关于文章中数据的疑问 #109

OKCup · 2024-05-05T01:11:44Z

为什么table2里面RENet+ResNet12复现准确率已经是82.13了，table3又变成79.9了

WenbinLee · 2024-05-06T03:59:13Z

您好，Table 2里是完全按照原文的代码里的设置和使用各种trick，但是Table 3是尽可能让所有方法使用差不多的设置和相同的训练trick，包括训练的轮数等，主要是这个原因造成的，这样可能也不是非常公平公正，但已经是相对合理的了。

OKCup · 2024-05-07T04:33:20Z

你好，我在使用model zoo给出的配置文件运行RENet的时候，好像完全达不到文章中的准确率，在miniimagenet上，5-5-table2的配置文件运行下来只能到77%，78%左右，5-5-Reproduce的配置文件运行下来只有79%，80%左右，与文章所给的准确度都有2%左右的差距。因为环境不同可能是会有一定差异，但是从日志上看好像不太对，因为与model zoo给的日志文件中，epoch0的train准确率就已经48%了，但是我的复现中epoch0只有36%左右。还有一个问题就是5-5-Reproduce给出的日志中，epoch59的train准确率为90.764%，test准确率为82.427，但我的复现中，epoch59的train准确率已经有96.867%了，但是test准确率只有80.140%，并且还不是best acc，此时best acc还是79.28。
也就是我的初始train准确率是低于model zoo的训练结果的，但是我的最终的train准确率是高于甚至大幅度高于model zoo的训练结果，而test准确率反而是偏低的。不知道是否是backbone有问题还是参数有问题。下面是我使用5-5-Reproduce运行的配置文件和日志文件：

config.yaml:
augment: true
augment_method: null
augment_times: 1
augment_times_query: 1
backbone:
kwargs:
avg_pool: false
drop_rate: 0.0
is_flatten: false
keep_prob: 0.0
maxpool_last2: true
name: resnet12
batch_size: 128
classifier:
kwargs:
feat_dim: 640
lambda_epi: 0.25
num_classes: 64
temperature: 0.2
temperature_attn: 5.0
name: RENet
data_root: /root/autodl-tmp/data/miniImageNet--ravi
dataloader_num: 2
deterministic: true
device_ids: 0
episode_size: 1
epoch: 100
image_size: 84
includes:

headers/data.yaml
headers/device.yaml
headers/misc.yaml
headers/model.yaml
headers/optimizer.yaml
classifiers/RENet.yaml
backbones/resnet12.yaml
log_interval: 100
log_level: info
log_name: null
log_paramerter: false
lr_scheduler:
kwargs:
gamma: 0.05
milestones:
- 40
- 50
  name: MultiStepLR
  n_gpu: 1
  optimizer:
  kwargs:
  lr: 0.1
  momentum: 0.9
  nesterov: true
  weight_decay: 0.0005
  name: SGD
  other:
  emb_func: 0.1
  parallel_part:
emb_func
port: 48703
pretrain_path: null
query_num: 15
rank: 0
result_root: ./results
resume: false
save_interval: 20
save_part:
emb_func
seed: 0
shot_num: 5
tag: null
tb_scale: 1.5
test_episode: 200
test_epoch: 5
test_query: 15
test_shot: 5
test_way: 5
train_episode: 300
use_memory: false
val_per_epoch: 1
warmup: 0
way_num: 5
workers: 16

log:

2024-05-06 19:16:07,299 [INFO] core.trainer: {'data_root': '/root/autodl-tmp/data/miniImageNet--ravi', 'image_size': 84, 'use_memory': False, 'augment': True, 'augment_times': 1, 'augment_times_query': 1, 'workers': 16, 'dataloader_num': 2, 'device_ids': 0, 'n_gpu': 1, 'seed': 0, 'deterministic': True, 'port': 48703, 'log_name': None, 'log_level': 'info', 'log_interval': 100, 'log_paramerter': False, 'result_root': './results', 'save_interval': 10, 'save_part': ['emb_func'], 'tag': None, 'epoch': 60, 'test_epoch': 5, 'parallel_part': ['emb_func'], 'pretrain_path': None, 'resume': False, 'way_num': 5, 'shot_num': 5, 'query_num': 15, 'test_way': 5, 'test_shot': 5, 'test_query': 15, 'episode_size': 1, 'train_episode': 300, 'test_episode': 200, 'batch_size': 128, 'val_per_epoch': 1, 'optimizer': {'kwargs': {'lr': 0.1, 'momentum': 0.9, 'nesterov': True, 'weight_decay': 0.0005}, 'name': 'SGD', 'other': {'emb_func': 0.1}}, 'lr_scheduler': {'kwargs': {'gamma': 0.05, 'milestones': [40, 50]}, 'name': 'MultiStepLR'}, 'warmup': 0, 'includes': ['headers/data.yaml', 'headers/device.yaml', 'headers/misc.yaml', 'headers/model.yaml', 'headers/optimizer.yaml', 'classifiers/RENet.yaml', 'backbones/resnet12.yaml'], 'augment_method': None, 'backbone': {'kwargs': {'avg_pool': False, 'drop_rate': 0.0, 'is_flatten': False, 'keep_prob': 0.0, 'maxpool_last2': True}, 'name': 'resnet12'}, 'classifier': {'kwargs': {'feat_dim': 640, 'lambda_epi': 0.25, 'num_classes': 64, 'temperature': 0.2, 'temperature_attn': 5.0}, 'name': 'RENet'}, 'tb_scale': 1.5, 'rank': 0}
2024-05-06 19:16:07,519 [INFO] core.trainer: RENet(
(emb_func): ResNet(
(layer1): Sequential(
(0): BasicBlock(
(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): LeakyReLU(negative_slope=0.1)
(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)
(conv3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(maxpool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(downsample): Sequential(
(0): Conv2d(3, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(DropBlock): DropBlock()
)
)
(layer2): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): LeakyReLU(negative_slope=0.1)
(conv2): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(maxpool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(downsample): Sequential(
(0): Conv2d(64, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(DropBlock): DropBlock()
)
)
(layer3): Sequential(
(0): BasicBlock(
(conv1): Conv2d(160, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): LeakyReLU(negative_slope=0.1)
(conv2): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn3): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(maxpool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(downsample): Sequential(
(0): Conv2d(160, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(DropBlock): DropBlock()
)
)
(layer4): Sequential(
(0): BasicBlock(
(conv1): Conv2d(320, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): LeakyReLU(negative_slope=0.1)
(conv2): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn3): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(maxpool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(downsample): Sequential(
(0): Conv2d(320, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(DropBlock): DropBlock()
)
)
(dropout): Dropout(p=1.0, inplace=False)
)
(fc): Linear(in_features=640, out_features=64, bias=True)
(scr_layer): SCRLayer(
(model): Sequential(
(0): SelfCorrelationComputation(
(unfold): Unfold(kernel_size=(5, 5), dilation=1, padding=2, stride=1)
(relu): ReLU()
)
(1): SCR(
(conv1x1_in): Sequential(
(0): Conv2d(640, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv1): Sequential(
(0): Conv3d(64, 64, kernel_size=(1, 3, 3), stride=(1, 1, 1), bias=False)
(1): BatchNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv3d(64, 64, kernel_size=(1, 3, 3), stride=(1, 1, 1), bias=False)
(1): BatchNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(conv1x1_out): Sequential(
(0): Conv2d(64, 640, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
)
)
(cca_layer): CCALayer(
(cca_module): CCA(
(conv): Sequential(
(0): SepConv4d(
(proj): Sequential(
(0): Conv2d(1, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(conv1): Sequential(
(0): Conv3d(1, 1, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1), bias=False)
(1): BatchNorm3d(1, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(conv2): Sequential(
(0): Conv3d(1, 1, kernel_size=(3, 3, 1), stride=(1, 1, 1), padding=(1, 1, 0), bias=False)
(1): BatchNorm3d(1, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
(1): ReLU(inplace=True)
(2): SepConv4d(
(proj): Sequential(
(0): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(1, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(conv1): Sequential(
(0): Conv3d(16, 16, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1), bias=False)
(1): BatchNorm3d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(conv2): Sequential(
(0): Conv3d(16, 16, kernel_size=(3, 3, 1), stride=(1, 1, 1), padding=(1, 1, 0), bias=False)
(1): BatchNorm3d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(relu): ReLU(inplace=True)
)
)
)
(cca_1x1): Sequential(
(0): Conv2d(640, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU()
)
)
(loss_func): CrossEntropyLoss()
)
2024-05-06 19:16:07,577 [INFO] core.trainer: Trainable params in the model: 12668504
2024-05-06 19:16:07,709 [INFO] core.trainer: load 38400 train image with 64 label.
2024-05-06 19:16:07,721 [INFO] core.trainer: load 9600 val image with 16 label.
2024-05-06 19:16:08,057 [INFO] core.trainer: load 12000 test image with 20 label.
2024-05-06 19:16:08,422 [INFO] core.trainer: SGD (
Parameter Group 0
dampening: 0
differentiable: False
foreach: None
initial_lr: 0.1
lr: 0.1
maximize: False
momentum: 0.9
nesterov: True
weight_decay: 0.0005

