Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

not found headers/losses.yaml in reproduce SKD config #26

Closed
HengYuD opened this issue Nov 15, 2021 · 3 comments
Closed

not found headers/losses.yaml in reproduce SKD config #26

HengYuD opened this issue Nov 15, 2021 · 3 comments

Comments

@HengYuD
Copy link

HengYuD commented Nov 15, 2021

happy to see the new config file in reproduce folder but the losses.yaml file in ./config/headers/losses.yaml seems loss in SKD config file
@HengYuD
Copy link
Author

HengYuD commented Nov 16, 2021

seem the default loss dont work, would you forget to upload it ?

2021-11-16 02:17:36,417 [INFO] core.trainer: {'data_root': '/media/xaserver/DATA/xxx/Datasets/miniImageNet', 'image_size': 84, 'use_memory': False, 'augment': True, 'augment_times': 5, 'augment_times_query': 1, 'device_ids': 2, 'n_gpu': 1, 'seed': 0, 'deterministic': True, 'log_name': None, 'log_level': 'info', 'log_interval': 100, 'log_paramerter': False, 'result_root': './results', 'save_interval': 10, 'save_part': ['emb_func', 'cls_classifier', 'rot_classifier'], 'tag': None, 'epoch': 100, 'test_epoch': 5, 'parallel_part': ['emb_func', 'cls_classifier', 'rot_classifier'], 'pretrain_path': None, 'resume': False, 'way_num': 5, 'shot_num': 1, 'query_num': 15, 'test_way': 5, 'test_shot': 1, 'test_query': 15, 'episode_size': 1, 'train_episode': 1000, 'test_episode': 600, 'batch_size': 16, 'optimizer': {'kwargs': {'lr': 0.00025, 'momentum': 0.9, 'weight_decay': 0.0005}, 'name': 'SGD', 'other': {'emb_func': 0.05}}, 'lr_scheduler': {'kwargs': {'T_max': 100, 'eta_min': 0}, 'name': 'CosineAnnealingLR'}, 'includes': ['headers/data.yaml', 'headers/device.yaml', 'headers/misc.yaml', 'headers/model.yaml', 'headers/optimizer.yaml', 'classifiers/SKD.yaml', 'backbones/resnet18.yaml'], 'backbone': {'kwargs': {'avg_pool': True, 'is_feature': False, 'is_flatten': True}, 'name': 'resnet18'}, 'classifier': {'kwargs': {'alpha': 0.1, 'feat_dim': 512, 'gamma': 1.0, 'is_distill': True, 'num_class': 64}, 'name': 'SKDModel'}, 'loss': {'kwargs': None, 'name': 'CrossEntropyLoss'}, 'tb_scale': 1.6666666666666667, 'use_loss_yaml': True}
2021-11-16 02:17:36,778 [INFO] core.trainer: SKDModel(
(emb_func): ResNet(
(conv1): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(layer1): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(1): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(layer2): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(layer3): Sequential(
(0): BasicBlock(
(conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(layer4): Sequential(
(0): BasicBlock(
(conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
)
(cls_classifier): Linear(in_features=512, out_features=64, bias=True)
(rot_classifier): Linear(in_features=64, out_features=4, bias=True)
(ce_loss_func): CrossEntropyLoss()
(l2_loss_func): L2DistLoss()
(kl_loss_func): DistillKLLoss()
(distill_layer): DistillLayer()
)
2021-11-16 02:17:36,854 [INFO] core.trainer: Trainable params in the model: 11201924
2021-11-16 02:17:40,355 [INFO] core.data.dataset: load 38400 image with 64 label.
2021-11-16 02:17:40,366 [INFO] core.data.dataset: load 9600 image with 16 label.
2021-11-16 02:17:40,378 [INFO] core.data.dataset: load 12000 image with 20 label.
2021-11-16 02:17:40,383 [INFO] core.trainer: SGD (
Parameter Group 0
dampening: 0
initial_lr: 0.05
lr: 0.05
momentum: 0.9
nesterov: False
weight_decay: 0.0005

