prec@5 98.438 (97.948)
[2021-05-01 10:08:58 train_lshot.py:257] INFO Epoch: [78][140/150] Time 0.274 (0.346) Data 0.000 (0.051) Loss 0.2429 (0.3221) Prec@1 94.141 (91.406) Prec@5 98.438 (97.958)
[2021-05-01 10:09:07 train_lshot.py:257] INFO Epoch: [79][0/150] Time 5.111 (5.111) Data 4.687 (4.687) Loss 0.3002 (0.3002) Prec@1 92.969 (92.969) Prec@5 98.047 (98.047)
[2021-05-01 10:09:11 train_lshot.py:257] INFO Epoch: [79][10/150] Time 0.362 (0.882) Data 0.001 (0.514) Loss 0.4117 (0.3451) Prec@1 88.281 (90.874) Prec@5 97.656 (97.798)
[2021-05-01 10:09:14 train_lshot.py:257] INFO Epoch: [79][20/150] Time 0.285 (0.602) Data 0.000 (0.269) Loss 0.3041 (0.3429) Prec@1 93.359 (91.016) Prec@5 98.047 (97.731)
[2021-05-01 10:09:17 train_lshot.py:257] INFO Epoch: [79][30/150] Time 0.292 (0.500) Data 0.000 (0.183) Loss 0.3197 (0.3511) Prec@1 91.016 (90.864) Prec@5 98.438 (97.593)
[2021-05-01 10:09:20 train_lshot.py:257] INFO Epoch: [79][40/150] Time 0.275 (0.446) Data 0.000 (0.138) Loss 0.2866 (0.3406) Prec@1 93.750 (91.149) Prec@5 98.438 (97.809)
[2021-05-01 10:09:23 train_lshot.py:257] INFO Epoch: [79][50/150] Time 0.286 (0.414) Data 0.000 (0.111) Loss 0.2461 (0.3367) Prec@1 92.188 (91.115) Prec@5 100.000 (97.901)
[2021-05-01 10:09:25 train_lshot.py:257] INFO Epoch: [79][60/150] Time 0.282 (0.393) Data 0.001 (0.093) Loss 0.2095 (0.3310) Prec@1 95.703 (91.240) Prec@5 98.438 (97.957)
[2021-05-01 10:09:28 train_lshot.py:257] INFO Epoch: [79][70/150] Time 0.289 (0.377) Data 0.001 (0.080) Loss 0.3310 (0.3301) Prec@1 92.188 (91.230) Prec@5 97.266 (97.953)
[2021-05-01 10:09:31 train_lshot.py:257] INFO Epoch: [79][80/150] Time 0.281 (0.365) Data 0.000 (0.070) Loss 0.3233 (0.3294) Prec@1 90.234 (91.252) Prec@5 98.047 (97.917)
[2021-05-01 10:09:34 train_lshot.py:257] INFO Epoch: [79][90/150] Time 0.284 (0.356) Data 0.000 (0.062) Loss 0.2443 (0.3298) Prec@1 93.359 (91.265) Prec@5 100.000 (97.910)
[2021-05-01 10:09:37 train_lshot.py:257] INFO Epoch: [79][100/150] Time 0.297 (0.350) Data 0.000 (0.056) Loss 0.2601 (0.3314) Prec@1 94.531 (91.252) Prec@5 98.828 (97.908)
[2021-05-01 10:09:40 train_lshot.py:257] INFO Epoch: [79][110/150] Time 0.272 (0.344) Data 0.000 (0.051) Loss 0.2543 (0.3292) Prec@1 94.141 (91.269) Prec@5 98.438 (97.945)
[2021-05-01 10:09:42 train_lshot.py:257] INFO Epoch: [79][120/150] Time 0.288 (0.339) Data 0.000 (0.047) Loss 0.3414 (0.3313) Prec@1 90.234 (91.187) Prec@5 97.656 (97.921)
[2021-05-01 10:09:45 train_lshot.py:257] INFO Epoch: [79][130/150] Time 0.288 (0.335) Data 0.000 (0.043) Loss 0.2313 (0.3292) Prec@1 93.359 (91.236) Prec@5 99.219 (97.948)
[2021-05-01 10:09:48 train_lshot.py:257] INFO Epoch: [79][140/150] Time 0.281 (0.331) Data 0.000 (0.040) Loss 0.3522 (0.3304) Prec@1 89.453 (91.193) Prec@5 97.656 (97.950)
[2021-05-01 10:10:19 train_lshot.py:119] INFO Meta Val 79: 0.6097333469986915
[2021-05-01 10:10:26 train_lshot.py:257] INFO Epoch: [80][0/150] Time 7.022 (7.022) Data 6.643 (6.643) Loss 0.2582 (0.2582) Prec@1 93.750 (93.750) Prec@5 98.438 (98.438)
[2021-05-01 10:10:29 train_lshot.py:257] INFO Epoch: [80][10/150] Time 0.275 (0.924) Data 0.000 (0.606) Loss 0.2519 (0.3274) Prec@1 94.922 (91.797) Prec@5 98.828 (97.621)
[2021-05-01 10:10:32 train_lshot.py:257] INFO Epoch: [80][20/150] Time 0.275 (0.617) Data 0.000 (0.318) Loss 0.3620 (0.3212) Prec@1 91.406 (91.667) Prec@5 97.266 (97.879)
[2021-05-01 10:10:35 train_lshot.py:257] INFO Epoch: [80][30/150] Time 0.284 (0.509) Data 0.000 (0.215) Loss 0.3159 (0.3251) Prec@1 92.188 (91.557) Prec@5 98.438 (97.908)
[2021-05-01 10:10:38 train_lshot.py:257] INFO Epoch: [80][40/150] Time 0.284 (0.456) Data 0.001 (0.163) Loss 0.3712 (0.3291) Prec@1 92.188 (91.530) Prec@5 97.656 (97.894)
[2021-05-01 10:10:41 train_lshot.py:257] INFO Epoch: [80][50/150] Time 0.282 (0.422) Data 0.000 (0.131) Loss 0.3235 (0.3218) Prec@1 92.188 (91.728) Prec@5 97.266 (97.970)