Parameter Group 1
dampening: 0
differentiable: False
foreach: None
initial_lr: 0.1
lr: 0.1
maximize: False
momentum: 0.9
nesterov: True
weight_decay: 0.0005
)
2024-05-06 19:16:08,427 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:16:08,429 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:16:34,627 [INFO] core.trainer: Epoch-(0): [100/300] Time 0.242 (0.261) Calc 0.085 (0.095) Data 0.002 (0.016) Loss 8.537 (9.776) Acc@1 49.333 (31.147)
2024-05-06 19:16:58,695 [INFO] core.trainer: Epoch-(0): [200/300] Time 0.241 (0.251) Calc 0.088 (0.091) Data 0.001 (0.008) Loss 7.820 (9.030) Acc@1 32.000 (34.733)
2024-05-06 19:17:22,865 [INFO] core.trainer: Epoch-(0): [300/300] Time 0.240 (0.248) Calc 0.089 (0.091) Data 0.000 (0.006) Loss 7.816 (8.702) Acc@1 44.000 (36.702)
2024-05-06 19:17:22,956 [INFO] core.trainer: * Acc@1 36.702
2024-05-06 19:17:22,957 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:17:26,214 [INFO] core.trainer: Epoch-(0): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.000) Acc@1 44.000 (38.920)
2024-05-06 19:17:29,473 [INFO] core.trainer: Epoch-(0): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 40.000 (38.620)
2024-05-06 19:17:29,476 [INFO] core.trainer: * Acc@1 38.620 Best acc -inf
2024-05-06 19:17:29,477 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:17:32,770 [INFO] core.trainer: Epoch-(0): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 32.000 (38.547)
2024-05-06 19:17:36,073 [INFO] core.trainer: Epoch-(0): [200/200] Time 0.034 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 38.667 (38.713)
2024-05-06 19:17:36,076 [INFO] core.trainer: * Acc@1 38.713 Best acc -inf
2024-05-06 19:17:36,077 [INFO] core.trainer: * Time: 0:01:27/1:27:00
2024-05-06 19:17:36,274 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:17:36,275 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:18:01,081 [INFO] core.trainer: Epoch-(1): [100/300] Time 0.241 (0.248) Calc 0.088 (0.087) Data 0.001 (0.008) Loss 7.857 (7.830) Acc@1 40.000 (42.467)
2024-05-06 19:18:25,170 [INFO] core.trainer: Epoch-(1): [200/300] Time 0.241 (0.244) Calc 0.088 (0.088) Data 0.001 (0.004) Loss 7.954 (7.722) Acc@1 46.667 (44.760)
2024-05-06 19:18:49,244 [INFO] core.trainer: Epoch-(1): [300/300] Time 0.240 (0.243) Calc 0.088 (0.087) Data 0.000 (0.003) Loss 7.414 (7.639) Acc@1 54.667 (45.396)
2024-05-06 19:18:49,358 [INFO] core.trainer: * Acc@1 45.396
2024-05-06 19:18:49,359 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:18:52,628 [INFO] core.trainer: Epoch-(1): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 52.000 (43.107)
2024-05-06 19:18:55,918 [INFO] core.trainer: Epoch-(1): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 44.000 (42.700)
2024-05-06 19:18:55,921 [INFO] core.trainer: * Acc@1 42.700 Best acc 38.620
2024-05-06 19:18:55,923 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:18:59,264 [INFO] core.trainer: Epoch-(1): [100/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 34.667 (43.440)
2024-05-06 19:19:02,610 [INFO] core.trainer: Epoch-(1): [200/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.000 (0.001) Acc@1 42.667 (43.913)
2024-05-06 19:19:02,614 [INFO] core.trainer: * Acc@1 43.913 Best acc 38.713
2024-05-06 19:19:02,615 [INFO] core.trainer: * Time: 0:02:54/1:27:00
2024-05-06 19:19:02,866 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:19:02,868 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:19:27,635 [INFO] core.trainer: Epoch-(2): [100/300] Time 0.240 (0.247) Calc 0.088 (0.087) Data 0.001 (0.007) Loss 7.267 (7.315) Acc@1 38.667 (48.827)
2024-05-06 19:19:51,784 [INFO] core.trainer: Epoch-(2): [200/300] Time 0.240 (0.244) Calc 0.092 (0.088) Data 0.001 (0.004) Loss 6.668 (7.248) Acc@1 53.333 (49.013)
2024-05-06 19:20:15,870 [INFO] core.trainer: Epoch-(2): [300/300] Time 0.240 (0.243) Calc 0.088 (0.088) Data 0.000 (0.003) Loss 6.825 (7.163) Acc@1 50.667 (49.680)
2024-05-06 19:20:15,996 [INFO] core.trainer: * Acc@1 49.680
2024-05-06 19:20:15,998 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:20:19,297 [INFO] core.trainer: Epoch-(2): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 46.667 (47.693)
2024-05-06 19:20:22,739 [INFO] core.trainer: Epoch-(2): [200/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.000 (0.001) Acc@1 57.333 (48.367)
2024-05-06 19:20:22,742 [INFO] core.trainer: * Acc@1 48.367 Best acc 42.700
2024-05-06 19:20:22,744 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:20:26,098 [INFO] core.trainer: Epoch-(2): [100/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 56.000 (48.720)
2024-05-06 19:20:29,403 [INFO] core.trainer: Epoch-(2): [200/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 48.000 (49.220)
2024-05-06 19:20:29,405 [INFO] core.trainer: * Acc@1 49.220 Best acc 43.913
2024-05-06 19:20:29,406 [INFO] core.trainer: * Time: 0:04:20/1:26:40
2024-05-06 19:20:29,656 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:20:29,658 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:20:54,544 [INFO] core.trainer: Epoch-(3): [100/300] Time 0.241 (0.248) Calc 0.081 (0.089) Data 0.001 (0.008) Loss 7.393 (6.791) Acc@1 41.333 (52.040)
2024-05-06 19:21:18,674 [INFO] core.trainer: Epoch-(3): [200/300] Time 0.240 (0.245) Calc 0.085 (0.088) Data 0.001 (0.004) Loss 6.505 (6.646) Acc@1 56.000 (53.847)
2024-05-06 19:21:42,827 [INFO] core.trainer: Epoch-(3): [300/300] Time 0.241 (0.243) Calc 0.090 (0.089) Data 0.000 (0.003) Loss 5.964 (6.522) Acc@1 58.667 (54.502)
2024-05-06 19:21:42,959 [INFO] core.trainer: * Acc@1 54.502
2024-05-06 19:21:42,960 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:21:46,301 [INFO] core.trainer: Epoch-(3): [100/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 46.667 (51.560)
2024-05-06 19:21:49,581 [INFO] core.trainer: Epoch-(3): [200/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 69.333 (51.620)
2024-05-06 19:21:49,584 [INFO] core.trainer: * Acc@1 51.620 Best acc 48.367
2024-05-06 19:21:49,585 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:21:52,894 [INFO] core.trainer: Epoch-(3): [100/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 58.667 (54.813)
2024-05-06 19:21:56,183 [INFO] core.trainer: Epoch-(3): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 56.000 (54.220)
2024-05-06 19:21:56,186 [INFO] core.trainer: * Acc@1 54.220 Best acc 49.220
2024-05-06 19:21:56,187 [INFO] core.trainer: * Time: 0:05:47/1:26:45
2024-05-06 19:21:56,429 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:21:56,431 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:22:21,196 [INFO] core.trainer: Epoch-(4): [100/300] Time 0.240 (0.247) Calc 0.087 (0.087) Data 0.001 (0.008) Loss 5.803 (5.949) Acc@1 62.667 (61.520)
2024-05-06 19:22:45,286 [INFO] core.trainer: Epoch-(4): [200/300] Time 0.240 (0.244) Calc 0.081 (0.087) Data 0.001 (0.004) Loss 5.999 (5.855) Acc@1 58.667 (62.913)
2024-05-06 19:23:09,404 [INFO] core.trainer: Epoch-(4): [300/300] Time 0.240 (0.243) Calc 0.088 (0.087) Data 0.000 (0.003) Loss 5.937 (5.799) Acc@1 50.667 (62.280)
2024-05-06 19:23:09,547 [INFO] core.trainer: * Acc@1 62.280
2024-05-06 19:23:09,549 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:23:12,857 [INFO] core.trainer: Epoch-(4): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 58.667 (56.200)
2024-05-06 19:23:16,174 [INFO] core.trainer: Epoch-(4): [200/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 46.667 (55.640)
2024-05-06 19:23:16,177 [INFO] core.trainer: * Acc@1 55.640 Best acc 51.620
2024-05-06 19:23:16,179 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:23:19,459 [INFO] core.trainer: Epoch-(4): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 58.667 (58.733)
2024-05-06 19:23:22,735 [INFO] core.trainer: Epoch-(4): [200/200] Time 0.033 (0.032) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 68.000 (58.387)
2024-05-06 19:23:22,738 [INFO] core.trainer: * Acc@1 58.387 Best acc 54.220
2024-05-06 19:23:22,739 [INFO] core.trainer: * Time: 0:07:14/1:26:48
2024-05-06 19:23:22,968 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:23:22,970 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:23:47,841 [INFO] core.trainer: Epoch-(5): [100/300] Time 0.241 (0.248) Calc 0.089 (0.088) Data 0.001 (0.008) Loss 5.083 (5.367) Acc@1 53.333 (65.573)
2024-05-06 19:24:11,977 [INFO] core.trainer: Epoch-(5): [200/300] Time 0.241 (0.245) Calc 0.089 (0.088) Data 0.001 (0.005) Loss 5.556 (5.291) Acc@1 58.667 (65.960)
2024-05-06 19:24:36,094 [INFO] core.trainer: Epoch-(5): [300/300] Time 0.240 (0.243) Calc 0.088 (0.088) Data 0.000 (0.003) Loss 4.779 (5.208) Acc@1 78.667 (66.422)
2024-05-06 19:24:36,215 [INFO] core.trainer: * Acc@1 66.422
2024-05-06 19:24:36,216 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:24:39,526 [INFO] core.trainer: Epoch-(5): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 57.333 (62.320)
2024-05-06 19:24:42,837 [INFO] core.trainer: Epoch-(5): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 62.667 (61.853)
2024-05-06 19:24:42,840 [INFO] core.trainer: * Acc@1 61.853 Best acc 55.640
2024-05-06 19:24:42,841 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:24:46,124 [INFO] core.trainer: Epoch-(5): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 52.000 (65.147)
2024-05-06 19:24:49,399 [INFO] core.trainer: Epoch-(5): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 68.000 (64.047)
2024-05-06 19:24:49,402 [INFO] core.trainer: * Acc@1 64.047 Best acc 58.387
2024-05-06 19:24:49,403 [INFO] core.trainer: * Time: 0:08:40/1:26:40
2024-05-06 19:24:49,628 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:24:49,630 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:25:14,436 [INFO] core.trainer: Epoch-(6): [100/300] Time 0.240 (0.248) Calc 0.088 (0.088) Data 0.001 (0.008) Loss 4.687 (4.791) Acc@1 53.333 (68.747)
2024-05-06 19:25:38,552 [INFO] core.trainer: Epoch-(6): [200/300] Time 0.240 (0.244) Calc 0.090 (0.088) Data 0.001 (0.004) Loss 5.001 (4.747) Acc@1 60.000 (69.093)
2024-05-06 19:26:02,670 [INFO] core.trainer: Epoch-(6): [300/300] Time 0.241 (0.243) Calc 0.089 (0.088) Data 0.000 (0.003) Loss 4.310 (4.652) Acc@1 69.333 (70.422)
2024-05-06 19:26:02,796 [INFO] core.trainer: * Acc@1 70.422
2024-05-06 19:26:02,798 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:26:06,106 [INFO] core.trainer: Epoch-(6): [100/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.002 (0.001) Acc@1 52.000 (63.267)
2024-05-06 19:26:09,393 [INFO] core.trainer: Epoch-(6): [200/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 64.000 (63.313)
2024-05-06 19:26:09,396 [INFO] core.trainer: * Acc@1 63.313 Best acc 61.853
2024-05-06 19:26:09,397 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:26:12,685 [INFO] core.trainer: Epoch-(6): [100/200] Time 0.034 (0.032) Calc 0.030 (0.030) Data 0.002 (0.001) Acc@1 53.333 (63.467)
2024-05-06 19:26:15,964 [INFO] core.trainer: Epoch-(6): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 72.000 (64.400)
2024-05-06 19:26:15,966 [INFO] core.trainer: * Acc@1 64.400 Best acc 64.047
2024-05-06 19:26:15,968 [INFO] core.trainer: * Time: 0:10:07/1:26:42.857143
2024-05-06 19:26:16,209 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:26:16,210 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:26:41,061 [INFO] core.trainer: Epoch-(7): [100/300] Time 0.240 (0.248) Calc 0.087 (0.087) Data 0.001 (0.009) Loss 4.676 (4.345) Acc@1 68.000 (73.133)
2024-05-06 19:27:05,160 [INFO] core.trainer: Epoch-(7): [200/300] Time 0.241 (0.244) Calc 0.088 (0.087) Data 0.001 (0.005) Loss 3.910 (4.279) Acc@1 68.000 (73.747)
2024-05-06 19:27:29,235 [INFO] core.trainer: Epoch-(7): [300/300] Time 0.240 (0.243) Calc 0.088 (0.086) Data 0.000 (0.003) Loss 3.937 (4.241) Acc@1 76.000 (74.378)
2024-05-06 19:27:29,358 [INFO] core.trainer: * Acc@1 74.378
2024-05-06 19:27:29,360 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:27:32,630 [INFO] core.trainer: Epoch-(7): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 52.000 (65.733)
2024-05-06 19:27:35,908 [INFO] core.trainer: Epoch-(7): [200/200] Time 0.032 (0.032) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 65.333 (65.213)
2024-05-06 19:27:35,911 [INFO] core.trainer: * Acc@1 65.213 Best acc 63.313
2024-05-06 19:27:35,913 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:27:39,213 [INFO] core.trainer: Epoch-(7): [100/200] Time 0.034 (0.033) Calc 0.031 (0.030) Data 0.002 (0.001) Acc@1 61.333 (67.853)
2024-05-06 19:27:42,501 [INFO] core.trainer: Epoch-(7): [200/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 65.333 (66.067)
2024-05-06 19:27:42,504 [INFO] core.trainer: * Acc@1 66.067 Best acc 64.400
2024-05-06 19:27:42,505 [INFO] core.trainer: * Time: 0:11:34/1:26:45
2024-05-06 19:27:42,739 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:27:42,741 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:28:07,573 [INFO] core.trainer: Epoch-(8): [100/300] Time 0.241 (0.248) Calc 0.088 (0.085) Data 0.001 (0.008) Loss 4.125 (3.979) Acc@1 61.333 (76.093)
2024-05-06 19:28:31,680 [INFO] core.trainer: Epoch-(8): [200/300] Time 0.240 (0.244) Calc 0.084 (0.086) Data 0.001 (0.005) Loss 4.719 (3.941) Acc@1 62.667 (76.573)
2024-05-06 19:28:55,764 [INFO] core.trainer: Epoch-(8): [300/300] Time 0.240 (0.243) Calc 0.088 (0.086) Data 0.000 (0.003) Loss 2.867 (3.899) Acc@1 82.667 (76.573)
2024-05-06 19:28:55,894 [INFO] core.trainer: * Acc@1 76.573
2024-05-06 19:28:55,895 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:28:59,158 [INFO] core.trainer: Epoch-(8): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 64.000 (67.520)
2024-05-06 19:29:02,450 [INFO] core.trainer: Epoch-(8): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 56.000 (66.887)
2024-05-06 19:29:02,452 [INFO] core.trainer: * Acc@1 66.887 Best acc 65.213