Parameter Group 1
dampening: 0
initial_lr: 0.00025
lr: 0.00025
momentum: 0.9
nesterov: False
weight_decay: 0.0005
)
2021-11-16 02:17:40,386 [INFO] core.trainer: ============ Train on the train set ============
2021-11-16 02:18:42,112 [INFO] core.trainer: Epoch-(0): [100/2400] Time 0.657 (0.617) Calc 0.218 (0.207) Data 0.001 (0.006) Loss 0.010 (0.014) Acc@1 0.625 (1.087)
2021-11-16 02:19:46,647 [INFO] core.trainer: Epoch-(0): [200/2400] Time 0.625 (0.631) Calc 0.212 (0.212) Data 0.001 (0.003) Loss 0.005 (0.010) Acc@1 0.000 (1.244)
2021-11-16 02:20:51,313 [INFO] core.trainer: Epoch-(0): [300/2400] Time 0.653 (0.636) Calc 0.216 (0.213) Data 0.001 (0.003) Loss 0.004 (0.008) Acc@1 0.000 (1.302)
2021-11-16 02:21:56,969 [INFO] core.trainer: Epoch-(0): [400/2400] Time 0.671 (0.641) Calc 0.226 (0.215) Data 0.001 (0.002) Loss 0.002 (0.007) Acc@1 0.000 (1.402)
2021-11-16 02:23:01,282 [INFO] core.trainer: Epoch-(0): [500/2400] Time 0.652 (0.641) Calc 0.219 (0.215) Data 0.001 (0.002) Loss 0.001 (0.006) Acc@1 5.000 (1.405)
2021-11-16 02:24:06,267 [INFO] core.trainer: Epoch-(0): [600/2400] Time 0.639 (0.643) Calc 0.212 (0.216) Data 0.000 (0.002) Loss 0.002 (0.005) Acc@1 0.000 (1.407)
2021-11-16 02:25:10,751 [INFO] core.trainer: Epoch-(0): [700/2400] Time 0.630 (0.643) Calc 0.210 (0.216) Data 0.002 (0.002) Loss 0.001 (0.005) Acc@1 0.000 (1.339)
2021-11-16 02:26:15,880 [INFO] core.trainer: Epoch-(0): [800/2400] Time 0.631 (0.644) Calc 0.212 (0.216) Data 0.001 (0.001) Loss 0.001 (0.004) Acc@1 5.625 (1.341)
2021-11-16 02:27:21,166 [INFO] core.trainer: Epoch-(0): [900/2400] Time 0.672 (0.645) Calc 0.225 (0.216) Data 0.001 (0.001) Loss 0.001 (0.004) Acc@1 0.000 (1.344)
2021-11-16 02:28:25,936 [INFO] core.trainer: Epoch-(0): [1000/2400] Time 0.621 (0.645) Calc 0.206 (0.216) Data 0.001 (0.001) Loss 0.001 (0.004) Acc@1 0.000 (1.365)
2021-11-16 02:29:31,151 [INFO] core.trainer: Epoch-(0): [1100/2400] Time 0.671 (0.646) Calc 0.225 (0.216) Data 0.001 (0.001) Loss 0.001 (0.003) Acc@1 1.250 (1.397)
2021-11-16 02:30:35,984 [INFO] core.trainer: Epoch-(0): [1200/2400] Time 0.636 (0.646) Calc 0.214 (0.216) Data 0.001 (0.001) Loss 0.001 (0.003) Acc@1 0.000 (1.401)
2021-11-16 02:31:41,152 [INFO] core.trainer: Epoch-(0): [1300/2400] Time 0.651 (0.646) Calc 0.219 (0.216) Data 0.001 (0.001) Loss 0.001 (0.003) Acc@1 0.000 (1.414)
2021-11-16 02:32:46,173 [INFO] core.trainer: Epoch-(0): [1400/2400] Time 0.674 (0.647) Calc 0.228 (0.216) Data 0.001 (0.001) Loss 0.001 (0.003) Acc@1 3.750 (1.428)
2021-11-16 02:33:50,885 [INFO] core.trainer: Epoch-(0): [1500/2400] Time 0.675 (0.647) Calc 0.226 (0.216) Data 0.001 (0.001) Loss 0.001 (0.003) Acc@1 0.000 (1.437)
2021-11-16 02:34:55,342 [INFO] core.trainer: Epoch-(0): [1600/2400] Time 0.638 (0.646) Calc 0.213 (0.216) Data 0.001 (0.001) Loss 0.001 (0.002) Acc@1 0.000 (1.422)
2021-11-16 02:36:00,473 [INFO] core.trainer: Epoch-(0): [1700/2400] Time 0.629 (0.647) Calc 0.213 (0.216) Data 0.001 (0.001) Loss 0.000 (0.002) Acc@1 0.000 (1.450)
2021-11-16 02:37:05,085 [INFO] core.trainer: Epoch-(0): [1800/2400] Time 0.643 (0.647) Calc 0.219 (0.216) Data 0.002 (0.001) Loss 0.001 (0.002) Acc@1 0.000 (1.478)
2021-11-16 02:38:09,878 [INFO] core.trainer: Epoch-(0): [1900/2400] Time 0.625 (0.647) Calc 0.218 (0.216) Data 0.001 (0.001) Loss 0.001 (0.002) Acc@1 1.250 (1.481)
2021-11-16 02:39:14,504 [INFO] core.trainer: Epoch-(0): [2000/2400] Time 0.673 (0.647) Calc 0.227 (0.216) Data 0.001 (0.001) Loss 0.001 (0.002) Acc@1 0.000 (1.472)
2021-11-16 02:40:19,555 [INFO] core.trainer: Epoch-(0): [2100/2400] Time 0.649 (0.647) Calc 0.218 (0.216) Data 0.001 (0.001) Loss 0.000 (0.002) Acc@1 0.000 (1.462)
2021-11-16 02:41:24,771 [INFO] core.trainer: Epoch-(0): [2200/2400] Time 0.674 (0.647) Calc 0.226 (0.216) Data 0.001 (0.001) Loss 0.000 (0.002) Acc@1 6.250 (1.461)
2021-11-16 02:42:30,517 [INFO] core.trainer: Epoch-(0): [2300/2400] Time 0.655 (0.647) Calc 0.220 (0.217) Data 0.001 (0.001) Loss 0.000 (0.002) Acc@1 0.000 (1.466)
2021-11-16 02:43:35,746 [INFO] core.trainer: Epoch-(0): [2400/2400] Time 0.704 (0.648) Calc 0.219 (0.217) Data 0.048 (0.001) Loss 0.000 (0.002) Acc@1 0.000 (1.462)
2021-11-16 02:43:35,751 [INFO] core.trainer: * Acc@1 1.462
2021-11-16 02:43:35,753 [INFO] core.trainer: ============ Validation on the val set ============
2021-11-16 02:44:06,944 [INFO] core.trainer: Epoch-(0): [100/600] Time 0.576 (0.311) Calc 0.129 (0.131) Data 0.442 (0.179) Acc@1 30.667 (23.387)
2021-11-16 02:44:28,138 [INFO] core.trainer: Epoch-(0): [200/600] Time 0.432 (0.261) Calc 0.125 (0.128) Data 0.306 (0.131) Acc@1 29.333 (23.840)
2021-11-16 02:44:48,635 [INFO] core.trainer: Epoch-(0): [300/600] Time 0.433 (0.242) Calc 0.122 (0.127) Data 0.309 (0.113) Acc@1 22.667 (23.631)