[2021-05-01 10:10:43 train_lshot.py:257] INFO Epoch: [80][60/150] Time 0.273 (0.398) Data 0.000 (0.110) Loss 0.2949 (0.3223) Prec@1 92.969 (91.714) Prec@5 97.656 (97.964)
[2021-05-01 10:10:46 train_lshot.py:257] INFO Epoch: [80][70/150] Time 0.277 (0.382) Data 0.001 (0.094) Loss 0.3649 (0.3231) Prec@1 89.062 (91.670) Prec@5 98.047 (98.003)
[2021-05-01 10:10:49 train_lshot.py:257] INFO Epoch: [80][80/150] Time 0.279 (0.369) Data 0.000 (0.083) Loss 0.3277 (0.3262) Prec@1 91.797 (91.483) Prec@5 98.438 (97.984)
[2021-05-01 10:10:52 train_lshot.py:257] INFO Epoch: [80][90/150] Time 0.281 (0.359) Data 0.000 (0.074) Loss 0.3850 (0.3260) Prec@1 89.453 (91.522) Prec@5 96.875 (97.965)
[2021-05-01 10:10:55 train_lshot.py:257] INFO Epoch: [80][100/150] Time 0.449 (0.353) Data 0.000 (0.066) Loss 0.2712 (0.3254) Prec@1 93.750 (91.499) Prec@5 99.219 (97.985)
[2021-05-01 10:10:58 train_lshot.py:257] INFO Epoch: [80][110/150] Time 0.285 (0.350) Data 0.000 (0.060) Loss 0.2282 (0.3271) Prec@1 94.141 (91.463) Prec@5 99.609 (97.959)
[2021-05-01 10:11:01 train_lshot.py:257] INFO Epoch: [80][120/150] Time 0.291 (0.344) Data 0.000 (0.055) Loss 0.4298 (0.3293) Prec@1 87.891 (91.426) Prec@5 96.484 (97.921)
[2021-05-01 10:11:04 train_lshot.py:257] INFO Epoch: [80][130/150] Time 0.279 (0.339) Data 0.000 (0.051) Loss 0.2859 (0.3280) Prec@1 91.797 (91.475) Prec@5 98.828 (97.925)
[2021-05-01 10:11:06 train_lshot.py:257] INFO Epoch: [80][140/150] Time 0.275 (0.335) Data 0.000 (0.048) Loss 0.3774 (0.3297) Prec@1 88.672 (91.420) Prec@5 96.094 (97.914)
[2021-05-01 10:11:16 train_lshot.py:257] INFO Epoch: [81][0/150] Time 6.459 (6.459) Data 6.102 (6.102) Loss 0.3006 (0.3006) Prec@1 91.406 (91.406) Prec@5 98.047 (98.047)
[2021-05-01 10:11:19 train_lshot.py:257] INFO Epoch: [81][10/150] Time 0.295 (0.875) Data 0.000 (0.555) Loss 0.2561 (0.2837) Prec@1 91.797 (92.010) Prec@5 99.219 (98.686)
[2021-05-01 10:11:22 train_lshot.py:257] INFO Epoch: [81][20/150] Time 0.300 (0.594) Data 0.006 (0.291) Loss 0.3063 (0.3180) Prec@1 92.188 (91.239) Prec@5 96.875 (98.084)
[2021-05-01 10:11:25 train_lshot.py:257] INFO Epoch: [81][30/150] Time 0.274 (0.499) Data 0.000 (0.197) Loss 0.2515 (0.3184) Prec@1 94.531 (91.482) Prec@5 98.828 (98.022)
[2021-05-01 10:11:28 train_lshot.py:257] INFO Epoch: [81][40/150] Time 0.287 (0.447) Data 0.000 (0.149) Loss 0.2464 (0.3287) Prec@1 92.188 (91.187) Prec@5 99.219 (97.904)
[2021-05-01 10:11:31 train_lshot.py:257] INFO Epoch: [81][50/150] Time 0.275 (0.415) Data 0.000 (0.120) Loss 0.3967 (0.3325) Prec@1 90.234 (91.222) Prec@5 97.656 (97.871)
[2021-05-01 10:11:34 train_lshot.py:257] INFO Epoch: [81][60/150] Time 0.292 (0.394) Data 0.001 (0.101) Loss 0.3738 (0.3313) Prec@1 91.797 (91.253) Prec@5 96.484 (97.887)
[2021-05-01 10:11:36 train_lshot.py:257] INFO Epoch: [81][70/150] Time 0.289 (0.379) Data 0.002 (0.087) Loss 0.2788 (0.3308) Prec@1 92.188 (91.307) Prec@5 98.828 (97.898)
[2021-05-01 10:11:39 train_lshot.py:257] INFO Epoch: [81][80/150] Time 0.288 (0.367) Data 0.000 (0.076) Loss 0.2628 (0.3285) Prec@1 92.969 (91.387) Prec@5 99.219 (97.941)
[2021-05-01 10:11:42 train_lshot.py:257] INFO Epoch: [81][90/150] Time 0.286 (0.358) Data 0.000 (0.068) Loss 0.4076 (0.3286) Prec@1 88.281 (91.406) Prec@5 96.875 (97.910)
[2021-05-01 10:11:45 train_lshot.py:257] INFO Epoch: [81][100/150] Time 0.294 (0.351) Data 0.000 (0.061) Loss 0.4134 (0.3291) Prec@1 89.062 (91.371) Prec@5 97.656 (97.931)
[2021-05-01 10:11:48 train_lshot.py:257] INFO Epoch: [81][110/150] Time 0.278 (0.345) Data 0.000 (0.055) Loss 0.3286 (0.3289) Prec@1 91.797 (91.434) Prec@5 98.828 (97.959)
[2021-05-01 10:11:51 train_lshot.py:257] INFO Epoch: [81][120/150] Time 0.284 (0.340) Data 0.000 (0.051) Loss 0.3333 (0.3278) Prec@1 91.016 (91.461) Prec@5 97.266 (97.966)