2024-05-06 19:29:02,453 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:29:05,743 [INFO] core.trainer: Epoch-(8): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 73.333 (68.240)
2024-05-06 19:29:09,023 [INFO] core.trainer: Epoch-(8): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 62.667 (68.787)
2024-05-06 19:29:09,026 [INFO] core.trainer: * Acc@1 68.787 Best acc 66.067
2024-05-06 19:29:09,027 [INFO] core.trainer: * Time: 0:13:00/1:26:40
2024-05-06 19:29:09,267 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:29:09,269 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:29:34,058 [INFO] core.trainer: Epoch-(9): [100/300] Time 0.239 (0.247) Calc 0.079 (0.087) Data 0.001 (0.008) Loss 3.700 (3.816) Acc@1 81.333 (75.933)
2024-05-06 19:29:58,159 [INFO] core.trainer: Epoch-(9): [200/300] Time 0.240 (0.244) Calc 0.090 (0.087) Data 0.001 (0.004) Loss 3.342 (3.725) Acc@1 82.667 (77.087)
2024-05-06 19:30:22,265 [INFO] core.trainer: Epoch-(9): [300/300] Time 0.240 (0.243) Calc 0.089 (0.087) Data 0.000 (0.003) Loss 3.335 (3.695) Acc@1 81.333 (77.422)
2024-05-06 19:30:22,388 [INFO] core.trainer: * Acc@1 77.422
2024-05-06 19:30:22,390 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:30:25,687 [INFO] core.trainer: Epoch-(9): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 64.000 (69.587)
2024-05-06 19:30:28,976 [INFO] core.trainer: Epoch-(9): [200/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 73.333 (68.833)
2024-05-06 19:30:28,979 [INFO] core.trainer: * Acc@1 68.833 Best acc 66.887
2024-05-06 19:30:28,980 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:30:32,247 [INFO] core.trainer: Epoch-(9): [100/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 53.333 (67.693)
2024-05-06 19:30:35,526 [INFO] core.trainer: Epoch-(9): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 70.667 (68.167)
2024-05-06 19:30:35,530 [INFO] core.trainer: * Acc@1 68.167 Best acc 68.787
2024-05-06 19:30:35,531 [INFO] core.trainer: * Time: 0:14:27/1:26:42
2024-05-06 19:30:35,773 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:30:35,775 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:31:00,662 [INFO] core.trainer: Epoch-(10): [100/300] Time 0.241 (0.248) Calc 0.089 (0.087) Data 0.001 (0.009) Loss 3.527 (3.504) Acc@1 72.000 (78.680)
2024-05-06 19:31:24,779 [INFO] core.trainer: Epoch-(10): [200/300] Time 0.241 (0.245) Calc 0.088 (0.087) Data 0.001 (0.005) Loss 2.904 (3.473) Acc@1 89.333 (79.180)
2024-05-06 19:31:48,912 [INFO] core.trainer: Epoch-(10): [300/300] Time 0.240 (0.243) Calc 0.088 (0.087) Data 0.000 (0.003) Loss 2.831 (3.418) Acc@1 90.667 (79.644)
2024-05-06 19:31:49,040 [INFO] core.trainer: * Acc@1 79.644
2024-05-06 19:31:49,042 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:31:52,324 [INFO] core.trainer: Epoch-(10): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 78.667 (69.413)
2024-05-06 19:31:55,612 [INFO] core.trainer: Epoch-(10): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 60.000 (69.307)
2024-05-06 19:31:55,615 [INFO] core.trainer: * Acc@1 69.307 Best acc 68.833
2024-05-06 19:31:55,616 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:31:58,915 [INFO] core.trainer: Epoch-(10): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 73.333 (69.040)
2024-05-06 19:32:02,207 [INFO] core.trainer: Epoch-(10): [200/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 82.667 (69.080)
2024-05-06 19:32:02,210 [INFO] core.trainer: * Acc@1 69.080 Best acc 68.167
2024-05-06 19:32:02,212 [INFO] core.trainer: * Time: 0:15:53/1:26:38.181818
2024-05-06 19:32:02,549 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:32:02,551 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:32:27,389 [INFO] core.trainer: Epoch-(11): [100/300] Time 0.240 (0.248) Calc 0.088 (0.088) Data 0.001 (0.008) Loss 3.464 (3.258) Acc@1 80.000 (80.573)
2024-05-06 19:32:51,512 [INFO] core.trainer: Epoch-(11): [200/300] Time 0.241 (0.244) Calc 0.088 (0.088) Data 0.001 (0.004) Loss 3.411 (3.243) Acc@1 81.333 (80.833)
2024-05-06 19:33:15,609 [INFO] core.trainer: Epoch-(11): [300/300] Time 0.239 (0.243) Calc 0.087 (0.088) Data 0.000 (0.003) Loss 3.035 (3.231) Acc@1 85.333 (80.849)
2024-05-06 19:33:15,756 [INFO] core.trainer: * Acc@1 80.849
2024-05-06 19:33:15,757 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:33:19,022 [INFO] core.trainer: Epoch-(11): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 69.333 (70.867)
2024-05-06 19:33:22,292 [INFO] core.trainer: Epoch-(11): [200/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 70.667 (70.973)
2024-05-06 19:33:22,295 [INFO] core.trainer: * Acc@1 70.973 Best acc 69.307
2024-05-06 19:33:22,296 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:33:25,607 [INFO] core.trainer: Epoch-(11): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 73.333 (71.187)
2024-05-06 19:33:28,887 [INFO] core.trainer: Epoch-(11): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 68.000 (71.227)
2024-05-06 19:33:28,890 [INFO] core.trainer: * Acc@1 71.227 Best acc 69.080
2024-05-06 19:33:28,891 [INFO] core.trainer: * Time: 0:17:20/1:26:40
2024-05-06 19:33:29,126 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:33:29,128 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:33:54,021 [INFO] core.trainer: Epoch-(12): [100/300] Time 0.241 (0.248) Calc 0.088 (0.086) Data 0.001 (0.009) Loss 2.339 (3.014) Acc@1 78.667 (82.320)
2024-05-06 19:34:18,134 [INFO] core.trainer: Epoch-(12): [200/300] Time 0.241 (0.245) Calc 0.088 (0.087) Data 0.001 (0.005) Loss 3.194 (3.018) Acc@1 90.667 (82.167)
2024-05-06 19:34:42,233 [INFO] core.trainer: Epoch-(12): [300/300] Time 0.240 (0.243) Calc 0.087 (0.087) Data 0.000 (0.004) Loss 3.583 (3.007) Acc@1 76.000 (82.133)
2024-05-06 19:34:42,367 [INFO] core.trainer: * Acc@1 82.133
2024-05-06 19:34:42,368 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:34:45,646 [INFO] core.trainer: Epoch-(12): [100/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 72.000 (69.507)
2024-05-06 19:34:49,179 [INFO] core.trainer: Epoch-(12): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 66.667 (69.827)
2024-05-06 19:34:49,182 [INFO] core.trainer: * Acc@1 69.827 Best acc 70.973
2024-05-06 19:34:49,183 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:34:52,450 [INFO] core.trainer: Epoch-(12): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 77.333 (69.987)
2024-05-06 19:34:55,719 [INFO] core.trainer: Epoch-(12): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 73.333 (69.680)
2024-05-06 19:34:55,722 [INFO] core.trainer: * Acc@1 69.680 Best acc 71.227
2024-05-06 19:34:55,723 [INFO] core.trainer: * Time: 0:18:47/1:26:41.538462
2024-05-06 19:34:55,846 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:34:55,847 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:35:20,672 [INFO] core.trainer: Epoch-(13): [100/300] Time 0.241 (0.248) Calc 0.088 (0.086) Data 0.001 (0.008) Loss 2.759 (2.950) Acc@1 89.333 (81.373)
2024-05-06 19:35:44,789 [INFO] core.trainer: Epoch-(13): [200/300] Time 0.241 (0.244) Calc 0.088 (0.087) Data 0.001 (0.005) Loss 3.242 (2.870) Acc@1 84.000 (82.253)
2024-05-06 19:36:08,899 [INFO] core.trainer: Epoch-(13): [300/300] Time 0.241 (0.243) Calc 0.090 (0.087) Data 0.000 (0.003) Loss 2.547 (2.848) Acc@1 90.667 (82.329)
2024-05-06 19:36:09,036 [INFO] core.trainer: * Acc@1 82.329
2024-05-06 19:36:09,038 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:36:12,322 [INFO] core.trainer: Epoch-(13): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 60.000 (69.827)
2024-05-06 19:36:15,607 [INFO] core.trainer: Epoch-(13): [200/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 70.667 (69.993)
2024-05-06 19:36:15,610 [INFO] core.trainer: * Acc@1 69.993 Best acc 70.973
2024-05-06 19:36:15,611 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:36:18,879 [INFO] core.trainer: Epoch-(13): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 80.000 (71.360)
2024-05-06 19:36:22,173 [INFO] core.trainer: Epoch-(13): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 68.000 (70.993)
2024-05-06 19:36:22,177 [INFO] core.trainer: * Acc@1 70.993 Best acc 71.227
2024-05-06 19:36:22,178 [INFO] core.trainer: * Time: 0:20:13/1:26:38.571429
2024-05-06 19:36:22,304 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:36:22,306 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:36:47,224 [INFO] core.trainer: Epoch-(14): [100/300] Time 0.241 (0.249) Calc 0.088 (0.088) Data 0.001 (0.009) Loss 2.984 (2.759) Acc@1 85.333 (82.333)
2024-05-06 19:37:11,379 [INFO] core.trainer: Epoch-(14): [200/300] Time 0.241 (0.245) Calc 0.090 (0.088) Data 0.001 (0.005) Loss 2.464 (2.762) Acc@1 77.333 (82.767)
2024-05-06 19:37:35,490 [INFO] core.trainer: Epoch-(14): [300/300] Time 0.239 (0.244) Calc 0.084 (0.088) Data 0.000 (0.004) Loss 2.163 (2.754) Acc@1 88.000 (83.236)
2024-05-06 19:37:35,625 [INFO] core.trainer: * Acc@1 83.236
2024-05-06 19:37:35,627 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:37:38,899 [INFO] core.trainer: Epoch-(14): [100/200] Time 0.033 (0.032) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 85.333 (72.173)
2024-05-06 19:37:42,169 [INFO] core.trainer: Epoch-(14): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 69.333 (71.607)
2024-05-06 19:37:42,172 [INFO] core.trainer: * Acc@1 71.607 Best acc 70.973
2024-05-06 19:37:42,174 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:37:45,454 [INFO] core.trainer: Epoch-(14): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 74.667 (69.893)
2024-05-06 19:37:48,735 [INFO] core.trainer: Epoch-(14): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 64.000 (70.447)
2024-05-06 19:37:48,738 [INFO] core.trainer: * Acc@1 70.447 Best acc 71.227
2024-05-06 19:37:48,739 [INFO] core.trainer: * Time: 0:21:40/1:26:40
2024-05-06 19:37:48,974 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:37:48,976 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:38:13,833 [INFO] core.trainer: Epoch-(15): [100/300] Time 0.241 (0.248) Calc 0.088 (0.088) Data 0.001 (0.008) Loss 2.469 (2.606) Acc@1 90.667 (84.427)
2024-05-06 19:38:37,965 [INFO] core.trainer: Epoch-(15): [200/300] Time 0.240 (0.245) Calc 0.088 (0.088) Data 0.001 (0.005) Loss 2.910 (2.584) Acc@1 93.333 (84.613)
2024-05-06 19:39:02,074 [INFO] core.trainer: Epoch-(15): [300/300] Time 0.240 (0.243) Calc 0.086 (0.088) Data 0.000 (0.003) Loss 2.833 (2.578) Acc@1 82.667 (84.458)
2024-05-06 19:39:02,207 [INFO] core.trainer: * Acc@1 84.458
2024-05-06 19:39:02,208 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:39:05,482 [INFO] core.trainer: Epoch-(15): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 72.000 (72.653)
2024-05-06 19:39:08,770 [INFO] core.trainer: Epoch-(15): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 74.667 (73.553)
2024-05-06 19:39:08,773 [INFO] core.trainer: * Acc@1 73.553 Best acc 71.607
2024-05-06 19:39:08,774 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:39:12,057 [INFO] core.trainer: Epoch-(15): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 72.000 (72.987)
2024-05-06 19:39:15,344 [INFO] core.trainer: Epoch-(15): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 69.333 (73.027)
2024-05-06 19:39:15,347 [INFO] core.trainer: * Acc@1 73.027 Best acc 70.447
2024-05-06 19:39:15,348 [INFO] core.trainer: * Time: 0:23:06/1:26:37.500000
2024-05-06 19:39:15,586 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:39:15,588 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:39:40,495 [INFO] core.trainer: Epoch-(16): [100/300] Time 0.240 (0.249) Calc 0.080 (0.085) Data 0.001 (0.009) Loss 2.410 (2.495) Acc@1 93.333 (84.893)
2024-05-06 19:40:04,629 [INFO] core.trainer: Epoch-(16): [200/300] Time 0.241 (0.245) Calc 0.089 (0.086) Data 0.001 (0.005) Loss 1.979 (2.481) Acc@1 88.000 (85.093)
2024-05-06 19:40:28,752 [INFO] core.trainer: Epoch-(16): [300/300] Time 0.240 (0.243) Calc 0.087 (0.087) Data 0.000 (0.004) Loss 2.373 (2.491) Acc@1 78.667 (85.049)
2024-05-06 19:40:28,891 [INFO] core.trainer: * Acc@1 85.049
2024-05-06 19:40:28,893 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:40:32,181 [INFO] core.trainer: Epoch-(16): [100/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 73.333 (72.640)
2024-05-06 19:40:35,459 [INFO] core.trainer: Epoch-(16): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 78.667 (72.687)
2024-05-06 19:40:35,462 [INFO] core.trainer: * Acc@1 72.687 Best acc 73.553
2024-05-06 19:40:35,463 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:40:38,731 [INFO] core.trainer: Epoch-(16): [100/200] Time 0.033 (0.032) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 66.667 (72.893)
2024-05-06 19:40:42,023 [INFO] core.trainer: Epoch-(16): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 73.333 (73.740)
2024-05-06 19:40:42,026 [INFO] core.trainer: * Acc@1 73.740 Best acc 73.027
2024-05-06 19:40:42,027 [INFO] core.trainer: * Time: 0:24:33/1:26:38.823529
2024-05-06 19:40:42,168 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:40:42,170 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:41:06,955 [INFO] core.trainer: Epoch-(17): [100/300] Time 0.240 (0.247) Calc 0.089 (0.084) Data 0.001 (0.008) Loss 2.623 (2.523) Acc@1 80.000 (85.080)
2024-05-06 19:41:31,054 [INFO] core.trainer: Epoch-(17): [200/300] Time 0.241 (0.244) Calc 0.088 (0.086) Data 0.001 (0.004) Loss 1.859 (2.480) Acc@1 96.000 (85.780)
2024-05-06 19:41:55,184 [INFO] core.trainer: Epoch-(17): [300/300] Time 0.239 (0.243) Calc 0.082 (0.086) Data 0.000 (0.003) Loss 2.370 (2.468) Acc@1 80.000 (86.062)
2024-05-06 19:41:55,318 [INFO] core.trainer: * Acc@1 86.062
2024-05-06 19:41:55,319 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:41:58,606 [INFO] core.trainer: Epoch-(17): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 62.667 (75.893)
2024-05-06 19:42:01,913 [INFO] core.trainer: Epoch-(17): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 77.333 (75.193)