2021-11-16 02:45:05,580 [INFO] core.trainer: Epoch-(0): [400/600] Time 0.131 (0.224) Calc 0.128 (0.127) Data 0.001 (0.095) Acc@1 26.667 (23.617)
2021-11-16 02:45:22,422 [INFO] core.trainer: Epoch-(0): [500/600] Time 0.135 (0.213) Calc 0.129 (0.127) Data 0.004 (0.083) Acc@1 36.000 (23.568)
2021-11-16 02:45:37,829 [INFO] core.trainer: Epoch-(0): [600/600] Time 0.181 (0.203) Calc 0.123 (0.127) Data 0.057 (0.073) Acc@1 30.667 (23.509)
2021-11-16 02:45:37,833 [INFO] core.trainer: * Acc@1 23.509 Best acc -inf
2021-11-16 02:45:37,835 [INFO] core.trainer: ============ Testing on the test set ============
2021-11-16 02:46:06,047 [INFO] core.trainer: Epoch-(0): [100/600] Time 0.477 (0.282) Calc 0.126 (0.130) Data 0.349 (0.150) Acc@1 32.000 (25.347)
2021-11-16 02:46:26,641 [INFO] core.trainer: Epoch-(0): [200/600] Time 0.146 (0.244) Calc 0.134 (0.130) Data 0.010 (0.112) Acc@1 26.667 (25.007)
2021-11-16 02:46:43,370 [INFO] core.trainer: Epoch-(0): [300/600] Time 0.198 (0.218) Calc 0.132 (0.130) Data 0.063 (0.086) Acc@1 29.333 (24.942)
2021-11-16 02:46:59,586 [INFO] core.trainer: Epoch-(0): [400/600] Time 0.132 (0.204) Calc 0.128 (0.131) Data 0.002 (0.071) Acc@1 16.000 (24.733)
2021-11-16 02:47:14,386 [INFO] core.trainer: Epoch-(0): [500/600] Time 0.132 (0.193) Calc 0.128 (0.131) Data 0.002 (0.060) Acc@1 24.000 (24.488)
2021-11-16 02:47:29,057 [INFO] core.trainer: Epoch-(0): [600/600] Time 0.203 (0.185) Calc 0.145 (0.131) Data 0.056 (0.052) Acc@1 33.333 (24.658)
2021-11-16 02:47:29,065 [INFO] core.trainer: * Acc@1 24.658 Best acc -inf
2021-11-16 02:47:29,068 [INFO] core.trainer: * Time: 0:29:48/2 days, 1:40:00
2021-11-16 02:47:29,548 [INFO] core.trainer: ============ Train on the train set ============
2021-11-16 02:48:35,709 [INFO] core.trainer: Epoch-(1): [100/2400] Time 0.648 (0.661) Calc 0.217 (0.220) Data 0.001 (0.005) Loss 0.000 (0.000) Acc@1 0.000 (1.594)
2021-11-16 02:49:40,397 [INFO] core.trainer: Epoch-(1): [200/2400] Time 0.620 (0.654) Calc 0.206 (0.218) Data 0.001 (0.003) Loss 0.000 (0.000) Acc@1 0.000 (1.422)
2021-11-16 02:50:45,496 [INFO] core.trainer: Epoch-(1): [300/2400] Time 0.663 (0.653) Calc 0.221 (0.218) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.467)
2021-11-16 02:51:50,169 [INFO] core.trainer: Epoch-(1): [400/2400] Time 0.639 (0.651) Calc 0.215 (0.217) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.427)
2021-11-16 02:52:55,077 [INFO] core.trainer: Epoch-(1): [500/2400] Time 0.622 (0.651) Calc 0.207 (0.217) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.401)
2021-11-16 02:54:00,156 [INFO] core.trainer: Epoch-(1): [600/2400] Time 0.661 (0.651) Calc 0.221 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.386)
2021-11-16 02:55:05,097 [INFO] core.trainer: Epoch-(1): [700/2400] Time 0.669 (0.650) Calc 0.225 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.350)
2021-11-16 02:56:10,710 [INFO] core.trainer: Epoch-(1): [800/2400] Time 0.670 (0.651) Calc 0.230 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 6.250 (1.358)
2021-11-16 02:57:16,302 [INFO] core.trainer: Epoch-(1): [900/2400] Time 0.670 (0.651) Calc 0.222 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.381)
2021-11-16 02:58:21,672 [INFO] core.trainer: Epoch-(1): [1000/2400] Time 0.677 (0.652) Calc 0.229 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.403)
2021-11-16 02:59:27,012 [INFO] core.trainer: Epoch-(1): [1100/2400] Time 0.624 (0.652) Calc 0.209 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.420)
2021-11-16 03:00:32,122 [INFO] core.trainer: Epoch-(1): [1200/2400] Time 0.625 (0.652) Calc 0.209 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.472)
2021-11-16 03:01:36,958 [INFO] core.trainer: Epoch-(1): [1300/2400] Time 0.671 (0.651) Calc 0.222 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.492)
2021-11-16 03:02:41,829 [INFO] core.trainer: Epoch-(1): [1400/2400] Time 0.667 (0.651) Calc 0.224 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.488)
2021-11-16 03:03:45,876 [INFO] core.trainer: Epoch-(1): [1500/2400] Time 0.635 (0.650) Calc 0.215 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.499)
2021-11-16 03:04:50,882 [INFO] core.trainer: Epoch-(1): [1600/2400] Time 0.667 (0.650) Calc 0.221 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.508)
2021-11-16 03:05:55,646 [INFO] core.trainer: Epoch-(1): [1700/2400] Time 0.678 (0.650) Calc 0.229 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.528)
2021-11-16 03:07:00,794 [INFO] core.trainer: Epoch-(1): [1800/2400] Time 0.650 (0.650) Calc 0.217 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.553)
2021-11-16 03:08:06,027 [INFO] core.trainer: Epoch-(1): [1900/2400] Time 0.631 (0.650) Calc 0.211 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.535)
2021-11-16 03:09:11,171 [INFO] core.trainer: Epoch-(1): [2000/2400] Time 0.667 (0.650) Calc 0.223 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 6.250 (1.542)