[2021-05-01 10:11:54 train_lshot.py:257] INFO Epoch: [81][130/150] Time 0.296 (0.340) Data 0.000 (0.047) Loss 0.3309 (0.3260) Prec@1 91.797 (91.534) Prec@5 97.266 (97.987)
[2021-05-01 10:11:57 train_lshot.py:257] INFO Epoch: [81][140/150] Time 0.275 (0.336) Data 0.000 (0.044) Loss 0.3354 (0.3253) Prec@1 90.625 (91.553) Prec@5 98.438 (97.980)
[2021-05-01 10:12:05 train_lshot.py:257] INFO Epoch: [82][0/150] Time 4.993 (4.993) Data 4.538 (4.538) Loss 0.3409 (0.3409) Prec@1 91.406 (91.406) Prec@5 98.438 (98.438)
[2021-05-01 10:12:09 train_lshot.py:257] INFO Epoch: [82][10/150] Time 0.327 (0.846) Data 0.000 (0.519) Loss 0.4041 (0.3436) Prec@1 88.672 (91.193) Prec@5 98.438 (97.834)
[2021-05-01 10:12:13 train_lshot.py:257] INFO Epoch: [82][20/150] Time 0.288 (0.602) Data 0.001 (0.272) Loss 0.3302 (0.3379) Prec@1 92.188 (91.239) Prec@5 98.047 (97.842)
[2021-05-01 10:12:15 train_lshot.py:257] INFO Epoch: [82][30/150] Time 0.287 (0.499) Data 0.000 (0.185) Loss 0.3601 (0.3338) Prec@1 90.625 (91.356) Prec@5 97.266 (97.896)
[2021-05-01 10:12:18 train_lshot.py:257] INFO Epoch: [82][40/150] Time 0.279 (0.446) Data 0.000 (0.140) Loss 0.3477 (0.3274) Prec@1 91.016 (91.463) Prec@5 97.266 (98.009)
[2021-05-01 10:12:21 train_lshot.py:257] INFO Epoch: [82][50/150] Time 0.288 (0.414) Data 0.000 (0.112) Loss 0.2906 (0.3237) Prec@1 91.797 (91.598) Prec@5 98.438 (98.055)
[2021-05-01 10:12:24 train_lshot.py:257] INFO Epoch: [82][60/150] Time 0.290 (0.393) Data 0.000 (0.094) Loss 0.3798 (0.3171) Prec@1 89.844 (91.694) Prec@5 97.266 (98.124)
[2021-05-01 10:12:27 train_lshot.py:257] INFO Epoch: [82][70/150] Time 0.278 (0.378) Data 0.003 (0.081) Loss 0.3256 (0.3129) Prec@1 91.797 (91.808) Prec@5 98.438 (98.146)
[2021-05-01 10:12:30 train_lshot.py:257] INFO Epoch: [82][80/150] Time 0.299 (0.366) Data 0.000 (0.071) Loss 0.3534 (0.3165) Prec@1 91.797 (91.705) Prec@5 96.875 (98.057)
[2021-05-01 10:12:32 train_lshot.py:257] INFO Epoch: [82][90/150] Time 0.276 (0.357) Data 0.000 (0.063) Loss 0.3390 (0.3183) Prec@1 92.188 (91.698) Prec@5 98.438 (98.051)
[2021-05-01 10:12:35 train_lshot.py:257] INFO Epoch: [82][100/150] Time 0.283 (0.349) Data 0.000 (0.057) Loss 0.4439 (0.3192) Prec@1 87.109 (91.596) Prec@5 97.266 (98.051)
[2021-05-01 10:12:38 train_lshot.py:257] INFO Epoch: [82][110/150] Time 0.285 (0.344) Data 0.000 (0.052) Loss 0.4393 (0.3215) Prec@1 88.672 (91.561) Prec@5 96.484 (98.015)
[2021-05-01 10:12:41 train_lshot.py:257] INFO Epoch: [82][120/150] Time 0.296 (0.342) Data 0.000 (0.048) Loss 0.4259 (0.3227) Prec@1 86.328 (91.526) Prec@5 96.094 (97.963)
[2021-05-01 10:12:44 train_lshot.py:257] INFO Epoch: [82][130/150] Time 0.279 (0.337) Data 0.000 (0.044) Loss 0.2927 (0.3217) Prec@1 92.578 (91.603) Prec@5 98.047 (97.948)
[2021-05-01 10:12:47 train_lshot.py:257] INFO Epoch: [82][140/150] Time 0.287 (0.334) Data 0.000 (0.041) Loss 0.3997 (0.3211) Prec@1 89.062 (91.600) Prec@5 97.656 (97.983)
[2021-05-01 10:12:57 train_lshot.py:257] INFO Epoch: [83][0/150] Time 7.183 (7.183) Data 6.799 (6.799) Loss 0.3861 (0.3861) Prec@1 88.672 (88.672) Prec@5 97.656 (97.656)
[2021-05-01 10:13:01 train_lshot.py:257] INFO Epoch: [83][10/150] Time 0.282 (0.961) Data 0.000 (0.619) Loss 0.3733 (0.3234) Prec@1 89.844 (91.371) Prec@5 97.656 (97.834)
[2021-05-01 10:13:04 train_lshot.py:257] INFO Epoch: [83][20/150] Time 0.289 (0.639) Data 0.000 (0.324) Loss 0.2880 (0.3273) Prec@1 92.969 (91.276) Prec@5 98.828 (98.010)
[2021-05-01 10:13:06 train_lshot.py:257] INFO Epoch: [83][30/150] Time 0.285 (0.525) Data 0.000 (0.220) Loss 0.2396 (0.3243) Prec@1 94.531 (91.368) Prec@5 98.438 (98.009)
[2021-05-01 10:13:09 train_lshot.py:257] INFO Epoch: [83][40/150] Time 0.274 (0.466) Data 0.001 (0.166) Loss 0.2867 (0.3235) Prec@1 94.531 (91.454) Prec@5 97.266 (98.028)
[2021-05-01 10:13:12 train_lshot.py:257] INFO Epoch: [83][50/150] Time 0.277 (0.429) Data 0.000 (0.134) Loss 0.2683 (0.3240) Prec@1 92.969 (91.445) Prec@5 98.438 (98.039)