2024-05-06 19:42:01,916 [INFO] core.trainer: * Acc@1 75.193 Best acc 73.553
2024-05-06 19:42:01,917 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:42:05,230 [INFO] core.trainer: Epoch-(17): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 57.333 (73.253)
2024-05-06 19:42:08,511 [INFO] core.trainer: Epoch-(17): [200/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 70.667 (73.093)
2024-05-06 19:42:08,514 [INFO] core.trainer: * Acc@1 73.093 Best acc 73.027
2024-05-06 19:42:08,515 [INFO] core.trainer: * Time: 0:26:00/1:26:40
2024-05-06 19:42:08,761 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:42:08,763 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:42:33,806 [INFO] core.trainer: Epoch-(18): [100/300] Time 0.240 (0.250) Calc 0.088 (0.087) Data 0.001 (0.010) Loss 2.267 (2.351) Acc@1 82.667 (86.373)
2024-05-06 19:42:57,907 [INFO] core.trainer: Epoch-(18): [200/300] Time 0.240 (0.245) Calc 0.088 (0.087) Data 0.001 (0.006) Loss 2.729 (2.358) Acc@1 80.000 (86.360)
2024-05-06 19:43:22,032 [INFO] core.trainer: Epoch-(18): [300/300] Time 0.240 (0.244) Calc 0.080 (0.087) Data 0.000 (0.004) Loss 2.408 (2.352) Acc@1 84.000 (86.387)
2024-05-06 19:43:22,166 [INFO] core.trainer: * Acc@1 86.387
2024-05-06 19:43:22,168 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:43:25,459 [INFO] core.trainer: Epoch-(18): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 68.000 (74.307)
2024-05-06 19:43:28,759 [INFO] core.trainer: Epoch-(18): [200/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 68.000 (74.533)
2024-05-06 19:43:28,762 [INFO] core.trainer: * Acc@1 74.533 Best acc 75.193
2024-05-06 19:43:28,763 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:43:32,065 [INFO] core.trainer: Epoch-(18): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 73.333 (74.000)
2024-05-06 19:43:35,350 [INFO] core.trainer: Epoch-(18): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 81.333 (74.440)
2024-05-06 19:43:35,352 [INFO] core.trainer: * Acc@1 74.440 Best acc 73.093
2024-05-06 19:43:35,354 [INFO] core.trainer: * Time: 0:27:26/1:26:37.894737
2024-05-06 19:43:35,480 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:43:35,482 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:44:00,251 [INFO] core.trainer: Epoch-(19): [100/300] Time 0.240 (0.247) Calc 0.080 (0.085) Data 0.001 (0.008) Loss 2.002 (2.246) Acc@1 92.000 (86.347)
2024-05-06 19:44:24,336 [INFO] core.trainer: Epoch-(19): [200/300] Time 0.241 (0.244) Calc 0.084 (0.085) Data 0.001 (0.004) Loss 2.269 (2.255) Acc@1 88.000 (86.713)
2024-05-06 19:44:48,446 [INFO] core.trainer: Epoch-(19): [300/300] Time 0.239 (0.243) Calc 0.080 (0.085) Data 0.000 (0.003) Loss 2.355 (2.267) Acc@1 90.667 (86.529)
2024-05-06 19:44:48,592 [INFO] core.trainer: * Acc@1 86.529
2024-05-06 19:44:48,594 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:44:51,892 [INFO] core.trainer: Epoch-(19): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 66.667 (72.933)
2024-05-06 19:44:55,188 [INFO] core.trainer: Epoch-(19): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 68.000 (72.487)
2024-05-06 19:44:55,191 [INFO] core.trainer: * Acc@1 72.487 Best acc 75.193
2024-05-06 19:44:55,192 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:44:58,483 [INFO] core.trainer: Epoch-(19): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 46.667 (73.747)
2024-05-06 19:45:01,786 [INFO] core.trainer: Epoch-(19): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 62.667 (73.687)
2024-05-06 19:45:01,789 [INFO] core.trainer: * Acc@1 73.687 Best acc 73.093
2024-05-06 19:45:01,790 [INFO] core.trainer: * Time: 0:28:53/1:26:39
2024-05-06 19:45:01,921 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:45:01,923 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:45:26,777 [INFO] core.trainer: Epoch-(20): [100/300] Time 0.241 (0.248) Calc 0.088 (0.087) Data 0.001 (0.008) Loss 1.994 (2.269) Acc@1 92.000 (86.653)
2024-05-06 19:45:50,913 [INFO] core.trainer: Epoch-(20): [200/300] Time 0.241 (0.245) Calc 0.088 (0.087) Data 0.001 (0.005) Loss 1.722 (2.241) Acc@1 93.333 (86.500)
2024-05-06 19:46:15,032 [INFO] core.trainer: Epoch-(20): [300/300] Time 0.240 (0.243) Calc 0.088 (0.087) Data 0.000 (0.003) Loss 2.033 (2.228) Acc@1 89.333 (86.640)
2024-05-06 19:46:15,146 [INFO] core.trainer: * Acc@1 86.640
2024-05-06 19:46:15,148 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:46:18,442 [INFO] core.trainer: Epoch-(20): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 74.667 (73.640)
2024-05-06 19:46:21,751 [INFO] core.trainer: Epoch-(20): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 66.667 (73.567)
2024-05-06 19:46:21,754 [INFO] core.trainer: * Acc@1 73.567 Best acc 75.193
2024-05-06 19:46:21,755 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:46:25,045 [INFO] core.trainer: Epoch-(20): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 66.667 (73.227)
2024-05-06 19:46:28,329 [INFO] core.trainer: Epoch-(20): [200/200] Time 0.032 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 85.333 (73.673)
2024-05-06 19:46:28,331 [INFO] core.trainer: * Acc@1 73.673 Best acc 73.093
2024-05-06 19:46:28,332 [INFO] core.trainer: * Time: 0:30:19/1:26:37.142857
2024-05-06 19:46:28,553 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:46:28,555 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:46:53,426 [INFO] core.trainer: Epoch-(21): [100/300] Time 0.241 (0.248) Calc 0.088 (0.087) Data 0.001 (0.008) Loss 2.760 (2.149) Acc@1 72.000 (87.573)
2024-05-06 19:47:17,547 [INFO] core.trainer: Epoch-(21): [200/300] Time 0.241 (0.245) Calc 0.084 (0.087) Data 0.001 (0.005) Loss 2.005 (2.169) Acc@1 93.333 (87.187)
2024-05-06 19:47:41,656 [INFO] core.trainer: Epoch-(21): [300/300] Time 0.240 (0.243) Calc 0.083 (0.087) Data 0.000 (0.003) Loss 2.725 (2.139) Acc@1 78.667 (87.880)
2024-05-06 19:47:41,785 [INFO] core.trainer: * Acc@1 87.880
2024-05-06 19:47:41,787 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:47:45,104 [INFO] core.trainer: Epoch-(21): [100/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 72.000 (71.147)
2024-05-06 19:47:48,396 [INFO] core.trainer: Epoch-(21): [200/200] Time 0.032 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 80.000 (71.727)
2024-05-06 19:47:48,399 [INFO] core.trainer: * Acc@1 71.727 Best acc 75.193
2024-05-06 19:47:48,400 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:47:51,698 [INFO] core.trainer: Epoch-(21): [100/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 70.667 (72.973)
2024-05-06 19:47:54,994 [INFO] core.trainer: Epoch-(21): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 74.667 (73.653)
2024-05-06 19:47:54,997 [INFO] core.trainer: * Acc@1 73.653 Best acc 73.093
2024-05-06 19:47:54,998 [INFO] core.trainer: * Time: 0:31:46/1:26:38.181818
2024-05-06 19:47:55,127 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:47:55,129 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:48:19,971 [INFO] core.trainer: Epoch-(22): [100/300] Time 0.241 (0.248) Calc 0.081 (0.086) Data 0.001 (0.008) Loss 2.284 (2.064) Acc@1 74.667 (88.907)
2024-05-06 19:48:44,089 [INFO] core.trainer: Epoch-(22): [200/300] Time 0.241 (0.244) Calc 0.088 (0.087) Data 0.001 (0.005) Loss 2.130 (2.095) Acc@1 77.333 (88.320)
2024-05-06 19:49:08,167 [INFO] core.trainer: Epoch-(22): [300/300] Time 0.239 (0.243) Calc 0.079 (0.086) Data 0.000 (0.003) Loss 1.949 (2.085) Acc@1 93.333 (88.382)
2024-05-06 19:49:08,298 [INFO] core.trainer: * Acc@1 88.382
2024-05-06 19:49:08,300 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:49:11,595 [INFO] core.trainer: Epoch-(22): [100/200] Time 0.034 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 81.333 (72.667)
2024-05-06 19:49:14,916 [INFO] core.trainer: Epoch-(22): [200/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 70.667 (74.253)
2024-05-06 19:49:14,918 [INFO] core.trainer: * Acc@1 74.253 Best acc 75.193
2024-05-06 19:49:14,920 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:49:18,214 [INFO] core.trainer: Epoch-(22): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 69.333 (74.653)
2024-05-06 19:49:21,531 [INFO] core.trainer: Epoch-(22): [200/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 78.667 (74.460)
2024-05-06 19:49:21,534 [INFO] core.trainer: * Acc@1 74.460 Best acc 73.093
2024-05-06 19:49:21,536 [INFO] core.trainer: * Time: 0:33:13/1:26:39.130435
2024-05-06 19:49:21,688 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:49:21,690 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:49:46,651 [INFO] core.trainer: Epoch-(23): [100/300] Time 0.241 (0.249) Calc 0.089 (0.086) Data 0.001 (0.009) Loss 1.961 (2.073) Acc@1 90.667 (87.987)
2024-05-06 19:50:10,772 [INFO] core.trainer: Epoch-(23): [200/300] Time 0.241 (0.245) Calc 0.088 (0.086) Data 0.001 (0.005) Loss 2.354 (2.058) Acc@1 88.000 (88.647)
2024-05-06 19:50:34,870 [INFO] core.trainer: Epoch-(23): [300/300] Time 0.240 (0.244) Calc 0.087 (0.086) Data 0.000 (0.004) Loss 1.465 (2.040) Acc@1 90.667 (88.880)
2024-05-06 19:50:35,002 [INFO] core.trainer: * Acc@1 88.880
2024-05-06 19:50:35,004 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:50:38,309 [INFO] core.trainer: Epoch-(23): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 76.000 (74.707)
2024-05-06 19:50:41,612 [INFO] core.trainer: Epoch-(23): [200/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 80.000 (74.147)
2024-05-06 19:50:41,615 [INFO] core.trainer: * Acc@1 74.147 Best acc 75.193
2024-05-06 19:50:41,616 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:50:44,931 [INFO] core.trainer: Epoch-(23): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 68.000 (74.880)
2024-05-06 19:50:48,233 [INFO] core.trainer: Epoch-(23): [200/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 74.667 (74.360)
2024-05-06 19:50:48,236 [INFO] core.trainer: * Acc@1 74.360 Best acc 73.093
2024-05-06 19:50:48,237 [INFO] core.trainer: * Time: 0:34:39/1:26:37.500000
2024-05-06 19:50:48,362 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:50:48,364 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:51:13,158 [INFO] core.trainer: Epoch-(24): [100/300] Time 0.240 (0.248) Calc 0.079 (0.083) Data 0.001 (0.008) Loss 1.959 (2.056) Acc@1 77.333 (87.080)
2024-05-06 19:51:37,241 [INFO] core.trainer: Epoch-(24): [200/300] Time 0.241 (0.244) Calc 0.088 (0.084) Data 0.001 (0.005) Loss 2.075 (2.048) Acc@1 82.667 (87.613)
2024-05-06 19:52:01,347 [INFO] core.trainer: Epoch-(24): [300/300] Time 0.240 (0.243) Calc 0.080 (0.085) Data 0.000 (0.003) Loss 1.923 (2.031) Acc@1 97.333 (88.089)
2024-05-06 19:52:01,488 [INFO] core.trainer: * Acc@1 88.089
2024-05-06 19:52:01,490 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:52:04,766 [INFO] core.trainer: Epoch-(24): [100/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 78.667 (73.813)
2024-05-06 19:52:08,063 [INFO] core.trainer: Epoch-(24): [200/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 82.667 (74.753)
2024-05-06 19:52:08,065 [INFO] core.trainer: * Acc@1 74.753 Best acc 75.193
2024-05-06 19:52:08,067 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:52:11,336 [INFO] core.trainer: Epoch-(24): [100/200] Time 0.033 (0.032) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 73.333 (74.200)
2024-05-06 19:52:14,606 [INFO] core.trainer: Epoch-(24): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 77.333 (75.087)
2024-05-06 19:52:14,609 [INFO] core.trainer: * Acc@1 75.087 Best acc 73.093
2024-05-06 19:52:14,610 [INFO] core.trainer: * Time: 0:36:06/1:26:38.400000
2024-05-06 19:52:14,757 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:52:14,759 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:52:39,644 [INFO] core.trainer: Epoch-(25): [100/300] Time 0.242 (0.248) Calc 0.090 (0.087) Data 0.001 (0.008) Loss 2.565 (1.966) Acc@1 84.000 (89.227)
2024-05-06 19:53:03,716 [INFO] core.trainer: Epoch-(25): [200/300] Time 0.240 (0.244) Calc 0.087 (0.085) Data 0.001 (0.005) Loss 1.653 (1.983) Acc@1 86.667 (88.927)
2024-05-06 19:53:27,806 [INFO] core.trainer: Epoch-(25): [300/300] Time 0.240 (0.243) Calc 0.088 (0.085) Data 0.000 (0.003) Loss 1.788 (2.001) Acc@1 94.667 (88.484)
2024-05-06 19:53:27,943 [INFO] core.trainer: * Acc@1 88.484
2024-05-06 19:53:27,945 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:53:31,229 [INFO] core.trainer: Epoch-(25): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 65.333 (73.400)
2024-05-06 19:53:34,528 [INFO] core.trainer: Epoch-(25): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 61.333 (73.033)
2024-05-06 19:53:34,531 [INFO] core.trainer: * Acc@1 73.033 Best acc 75.193
2024-05-06 19:53:34,532 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:53:37,826 [INFO] core.trainer: Epoch-(25): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 78.667 (75.267)
2024-05-06 19:53:41,109 [INFO] core.trainer: Epoch-(25): [200/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 72.000 (74.933)
2024-05-06 19:53:41,112 [INFO] core.trainer: * Acc@1 74.933 Best acc 73.093
2024-05-06 19:53:41,114 [INFO] core.trainer: * Time: 0:37:32/1:26:36.923077
2024-05-06 19:53:41,239 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:53:41,241 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:54:06,139 [INFO] core.trainer: Epoch-(26): [100/300] Time 0.240 (0.249) Calc 0.089 (0.088) Data 0.001 (0.009) Loss 2.193 (1.933) Acc@1 89.333 (88.533)
2024-05-06 19:54:30,258 [INFO] core.trainer: Epoch-(26): [200/300] Time 0.240 (0.245) Calc 0.088 (0.087) Data 0.001 (0.005) Loss 1.846 (1.947) Acc@1 92.000 (88.800)
2024-05-06 19:54:54,360 [INFO] core.trainer: Epoch-(26): [300/300] Time 0.240 (0.243) Calc 0.089 (0.087) Data 0.000 (0.004) Loss 1.800 (1.968) Acc@1 92.000 (88.609)
2024-05-06 19:54:54,489 [INFO] core.trainer: * Acc@1 88.609