2021-11-16 03:10:16,424 [INFO] core.trainer: Epoch-(1): [2100/2400] Time 0.667 (0.650) Calc 0.221 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.532)
2021-11-16 03:11:21,408 [INFO] core.trainer: Epoch-(1): [2200/2400] Time 0.674 (0.650) Calc 0.229 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.536)
2021-11-16 03:12:26,367 [INFO] core.trainer: Epoch-(1): [2300/2400] Time 0.620 (0.650) Calc 0.212 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.544)
2021-11-16 03:13:31,056 [INFO] core.trainer: Epoch-(1): [2400/2400] Time 0.671 (0.650) Calc 0.202 (0.217) Data 0.049 (0.001) Loss 0.000 (0.000) Acc@1 6.250 (1.545)
2021-11-16 03:13:31,060 [INFO] core.trainer: * Acc@1 1.545
2021-11-16 03:13:31,062 [INFO] core.trainer: ============ Validation on the val set ============
2021-11-16 03:13:46,312 [INFO] core.trainer: Epoch-(1): [100/600] Time 0.136 (0.152) Calc 0.133 (0.130) Data 0.001 (0.021) Acc@1 18.667 (23.573)
2021-11-16 03:14:00,632 [INFO] core.trainer: Epoch-(1): [200/600] Time 0.136 (0.147) Calc 0.133 (0.130) Data 0.001 (0.016) Acc@1 26.667 (23.580)
2021-11-16 03:14:15,146 [INFO] core.trainer: Epoch-(1): [300/600] Time 0.128 (0.146) Calc 0.124 (0.129) Data 0.002 (0.016) Acc@1 29.333 (23.684)
2021-11-16 03:14:29,609 [INFO] core.trainer: Epoch-(1): [400/600] Time 0.142 (0.146) Calc 0.139 (0.129) Data 0.002 (0.015) Acc@1 12.000 (23.637)
2021-11-16 03:14:44,639 [INFO] core.trainer: Epoch-(1): [500/600] Time 0.137 (0.147) Calc 0.133 (0.129) Data 0.002 (0.016) Acc@1 29.333 (23.432)
2021-11-16 03:14:59,078 [INFO] core.trainer: Epoch-(1): [600/600] Time 0.187 (0.146) Calc 0.129 (0.129) Data 0.056 (0.016) Acc@1 24.000 (23.300)
2021-11-16 03:14:59,083 [INFO] core.trainer: * Acc@1 23.300 Best acc 23.509
2021-11-16 03:14:59,084 [INFO] core.trainer: ============ Testing on the test set ============
2021-11-16 03:15:17,054 [INFO] core.trainer: Epoch-(1): [100/600] Time 0.223 (0.179) Calc 0.124 (0.130) Data 0.096 (0.047) Acc@1 28.000 (24.080)
2021-11-16 03:15:32,730 [INFO] core.trainer: Epoch-(1): [200/600] Time 0.185 (0.168) Calc 0.145 (0.130) Data 0.037 (0.035) Acc@1 16.000 (24.427)
2021-11-16 03:15:47,081 [INFO] core.trainer: Epoch-(1): [300/600] Time 0.130 (0.159) Calc 0.127 (0.130) Data 0.001 (0.028) Acc@1 36.000 (24.493)
2021-11-16 03:16:02,335 [INFO] core.trainer: Epoch-(1): [400/600] Time 0.137 (0.158) Calc 0.134 (0.130) Data 0.001 (0.026) Acc@1 28.000 (24.593)
2021-11-16 03:16:17,205 [INFO] core.trainer: Epoch-(1): [500/600] Time 0.413 (0.156) Calc 0.134 (0.130) Data 0.277 (0.024) Acc@1 14.667 (24.501)
2021-11-16 03:16:31,758 [INFO] core.trainer: Epoch-(1): [600/600] Time 0.194 (0.154) Calc 0.135 (0.130) Data 0.056 (0.022) Acc@1 20.000 (24.540)
2021-11-16 03:16:31,762 [INFO] core.trainer: * Acc@1 24.540 Best acc 24.658
2021-11-16 03:16:31,764 [INFO] core.trainer: * Time: 0:58:51/2 days, 1:02:30
2021-11-16 03:16:32,602 [INFO] core.trainer: ============ Train on the train set ============
2021-11-16 03:17:38,622 [INFO] core.trainer: Epoch-(2): [100/2400] Time 0.637 (0.660) Calc 0.214 (0.219) Data 0.001 (0.006) Loss 0.000 (0.000) Acc@1 0.000 (1.956)
2021-11-16 03:18:44,420 [INFO] core.trainer: Epoch-(2): [200/2400] Time 0.646 (0.659) Calc 0.217 (0.220) Data 0.001 (0.004) Loss 0.000 (0.000) Acc@1 6.250 (1.856)
2021-11-16 03:19:49,563 [INFO] core.trainer: Epoch-(2): [300/2400] Time 0.670 (0.656) Calc 0.223 (0.219) Data 0.001 (0.003) Loss 0.000 (0.000) Acc@1 0.000 (1.792)
2021-11-16 03:20:54,865 [INFO] core.trainer: Epoch-(2): [400/2400] Time 0.634 (0.655) Calc 0.213 (0.219) Data 0.000 (0.002) Loss 0.000 (0.000) Acc@1 1.250 (1.748)
2021-11-16 03:22:00,359 [INFO] core.trainer: Epoch-(2): [500/2400] Time 0.668 (0.655) Calc 0.218 (0.219) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.671)
2021-11-16 03:23:06,189 [INFO] core.trainer: Epoch-(2): [600/2400] Time 0.667 (0.655) Calc 0.222 (0.219) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.601)
2021-11-16 03:24:11,035 [INFO] core.trainer: Epoch-(2): [700/2400] Time 0.670 (0.654) Calc 0.223 (0.219) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 22.500 (1.596)
2021-11-16 03:25:16,288 [INFO] core.trainer: Epoch-(2): [800/2400] Time 0.639 (0.654) Calc 0.213 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.572)
2021-11-16 03:26:21,662 [INFO] core.trainer: Epoch-(2): [900/2400] Time 0.659 (0.654) Calc 0.221 (0.218) Data 0.000 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.599)
2021-11-16 03:27:26,287 [INFO] core.trainer: Epoch-(2): [1000/2400] Time 0.647 (0.653) Calc 0.214 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.592)
2021-11-16 03:28:30,802 [INFO] core.trainer: Epoch-(2): [1100/2400] Time 0.630 (0.652) Calc 0.209 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 6.250 (1.584)