[2021-05-01 10:13:15 train_lshot.py:257] INFO Epoch: [83][60/150] Time 0.280 (0.405) Data 0.000 (0.112) Loss 0.3962 (0.3251) Prec@1 90.625 (91.419) Prec@5 96.484 (98.040)
[2021-05-01 10:13:18 train_lshot.py:257] INFO Epoch: [83][70/150] Time 0.296 (0.388) Data 0.001 (0.096) Loss 0.3580 (0.3285) Prec@1 90.234 (91.335) Prec@5 97.656 (98.014)
[2021-05-01 10:13:20 train_lshot.py:257] INFO Epoch: [83][80/150] Time 0.274 (0.374) Data 0.000 (0.084) Loss 0.3337 (0.3303) Prec@1 91.797 (91.329) Prec@5 96.875 (97.955)
[2021-05-01 10:13:23 train_lshot.py:257] INFO Epoch: [83][90/150] Time 0.290 (0.364) Data 0.000 (0.075) Loss 0.3168 (0.3335) Prec@1 88.672 (91.204) Prec@5 98.047 (97.948)
[2021-05-01 10:13:26 train_lshot.py:257] INFO Epoch: [83][100/150] Time 0.305 (0.360) Data 0.000 (0.068) Loss 0.2999 (0.3330) Prec@1 93.750 (91.178) Prec@5 97.266 (97.919)
[2021-05-01 10:13:29 train_lshot.py:257] INFO Epoch: [83][110/150] Time 0.276 (0.353) Data 0.000 (0.062) Loss 0.2845 (0.3322) Prec@1 94.141 (91.258) Prec@5 98.047 (97.899)
[2021-05-01 10:13:32 train_lshot.py:257] INFO Epoch: [83][120/150] Time 0.280 (0.347) Data 0.000 (0.057) Loss 0.3240 (0.3320) Prec@1 90.625 (91.274) Prec@5 98.047 (97.889)
[2021-05-01 10:13:36 train_lshot.py:257] INFO Epoch: [83][130/150] Time 0.293 (0.350) Data 0.000 (0.052) Loss 0.3821 (0.3331) Prec@1 89.453 (91.233) Prec@5 96.875 (97.868)
[2021-05-01 10:13:39 train_lshot.py:257] INFO Epoch: [83][140/150] Time 0.295 (0.345) Data 0.000 (0.049) Loss 0.2888 (0.3330) Prec@1 90.625 (91.234) Prec@5 98.047 (97.870)
[2021-05-01 10:14:10 train_lshot.py:119] INFO Meta Val 83: 0.6152800129055976
[2021-05-01 10:14:17 train_lshot.py:257] INFO Epoch: [84][0/150] Time 7.092 (7.092) Data 6.669 (6.669) Loss 0.3897 (0.3897) Prec@1 88.281 (88.281) Prec@5 96.875 (96.875)
[2021-05-01 10:14:20 train_lshot.py:257] INFO Epoch: [84][10/150] Time 0.283 (0.936) Data 0.000 (0.607) Loss 0.2747 (0.3202) Prec@1 93.359 (91.584) Prec@5 98.438 (97.834)
[2021-05-01 10:14:23 train_lshot.py:257] INFO Epoch: [84][20/150] Time 0.292 (0.626) Data 0.000 (0.318) Loss 0.3695 (0.3264) Prec@1 91.016 (91.574) Prec@5 96.094 (97.768)
[2021-05-01 10:14:26 train_lshot.py:257] INFO Epoch: [84][30/150] Time 0.272 (0.514) Data 0.000 (0.216) Loss 0.2637 (0.3272) Prec@1 93.750 (91.482) Prec@5 98.047 (97.782)
[2021-05-01 10:14:29 train_lshot.py:257] INFO Epoch: [84][40/150] Time 0.274 (0.461) Data 0.000 (0.163) Loss 0.3093 (0.3319) Prec@1 91.797 (91.197) Prec@5 98.047 (97.742)
[2021-05-01 10:14:32 train_lshot.py:257] INFO Epoch: [84][50/150] Time 0.274 (0.425) Data 0.000 (0.131) Loss 0.3220 (0.3257) Prec@1 92.188 (91.376) Prec@5 98.438 (97.863)
[2021-05-01 10:14:34 train_lshot.py:257] INFO Epoch: [84][60/150] Time 0.275 (0.401) Data 0.000 (0.110) Loss 0.4419 (0.3243) Prec@1 87.500 (91.438) Prec@5 98.047 (97.912)
[2021-05-01 10:14:37 train_lshot.py:257] INFO Epoch: [84][70/150] Time 0.274 (0.384) Data 0.001 (0.094) Loss 0.2935 (0.3269) Prec@1 92.188 (91.346) Prec@5 98.438 (97.882)
[2021-05-01 10:14:40 train_lshot.py:257] INFO Epoch: [84][80/150] Time 0.275 (0.371) Data 0.000 (0.083) Loss 0.3264 (0.3287) Prec@1 91.406 (91.377) Prec@5 98.438 (97.840)
[2021-05-01 10:14:43 train_lshot.py:257] INFO Epoch: [84][90/150] Time 0.284 (0.361) Data 0.000 (0.074) Loss 0.4044 (0.3293) Prec@1 88.672 (91.355) Prec@5 96.484 (97.854)
[2021-05-01 10:14:46 train_lshot.py:257] INFO Epoch: [84][100/150] Time 0.279 (0.352) Data 0.000 (0.066) Loss 0.2762 (0.3310) Prec@1 91.797 (91.279) Prec@5 99.219 (97.865)
[2021-05-01 10:14:48 train_lshot.py:257] INFO Epoch: [84][110/150] Time 0.283 (0.346) Data 0.000 (0.060) Loss 0.2423 (0.3269) Prec@1 94.531 (91.427) Prec@5 98.438 (97.889)
[2021-05-01 10:14:51 train_lshot.py:257] INFO Epoch: [84][120/150] Time 0.288 (0.341) Data 0.000 (0.055) Loss 0.2449 (0.3265) Prec@1 92.969 (91.445) Prec@5 98.047 (97.863)