2024-05-06 19:54:54,490 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:54:57,774 [INFO] core.trainer: Epoch-(26): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 82.667 (74.373)
2024-05-06 19:55:01,035 [INFO] core.trainer: Epoch-(26): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 72.000 (74.093)
2024-05-06 19:55:01,037 [INFO] core.trainer: * Acc@1 74.093 Best acc 75.193
2024-05-06 19:55:01,038 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:55:04,314 [INFO] core.trainer: Epoch-(26): [100/200] Time 0.033 (0.032) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 88.000 (73.573)
2024-05-06 19:55:07,607 [INFO] core.trainer: Epoch-(26): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 81.333 (73.793)
2024-05-06 19:55:07,610 [INFO] core.trainer: * Acc@1 73.793 Best acc 73.093
2024-05-06 19:55:07,611 [INFO] core.trainer: * Time: 0:38:59/1:26:37.777778
2024-05-06 19:55:07,737 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:55:07,738 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:55:32,610 [INFO] core.trainer: Epoch-(27): [100/300] Time 0.241 (0.248) Calc 0.088 (0.087) Data 0.002 (0.008) Loss 2.038 (1.852) Acc@1 88.000 (90.013)
2024-05-06 19:55:56,739 [INFO] core.trainer: Epoch-(27): [200/300] Time 0.240 (0.245) Calc 0.088 (0.087) Data 0.001 (0.005) Loss 1.860 (1.895) Acc@1 96.000 (88.927)
2024-05-06 19:56:20,866 [INFO] core.trainer: Epoch-(27): [300/300] Time 0.240 (0.243) Calc 0.085 (0.087) Data 0.000 (0.003) Loss 2.390 (1.901) Acc@1 73.333 (88.893)
2024-05-06 19:56:21,008 [INFO] core.trainer: * Acc@1 88.893
2024-05-06 19:56:21,009 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:56:24,284 [INFO] core.trainer: Epoch-(27): [100/200] Time 0.033 (0.032) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 76.000 (72.973)
2024-05-06 19:56:27,562 [INFO] core.trainer: Epoch-(27): [200/200] Time 0.034 (0.032) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 73.333 (73.840)
2024-05-06 19:56:27,565 [INFO] core.trainer: * Acc@1 73.840 Best acc 75.193
2024-05-06 19:56:27,566 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:56:30,846 [INFO] core.trainer: Epoch-(27): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 69.333 (73.187)
2024-05-06 19:56:34,136 [INFO] core.trainer: Epoch-(27): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 68.000 (73.013)
2024-05-06 19:56:34,138 [INFO] core.trainer: * Acc@1 73.013 Best acc 73.093
2024-05-06 19:56:34,139 [INFO] core.trainer: * Time: 0:40:25/1:26:36.428571
2024-05-06 19:56:34,269 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:56:34,271 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:56:59,170 [INFO] core.trainer: Epoch-(28): [100/300] Time 0.241 (0.249) Calc 0.093 (0.086) Data 0.001 (0.009) Loss 1.371 (1.877) Acc@1 97.333 (87.293)
2024-05-06 19:57:23,288 [INFO] core.trainer: Epoch-(28): [200/300] Time 0.241 (0.245) Calc 0.085 (0.085) Data 0.001 (0.005) Loss 1.670 (1.869) Acc@1 93.333 (87.833)
2024-05-06 19:57:47,399 [INFO] core.trainer: Epoch-(28): [300/300] Time 0.240 (0.243) Calc 0.086 (0.086) Data 0.000 (0.004) Loss 2.186 (1.861) Acc@1 88.000 (88.271)
2024-05-06 19:57:47,529 [INFO] core.trainer: * Acc@1 88.271
2024-05-06 19:57:47,531 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:57:50,804 [INFO] core.trainer: Epoch-(28): [100/200] Time 0.033 (0.032) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 76.000 (74.680)
2024-05-06 19:57:54,106 [INFO] core.trainer: Epoch-(28): [200/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 88.000 (74.853)
2024-05-06 19:57:54,109 [INFO] core.trainer: * Acc@1 74.853 Best acc 75.193
2024-05-06 19:57:54,111 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:57:57,417 [INFO] core.trainer: Epoch-(28): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 70.667 (73.440)
2024-05-06 19:58:00,702 [INFO] core.trainer: Epoch-(28): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 81.333 (74.300)
2024-05-06 19:58:00,705 [INFO] core.trainer: * Acc@1 74.300 Best acc 73.093
2024-05-06 19:58:00,706 [INFO] core.trainer: * Time: 0:41:52/1:26:37.241379
2024-05-06 19:58:00,831 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:58:00,832 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:58:25,706 [INFO] core.trainer: Epoch-(29): [100/300] Time 0.240 (0.248) Calc 0.087 (0.087) Data 0.001 (0.009) Loss 1.842 (1.821) Acc@1 90.667 (89.813)
2024-05-06 19:58:49,820 [INFO] core.trainer: Epoch-(29): [200/300] Time 0.241 (0.245) Calc 0.087 (0.087) Data 0.000 (0.005) Loss 1.817 (1.816) Acc@1 84.000 (89.740)
2024-05-06 19:59:13,923 [INFO] core.trainer: Epoch-(29): [300/300] Time 0.240 (0.243) Calc 0.084 (0.087) Data 0.000 (0.003) Loss 1.796 (1.832) Acc@1 97.333 (89.658)
2024-05-06 19:59:14,060 [INFO] core.trainer: * Acc@1 89.658
2024-05-06 19:59:14,062 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 19:59:17,376 [INFO] core.trainer: Epoch-(29): [100/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.000 (0.001) Acc@1 86.667 (73.440)
2024-05-06 19:59:20,704 [INFO] core.trainer: Epoch-(29): [200/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 76.000 (73.933)
2024-05-06 19:59:20,707 [INFO] core.trainer: * Acc@1 73.933 Best acc 75.193
2024-05-06 19:59:20,708 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 19:59:23,984 [INFO] core.trainer: Epoch-(29): [100/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 56.000 (73.813)
2024-05-06 19:59:27,272 [INFO] core.trainer: Epoch-(29): [200/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 64.000 (73.167)
2024-05-06 19:59:27,275 [INFO] core.trainer: * Acc@1 73.167 Best acc 73.093
2024-05-06 19:59:27,276 [INFO] core.trainer: * Time: 0:43:18/1:26:36
2024-05-06 19:59:27,407 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 19:59:27,409 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 19:59:52,302 [INFO] core.trainer: Epoch-(30): [100/300] Time 0.241 (0.249) Calc 0.088 (0.087) Data 0.001 (0.009) Loss 2.256 (1.859) Acc@1 81.333 (89.747)
2024-05-06 20:00:16,420 [INFO] core.trainer: Epoch-(30): [200/300] Time 0.241 (0.245) Calc 0.089 (0.087) Data 0.001 (0.005) Loss 2.069 (1.839) Acc@1 85.333 (89.520)
2024-05-06 20:00:40,545 [INFO] core.trainer: Epoch-(30): [300/300] Time 0.240 (0.243) Calc 0.089 (0.087) Data 0.000 (0.003) Loss 2.126 (1.835) Acc@1 78.667 (89.560)
2024-05-06 20:00:40,670 [INFO] core.trainer: * Acc@1 89.560
2024-05-06 20:00:40,671 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:00:43,961 [INFO] core.trainer: Epoch-(30): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 70.667 (76.533)
2024-05-06 20:00:47,245 [INFO] core.trainer: Epoch-(30): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 70.667 (76.420)
2024-05-06 20:00:47,248 [INFO] core.trainer: * Acc@1 76.420 Best acc 75.193
2024-05-06 20:00:47,249 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:00:50,536 [INFO] core.trainer: Epoch-(30): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 89.333 (75.747)
2024-05-06 20:00:53,840 [INFO] core.trainer: Epoch-(30): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 66.667 (75.793)
2024-05-06 20:00:53,843 [INFO] core.trainer: * Acc@1 75.793 Best acc 73.093
2024-05-06 20:00:53,844 [INFO] core.trainer: * Time: 0:44:45/1:26:36.774194
2024-05-06 20:00:54,173 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:00:54,175 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 20:01:19,080 [INFO] core.trainer: Epoch-(31): [100/300] Time 0.240 (0.249) Calc 0.087 (0.087) Data 0.001 (0.009) Loss 2.100 (1.778) Acc@1 86.667 (90.053)
2024-05-06 20:01:43,198 [INFO] core.trainer: Epoch-(31): [200/300] Time 0.240 (0.245) Calc 0.084 (0.087) Data 0.001 (0.005) Loss 1.749 (1.803) Acc@1 93.333 (89.953)
2024-05-06 20:02:07,303 [INFO] core.trainer: Epoch-(31): [300/300] Time 0.240 (0.243) Calc 0.088 (0.087) Data 0.000 (0.003) Loss 2.141 (1.812) Acc@1 89.333 (89.809)
2024-05-06 20:02:07,433 [INFO] core.trainer: * Acc@1 89.809
2024-05-06 20:02:07,435 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:02:10,733 [INFO] core.trainer: Epoch-(31): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 77.333 (75.440)
2024-05-06 20:02:14,041 [INFO] core.trainer: Epoch-(31): [200/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 68.000 (75.813)
2024-05-06 20:02:14,044 [INFO] core.trainer: * Acc@1 75.813 Best acc 76.420
2024-05-06 20:02:14,045 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:02:17,330 [INFO] core.trainer: Epoch-(31): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 74.667 (75.333)
2024-05-06 20:02:20,632 [INFO] core.trainer: Epoch-(31): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 68.000 (75.127)
2024-05-06 20:02:20,635 [INFO] core.trainer: * Acc@1 75.127 Best acc 75.793
2024-05-06 20:02:20,636 [INFO] core.trainer: * Time: 0:46:12/1:26:37.500000
2024-05-06 20:02:20,791 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:02:20,793 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 20:02:45,624 [INFO] core.trainer: Epoch-(32): [100/300] Time 0.241 (0.248) Calc 0.087 (0.088) Data 0.001 (0.008) Loss 1.604 (1.785) Acc@1 94.667 (90.040)
2024-05-06 20:03:09,751 [INFO] core.trainer: Epoch-(32): [200/300] Time 0.240 (0.244) Calc 0.092 (0.088) Data 0.001 (0.004) Loss 1.833 (1.773) Acc@1 88.000 (90.180)
2024-05-06 20:03:33,858 [INFO] core.trainer: Epoch-(32): [300/300] Time 0.240 (0.243) Calc 0.088 (0.087) Data 0.000 (0.003) Loss 1.968 (1.801) Acc@1 93.333 (89.582)
2024-05-06 20:03:33,995 [INFO] core.trainer: * Acc@1 89.582
2024-05-06 20:03:33,996 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:03:37,285 [INFO] core.trainer: Epoch-(32): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 61.333 (74.307)
2024-05-06 20:03:40,597 [INFO] core.trainer: Epoch-(32): [200/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 62.667 (74.107)
2024-05-06 20:03:40,599 [INFO] core.trainer: * Acc@1 74.107 Best acc 76.420
2024-05-06 20:03:40,601 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:03:43,879 [INFO] core.trainer: Epoch-(32): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 65.333 (75.373)
2024-05-06 20:03:47,184 [INFO] core.trainer: Epoch-(32): [200/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 81.333 (74.780)
2024-05-06 20:03:47,187 [INFO] core.trainer: * Acc@1 74.780 Best acc 75.793
2024-05-06 20:03:47,188 [INFO] core.trainer: * Time: 0:47:38/1:26:36.363636
2024-05-06 20:03:47,338 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:03:47,340 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 20:04:12,194 [INFO] core.trainer: Epoch-(33): [100/300] Time 0.241 (0.248) Calc 0.088 (0.087) Data 0.001 (0.008) Loss 1.624 (1.679) Acc@1 90.667 (90.373)
2024-05-06 20:04:36,321 [INFO] core.trainer: Epoch-(33): [200/300] Time 0.241 (0.244) Calc 0.088 (0.087) Data 0.001 (0.004) Loss 1.297 (1.717) Acc@1 94.667 (90.107)
2024-05-06 20:05:00,437 [INFO] core.trainer: Epoch-(33): [300/300] Time 0.240 (0.243) Calc 0.088 (0.087) Data 0.000 (0.003) Loss 1.289 (1.735) Acc@1 96.000 (90.076)
2024-05-06 20:05:00,576 [INFO] core.trainer: * Acc@1 90.076
2024-05-06 20:05:00,577 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:05:03,839 [INFO] core.trainer: Epoch-(33): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 61.333 (75.160)
2024-05-06 20:05:07,093 [INFO] core.trainer: Epoch-(33): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 80.000 (74.627)
2024-05-06 20:05:07,096 [INFO] core.trainer: * Acc@1 74.627 Best acc 76.420
2024-05-06 20:05:07,097 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:05:10,363 [INFO] core.trainer: Epoch-(33): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 77.333 (75.880)
2024-05-06 20:05:13,675 [INFO] core.trainer: Epoch-(33): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 74.667 (76.107)
2024-05-06 20:05:13,678 [INFO] core.trainer: * Acc@1 76.107 Best acc 75.793
2024-05-06 20:05:13,679 [INFO] core.trainer: * Time: 0:49:05/1:26:37.058824
2024-05-06 20:05:13,804 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:05:13,806 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 20:05:38,699 [INFO] core.trainer: Epoch-(34): [100/300] Time 0.240 (0.249) Calc 0.088 (0.087) Data 0.001 (0.009) Loss 1.480 (1.646) Acc@1 78.667 (90.013)
2024-05-06 20:06:02,801 [INFO] core.trainer: Epoch-(34): [200/300] Time 0.242 (0.245) Calc 0.089 (0.087) Data 0.001 (0.005) Loss 1.888 (1.720) Acc@1 82.667 (89.640)
2024-05-06 20:06:26,878 [INFO] core.trainer: Epoch-(34): [300/300] Time 0.239 (0.243) Calc 0.087 (0.087) Data 0.000 (0.004) Loss 1.733 (1.719) Acc@1 88.000 (89.933)
2024-05-06 20:06:27,022 [INFO] core.trainer: * Acc@1 89.933
2024-05-06 20:06:27,023 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:06:30,296 [INFO] core.trainer: Epoch-(34): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 85.333 (76.573)
2024-05-06 20:06:33,587 [INFO] core.trainer: Epoch-(34): [200/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 74.667 (77.307)
2024-05-06 20:06:33,590 [INFO] core.trainer: * Acc@1 77.307 Best acc 76.420
2024-05-06 20:06:33,592 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:06:36,880 [INFO] core.trainer: Epoch-(34): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 60.000 (76.360)
2024-05-06 20:06:40,158 [INFO] core.trainer: Epoch-(34): [200/200] Time 0.032 (0.032) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 92.000 (76.160)
2024-05-06 20:06:40,161 [INFO] core.trainer: * Acc@1 76.160 Best acc 75.793
2024-05-06 20:06:40,162 [INFO] core.trainer: * Time: 0:50:31/1:26:36
2024-05-06 20:06:40,398 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:06:40,399 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 20:07:05,194 [INFO] core.trainer: Epoch-(35): [100/300] Time 0.242 (0.248) Calc 0.087 (0.086) Data 0.001 (0.008) Loss 2.009 (1.689) Acc@1 85.333 (90.373)