2021-11-16 03:29:35,326 [INFO] core.trainer: Epoch-(2): [1200/2400] Time 0.662 (0.652) Calc 0.220 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 6.250 (1.609)
2021-11-16 03:30:40,560 [INFO] core.trainer: Epoch-(2): [1300/2400] Time 0.671 (0.652) Calc 0.220 (0.218) Data 0.000 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.592)
2021-11-16 03:31:45,029 [INFO] core.trainer: Epoch-(2): [1400/2400] Time 0.640 (0.651) Calc 0.215 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 2.500 (1.588)
2021-11-16 03:32:50,327 [INFO] core.trainer: Epoch-(2): [1500/2400] Time 0.656 (0.651) Calc 0.219 (0.217) Data 0.000 (0.001) Loss 0.000 (0.000) Acc@1 7.500 (1.599)
2021-11-16 03:33:55,490 [INFO] core.trainer: Epoch-(2): [1600/2400] Time 0.661 (0.651) Calc 0.220 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.586)
2021-11-16 03:35:00,791 [INFO] core.trainer: Epoch-(2): [1700/2400] Time 0.622 (0.651) Calc 0.207 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.586)
2021-11-16 03:36:06,097 [INFO] core.trainer: Epoch-(2): [1800/2400] Time 0.647 (0.651) Calc 0.215 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.575)
2021-11-16 03:37:11,374 [INFO] core.trainer: Epoch-(2): [1900/2400] Time 0.628 (0.651) Calc 0.209 (0.218) Data 0.003 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.595)
2021-11-16 03:38:16,611 [INFO] core.trainer: Epoch-(2): [2000/2400] Time 0.647 (0.652) Calc 0.213 (0.218) Data 0.000 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.582)
2021-11-16 03:39:21,652 [INFO] core.trainer: Epoch-(2): [2100/2400] Time 0.628 (0.651) Calc 0.211 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 1.250 (1.581)
2021-11-16 03:40:26,430 [INFO] core.trainer: Epoch-(2): [2200/2400] Time 0.639 (0.651) Calc 0.212 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.559)
2021-11-16 03:41:31,775 [INFO] core.trainer: Epoch-(2): [2300/2400] Time 0.677 (0.651) Calc 0.227 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.555)
2021-11-16 03:42:36,664 [INFO] core.trainer: Epoch-(2): [2400/2400] Time 0.721 (0.651) Calc 0.227 (0.218) Data 0.048 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.545)
2021-11-16 03:42:36,669 [INFO] core.trainer: * Acc@1 1.545
2021-11-16 03:42:36,671 [INFO] core.trainer: ============ Validation on the val set ============
2021-11-16 03:42:51,481 [INFO] core.trainer: Epoch-(2): [100/600] Time 0.147 (0.148) Calc 0.143 (0.129) Data 0.002 (0.017) Acc@1 32.000 (24.227)
2021-11-16 03:43:05,846 [INFO] core.trainer: Epoch-(2): [200/600] Time 0.133 (0.145) Calc 0.129 (0.128) Data 0.002 (0.016) Acc@1 28.000 (23.907)
2021-11-16 03:43:19,522 [INFO] core.trainer: Epoch-(2): [300/600] Time 0.127 (0.142) Calc 0.124 (0.127) Data 0.001 (0.013) Acc@1 20.000 (23.658)
2021-11-16 03:43:33,584 [INFO] core.trainer: Epoch-(2): [400/600] Time 0.130 (0.142) Calc 0.126 (0.128) Data 0.002 (0.012) Acc@1 20.000 (23.520)
2021-11-16 03:43:48,952 [INFO] core.trainer: Epoch-(2): [500/600] Time 0.126 (0.144) Calc 0.123 (0.128) Data 0.001 (0.014) Acc@1 25.333 (23.680)
2021-11-16 03:44:02,914 [INFO] core.trainer: Epoch-(2): [600/600] Time 0.180 (0.143) Calc 0.126 (0.128) Data 0.052 (0.013) Acc@1 25.333 (23.667)
2021-11-16 03:44:02,918 [INFO] core.trainer: * Acc@1 23.667 Best acc 23.509
2021-11-16 03:44:02,920 [INFO] core.trainer: ============ Testing on the test set ============
2021-11-16 03:44:17,819 [INFO] core.trainer: Epoch-(2): [100/600] Time 0.139 (0.149) Calc 0.136 (0.130) Data 0.001 (0.016) Acc@1 24.000 (25.107)
2021-11-16 03:44:32,061 [INFO] core.trainer: Epoch-(2): [200/600] Time 0.131 (0.145) Calc 0.127 (0.129) Data 0.002 (0.015) Acc@1 32.000 (24.893)
2021-11-16 03:44:46,139 [INFO] core.trainer: Epoch-(2): [300/600] Time 0.125 (0.144) Calc 0.122 (0.129) Data 0.001 (0.013) Acc@1 29.333 (24.573)
2021-11-16 03:44:59,484 [INFO] core.trainer: Epoch-(2): [400/600] Time 0.138 (0.141) Calc 0.132 (0.129) Data 0.001 (0.010) Acc@1 12.000 (24.453)
2021-11-16 03:45:13,180 [INFO] core.trainer: Epoch-(2): [500/600] Time 0.125 (0.140) Calc 0.122 (0.129) Data 0.001 (0.010) Acc@1 22.667 (24.285)
2021-11-16 03:45:26,595 [INFO] core.trainer: Epoch-(2): [600/600] Time 0.181 (0.139) Calc 0.126 (0.128) Data 0.053 (0.009) Acc@1 17.333 (24.353)
2021-11-16 03:45:26,598 [INFO] core.trainer: * Acc@1 24.353 Best acc 24.658
2021-11-16 03:45:26,599 [INFO] core.trainer: * Time: 1:27:46/2 days, 0:45:33.333333
2021-11-16 03:45:28,075 [INFO] core.trainer: ============ Train on the train set ============
2021-11-16 03:46:33,774 [INFO] core.trainer: Epoch-(3): [100/2400] Time 0.667 (0.656) Calc 0.220 (0.218) Data 0.001 (0.007) Loss 0.000 (0.000) Acc@1 12.500 (1.119)
2021-11-16 03:47:39,130 [INFO] core.trainer: Epoch-(3): [200/2400] Time 0.677 (0.655) Calc 0.229 (0.218) Data 0.001 (0.004) Loss 0.000 (0.000) Acc@1 0.000 (1.119)