[2021-05-01 10:14:54 train_lshot.py:257] INFO Epoch: [84][130/150] Time 0.345 (0.337) Data 0.000 (0.051) Loss 0.3358 (0.3260) Prec@1 92.578 (91.457) Prec@5 98.047 (97.862)
[2021-05-01 10:14:57 train_lshot.py:257] INFO Epoch: [84][140/150] Time 0.286 (0.334) Data 0.000 (0.048) Loss 0.4799 (0.3280) Prec@1 86.719 (91.370) Prec@5 96.094 (97.834)
[2021-05-01 10:15:06 train_lshot.py:257] INFO Epoch: [85][0/150] Time 6.203 (6.203) Data 5.820 (5.820) Loss 0.2578 (0.2578) Prec@1 92.969 (92.969) Prec@5 99.219 (99.219)
[2021-05-01 10:15:11 train_lshot.py:257] INFO Epoch: [85][10/150] Time 0.295 (0.940) Data 0.001 (0.598) Loss 0.2782 (0.3316) Prec@1 94.531 (91.442) Prec@5 98.828 (97.514)
[2021-05-01 10:15:13 train_lshot.py:257] INFO Epoch: [85][20/150] Time 0.285 (0.629) Data 0.000 (0.313) Loss 0.3286 (0.3335) Prec@1 91.406 (91.313) Prec@5 98.047 (97.712)
[2021-05-01 10:15:16 train_lshot.py:257] INFO Epoch: [85][30/150] Time 0.281 (0.519) Data 0.000 (0.212) Loss 0.3812 (0.3319) Prec@1 89.844 (91.343) Prec@5 97.656 (97.719)
[2021-05-01 10:15:19 train_lshot.py:257] INFO Epoch: [85][40/150] Time 0.276 (0.461) Data 0.000 (0.161) Loss 0.3953 (0.3341) Prec@1 88.672 (91.282) Prec@5 97.656 (97.723)
[2021-05-01 10:15:22 train_lshot.py:257] INFO Epoch: [85][50/150] Time 0.291 (0.427) Data 0.000 (0.129) Loss 0.2263 (0.3271) Prec@1 94.531 (91.445) Prec@5 98.828 (97.817)
[2021-05-01 10:15:25 train_lshot.py:257] INFO Epoch: [85][60/150] Time 0.283 (0.403) Data 0.000 (0.108) Loss 0.3001 (0.3280) Prec@1 92.188 (91.387) Prec@5 98.438 (97.829)
[2021-05-01 10:15:28 train_lshot.py:257] INFO Epoch: [85][70/150] Time 0.283 (0.386) Data 0.001 (0.093) Loss 0.2455 (0.3255) Prec@1 94.141 (91.456) Prec@5 98.438 (97.849)
[2021-05-01 10:15:30 train_lshot.py:257] INFO Epoch: [85][80/150] Time 0.282 (0.373) Data 0.000 (0.082) Loss 0.2514 (0.3285) Prec@1 92.188 (91.281) Prec@5 99.219 (97.830)
[2021-05-01 10:15:33 train_lshot.py:257] INFO Epoch: [85][90/150] Time 0.282 (0.363) Data 0.000 (0.073) Loss 0.3092 (0.3259) Prec@1 92.969 (91.368) Prec@5 97.656 (97.858)
[2021-05-01 10:15:36 train_lshot.py:257] INFO Epoch: [85][100/150] Time 0.287 (0.355) Data 0.000 (0.065) Loss 0.3417 (0.3276) Prec@1 89.844 (91.344) Prec@5 98.438 (97.846)
[2021-05-01 10:15:39 train_lshot.py:257] INFO Epoch: [85][110/150] Time 0.290 (0.351) Data 0.000 (0.060) Loss 0.3550 (0.3267) Prec@1 91.406 (91.375) Prec@5 96.484 (97.832)
[2021-05-01 10:15:42 train_lshot.py:257] INFO Epoch: [85][120/150] Time 0.286 (0.345) Data 0.000 (0.055) Loss 0.2852 (0.3242) Prec@1 91.016 (91.439) Prec@5 98.438 (97.876)
[2021-05-01 10:15:45 train_lshot.py:257] INFO Epoch: [85][130/150] Time 0.279 (0.341) Data 0.000 (0.051) Loss 0.4133 (0.3282) Prec@1 89.844 (91.332) Prec@5 98.828 (97.865)
[2021-05-01 10:15:48 train_lshot.py:257] INFO Epoch: [85][140/150] Time 0.294 (0.337) Data 0.000 (0.047) Loss 0.2566 (0.3272) Prec@1 92.969 (91.365) Prec@5 98.828 (97.856)
[2021-05-01 10:15:57 train_lshot.py:257] INFO Epoch: [86][0/150] Time 5.991 (5.991) Data 5.580 (5.580) Loss 0.3043 (0.3043) Prec@1 91.797 (91.797) Prec@5 98.047 (98.047)
[2021-05-01 10:16:00 train_lshot.py:257] INFO Epoch: [86][10/150] Time 0.367 (0.883) Data 0.000 (0.508) Loss 0.3408 (0.3188) Prec@1 91.406 (91.584) Prec@5 97.266 (97.976)
[2021-05-01 10:16:03 train_lshot.py:257] INFO Epoch: [86][20/150] Time 0.284 (0.604) Data 0.000 (0.266) Loss 0.3538 (0.3087) Prec@1 92.188 (91.927) Prec@5 97.266 (98.047)
[2021-05-01 10:16:06 train_lshot.py:257] INFO Epoch: [86][30/150] Time 0.287 (0.502) Data 0.000 (0.181) Loss 0.2427 (0.3120) Prec@1 93.359 (91.910) Prec@5 98.828 (98.022)
[2021-05-01 10:16:09 train_lshot.py:257] INFO Epoch: [86][40/150] Time 0.282 (0.448) Data 0.000 (0.137) Loss 0.3985 (0.3250) Prec@1 90.625 (91.540) Prec@5 96.875 (97.875)