2024-05-06 20:07:29,298 [INFO] core.trainer: Epoch-(35): [200/300] Time 0.241 (0.244) Calc 0.088 (0.087) Data 0.001 (0.004) Loss 1.411 (1.731) Acc@1 98.667 (89.800)
2024-05-06 20:07:53,409 [INFO] core.trainer: Epoch-(35): [300/300] Time 0.240 (0.243) Calc 0.087 (0.087) Data 0.000 (0.003) Loss 1.382 (1.730) Acc@1 92.000 (90.258)
2024-05-06 20:07:53,538 [INFO] core.trainer: * Acc@1 90.258
2024-05-06 20:07:53,539 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:07:56,820 [INFO] core.trainer: Epoch-(35): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 73.333 (76.720)
2024-05-06 20:08:00,106 [INFO] core.trainer: Epoch-(35): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 73.333 (76.793)
2024-05-06 20:08:00,109 [INFO] core.trainer: * Acc@1 76.793 Best acc 77.307
2024-05-06 20:08:00,110 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:08:03,392 [INFO] core.trainer: Epoch-(35): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 77.333 (75.133)
2024-05-06 20:08:06,686 [INFO] core.trainer: Epoch-(35): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 78.667 (75.300)
2024-05-06 20:08:06,689 [INFO] core.trainer: * Acc@1 75.300 Best acc 76.160
2024-05-06 20:08:06,690 [INFO] core.trainer: * Time: 0:51:58/1:26:36.666667
2024-05-06 20:08:06,888 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:08:06,890 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 20:08:31,739 [INFO] core.trainer: Epoch-(36): [100/300] Time 0.240 (0.248) Calc 0.086 (0.087) Data 0.001 (0.008) Loss 1.388 (1.622) Acc@1 85.333 (90.880)
2024-05-06 20:08:55,869 [INFO] core.trainer: Epoch-(36): [200/300] Time 0.241 (0.244) Calc 0.088 (0.087) Data 0.001 (0.005) Loss 1.503 (1.664) Acc@1 85.333 (90.527)
2024-05-06 20:09:19,988 [INFO] core.trainer: Epoch-(36): [300/300] Time 0.240 (0.243) Calc 0.088 (0.087) Data 0.000 (0.003) Loss 1.745 (1.674) Acc@1 89.333 (90.538)
2024-05-06 20:09:20,125 [INFO] core.trainer: * Acc@1 90.538
2024-05-06 20:09:20,127 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:09:23,425 [INFO] core.trainer: Epoch-(36): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 66.667 (75.560)
2024-05-06 20:09:26,716 [INFO] core.trainer: Epoch-(36): [200/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 72.000 (75.527)
2024-05-06 20:09:26,719 [INFO] core.trainer: * Acc@1 75.527 Best acc 77.307
2024-05-06 20:09:26,720 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:09:29,986 [INFO] core.trainer: Epoch-(36): [100/200] Time 0.033 (0.032) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 84.000 (76.107)
2024-05-06 20:09:33,274 [INFO] core.trainer: Epoch-(36): [200/200] Time 0.033 (0.032) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 74.667 (76.040)
2024-05-06 20:09:33,277 [INFO] core.trainer: * Acc@1 76.040 Best acc 76.160
2024-05-06 20:09:33,278 [INFO] core.trainer: * Time: 0:53:24/1:26:35.675676
2024-05-06 20:09:33,405 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:09:33,407 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 20:09:58,280 [INFO] core.trainer: Epoch-(37): [100/300] Time 0.241 (0.248) Calc 0.089 (0.088) Data 0.001 (0.008) Loss 1.710 (1.679) Acc@1 84.000 (89.640)
2024-05-06 20:10:22,418 [INFO] core.trainer: Epoch-(37): [200/300] Time 0.241 (0.245) Calc 0.088 (0.088) Data 0.001 (0.005) Loss 1.817 (1.686) Acc@1 88.000 (89.853)
2024-05-06 20:10:46,539 [INFO] core.trainer: Epoch-(37): [300/300] Time 0.240 (0.243) Calc 0.089 (0.088) Data 0.000 (0.003) Loss 1.497 (1.666) Acc@1 96.000 (90.093)
2024-05-06 20:10:46,676 [INFO] core.trainer: * Acc@1 90.093
2024-05-06 20:10:46,678 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:10:49,963 [INFO] core.trainer: Epoch-(37): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 77.333 (75.200)
2024-05-06 20:10:53,239 [INFO] core.trainer: Epoch-(37): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 72.000 (74.880)
2024-05-06 20:10:53,241 [INFO] core.trainer: * Acc@1 74.880 Best acc 77.307
2024-05-06 20:10:53,243 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:10:56,527 [INFO] core.trainer: Epoch-(37): [100/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 72.000 (75.640)
2024-05-06 20:10:59,828 [INFO] core.trainer: Epoch-(37): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 64.000 (74.673)
2024-05-06 20:10:59,831 [INFO] core.trainer: * Acc@1 74.673 Best acc 76.160
2024-05-06 20:10:59,832 [INFO] core.trainer: * Time: 0:54:51/1:26:36.315789
2024-05-06 20:10:59,997 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:10:59,999 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 20:11:24,899 [INFO] core.trainer: Epoch-(38): [100/300] Time 0.240 (0.249) Calc 0.087 (0.087) Data 0.001 (0.009) Loss 1.245 (1.642) Acc@1 90.667 (90.467)
2024-05-06 20:11:48,998 [INFO] core.trainer: Epoch-(38): [200/300] Time 0.240 (0.245) Calc 0.080 (0.087) Data 0.001 (0.005) Loss 1.646 (1.647) Acc@1 90.667 (90.913)
2024-05-06 20:12:13,111 [INFO] core.trainer: Epoch-(38): [300/300] Time 0.240 (0.243) Calc 0.088 (0.087) Data 0.000 (0.004) Loss 1.916 (1.668) Acc@1 86.667 (90.827)
2024-05-06 20:12:13,238 [INFO] core.trainer: * Acc@1 90.827
2024-05-06 20:12:13,240 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:12:16,524 [INFO] core.trainer: Epoch-(38): [100/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 82.667 (73.227)
2024-05-06 20:12:19,830 [INFO] core.trainer: Epoch-(38): [200/200] Time 0.034 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 80.000 (74.780)
2024-05-06 20:12:19,833 [INFO] core.trainer: * Acc@1 74.780 Best acc 77.307
2024-05-06 20:12:19,834 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:12:23,146 [INFO] core.trainer: Epoch-(38): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 82.667 (76.373)
2024-05-06 20:12:26,467 [INFO] core.trainer: Epoch-(38): [200/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 82.667 (75.427)
2024-05-06 20:12:26,469 [INFO] core.trainer: * Acc@1 75.427 Best acc 76.160
2024-05-06 20:12:26,471 [INFO] core.trainer: * Time: 0:56:18/1:26:36.923077
2024-05-06 20:12:26,597 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:12:26,598 [INFO] core.trainer: learning rate: [0.1, 0.1]
2024-05-06 20:12:51,438 [INFO] core.trainer: Epoch-(39): [100/300] Time 0.240 (0.248) Calc 0.088 (0.088) Data 0.001 (0.008) Loss 1.494 (1.626) Acc@1 93.333 (91.053)
2024-05-06 20:13:15,554 [INFO] core.trainer: Epoch-(39): [200/300] Time 0.240 (0.244) Calc 0.081 (0.087) Data 0.001 (0.005) Loss 1.738 (1.663) Acc@1 86.667 (90.340)
2024-05-06 20:13:39,662 [INFO] core.trainer: Epoch-(39): [300/300] Time 0.241 (0.243) Calc 0.089 (0.087) Data 0.000 (0.003) Loss 1.464 (1.662) Acc@1 97.333 (90.338)
2024-05-06 20:13:39,793 [INFO] core.trainer: * Acc@1 90.338
2024-05-06 20:13:39,795 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:13:43,094 [INFO] core.trainer: Epoch-(39): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 77.333 (75.520)
2024-05-06 20:13:46,354 [INFO] core.trainer: Epoch-(39): [200/200] Time 0.033 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 73.333 (75.387)
2024-05-06 20:13:46,357 [INFO] core.trainer: * Acc@1 75.387 Best acc 77.307
2024-05-06 20:13:46,358 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:13:49,636 [INFO] core.trainer: Epoch-(39): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 78.667 (76.200)
2024-05-06 20:13:52,910 [INFO] core.trainer: Epoch-(39): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 66.667 (76.420)
2024-05-06 20:13:52,912 [INFO] core.trainer: * Acc@1 76.420 Best acc 76.160
2024-05-06 20:13:52,914 [INFO] core.trainer: * Time: 0:57:44/1:26:36
2024-05-06 20:13:53,052 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:13:53,054 [INFO] core.trainer: learning rate: [0.005000000000000001, 0.005000000000000001]
2024-05-06 20:14:17,925 [INFO] core.trainer: Epoch-(40): [100/300] Time 0.240 (0.248) Calc 0.088 (0.088) Data 0.001 (0.008) Loss 1.136 (1.184) Acc@1 96.000 (91.707)
2024-05-06 20:14:42,053 [INFO] core.trainer: Epoch-(40): [200/300] Time 0.241 (0.245) Calc 0.087 (0.088) Data 0.001 (0.005) Loss 1.093 (1.091) Acc@1 93.333 (92.413)
2024-05-06 20:15:06,146 [INFO] core.trainer: Epoch-(40): [300/300] Time 0.239 (0.243) Calc 0.087 (0.087) Data 0.000 (0.003) Loss 0.904 (1.025) Acc@1 88.000 (92.929)
2024-05-06 20:15:06,280 [INFO] core.trainer: * Acc@1 92.929
2024-05-06 20:15:06,281 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:15:09,571 [INFO] core.trainer: Epoch-(40): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 80.000 (79.520)
2024-05-06 20:15:12,898 [INFO] core.trainer: Epoch-(40): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 76.000 (80.093)
2024-05-06 20:15:12,901 [INFO] core.trainer: * Acc@1 80.093 Best acc 77.307
2024-05-06 20:15:12,902 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:15:16,217 [INFO] core.trainer: Epoch-(40): [100/200] Time 0.037 (0.033) Calc 0.032 (0.031) Data 0.000 (0.001) Acc@1 86.667 (80.480)
2024-05-06 20:15:19,513 [INFO] core.trainer: Epoch-(40): [200/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 88.000 (80.433)
2024-05-06 20:15:19,515 [INFO] core.trainer: * Acc@1 80.433 Best acc 76.160
2024-05-06 20:15:19,517 [INFO] core.trainer: * Time: 0:59:11/1:26:36.585366
2024-05-06 20:15:19,854 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:15:19,856 [INFO] core.trainer: learning rate: [0.005000000000000001, 0.005000000000000001]
2024-05-06 20:15:44,758 [INFO] core.trainer: Epoch-(41): [100/300] Time 0.241 (0.249) Calc 0.089 (0.087) Data 0.001 (0.009) Loss 0.675 (0.836) Acc@1 96.000 (94.013)
2024-05-06 20:16:08,867 [INFO] core.trainer: Epoch-(41): [200/300] Time 0.241 (0.245) Calc 0.081 (0.086) Data 0.001 (0.005) Loss 0.946 (0.833) Acc@1 85.333 (94.007)
2024-05-06 20:16:33,019 [INFO] core.trainer: Epoch-(41): [300/300] Time 0.240 (0.243) Calc 0.088 (0.086) Data 0.000 (0.003) Loss 0.600 (0.806) Acc@1 96.000 (94.356)
2024-05-06 20:16:33,152 [INFO] core.trainer: * Acc@1 94.356
2024-05-06 20:16:33,153 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:16:36,447 [INFO] core.trainer: Epoch-(41): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 76.000 (79.160)
2024-05-06 20:16:39,752 [INFO] core.trainer: Epoch-(41): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 88.000 (79.320)
2024-05-06 20:16:39,755 [INFO] core.trainer: * Acc@1 79.320 Best acc 80.093
2024-05-06 20:16:39,756 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:16:43,035 [INFO] core.trainer: Epoch-(41): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 74.667 (79.320)
2024-05-06 20:16:46,308 [INFO] core.trainer: Epoch-(41): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 86.667 (79.053)
2024-05-06 20:16:46,311 [INFO] core.trainer: * Acc@1 79.053 Best acc 80.433
2024-05-06 20:16:46,312 [INFO] core.trainer: * Time: 1:00:37/1:26:35.714286
2024-05-06 20:16:46,439 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:16:46,440 [INFO] core.trainer: learning rate: [0.005000000000000001, 0.005000000000000001]
2024-05-06 20:17:11,272 [INFO] core.trainer: Epoch-(42): [100/300] Time 0.241 (0.248) Calc 0.088 (0.088) Data 0.001 (0.008) Loss 0.838 (0.693) Acc@1 90.667 (95.173)
2024-05-06 20:17:35,395 [INFO] core.trainer: Epoch-(42): [200/300] Time 0.240 (0.244) Calc 0.081 (0.087) Data 0.001 (0.004) Loss 0.774 (0.705) Acc@1 94.667 (94.873)
2024-05-06 20:17:59,527 [INFO] core.trainer: Epoch-(42): [300/300] Time 0.240 (0.243) Calc 0.088 (0.087) Data 0.000 (0.003) Loss 0.658 (0.693) Acc@1 100.000 (95.089)
2024-05-06 20:17:59,666 [INFO] core.trainer: * Acc@1 95.089
2024-05-06 20:17:59,667 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:18:02,984 [INFO] core.trainer: Epoch-(42): [100/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 89.333 (81.133)
2024-05-06 20:18:06,288 [INFO] core.trainer: Epoch-(42): [200/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.000 (0.001) Acc@1 80.000 (80.407)
2024-05-06 20:18:06,291 [INFO] core.trainer: * Acc@1 80.407 Best acc 80.093
2024-05-06 20:18:06,292 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:18:09,626 [INFO] core.trainer: Epoch-(42): [100/200] Time 0.034 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 76.000 (79.160)
2024-05-06 20:18:12,940 [INFO] core.trainer: Epoch-(42): [200/200] Time 0.034 (0.033) Calc 0.031 (0.031) Data 0.002 (0.001) Acc@1 74.667 (79.160)
2024-05-06 20:18:12,944 [INFO] core.trainer: * Acc@1 79.160 Best acc 80.433
2024-05-06 20:18:12,946 [INFO] core.trainer: * Time: 1:02:04/1:26:36.279070
2024-05-06 20:18:13,300 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:18:13,302 [INFO] core.trainer: learning rate: [0.005000000000000001, 0.005000000000000001]
2024-05-06 20:18:38,245 [INFO] core.trainer: Epoch-(43): [100/300] Time 0.240 (0.249) Calc 0.088 (0.086) Data 0.001 (0.009) Loss 0.924 (0.657) Acc@1 88.000 (95.120)
2024-05-06 20:19:02,420 [INFO] core.trainer: Epoch-(43): [200/300] Time 0.241 (0.245) Calc 0.091 (0.087) Data 0.001 (0.005) Loss 0.618 (0.652) Acc@1 100.000 (95.100)
2024-05-06 20:19:26,595 [INFO] core.trainer: Epoch-(43): [300/300] Time 0.240 (0.244) Calc 0.089 (0.087) Data 0.000 (0.004) Loss 0.445 (0.636) Acc@1 97.333 (95.311)
2024-05-06 20:19:26,733 [INFO] core.trainer: * Acc@1 95.311
2024-05-06 20:19:26,735 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:19:30,056 [INFO] core.trainer: Epoch-(43): [100/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 86.667 (79.933)
2024-05-06 20:19:33,359 [INFO] core.trainer: Epoch-(43): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 80.000 (79.787)
2024-05-06 20:19:33,362 [INFO] core.trainer: * Acc@1 79.787 Best acc 80.407
2024-05-06 20:19:33,363 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:19:36,673 [INFO] core.trainer: Epoch-(43): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 92.000 (79.413)
2024-05-06 20:19:39,981 [INFO] core.trainer: Epoch-(43): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 77.333 (78.513)