2021-11-16 03:48:44,632 [INFO] core.trainer: Epoch-(3): [300/2400] Time 0.671 (0.655) Calc 0.225 (0.218) Data 0.001 (0.003) Loss 0.000 (0.000) Acc@1 1.250 (1.217)
2021-11-16 03:49:49,689 [INFO] core.trainer: Epoch-(3): [400/2400] Time 0.667 (0.654) Calc 0.223 (0.218) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.262)
2021-11-16 03:50:55,548 [INFO] core.trainer: Epoch-(3): [500/2400] Time 0.648 (0.654) Calc 0.218 (0.218) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.369)
2021-11-16 03:52:00,504 [INFO] core.trainer: Epoch-(3): [600/2400] Time 0.628 (0.654) Calc 0.208 (0.218) Data 0.003 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.409)
2021-11-16 03:53:05,752 [INFO] core.trainer: Epoch-(3): [700/2400] Time 0.657 (0.653) Calc 0.218 (0.218) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.373)
2021-11-16 03:54:10,846 [INFO] core.trainer: Epoch-(3): [800/2400] Time 0.656 (0.653) Calc 0.224 (0.218) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 3.750 (1.452)
2021-11-16 03:55:16,004 [INFO] core.trainer: Epoch-(3): [900/2400] Time 0.645 (0.653) Calc 0.216 (0.218) Data 0.000 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.469)
2021-11-16 03:56:20,864 [INFO] core.trainer: Epoch-(3): [1000/2400] Time 0.629 (0.652) Calc 0.210 (0.218) Data 0.003 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.424)
2021-11-16 03:57:25,991 [INFO] core.trainer: Epoch-(3): [1100/2400] Time 0.671 (0.652) Calc 0.222 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.461)
2021-11-16 03:58:30,918 [INFO] core.trainer: Epoch-(3): [1200/2400] Time 0.626 (0.652) Calc 0.207 (0.218) Data 0.000 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.458)
2021-11-16 03:59:35,749 [INFO] core.trainer: Epoch-(3): [1300/2400] Time 0.671 (0.652) Calc 0.227 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.439)
2021-11-16 04:00:40,855 [INFO] core.trainer: Epoch-(3): [1400/2400] Time 0.651 (0.651) Calc 0.218 (0.218) Data 0.000 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.461)
2021-11-16 04:01:45,791 [INFO] core.trainer: Epoch-(3): [1500/2400] Time 0.632 (0.651) Calc 0.212 (0.218) Data 0.002 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.486)
2021-11-16 04:02:50,986 [INFO] core.trainer: Epoch-(3): [1600/2400] Time 0.624 (0.651) Calc 0.210 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 6.250 (1.459)
2021-11-16 04:03:56,311 [INFO] core.trainer: Epoch-(3): [1700/2400] Time 0.668 (0.651) Calc 0.222 (0.218) Data 0.000 (0.001) Loss 0.000 (0.000) Acc@1 5.000 (1.432)
2021-11-16 04:05:01,464 [INFO] core.trainer: Epoch-(3): [1800/2400] Time 0.634 (0.651) Calc 0.213 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.475)
2021-11-16 04:06:06,376 [INFO] core.trainer: Epoch-(3): [1900/2400] Time 0.650 (0.651) Calc 0.219 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.445)
2021-11-16 04:07:11,133 [INFO] core.trainer: Epoch-(3): [2000/2400] Time 0.627 (0.651) Calc 0.210 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 6.250 (1.447)
2021-11-16 04:08:16,063 [INFO] core.trainer: Epoch-(3): [2100/2400] Time 0.665 (0.651) Calc 0.220 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.441)
2021-11-16 04:09:20,707 [INFO] core.trainer: Epoch-(3): [2200/2400] Time 0.670 (0.651) Calc 0.220 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.449)
2021-11-16 04:10:25,427 [INFO] core.trainer: Epoch-(3): [2300/2400] Time 0.623 (0.651) Calc 0.206 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.440)
2021-11-16 04:11:30,137 [INFO] core.trainer: Epoch-(3): [2400/2400] Time 0.722 (0.650) Calc 0.223 (0.217) Data 0.050 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.423)
2021-11-16 04:11:30,142 [INFO] core.trainer: * Acc@1 1.423
2021-11-16 04:11:30,143 [INFO] core.trainer: ============ Validation on the val set ============
2021-11-16 04:11:45,709 [INFO] core.trainer: Epoch-(3): [100/600] Time 0.124 (0.155) Calc 0.120 (0.127) Data 0.002 (0.027) Acc@1 28.000 (24.840)
2021-11-16 04:12:00,923 [INFO] core.trainer: Epoch-(3): [200/600] Time 0.124 (0.153) Calc 0.121 (0.128) Data 0.001 (0.024) Acc@1 17.333 (23.980)
2021-11-16 04:12:15,906 [INFO] core.trainer: Epoch-(3): [300/600] Time 0.127 (0.152) Calc 0.124 (0.127) Data 0.002 (0.023) Acc@1 20.000 (24.067)
2021-11-16 04:12:30,467 [INFO] core.trainer: Epoch-(3): [400/600] Time 0.133 (0.150) Calc 0.130 (0.127) Data 0.002 (0.022) Acc@1 22.667 (23.737)
2021-11-16 04:12:45,102 [INFO] core.trainer: Epoch-(3): [500/600] Time 0.141 (0.149) Calc 0.138 (0.127) Data 0.002 (0.021) Acc@1 20.000 (23.744)
2021-11-16 04:12:58,555 [INFO] core.trainer: Epoch-(3): [600/600] Time 0.182 (0.147) Calc 0.121 (0.127) Data 0.059 (0.018) Acc@1 17.333 (23.671)
2021-11-16 04:12:58,559 [INFO] core.trainer: * Acc@1 23.671 Best acc 23.667