[2021-05-01 10:16:12 train_lshot.py:257] INFO Epoch: [86][50/150] Time 0.289 (0.416) Data 0.000 (0.110) Loss 0.3425 (0.3221) Prec@1 92.188 (91.636) Prec@5 96.875 (97.924)
[2021-05-01 10:16:15 train_lshot.py:257] INFO Epoch: [86][60/150] Time 0.281 (0.394) Data 0.000 (0.092) Loss 0.3259 (0.3251) Prec@1 91.016 (91.528) Prec@5 97.656 (97.912)
[2021-05-01 10:16:18 train_lshot.py:257] INFO Epoch: [86][70/150] Time 0.284 (0.378) Data 0.001 (0.079) Loss 0.3228 (0.3234) Prec@1 92.188 (91.549) Prec@5 97.656 (97.893)
[2021-05-01 10:16:20 train_lshot.py:257] INFO Epoch: [86][80/150] Time 0.286 (0.366) Data 0.000 (0.069) Loss 0.3059 (0.3237) Prec@1 92.188 (91.503) Prec@5 98.438 (97.931)
[2021-05-01 10:16:23 train_lshot.py:257] INFO Epoch: [86][90/150] Time 0.274 (0.357) Data 0.000 (0.062) Loss 0.2634 (0.3207) Prec@1 91.797 (91.514) Prec@5 99.609 (97.987)
[2021-05-01 10:16:27 train_lshot.py:257] INFO Epoch: [86][100/150] Time 0.287 (0.358) Data 0.000 (0.056) Loss 0.3459 (0.3230) Prec@1 90.234 (91.457) Prec@5 97.656 (97.931)
[2021-05-01 10:16:30 train_lshot.py:257] INFO Epoch: [86][110/150] Time 0.273 (0.351) Data 0.000 (0.051) Loss 0.2833 (0.3238) Prec@1 93.750 (91.487) Prec@5 97.266 (97.899)
[2021-05-01 10:16:32 train_lshot.py:257] INFO Epoch: [86][120/150] Time 0.285 (0.345) Data 0.000 (0.047) Loss 0.3189 (0.3242) Prec@1 91.406 (91.442) Prec@5 97.266 (97.885)
[2021-05-01 10:16:37 train_lshot.py:257] INFO Epoch: [86][130/150] Time 0.333 (0.352) Data 0.000 (0.043) Loss 0.3244 (0.3246) Prec@1 89.062 (91.403) Prec@5 98.047 (97.877)
[2021-05-01 10:16:40 train_lshot.py:257] INFO Epoch: [86][140/150] Time 0.279 (0.347) Data 0.000 (0.040) Loss 0.3738 (0.3261) Prec@1 91.016 (91.384) Prec@5 96.875 (97.872)
[2021-05-01 10:16:48 train_lshot.py:257] INFO Epoch: [87][0/150] Time 5.033 (5.033) Data 4.606 (4.606) Loss 0.4279 (0.4279) Prec@1 87.500 (87.500) Prec@5 95.703 (95.703)
[2021-05-01 10:16:52 train_lshot.py:257] INFO Epoch: [87][10/150] Time 0.402 (0.826) Data 0.000 (0.429) Loss 0.2777 (0.3125) Prec@1 93.359 (91.868) Prec@5 98.047 (98.082)
[2021-05-01 10:16:55 train_lshot.py:257] INFO Epoch: [87][20/150] Time 0.287 (0.587) Data 0.000 (0.225) Loss 0.4007 (0.3362) Prec@1 90.234 (91.220) Prec@5 97.266 (97.749)
[2021-05-01 10:16:58 train_lshot.py:257] INFO Epoch: [87][30/150] Time 0.286 (0.488) Data 0.000 (0.152) Loss 0.3098 (0.3278) Prec@1 91.406 (91.381) Prec@5 98.438 (97.908)
[2021-05-01 10:17:01 train_lshot.py:257] INFO Epoch: [87][40/150] Time 0.275 (0.438) Data 0.000 (0.115) Loss 0.3250 (0.3266) Prec@1 91.797 (91.454) Prec@5 96.484 (97.961)
[2021-05-01 10:17:04 train_lshot.py:257] INFO Epoch: [87][50/150] Time 0.280 (0.407) Data 0.001 (0.093) Loss 0.4639 (0.3254) Prec@1 88.281 (91.406) Prec@5 96.484 (98.032)
[2021-05-01 10:17:06 train_lshot.py:257] INFO Epoch: [87][60/150] Time 0.282 (0.386) Data 0.000 (0.078) Loss 0.3482 (0.3219) Prec@1 90.625 (91.605) Prec@5 98.438 (98.117)
[2021-05-01 10:17:09 train_lshot.py:257] INFO Epoch: [87][70/150] Time 0.282 (0.372) Data 0.001 (0.067) Loss 0.3347 (0.3207) Prec@1 91.406 (91.555) Prec@5 96.875 (98.102)
[2021-05-01 10:17:12 train_lshot.py:257] INFO Epoch: [87][80/150] Time 0.284 (0.361) Data 0.000 (0.059) Loss 0.3976 (0.3180) Prec@1 89.062 (91.628) Prec@5 97.656 (98.090)
[2021-05-01 10:17:15 train_lshot.py:257] INFO Epoch: [87][90/150] Time 0.289 (0.352) Data 0.000 (0.052) Loss 0.2845 (0.3166) Prec@1 92.578 (91.608) Prec@5 99.219 (98.090)
[2021-05-01 10:17:18 train_lshot.py:257] INFO Epoch: [87][100/150] Time 0.348 (0.352) Data 0.000 (0.047) Loss 0.4026 (0.3193) Prec@1 88.281 (91.596) Prec@5 95.312 (98.000)
[2021-05-01 10:17:21 train_lshot.py:257] INFO Epoch: [87][110/150] Time 0.284 (0.347) Data 0.000 (0.043) Loss 0.2822 (0.3192) Prec@1 92.188 (91.593) Prec@5 98.438 (98.012)
[2021-05-01 10:17:24 train_lshot.py:257] INFO Epoch: [87][120/150] Time 0.293 (0.341) Data 0.000 (0.039) Loss 0.2926 (0.3186) Prec@1 92.188 (91.561) Prec@5 98.047 (98.037)