2024-05-06 20:19:39,984 [INFO] core.trainer: * Acc@1 78.513 Best acc 79.160
2024-05-06 20:19:39,986 [INFO] core.trainer: * Time: 1:03:31/1:26:36.818182
2024-05-06 20:19:40,121 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:19:40,123 [INFO] core.trainer: learning rate: [0.005000000000000001, 0.005000000000000001]
2024-05-06 20:20:05,072 [INFO] core.trainer: Epoch-(44): [100/300] Time 0.240 (0.249) Calc 0.089 (0.087) Data 0.001 (0.009) Loss 0.390 (0.578) Acc@1 98.667 (95.960)
2024-05-06 20:20:29,192 [INFO] core.trainer: Epoch-(44): [200/300] Time 0.240 (0.245) Calc 0.084 (0.087) Data 0.001 (0.005) Loss 0.614 (0.576) Acc@1 97.333 (95.827)
2024-05-06 20:20:53,342 [INFO] core.trainer: Epoch-(44): [300/300] Time 0.244 (0.244) Calc 0.113 (0.087) Data 0.001 (0.004) Loss 0.558 (0.578) Acc@1 94.667 (95.827)
2024-05-06 20:20:53,494 [INFO] core.trainer: * Acc@1 95.827
2024-05-06 20:20:53,496 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:20:56,806 [INFO] core.trainer: Epoch-(44): [100/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 74.667 (79.520)
2024-05-06 20:21:00,110 [INFO] core.trainer: Epoch-(44): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 65.333 (79.593)
2024-05-06 20:21:00,113 [INFO] core.trainer: * Acc@1 79.593 Best acc 80.407
2024-05-06 20:21:00,114 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:21:03,389 [INFO] core.trainer: Epoch-(44): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 85.333 (79.800)
2024-05-06 20:21:06,670 [INFO] core.trainer: Epoch-(44): [200/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 56.000 (79.140)
2024-05-06 20:21:06,673 [INFO] core.trainer: * Acc@1 79.140 Best acc 79.160
2024-05-06 20:21:06,674 [INFO] core.trainer: * Time: 1:04:58/1:26:37.333333
2024-05-06 20:21:06,819 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:21:06,821 [INFO] core.trainer: learning rate: [0.005000000000000001, 0.005000000000000001]
2024-05-06 20:21:31,719 [INFO] core.trainer: Epoch-(45): [100/300] Time 0.245 (0.249) Calc 0.093 (0.088) Data 0.002 (0.008) Loss 0.619 (0.553) Acc@1 94.667 (95.947)
2024-05-06 20:21:56,092 [INFO] core.trainer: Epoch-(45): [200/300] Time 0.240 (0.246) Calc 0.081 (0.089) Data 0.001 (0.005) Loss 0.561 (0.550) Acc@1 96.000 (95.707)
2024-05-06 20:22:20,269 [INFO] core.trainer: Epoch-(45): [300/300] Time 0.240 (0.244) Calc 0.083 (0.089) Data 0.000 (0.003) Loss 0.565 (0.553) Acc@1 100.000 (95.720)
2024-05-06 20:22:20,418 [INFO] core.trainer: * Acc@1 95.720
2024-05-06 20:22:20,419 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:22:23,702 [INFO] core.trainer: Epoch-(45): [100/200] Time 0.032 (0.032) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 85.333 (81.467)
2024-05-06 20:22:27,042 [INFO] core.trainer: Epoch-(45): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 90.667 (80.507)
2024-05-06 20:22:27,045 [INFO] core.trainer: * Acc@1 80.507 Best acc 80.407
2024-05-06 20:22:27,046 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:22:30,362 [INFO] core.trainer: Epoch-(45): [100/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 82.667 (78.147)
2024-05-06 20:22:33,681 [INFO] core.trainer: Epoch-(45): [200/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 81.333 (79.020)
2024-05-06 20:22:33,684 [INFO] core.trainer: * Acc@1 79.020 Best acc 79.160
2024-05-06 20:22:33,685 [INFO] core.trainer: * Time: 1:06:25/1:26:37.826087
2024-05-06 20:22:33,935 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:22:33,937 [INFO] core.trainer: learning rate: [0.005000000000000001, 0.005000000000000001]
2024-05-06 20:22:58,860 [INFO] core.trainer: Epoch-(46): [100/300] Time 0.243 (0.249) Calc 0.097 (0.086) Data 0.001 (0.009) Loss 0.511 (0.544) Acc@1 100.000 (95.533)
2024-05-06 20:23:22,990 [INFO] core.trainer: Epoch-(46): [200/300] Time 0.240 (0.245) Calc 0.088 (0.086) Data 0.001 (0.005) Loss 0.491 (0.531) Acc@1 98.667 (95.707)
2024-05-06 20:23:47,140 [INFO] core.trainer: Epoch-(46): [300/300] Time 0.240 (0.244) Calc 0.084 (0.087) Data 0.000 (0.004) Loss 0.742 (0.520) Acc@1 86.667 (95.733)
2024-05-06 20:23:47,283 [INFO] core.trainer: * Acc@1 95.733
2024-05-06 20:23:47,285 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:23:50,600 [INFO] core.trainer: Epoch-(46): [100/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 68.000 (79.080)
2024-05-06 20:23:53,910 [INFO] core.trainer: Epoch-(46): [200/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 81.333 (80.280)
2024-05-06 20:23:53,913 [INFO] core.trainer: * Acc@1 80.280 Best acc 80.507
2024-05-06 20:23:53,914 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:23:57,249 [INFO] core.trainer: Epoch-(46): [100/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 74.667 (79.000)
2024-05-06 20:24:00,549 [INFO] core.trainer: Epoch-(46): [200/200] Time 0.032 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 85.333 (79.207)
2024-05-06 20:24:00,552 [INFO] core.trainer: * Acc@1 79.207 Best acc 79.020
2024-05-06 20:24:00,554 [INFO] core.trainer: * Time: 1:07:52/1:26:38.297872
2024-05-06 20:24:00,686 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:24:00,688 [INFO] core.trainer: learning rate: [0.005000000000000001, 0.005000000000000001]
2024-05-06 20:24:25,626 [INFO] core.trainer: Epoch-(47): [100/300] Time 0.240 (0.249) Calc 0.081 (0.086) Data 0.001 (0.009) Loss 0.460 (0.472) Acc@1 94.667 (96.320)
2024-05-06 20:24:49,790 [INFO] core.trainer: Epoch-(47): [200/300] Time 0.240 (0.245) Calc 0.088 (0.086) Data 0.001 (0.005) Loss 0.318 (0.480) Acc@1 100.000 (96.380)
2024-05-06 20:25:13,918 [INFO] core.trainer: Epoch-(47): [300/300] Time 0.243 (0.244) Calc 0.104 (0.086) Data 0.000 (0.004) Loss 0.376 (0.477) Acc@1 98.667 (96.351)
2024-05-06 20:25:14,054 [INFO] core.trainer: * Acc@1 96.351
2024-05-06 20:25:14,056 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:25:17,454 [INFO] core.trainer: Epoch-(47): [100/200] Time 0.033 (0.034) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 60.000 (80.827)
2024-05-06 20:25:20,791 [INFO] core.trainer: Epoch-(47): [200/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 84.000 (80.393)
2024-05-06 20:25:20,794 [INFO] core.trainer: * Acc@1 80.393 Best acc 80.507
2024-05-06 20:25:20,795 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:25:24,101 [INFO] core.trainer: Epoch-(47): [100/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 81.333 (78.987)
2024-05-06 20:25:27,470 [INFO] core.trainer: Epoch-(47): [200/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 80.000 (79.720)
2024-05-06 20:25:27,474 [INFO] core.trainer: * Acc@1 79.720 Best acc 79.020
2024-05-06 20:25:27,475 [INFO] core.trainer: * Time: 1:09:19/1:26:38.750000
2024-05-06 20:25:27,603 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:25:27,604 [INFO] core.trainer: learning rate: [0.005000000000000001, 0.005000000000000001]
2024-05-06 20:25:52,423 [INFO] core.trainer: Epoch-(48): [100/300] Time 0.241 (0.248) Calc 0.088 (0.085) Data 0.001 (0.008) Loss 0.506 (0.461) Acc@1 96.000 (96.293)
2024-05-06 20:26:16,606 [INFO] core.trainer: Epoch-(48): [200/300] Time 0.240 (0.245) Calc 0.088 (0.087) Data 0.001 (0.005) Loss 0.795 (0.454) Acc@1 78.667 (96.333)
2024-05-06 20:26:40,723 [INFO] core.trainer: Epoch-(48): [300/300] Time 0.240 (0.243) Calc 0.080 (0.087) Data 0.000 (0.003) Loss 0.457 (0.451) Acc@1 94.667 (96.338)
2024-05-06 20:26:40,867 [INFO] core.trainer: * Acc@1 96.338
2024-05-06 20:26:40,868 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:26:44,288 [INFO] core.trainer: Epoch-(48): [100/200] Time 0.035 (0.034) Calc 0.031 (0.031) Data 0.002 (0.001) Acc@1 85.333 (79.520)
2024-05-06 20:26:47,717 [INFO] core.trainer: Epoch-(48): [200/200] Time 0.034 (0.034) Calc 0.032 (0.031) Data 0.001 (0.001) Acc@1 72.000 (80.027)
2024-05-06 20:26:47,720 [INFO] core.trainer: * Acc@1 80.027 Best acc 80.507
2024-05-06 20:26:47,722 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:26:51,038 [INFO] core.trainer: Epoch-(48): [100/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.000 (0.001) Acc@1 88.000 (78.653)
2024-05-06 20:26:54,333 [INFO] core.trainer: Epoch-(48): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 77.333 (78.860)
2024-05-06 20:26:54,336 [INFO] core.trainer: * Acc@1 78.860 Best acc 79.020
2024-05-06 20:26:54,337 [INFO] core.trainer: * Time: 1:10:45/1:26:37.959184
2024-05-06 20:26:54,477 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:26:54,479 [INFO] core.trainer: learning rate: [0.005000000000000001, 0.005000000000000001]
2024-05-06 20:27:19,317 [INFO] core.trainer: Epoch-(49): [100/300] Time 0.241 (0.248) Calc 0.087 (0.087) Data 0.001 (0.008) Loss 0.310 (0.438) Acc@1 97.333 (96.933)
2024-05-06 20:27:43,466 [INFO] core.trainer: Epoch-(49): [200/300] Time 0.240 (0.245) Calc 0.087 (0.086) Data 0.001 (0.005) Loss 0.443 (0.438) Acc@1 97.333 (96.513)
2024-05-06 20:28:07,579 [INFO] core.trainer: Epoch-(49): [300/300] Time 0.240 (0.243) Calc 0.087 (0.086) Data 0.000 (0.003) Loss 0.427 (0.432) Acc@1 96.000 (96.524)
2024-05-06 20:28:07,726 [INFO] core.trainer: * Acc@1 96.524
2024-05-06 20:28:07,728 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:28:11,021 [INFO] core.trainer: Epoch-(49): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.000 (0.001) Acc@1 81.333 (78.640)
2024-05-06 20:28:14,359 [INFO] core.trainer: Epoch-(49): [200/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 82.667 (78.827)
2024-05-06 20:28:14,362 [INFO] core.trainer: * Acc@1 78.827 Best acc 80.507
2024-05-06 20:28:14,363 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:28:17,694 [INFO] core.trainer: Epoch-(49): [100/200] Time 0.034 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 80.000 (80.267)
2024-05-06 20:28:21,119 [INFO] core.trainer: Epoch-(49): [200/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 86.667 (80.053)
2024-05-06 20:28:21,121 [INFO] core.trainer: * Acc@1 80.053 Best acc 79.020
2024-05-06 20:28:21,123 [INFO] core.trainer: * Time: 1:12:12/1:26:38.400000
2024-05-06 20:28:21,290 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:28:21,292 [INFO] core.trainer: learning rate: [0.00025000000000000006, 0.00025000000000000006]
2024-05-06 20:28:46,146 [INFO] core.trainer: Epoch-(50): [100/300] Time 0.241 (0.248) Calc 0.088 (0.086) Data 0.001 (0.008) Loss 0.456 (0.422) Acc@1 97.333 (96.360)
2024-05-06 20:29:10,326 [INFO] core.trainer: Epoch-(50): [200/300] Time 0.240 (0.245) Calc 0.080 (0.086) Data 0.001 (0.005) Loss 0.454 (0.415) Acc@1 94.667 (96.693)
2024-05-06 20:29:34,453 [INFO] core.trainer: Epoch-(50): [300/300] Time 0.241 (0.243) Calc 0.088 (0.086) Data 0.000 (0.003) Loss 0.451 (0.412) Acc@1 97.333 (96.800)
2024-05-06 20:29:34,594 [INFO] core.trainer: * Acc@1 96.800
2024-05-06 20:29:34,597 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:29:37,910 [INFO] core.trainer: Epoch-(50): [100/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.000 (0.001) Acc@1 84.000 (80.320)
2024-05-06 20:29:41,211 [INFO] core.trainer: Epoch-(50): [200/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 77.333 (80.547)
2024-05-06 20:29:41,214 [INFO] core.trainer: * Acc@1 80.547 Best acc 80.507
2024-05-06 20:29:41,215 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:29:44,507 [INFO] core.trainer: Epoch-(50): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 77.333 (79.560)
2024-05-06 20:29:47,928 [INFO] core.trainer: Epoch-(50): [200/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.000 (0.001) Acc@1 68.000 (79.280)
2024-05-06 20:29:47,933 [INFO] core.trainer: * Acc@1 79.280 Best acc 79.020
2024-05-06 20:29:47,935 [INFO] core.trainer: * Time: 1:13:39/1:26:38.823529
2024-05-06 20:29:48,371 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:29:48,372 [INFO] core.trainer: learning rate: [0.00025000000000000006, 0.00025000000000000006]
2024-05-06 20:30:13,318 [INFO] core.trainer: Epoch-(51): [100/300] Time 0.241 (0.249) Calc 0.086 (0.086) Data 0.001 (0.009) Loss 0.393 (0.394) Acc@1 98.667 (96.973)
2024-05-06 20:30:37,433 [INFO] core.trainer: Epoch-(51): [200/300] Time 0.241 (0.245) Calc 0.089 (0.085) Data 0.001 (0.005) Loss 0.709 (0.397) Acc@1 85.333 (97.053)
2024-05-06 20:31:01,618 [INFO] core.trainer: Epoch-(51): [300/300] Time 0.239 (0.244) Calc 0.079 (0.085) Data 0.000 (0.004) Loss 0.344 (0.395) Acc@1 94.667 (97.160)
2024-05-06 20:31:01,758 [INFO] core.trainer: * Acc@1 97.160
2024-05-06 20:31:01,760 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:31:05,078 [INFO] core.trainer: Epoch-(51): [100/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 69.333 (79.893)
2024-05-06 20:31:08,372 [INFO] core.trainer: Epoch-(51): [200/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 96.000 (79.720)
2024-05-06 20:31:08,378 [INFO] core.trainer: * Acc@1 79.720 Best acc 80.547
2024-05-06 20:31:08,379 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:31:11,688 [INFO] core.trainer: Epoch-(51): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 73.333 (80.080)
2024-05-06 20:31:14,990 [INFO] core.trainer: Epoch-(51): [200/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 84.000 (80.053)
2024-05-06 20:31:14,993 [INFO] core.trainer: * Acc@1 80.053 Best acc 79.280
2024-05-06 20:31:14,994 [INFO] core.trainer: * Time: 1:15:06/1:26:39.230769
2024-05-06 20:31:15,126 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:31:15,128 [INFO] core.trainer: learning rate: [0.00025000000000000006, 0.00025000000000000006]
2024-05-06 20:31:40,064 [INFO] core.trainer: Epoch-(52): [100/300] Time 0.240 (0.249) Calc 0.088 (0.085) Data 0.001 (0.009) Loss 0.633 (0.417) Acc@1 88.000 (95.987)
2024-05-06 20:32:04,219 [INFO] core.trainer: Epoch-(52): [200/300] Time 0.241 (0.245) Calc 0.088 (0.086) Data 0.001 (0.005) Loss 0.302 (0.405) Acc@1 100.000 (96.480)
2024-05-06 20:32:28,386 [INFO] core.trainer: Epoch-(52): [300/300] Time 0.240 (0.244) Calc 0.088 (0.086) Data 0.000 (0.004) Loss 0.502 (0.400) Acc@1 92.000 (96.636)