2021-11-16 04:12:58,560 [INFO] core.trainer: ============ Testing on the test set ============
2021-11-16 04:13:13,098 [INFO] core.trainer: Epoch-(3): [100/600] Time 0.129 (0.145) Calc 0.126 (0.132) Data 0.001 (0.012) Acc@1 14.667 (24.253)
2021-11-16 04:13:27,632 [INFO] core.trainer: Epoch-(3): [200/600] Time 0.122 (0.145) Calc 0.119 (0.128) Data 0.001 (0.015) Acc@1 30.667 (24.093)
2021-11-16 04:13:41,432 [INFO] core.trainer: Epoch-(3): [300/600] Time 0.139 (0.142) Calc 0.136 (0.128) Data 0.001 (0.012) Acc@1 20.000 (23.911)
2021-11-16 04:13:54,820 [INFO] core.trainer: Epoch-(3): [400/600] Time 0.141 (0.140) Calc 0.137 (0.128) Data 0.002 (0.010) Acc@1 17.333 (24.073)
2021-11-16 04:14:08,081 [INFO] core.trainer: Epoch-(3): [500/600] Time 0.125 (0.139) Calc 0.123 (0.128) Data 0.001 (0.009) Acc@1 25.333 (24.208)
2021-11-16 04:14:20,998 [INFO] core.trainer: Epoch-(3): [600/600] Time 0.172 (0.137) Calc 0.124 (0.127) Data 0.047 (0.008) Acc@1 22.667 (24.069)
2021-11-16 04:14:21,001 [INFO] core.trainer: * Acc@1 24.069 Best acc 24.353
2021-11-16 04:14:21,002 [INFO] core.trainer: * Time: 1:56:40/2 days, 0:36:40
2021-11-16 04:14:22,574 [INFO] core.trainer: ============ Train on the train set ============
2021-11-16 04:15:28,191 [INFO] core.trainer: Epoch-(4): [100/2400] Time 0.640 (0.656) Calc 0.211 (0.217) Data 0.001 (0.006) Loss 0.000 (0.000) Acc@1 6.250 (1.644)
2021-11-16 04:16:33,308 [INFO] core.trainer: Epoch-(4): [200/2400] Time 0.651 (0.653) Calc 0.213 (0.217) Data 0.001 (0.003) Loss 0.000 (0.000) Acc@1 0.000 (1.672)
2021-11-16 04:17:38,863 [INFO] core.trainer: Epoch-(4): [300/2400] Time 0.626 (0.654) Calc 0.207 (0.218) Data 0.002 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.637)
2021-11-16 04:18:44,149 [INFO] core.trainer: Epoch-(4): [400/2400] Time 0.680 (0.653) Calc 0.229 (0.218) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.566)
2021-11-16 04:19:49,543 [INFO] core.trainer: Epoch-(4): [500/2400] Time 0.672 (0.653) Calc 0.225 (0.218) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.583)
2021-11-16 04:20:54,921 [INFO] core.trainer: Epoch-(4): [600/2400] Time 0.657 (0.653) Calc 0.220 (0.218) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.517)
2021-11-16 04:21:59,834 [INFO] core.trainer: Epoch-(4): [700/2400] Time 0.672 (0.653) Calc 0.225 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.457)
2021-11-16 04:23:04,594 [INFO] core.trainer: Epoch-(4): [800/2400] Time 0.675 (0.652) Calc 0.226 (0.218) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.469)
2021-11-16 04:24:09,390 [INFO] core.trainer: Epoch-(4): [900/2400] Time 0.647 (0.652) Calc 0.212 (0.217) Data 0.002 (0.001) Loss 0.000 (0.000) Acc@1 12.500 (1.476)
2021-11-16 04:25:13,931 [INFO] core.trainer: Epoch-(4): [1000/2400] Time 0.648 (0.651) Calc 0.218 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.481)
2021-11-16 04:26:18,775 [INFO] core.trainer: Epoch-(4): [1100/2400] Time 0.674 (0.651) Calc 0.229 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.527)
2021-11-16 04:27:23,778 [INFO] core.trainer: Epoch-(4): [1200/2400] Time 0.622 (0.651) Calc 0.208 (0.217) Data 0.000 (0.001) Loss 0.000 (0.000) Acc@1 6.250 (1.476)
2021-11-16 04:28:28,666 [INFO] core.trainer: Epoch-(4): [1300/2400] Time 0.676 (0.650) Calc 0.226 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.493)
2021-11-16 04:29:33,640 [INFO] core.trainer: Epoch-(4): [1400/2400] Time 0.661 (0.650) Calc 0.220 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.479)
2021-11-16 04:30:38,811 [INFO] core.trainer: Epoch-(4): [1500/2400] Time 0.646 (0.650) Calc 0.214 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 6.250 (1.510)
2021-11-16 04:31:43,680 [INFO] core.trainer: Epoch-(4): [1600/2400] Time 0.651 (0.650) Calc 0.216 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.498)
2021-11-16 04:32:48,876 [INFO] core.trainer: Epoch-(4): [1700/2400] Time 0.644 (0.650) Calc 0.217 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.499)
2021-11-16 04:33:53,935 [INFO] core.trainer: Epoch-(4): [1800/2400] Time 0.620 (0.650) Calc 0.205 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.527)
2021-11-16 04:34:59,186 [INFO] core.trainer: Epoch-(4): [1900/2400] Time 0.641 (0.650) Calc 0.215 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.548)
2021-11-16 04:36:03,966 [INFO] core.trainer: Epoch-(4): [2000/2400] Time 0.616 (0.650) Calc 0.204 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.550)
2021-11-16 04:37:08,764 [INFO] core.trainer: Epoch-(4): [2100/2400] Time 0.671 (0.650) Calc 0.223 (0.217) Data 0.000 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.543)
2021-11-16 04:38:13,586 [INFO] core.trainer: Epoch-(4): [2200/2400] Time 0.668 (0.650) Calc 0.220 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 6.250 (1.553)