[2021-05-01 10:17:27 train_lshot.py:257] INFO Epoch: [87][130/150] Time 0.290 (0.337) Data 0.000 (0.036) Loss 0.3420 (0.3210) Prec@1 88.672 (91.490) Prec@5 99.219 (98.026)
[2021-05-01 10:17:31 train_lshot.py:257] INFO Epoch: [87][140/150] Time 1.119 (0.339) Data 0.001 (0.034) Loss 0.3074 (0.3213) Prec@1 90.234 (91.476) Prec@5 100.000 (98.033)
[2021-05-01 10:18:03 train_lshot.py:119] INFO Meta Val 87: 0.6160533491373062
[2021-05-01 10:18:08 train_lshot.py:257] INFO Epoch: [88][0/150] Time 5.279 (5.279) Data 4.857 (4.857) Loss 0.2787 (0.2787) Prec@1 91.797 (91.797) Prec@5 98.438 (98.438)
[2021-05-01 10:18:13 train_lshot.py:257] INFO Epoch: [88][10/150] Time 0.281 (0.930) Data 0.000 (0.631) Loss 0.2544 (0.2964) Prec@1 93.359 (92.045) Prec@5 98.828 (98.260)
[2021-05-01 10:18:16 train_lshot.py:257] INFO Epoch: [88][20/150] Time 0.285 (0.620) Data 0.000 (0.331) Loss 0.3372 (0.3088) Prec@1 92.188 (91.853) Prec@5 97.266 (98.084)
[2021-05-01 10:18:19 train_lshot.py:257] INFO Epoch: [88][30/150] Time 0.289 (0.513) Data 0.001 (0.224) Loss 0.2895 (0.3088) Prec@1 93.359 (91.961) Prec@5 98.438 (98.160)
[2021-05-01 10:18:22 train_lshot.py:257] INFO Epoch: [88][40/150] Time 0.279 (0.459) Data 0.000 (0.170) Loss 0.2841 (0.3057) Prec@1 92.578 (92.016) Prec@5 98.047 (98.152)
[2021-05-01 10:18:24 train_lshot.py:257] INFO Epoch: [88][50/150] Time 0.275 (0.424) Data 0.000 (0.136) Loss 0.3780 (0.3129) Prec@1 88.672 (91.682) Prec@5 98.438 (98.146)
[2021-05-01 10:18:27 train_lshot.py:257] INFO Epoch: [88][60/150] Time 0.275 (0.401) Data 0.000 (0.114) Loss 0.3367 (0.3154) Prec@1 91.406 (91.675) Prec@5 97.266 (98.040)
[2021-05-01 10:18:30 train_lshot.py:257] INFO Epoch: [88][70/150] Time 0.279 (0.385) Data 0.002 (0.098) Loss 0.3399 (0.3177) Prec@1 89.453 (91.632) Prec@5 99.219 (97.981)
[2021-05-01 10:18:33 train_lshot.py:257] INFO Epoch: [88][80/150] Time 0.275 (0.372) Data 0.000 (0.086) Loss 0.2641 (0.3200) Prec@1 92.969 (91.536) Prec@5 98.828 (97.955)
[2021-05-01 10:18:36 train_lshot.py:257] INFO Epoch: [88][90/150] Time 0.278 (0.362) Data 0.000 (0.077) Loss 0.2547 (0.3186) Prec@1 94.141 (91.531) Prec@5 98.828 (97.987)
[2021-05-01 10:18:38 train_lshot.py:257] INFO Epoch: [88][100/150] Time 0.288 (0.354) Data 0.000 (0.069) Loss 0.2857 (0.3186) Prec@1 91.797 (91.557) Prec@5 98.047 (98.004)
[2021-05-01 10:18:41 train_lshot.py:257] INFO Epoch: [88][110/150] Time 0.276 (0.347) Data 0.000 (0.063) Loss 0.3142 (0.3195) Prec@1 91.797 (91.505) Prec@5 96.875 (97.980)
[2021-05-01 10:18:44 train_lshot.py:257] INFO Epoch: [88][120/150] Time 0.309 (0.343) Data 0.001 (0.058) Loss 0.2745 (0.3226) Prec@1 93.750 (91.503) Prec@5 99.219 (97.934)
[2021-05-01 10:18:47 train_lshot.py:257] INFO Epoch: [88][130/150] Time 0.275 (0.338) Data 0.000 (0.053) Loss 0.2593 (0.3219) Prec@1 92.578 (91.493) Prec@5 99.219 (97.940)
[2021-05-01 10:18:51 train_lshot.py:257] INFO Epoch: [88][140/150] Time 0.535 (0.342) Data 0.000 (0.050) Loss 0.4118 (0.3221) Prec@1 88.672 (91.498) Prec@5 95.703 (97.931)
[2021-05-01 10:19:01 train_lshot.py:257] INFO Epoch: [89][0/150] Time 6.601 (6.601) Data 6.105 (6.105) Loss 0.3141 (0.3141) Prec@1 91.406 (91.406) Prec@5 98.828 (98.828)
[2021-05-01 10:19:04 train_lshot.py:257] INFO Epoch: [89][10/150] Time 0.289 (0.913) Data 0.000 (0.556) Loss 0.3793 (0.3310) Prec@1 90.234 (91.300) Prec@5 96.875 (97.585)
[2021-05-01 10:19:07 train_lshot.py:257] INFO Epoch: [89][20/150] Time 0.275 (0.615) Data 0.000 (0.291) Loss 0.2944 (0.3243) Prec@1 92.188 (91.220) Prec@5 98.828 (97.786)
[2021-05-01 10:19:10 train_lshot.py:257] INFO Epoch: [89][30/150] Time 0.282 (0.513) Data 0.000 (0.197) Loss 0.3213 (0.3285) Prec@1 92.969 (91.280) Prec@5 98.438 (97.795)
[2021-05-01 10:19:13 train_lshot.py:257] INFO Epoch: [89][40/150] Time 0.274 (0.456) Data 0.000 (0.149) Loss 0.3842 (0.3331) Prec@1 87.500 (91.101) Prec@5 98.047 (97.847)