2024-05-06 20:32:28,520 [INFO] core.trainer: * Acc@1 96.636
2024-05-06 20:32:28,522 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:32:31,795 [INFO] core.trainer: Epoch-(52): [100/200] Time 0.033 (0.032) Calc 0.031 (0.030) Data 0.001 (0.001) Acc@1 74.667 (78.840)
2024-05-06 20:32:35,250 [INFO] core.trainer: Epoch-(52): [200/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.000 (0.001) Acc@1 85.333 (79.320)
2024-05-06 20:32:35,253 [INFO] core.trainer: * Acc@1 79.320 Best acc 80.547
2024-05-06 20:32:35,254 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:32:38,557 [INFO] core.trainer: Epoch-(52): [100/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 86.667 (79.320)
2024-05-06 20:32:41,878 [INFO] core.trainer: Epoch-(52): [200/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 70.667 (79.860)
2024-05-06 20:32:41,881 [INFO] core.trainer: * Acc@1 79.860 Best acc 79.280
2024-05-06 20:32:41,882 [INFO] core.trainer: * Time: 1:16:33/1:26:39.622642
2024-05-06 20:32:42,015 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:32:42,017 [INFO] core.trainer: learning rate: [0.00025000000000000006, 0.00025000000000000006]
2024-05-06 20:33:06,837 [INFO] core.trainer: Epoch-(53): [100/300] Time 0.241 (0.248) Calc 0.083 (0.085) Data 0.001 (0.008) Loss 0.243 (0.395) Acc@1 100.000 (97.133)
2024-05-06 20:33:31,013 [INFO] core.trainer: Epoch-(53): [200/300] Time 0.241 (0.245) Calc 0.088 (0.085) Data 0.001 (0.005) Loss 0.414 (0.394) Acc@1 97.333 (97.147)
2024-05-06 20:33:55,144 [INFO] core.trainer: Epoch-(53): [300/300] Time 0.242 (0.243) Calc 0.089 (0.086) Data 0.000 (0.003) Loss 0.444 (0.392) Acc@1 96.000 (97.298)
2024-05-06 20:33:55,283 [INFO] core.trainer: * Acc@1 97.298
2024-05-06 20:33:55,285 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:33:58,651 [INFO] core.trainer: Epoch-(53): [100/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 88.000 (79.973)
2024-05-06 20:34:01,952 [INFO] core.trainer: Epoch-(53): [200/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 85.333 (80.107)
2024-05-06 20:34:01,955 [INFO] core.trainer: * Acc@1 80.107 Best acc 80.547
2024-05-06 20:34:01,956 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:34:05,295 [INFO] core.trainer: Epoch-(53): [100/200] Time 0.035 (0.033) Calc 0.032 (0.031) Data 0.001 (0.001) Acc@1 80.000 (80.720)
2024-05-06 20:34:08,675 [INFO] core.trainer: Epoch-(53): [200/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 85.333 (79.680)
2024-05-06 20:34:08,678 [INFO] core.trainer: * Acc@1 79.680 Best acc 79.280
2024-05-06 20:34:08,680 [INFO] core.trainer: * Time: 1:18:00/1:26:40
2024-05-06 20:34:08,837 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:34:08,839 [INFO] core.trainer: learning rate: [0.00025000000000000006, 0.00025000000000000006]
2024-05-06 20:34:33,636 [INFO] core.trainer: Epoch-(54): [100/300] Time 0.241 (0.248) Calc 0.089 (0.086) Data 0.001 (0.008) Loss 0.312 (0.379) Acc@1 100.000 (97.333)
2024-05-06 20:34:57,807 [INFO] core.trainer: Epoch-(54): [200/300] Time 0.240 (0.244) Calc 0.088 (0.086) Data 0.001 (0.004) Loss 0.263 (0.384) Acc@1 100.000 (97.073)
2024-05-06 20:35:21,875 [INFO] core.trainer: Epoch-(54): [300/300] Time 0.240 (0.243) Calc 0.088 (0.086) Data 0.000 (0.003) Loss 0.329 (0.386) Acc@1 98.667 (97.164)
2024-05-06 20:35:22,003 [INFO] core.trainer: * Acc@1 97.164
2024-05-06 20:35:22,006 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:35:25,338 [INFO] core.trainer: Epoch-(54): [100/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.000 (0.001) Acc@1 62.667 (79.853)
2024-05-06 20:35:28,748 [INFO] core.trainer: Epoch-(54): [200/200] Time 0.034 (0.033) Calc 0.031 (0.031) Data 0.002 (0.001) Acc@1 76.000 (80.233)
2024-05-06 20:35:28,751 [INFO] core.trainer: * Acc@1 80.233 Best acc 80.547
2024-05-06 20:35:28,752 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:35:32,144 [INFO] core.trainer: Epoch-(54): [100/200] Time 0.033 (0.034) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 74.667 (78.080)
2024-05-06 20:35:35,468 [INFO] core.trainer: Epoch-(54): [200/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 70.667 (78.800)
2024-05-06 20:35:35,472 [INFO] core.trainer: * Acc@1 78.800 Best acc 79.280
2024-05-06 20:35:35,473 [INFO] core.trainer: * Time: 1:19:27/1:26:40.363636
2024-05-06 20:35:35,683 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:35:35,686 [INFO] core.trainer: learning rate: [0.00025000000000000006, 0.00025000000000000006]
2024-05-06 20:36:00,591 [INFO] core.trainer: Epoch-(55): [100/300] Time 0.245 (0.249) Calc 0.098 (0.088) Data 0.002 (0.008) Loss 0.189 (0.392) Acc@1 100.000 (97.160)
2024-05-06 20:36:24,815 [INFO] core.trainer: Epoch-(55): [200/300] Time 0.241 (0.245) Calc 0.088 (0.089) Data 0.001 (0.005) Loss 0.440 (0.393) Acc@1 98.667 (97.007)
2024-05-06 20:36:48,899 [INFO] core.trainer: Epoch-(55): [300/300] Time 0.240 (0.244) Calc 0.088 (0.088) Data 0.000 (0.003) Loss 0.292 (0.388) Acc@1 100.000 (97.049)
2024-05-06 20:36:49,028 [INFO] core.trainer: * Acc@1 97.049
2024-05-06 20:36:49,030 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:36:52,386 [INFO] core.trainer: Epoch-(55): [100/200] Time 0.034 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 81.333 (80.440)
2024-05-06 20:36:55,796 [INFO] core.trainer: Epoch-(55): [200/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 90.667 (79.660)
2024-05-06 20:36:55,798 [INFO] core.trainer: * Acc@1 79.660 Best acc 80.547
2024-05-06 20:36:55,800 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:36:59,123 [INFO] core.trainer: Epoch-(55): [100/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 72.000 (79.747)
2024-05-06 20:37:02,429 [INFO] core.trainer: Epoch-(55): [200/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 81.333 (79.607)
2024-05-06 20:37:02,432 [INFO] core.trainer: * Acc@1 79.607 Best acc 79.280
2024-05-06 20:37:02,434 [INFO] core.trainer: * Time: 1:20:54/1:26:40.714286
2024-05-06 20:37:02,573 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:37:02,575 [INFO] core.trainer: learning rate: [0.00025000000000000006, 0.00025000000000000006]
2024-05-06 20:37:27,481 [INFO] core.trainer: Epoch-(56): [100/300] Time 0.242 (0.249) Calc 0.088 (0.087) Data 0.002 (0.009) Loss 0.475 (0.381) Acc@1 97.333 (96.627)
2024-05-06 20:37:51,636 [INFO] core.trainer: Epoch-(56): [200/300] Time 0.247 (0.245) Calc 0.113 (0.087) Data 0.002 (0.005) Loss 0.314 (0.380) Acc@1 98.667 (96.840)
2024-05-06 20:38:15,778 [INFO] core.trainer: Epoch-(56): [300/300] Time 0.240 (0.244) Calc 0.088 (0.088) Data 0.000 (0.004) Loss 0.511 (0.387) Acc@1 97.333 (96.733)
2024-05-06 20:38:15,920 [INFO] core.trainer: * Acc@1 96.733
2024-05-06 20:38:15,922 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:38:19,220 [INFO] core.trainer: Epoch-(56): [100/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 84.000 (80.107)
2024-05-06 20:38:22,524 [INFO] core.trainer: Epoch-(56): [200/200] Time 0.032 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 80.000 (79.567)
2024-05-06 20:38:22,527 [INFO] core.trainer: * Acc@1 79.567 Best acc 80.547
2024-05-06 20:38:22,528 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:38:25,901 [INFO] core.trainer: Epoch-(56): [100/200] Time 0.035 (0.033) Calc 0.031 (0.031) Data 0.002 (0.001) Acc@1 77.333 (80.267)
2024-05-06 20:38:29,349 [INFO] core.trainer: Epoch-(56): [200/200] Time 0.033 (0.034) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 82.667 (80.100)
2024-05-06 20:38:29,353 [INFO] core.trainer: * Acc@1 80.100 Best acc 79.280
2024-05-06 20:38:29,354 [INFO] core.trainer: * Time: 1:22:20/1:26:40
2024-05-06 20:38:29,504 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:38:29,506 [INFO] core.trainer: learning rate: [0.00025000000000000006, 0.00025000000000000006]
2024-05-06 20:38:54,506 [INFO] core.trainer: Epoch-(57): [100/300] Time 0.240 (0.250) Calc 0.088 (0.088) Data 0.001 (0.009) Loss 0.289 (0.392) Acc@1 98.667 (96.840)
2024-05-06 20:39:18,673 [INFO] core.trainer: Epoch-(57): [200/300] Time 0.241 (0.245) Calc 0.097 (0.087) Data 0.001 (0.005) Loss 0.452 (0.393) Acc@1 94.667 (96.847)
2024-05-06 20:39:42,864 [INFO] core.trainer: Epoch-(57): [300/300] Time 0.240 (0.244) Calc 0.090 (0.087) Data 0.000 (0.004) Loss 0.417 (0.387) Acc@1 98.667 (96.956)
2024-05-06 20:39:43,001 [INFO] core.trainer: * Acc@1 96.956
2024-05-06 20:39:43,002 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:39:46,386 [INFO] core.trainer: Epoch-(57): [100/200] Time 0.035 (0.033) Calc 0.032 (0.031) Data 0.001 (0.001) Acc@1 81.333 (78.893)
2024-05-06 20:39:49,729 [INFO] core.trainer: Epoch-(57): [200/200] Time 0.034 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 85.333 (79.647)
2024-05-06 20:39:49,731 [INFO] core.trainer: * Acc@1 79.647 Best acc 80.547
2024-05-06 20:39:49,733 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:39:53,038 [INFO] core.trainer: Epoch-(57): [100/200] Time 0.033 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 85.333 (79.213)
2024-05-06 20:39:56,358 [INFO] core.trainer: Epoch-(57): [200/200] Time 0.034 (0.033) Calc 0.032 (0.031) Data 0.001 (0.001) Acc@1 74.667 (78.553)
2024-05-06 20:39:56,361 [INFO] core.trainer: * Acc@1 78.553 Best acc 79.280
2024-05-06 20:39:56,362 [INFO] core.trainer: * Time: 1:23:47/1:26:40.344828
2024-05-06 20:39:56,497 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:39:56,499 [INFO] core.trainer: learning rate: [0.00025000000000000006, 0.00025000000000000006]
2024-05-06 20:40:21,417 [INFO] core.trainer: Epoch-(58): [100/300] Time 0.243 (0.249) Calc 0.090 (0.086) Data 0.002 (0.009) Loss 0.564 (0.382) Acc@1 78.667 (96.880)
2024-05-06 20:40:45,638 [INFO] core.trainer: Epoch-(58): [200/300] Time 0.240 (0.245) Calc 0.080 (0.087) Data 0.001 (0.005) Loss 0.288 (0.384) Acc@1 98.667 (96.927)
2024-05-06 20:41:09,721 [INFO] core.trainer: Epoch-(58): [300/300] Time 0.240 (0.244) Calc 0.080 (0.086) Data 0.000 (0.004) Loss 0.397 (0.384) Acc@1 96.000 (96.787)
2024-05-06 20:41:09,857 [INFO] core.trainer: * Acc@1 96.787
2024-05-06 20:41:09,858 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:41:13,167 [INFO] core.trainer: Epoch-(58): [100/200] Time 0.032 (0.033) Calc 0.030 (0.030) Data 0.001 (0.001) Acc@1 88.000 (79.307)
2024-05-06 20:41:16,476 [INFO] core.trainer: Epoch-(58): [200/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 69.333 (79.693)
2024-05-06 20:41:16,479 [INFO] core.trainer: * Acc@1 79.693 Best acc 80.547
2024-05-06 20:41:16,480 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:41:19,788 [INFO] core.trainer: Epoch-(58): [100/200] Time 0.034 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 77.333 (79.413)
2024-05-06 20:41:23,101 [INFO] core.trainer: Epoch-(58): [200/200] Time 0.033 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 90.667 (78.660)
2024-05-06 20:41:23,104 [INFO] core.trainer: * Acc@1 78.660 Best acc 79.280
2024-05-06 20:41:23,106 [INFO] core.trainer: * Time: 1:25:14/1:26:40.677966
2024-05-06 20:41:23,232 [INFO] core.trainer: ============ Train on the train set ============
2024-05-06 20:41:23,234 [INFO] core.trainer: learning rate: [0.00025000000000000006, 0.00025000000000000006]
2024-05-06 20:41:48,089 [INFO] core.trainer: Epoch-(59): [100/300] Time 0.240 (0.248) Calc 0.080 (0.086) Data 0.001 (0.008) Loss 0.291 (0.385) Acc@1 100.000 (97.147)
2024-05-06 20:42:12,196 [INFO] core.trainer: Epoch-(59): [200/300] Time 0.241 (0.244) Calc 0.088 (0.085) Data 0.001 (0.005) Loss 0.410 (0.384) Acc@1 96.000 (96.920)
2024-05-06 20:42:36,291 [INFO] core.trainer: Epoch-(59): [300/300] Time 0.240 (0.243) Calc 0.087 (0.085) Data 0.000 (0.003) Loss 0.359 (0.383) Acc@1 96.000 (96.867)
2024-05-06 20:42:36,450 [INFO] core.trainer: * Acc@1 96.867
2024-05-06 20:42:36,452 [INFO] core.trainer: ============ Validation on the val set ============
2024-05-06 20:42:39,778 [INFO] core.trainer: Epoch-(59): [100/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.001 (0.001) Acc@1 77.333 (80.013)
2024-05-06 20:42:43,116 [INFO] core.trainer: Epoch-(59): [200/200] Time 0.033 (0.033) Calc 0.031 (0.031) Data 0.000 (0.001) Acc@1 90.667 (80.020)
2024-05-06 20:42:43,119 [INFO] core.trainer: * Acc@1 80.020 Best acc 80.547
2024-05-06 20:42:43,121 [INFO] core.trainer: ============ Testing on the test set ============
2024-05-06 20:42:46,435 [INFO] core.trainer: Epoch-(59): [100/200] Time 0.032 (0.033) Calc 0.030 (0.031) Data 0.001 (0.001) Acc@1 76.000 (79.987)
2024-05-06 20:42:49,705 [INFO] core.trainer: Epoch-(59): [200/200] Time 0.033 (0.033) Calc 0.031 (0.030) Data 0.000 (0.001) Acc@1 77.333 (80.140)
2024-05-06 20:42:49,708 [INFO] core.trainer: * Acc@1 80.140 Best acc 79.280
2024-05-06 20:42:49,709 [INFO] core.trainer: * Time: 1:26:41/1:26:41
2024-05-06 20:42:49,839 [INFO] core.trainer: End of experiment, took 1:26:41
2024-05-06 20:42:49,841 [INFO] core.trainer: Result DIR: ./results/RENet-miniImageNet--ravi-resnet12-5-5-May-06-2024-19-16-07

VincenDen · 2024-05-08T11:01:40Z

请问您是用的RENet-miniImageNet--ravi-resnet12-5-5-Reproduce文件还是RENet-miniImageNet--ravi-resnet12-5-5-Table2文件，根据您提供的结果看起来更符合RENet-miniImageNet--ravi-resnet12-5-5-Table2的结果

OKCup · 2024-05-08T11:33:15Z

上面的结果使用的是RENet-miniImageNet--ravi-resnet12-5-5-Reproduce的文件，使用RENet-miniImageNet--ravi-resnet12-5-5-Table2的文件的话，结果要再低一点，差不多77%左右

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

关于文章中数据的疑问 #109

关于文章中数据的疑问 #109

OKCup commented May 5, 2024

WenbinLee commented May 6, 2024

OKCup commented May 7, 2024 •

edited

VincenDen commented May 8, 2024

OKCup commented May 8, 2024

关于文章中数据的疑问 #109

关于文章中数据的疑问 #109

Comments

OKCup commented May 5, 2024

WenbinLee commented May 6, 2024

OKCup commented May 7, 2024 • edited

VincenDen commented May 8, 2024

OKCup commented May 8, 2024

OKCup commented May 7, 2024 •

edited