2021-11-16 04:39:18,129 [INFO] core.trainer: Epoch-(4): [2300/2400] Time 0.658 (0.650) Calc 0.220 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.551)
2021-11-16 04:40:22,732 [INFO] core.trainer: Epoch-(4): [2400/2400] Time 0.663 (0.650) Calc 0.204 (0.217) Data 0.047 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.535)
2021-11-16 04:40:22,736 [INFO] core.trainer: * Acc@1 1.535
2021-11-16 04:40:22,737 [INFO] core.trainer: ============ Validation on the val set ============
2021-11-16 04:40:38,272 [INFO] core.trainer: Epoch-(4): [100/600] Time 0.123 (0.155) Calc 0.120 (0.127) Data 0.002 (0.026) Acc@1 33.333 (23.787)
2021-11-16 04:40:52,587 [INFO] core.trainer: Epoch-(4): [200/600] Time 0.123 (0.149) Calc 0.120 (0.127) Data 0.001 (0.020) Acc@1 18.667 (23.520)
2021-11-16 04:41:06,291 [INFO] core.trainer: Epoch-(4): [300/600] Time 0.125 (0.145) Calc 0.122 (0.126) Data 0.001 (0.017) Acc@1 26.667 (23.644)
2021-11-16 04:41:19,831 [INFO] core.trainer: Epoch-(4): [400/600] Time 0.130 (0.142) Calc 0.127 (0.126) Data 0.001 (0.015) Acc@1 14.667 (23.430)
2021-11-16 04:41:33,332 [INFO] core.trainer: Epoch-(4): [500/600] Time 0.122 (0.141) Calc 0.119 (0.125) Data 0.001 (0.014) Acc@1 22.667 (23.536)
2021-11-16 04:41:47,577 [INFO] core.trainer: Epoch-(4): [600/600] Time 0.171 (0.141) Calc 0.117 (0.125) Data 0.052 (0.014) Acc@1 33.333 (23.609)
2021-11-16 04:41:47,580 [INFO] core.trainer: * Acc@1 23.609 Best acc 23.671
2021-11-16 04:41:47,581 [INFO] core.trainer: ============ Testing on the test set ============
2021-11-16 04:42:02,347 [INFO] core.trainer: Epoch-(4): [100/600] Time 0.138 (0.147) Calc 0.135 (0.129) Data 0.001 (0.017) Acc@1 34.667 (24.653)
2021-11-16 04:42:15,555 [INFO] core.trainer: Epoch-(4): [200/600] Time 0.134 (0.139) Calc 0.131 (0.129) Data 0.001 (0.009) Acc@1 16.000 (24.460)
2021-11-16 04:42:28,464 [INFO] core.trainer: Epoch-(4): [300/600] Time 0.128 (0.136) Calc 0.125 (0.128) Data 0.001 (0.007) Acc@1 22.667 (24.373)
2021-11-16 04:42:41,235 [INFO] core.trainer: Epoch-(4): [400/600] Time 0.123 (0.134) Calc 0.120 (0.127) Data 0.001 (0.005) Acc@1 22.667 (24.253)
2021-11-16 04:42:54,228 [INFO] core.trainer: Epoch-(4): [500/600] Time 0.122 (0.133) Calc 0.119 (0.126) Data 0.001 (0.005) Acc@1 29.333 (24.280)
2021-11-16 04:43:07,425 [INFO] core.trainer: Epoch-(4): [600/600] Time 0.179 (0.133) Calc 0.123 (0.126) Data 0.054 (0.005) Acc@1 20.000 (24.342)
2021-11-16 04:43:07,428 [INFO] core.trainer: * Acc@1 24.342 Best acc 24.069
2021-11-16 04:43:07,430 [INFO] core.trainer: * Time: 2:25:27/2 days, 0:29:00
2021-11-16 04:43:08,015 [INFO] core.trainer: ============ Train on the train set ============
2021-11-16 04:44:13,861 [INFO] core.trainer: Epoch-(5): [100/2400] Time 0.655 (0.658) Calc 0.221 (0.218) Data 0.001 (0.007) Loss 0.000 (0.000) Acc@1 6.250 (2.475)
2021-11-16 04:45:18,959 [INFO] core.trainer: Epoch-(5): [200/2400] Time 0.661 (0.654) Calc 0.221 (0.218) Data 0.001 (0.004) Loss 0.000 (0.000) Acc@1 0.000 (1.994)
2021-11-16 04:46:24,447 [INFO] core.trainer: Epoch-(5): [300/2400] Time 0.644 (0.654) Calc 0.215 (0.218) Data 0.001 (0.003) Loss 0.000 (0.000) Acc@1 6.250 (1.783)
2021-11-16 04:47:29,558 [INFO] core.trainer: Epoch-(5): [400/2400] Time 0.663 (0.653) Calc 0.221 (0.218) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.684)
2021-11-16 04:48:34,783 [INFO] core.trainer: Epoch-(5): [500/2400] Time 0.667 (0.653) Calc 0.217 (0.218) Data 0.002 (0.002) Loss 0.000 (0.000) Acc@1 0.000 (1.685)
2021-11-16 04:49:40,089 [INFO] core.trainer: Epoch-(5): [600/2400] Time 0.664 (0.653) Calc 0.218 (0.218) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 5.000 (1.663)
2021-11-16 04:50:44,913 [INFO] core.trainer: Epoch-(5): [700/2400] Time 0.628 (0.652) Calc 0.205 (0.218) Data 0.001 (0.002) Loss 0.000 (0.000) Acc@1 6.250 (1.714)
2021-11-16 04:51:50,026 [INFO] core.trainer: Epoch-(5): [800/2400] Time 0.647 (0.652) Calc 0.211 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.711)
2021-11-16 04:52:54,618 [INFO] core.trainer: Epoch-(5): [900/2400] Time 0.674 (0.651) Calc 0.229 (0.217) Data 0.001 (0.001) Loss 0.000 (0.000) Acc@1 0.000 (1.663)

@HengYuD HengYuD changed the title not found headers/losses.yaml in the reproduce config of SKD not found headers/losses.yaml in reproduce SKD config Nov 16, 2021
@wZuck
Copy link
Member

wZuck commented Nov 16, 2021

losses.yaml is temporarily removed in the released codes, you can delete it from include.

@wZuck
Copy link
Member

wZuck commented Nov 16, 2021

For SKD, if you turn is_distill to True, that means you are training SKD-Gen1, the emb_func_path and cls_classifier_path should also be specified.

@wZuck wZuck closed this as completed Nov 16, 2021
@wZuck wZuck mentioned this issue Nov 4, 2022
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@wZuck @HengYuD