[2021-05-01 10:19:16 train_lshot.py:257] INFO Epoch: [89][50/150] Time 0.281 (0.422) Data 0.000 (0.120) Loss 0.3781 (0.3329) Prec@1 89.453 (91.153) Prec@5 97.266 (97.848)
[2021-05-01 10:19:19 train_lshot.py:257] INFO Epoch: [89][60/150] Time 0.282 (0.399) Data 0.000 (0.101) Loss 0.2853 (0.3267) Prec@1 92.578 (91.189) Prec@5 98.828 (97.957)
[2021-05-01 10:19:21 train_lshot.py:257] INFO Epoch: [89][70/150] Time 0.289 (0.382) Data 0.001 (0.086) Loss 0.2724 (0.3246) Prec@1 91.016 (91.214) Prec@5 99.219 (97.937)
[2021-05-01 10:19:24 train_lshot.py:257] INFO Epoch: [89][80/150] Time 0.286 (0.370) Data 0.000 (0.076) Loss 0.2573 (0.3241) Prec@1 94.531 (91.281) Prec@5 98.047 (97.984)
[2021-05-01 10:19:27 train_lshot.py:257] INFO Epoch: [89][90/150] Time 0.289 (0.360) Data 0.000 (0.067) Loss 0.3203 (0.3202) Prec@1 92.188 (91.368) Prec@5 98.047 (98.025)
[2021-05-01 10:19:30 train_lshot.py:257] INFO Epoch: [89][100/150] Time 0.293 (0.353) Data 0.000 (0.061) Loss 0.3303 (0.3210) Prec@1 91.406 (91.414) Prec@5 98.047 (97.970)
[2021-05-01 10:19:33 train_lshot.py:257] INFO Epoch: [89][110/150] Time 0.285 (0.347) Data 0.000 (0.055) Loss 0.5006 (0.3225) Prec@1 88.281 (91.406) Prec@5 95.312 (97.980)
[2021-05-01 10:19:36 train_lshot.py:257] INFO Epoch: [89][120/150] Time 0.288 (0.342) Data 0.000 (0.051) Loss 0.3860 (0.3252) Prec@1 88.281 (91.287) Prec@5 98.047 (97.953)
[2021-05-01 10:19:40 train_lshot.py:257] INFO Epoch: [89][130/150] Time 0.290 (0.348) Data 0.000 (0.047) Loss 0.3194 (0.3236) Prec@1 91.797 (91.338) Prec@5 96.875 (97.951)
[2021-05-01 10:19:43 train_lshot.py:257] INFO Epoch: [89][140/150] Time 0.275 (0.343) Data 0.000 (0.044) Loss 0.3781 (0.3230) Prec@1 90.625 (91.384) Prec@5 96.094 (97.964)
[2021-05-01 10:20:35 train_lshot.py:570] INFO validation lmd=0.10: Best
feature CL2N
GVP 1Shot 0.7197(0.0094)
GVP_5Shot 0.8217(0.0064))
[2021-05-01 10:20:50 train_lshot.py:570] INFO validation lmd=0.30: Best
feature CL2N
GVP 1Shot 0.7211(0.0093)
GVP_5Shot 0.8254(0.0061))
[2021-05-01 10:21:05 train_lshot.py:570] INFO validation lmd=0.50: Best
feature CL2N
GVP 1Shot 0.7315(0.0093)
GVP_5Shot 0.8254(0.0063))
[2021-05-01 10:21:20 train_lshot.py:570] INFO validation lmd=0.70: Best
feature CL2N
GVP 1Shot 0.7123(0.0091)
GVP_5Shot 0.8141(0.0067))
[2021-05-01 10:21:36 train_lshot.py:570] INFO validation lmd=0.80: Best
feature CL2N
GVP 1Shot 0.7332(0.0087)
GVP_5Shot 0.8067(0.0063))
[2021-05-01 10:21:53 train_lshot.py:570] INFO validation lmd=1.00: Best
feature CL2N
GVP 1Shot 0.7153(0.0087)
GVP_5Shot 0.8056(0.0062))
[2021-05-01 10:22:10 train_lshot.py:570] INFO validation lmd=1.20: Best
feature CL2N
GVP 1Shot 0.7059(0.0086)
GVP_5Shot 0.7740(0.0069))
[2021-05-01 10:22:27 train_lshot.py:570] INFO validation lmd=1.50: Best
feature CL2N
GVP 1Shot 0.6949(0.0087)
GVP_5Shot 0.7322(0.0081))
[2021-05-01 10:22:27 train_lshot.py:580] INFO Best lambda on validation:
0.80 with 1 shot acc 0.7332
0.50 with 5 shot acc 0.8254
[2021-05-01 10:22:27 train_lshot.py:707] INFO Proto-rectification = True in Evaluation
[2021-05-01 10:23:03 train_lshot.py:713] INFO Run with lambda 0.8 for 1 shot
[2021-05-01 10:30:31 train_lshot.py:717] INFO Run with lambda 0.5 for 5 shot
[2021-05-01 10:37:40 train_lshot.py:724] INFO Meta Test: LAST
feature UN L2N CL2N
GVP 1Shot 0.6324(0.0020) 0.6575(0.0020) 0.7228(0.0020)
GVP_5Shot 0.7239(0.0020) 0.7434(0.0019) 0.8214(0.0014)
[2021-05-01 10:37:51 train_lshot.py:730] INFO Run with lambda 0.8 for 1 shot
[2021-05-01 10:45:19 train_lshot.py:734] INFO Run with lambda 0.5 for 5 shot
[2021-05-01 10:52:29 train_lshot.py:741] INFO Meta Test: BEST
feature UN L2N CL2N
GVP 1Shot 0.6467(0.0020) 0.6710(0.0019) 0.7193(0.0019)
GVP_5Shot 0.7477(0.0019) 0.7633(0.0018) 0.8191(0.0014)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment