2022/11/28 14:06:52 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.9.13 (main, Aug 25 2022, 23:26:10) [GCC 11.2.0] CUDA available: True numpy_random_seed: 44993439 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 5.4.0 PyTorch: 1.11.0 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.3 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.2 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.11.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.12.0 OpenCV: 4.6.0 MMEngine: 0.3.1 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None diff_rank_seed: False deterministic: False Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2022/11/28 14:06:52 - mmengine - INFO - Config: default_scope = 'mmaction' default_hooks = dict( runtime_info=dict(type='RuntimeInfoHook'), timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=100, ignore_last=False), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1, save_best='auto'), sampler_seed=dict(type='DistSamplerSeedHook'), sync_buffers=dict(type='SyncBuffersHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) log_processor = dict(type='LogProcessor', window_size=20, by_epoch=True) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='ActionVisualizer', vis_backends=[dict(type='LocalVisBackend')]) log_level = 'INFO' load_from = None resume = False model = dict( type='RecognizerGCN', backbone=dict( type='STGCN', graph_cfg=dict(layout='coco', mode='stgcn_spatial')), cls_head=dict(type='GCNHead', num_classes=60, in_channels=256)) dataset_type = 'PoseDataset' ann_file = 'data/skeleton/ntu60_2d.pkl' train_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['b']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] val_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['b']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] test_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['b']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=5, dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['b']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_train'))) val_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['b']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['b']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) val_evaluator = [dict(type='AccMetric')] test_evaluator = [dict(type='AccMetric')] train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=16, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='CosineAnnealingLR', eta_min=0, T_max=16, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( optimizer=dict( type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005, nesterov=True)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = './work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/11/28 14:06:52 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/modules_statistic_results.json Name of parameter - Initialization information data_bn.weight - torch.Size([51]): The value is the same before and after calling `init_weights` of STGCN data_bn.bias - torch.Size([51]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.PA - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.conv.weight - torch.Size([192, 3, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.0.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of STGCN gcn.0.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.0.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.0.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.0.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.PA - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.1.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of STGCN gcn.1.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.1.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.1.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.1.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.PA - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.2.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of STGCN gcn.2.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.2.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.2.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.2.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.PA - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.3.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of STGCN gcn.3.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.3.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.3.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.3.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.PA - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.conv.weight - torch.Size([384, 64, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.4.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of STGCN gcn.4.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.4.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.4.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.residual.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.4.residual.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.4.residual.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.4.residual.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.PA - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.conv.weight - torch.Size([384, 128, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.5.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of STGCN gcn.5.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.5.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.5.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.5.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.PA - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.conv.weight - torch.Size([384, 128, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.6.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of STGCN gcn.6.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.6.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.6.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.6.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.PA - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.conv.weight - torch.Size([768, 128, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.7.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of STGCN gcn.7.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.7.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.7.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.residual.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.7.residual.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.7.residual.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.7.residual.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.PA - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.conv.weight - torch.Size([768, 256, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.8.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of STGCN gcn.8.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.8.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.8.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.8.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.PA - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.conv.weight - torch.Size([768, 256, 1, 1]): The value is the same before and after calling `init_weights` of STGCN gcn.9.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of STGCN gcn.9.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.9.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 gcn.9.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN gcn.9.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of STGCN Name of parameter - Initialization information fc.weight - torch.Size([60, 256]): NormalInit: mean=0, std=0.01, bias=0 fc.bias - torch.Size([60]): NormalInit: mean=0, std=0.01, bias=0 2022/11/28 14:07:23 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d. 2022/11/28 14:07:28 - mmengine - INFO - Epoch(train) [1][100/1567] lr: 9.9996e-02 eta: 0:20:06 time: 0.0338 data_time: 0.0057 memory: 1253 loss: 2.3711 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.3711 2022/11/28 14:07:32 - mmengine - INFO - Epoch(train) [1][200/1567] lr: 9.9984e-02 eta: 0:17:01 time: 0.0337 data_time: 0.0059 memory: 1253 loss: 1.5725 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.5725 2022/11/28 14:07:35 - mmengine - INFO - Epoch(train) [1][300/1567] lr: 9.9965e-02 eta: 0:15:54 time: 0.0332 data_time: 0.0058 memory: 1253 loss: 1.3383 top1_acc: 0.3125 top5_acc: 0.8125 loss_cls: 1.3383 2022/11/28 14:07:38 - mmengine - INFO - Epoch(train) [1][400/1567] lr: 9.9938e-02 eta: 0:15:18 time: 0.0334 data_time: 0.0058 memory: 1253 loss: 1.0360 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.0360 2022/11/28 14:07:42 - mmengine - INFO - Epoch(train) [1][500/1567] lr: 9.9902e-02 eta: 0:14:58 time: 0.0348 data_time: 0.0062 memory: 1253 loss: 0.9256 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 0.9256 2022/11/28 14:07:45 - mmengine - INFO - Epoch(train) [1][600/1567] lr: 9.9859e-02 eta: 0:14:47 time: 0.0353 data_time: 0.0057 memory: 1253 loss: 0.9326 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.9326 2022/11/28 14:07:49 - mmengine - INFO - Epoch(train) [1][700/1567] lr: 9.9808e-02 eta: 0:14:40 time: 0.0352 data_time: 0.0058 memory: 1253 loss: 0.7476 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7476 2022/11/28 14:07:52 - mmengine - INFO - Epoch(train) [1][800/1567] lr: 9.9750e-02 eta: 0:14:32 time: 0.0347 data_time: 0.0059 memory: 1253 loss: 0.7355 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.7355 2022/11/28 14:07:55 - mmengine - INFO - Epoch(train) [1][900/1567] lr: 9.9683e-02 eta: 0:14:22 time: 0.0343 data_time: 0.0059 memory: 1253 loss: 0.8019 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 0.8019 2022/11/28 14:07:59 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:07:59 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 0:14:14 time: 0.0331 data_time: 0.0058 memory: 1253 loss: 0.7439 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7439 2022/11/28 14:08:02 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 0:14:06 time: 0.0338 data_time: 0.0059 memory: 1253 loss: 0.7304 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7304 2022/11/28 14:08:06 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 0:13:59 time: 0.0333 data_time: 0.0060 memory: 1253 loss: 0.6260 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.6260 2022/11/28 14:08:09 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 0:13:52 time: 0.0339 data_time: 0.0058 memory: 1253 loss: 0.5959 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5959 2022/11/28 14:08:12 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 0:13:47 time: 0.0342 data_time: 0.0058 memory: 1253 loss: 0.6029 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6029 2022/11/28 14:08:16 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 0:13:44 time: 0.0336 data_time: 0.0058 memory: 1253 loss: 0.5871 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5871 2022/11/28 14:08:18 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:08:18 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 0:13:41 time: 0.0356 data_time: 0.0059 memory: 1253 loss: 0.7203 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7203 2022/11/28 14:08:18 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/11/28 14:08:20 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:00 time: 0.0154 data_time: 0.0058 memory: 262 2022/11/28 14:08:21 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.5658 acc/top5: 0.9383 acc/mean1: 0.5660 2022/11/28 14:08:21 - mmengine - INFO - The best checkpoint with 0.5658 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/11/28 14:08:25 - mmengine - INFO - Epoch(train) [2][100/1567] lr: 9.8914e-02 eta: 0:13:39 time: 0.0357 data_time: 0.0067 memory: 1253 loss: 0.4910 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4910 2022/11/28 14:08:28 - mmengine - INFO - Epoch(train) [2][200/1567] lr: 9.8781e-02 eta: 0:13:34 time: 0.0340 data_time: 0.0060 memory: 1253 loss: 0.5837 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5837 2022/11/28 14:08:32 - mmengine - INFO - Epoch(train) [2][300/1567] lr: 9.8639e-02 eta: 0:13:30 time: 0.0348 data_time: 0.0062 memory: 1253 loss: 0.5080 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5080 2022/11/28 14:08:35 - mmengine - INFO - Epoch(train) [2][400/1567] lr: 9.8491e-02 eta: 0:13:25 time: 0.0332 data_time: 0.0059 memory: 1253 loss: 0.4379 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4379 2022/11/28 14:08:36 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:08:38 - mmengine - INFO - Epoch(train) [2][500/1567] lr: 9.8334e-02 eta: 0:13:20 time: 0.0333 data_time: 0.0060 memory: 1253 loss: 0.4499 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4499 2022/11/28 14:08:42 - mmengine - INFO - Epoch(train) [2][600/1567] lr: 9.8170e-02 eta: 0:13:16 time: 0.0339 data_time: 0.0060 memory: 1253 loss: 0.4420 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4420 2022/11/28 14:08:45 - mmengine - INFO - Epoch(train) [2][700/1567] lr: 9.7998e-02 eta: 0:13:11 time: 0.0334 data_time: 0.0061 memory: 1253 loss: 0.5145 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5145 2022/11/28 14:08:49 - mmengine - INFO - Epoch(train) [2][800/1567] lr: 9.7819e-02 eta: 0:13:07 time: 0.0333 data_time: 0.0061 memory: 1253 loss: 0.4827 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4827 2022/11/28 14:08:52 - mmengine - INFO - Epoch(train) [2][900/1567] lr: 9.7632e-02 eta: 0:13:02 time: 0.0345 data_time: 0.0061 memory: 1253 loss: 0.4773 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4773 2022/11/28 14:08:55 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:12:58 time: 0.0332 data_time: 0.0059 memory: 1253 loss: 0.4481 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4481 2022/11/28 14:08:59 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:12:54 time: 0.0340 data_time: 0.0060 memory: 1253 loss: 0.4990 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4990 2022/11/28 14:09:02 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:12:50 time: 0.0345 data_time: 0.0064 memory: 1253 loss: 0.3314 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3314 2022/11/28 14:09:06 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:12:48 time: 0.0358 data_time: 0.0067 memory: 1253 loss: 0.4215 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4215 2022/11/28 14:09:09 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:12:45 time: 0.0363 data_time: 0.0063 memory: 1253 loss: 0.3336 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3336 2022/11/28 14:09:10 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:09:13 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:12:41 time: 0.0334 data_time: 0.0062 memory: 1253 loss: 0.4218 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4218 2022/11/28 14:09:15 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:09:15 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:12:39 time: 0.0329 data_time: 0.0059 memory: 1253 loss: 0.4646 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4646 2022/11/28 14:09:15 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/11/28 14:09:17 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:00 time: 0.0149 data_time: 0.0056 memory: 262 2022/11/28 14:09:17 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.7215 acc/top5: 0.9662 acc/mean1: 0.7213 2022/11/28 14:09:17 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_1.pth is removed 2022/11/28 14:09:18 - mmengine - INFO - The best checkpoint with 0.7215 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/11/28 14:09:21 - mmengine - INFO - Epoch(train) [3][100/1567] lr: 9.5953e-02 eta: 0:12:36 time: 0.0354 data_time: 0.0061 memory: 1253 loss: 0.3789 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3789 2022/11/28 14:09:25 - mmengine - INFO - Epoch(train) [3][200/1567] lr: 9.5703e-02 eta: 0:12:33 time: 0.0336 data_time: 0.0060 memory: 1253 loss: 0.4364 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4364 2022/11/28 14:09:28 - mmengine - INFO - Epoch(train) [3][300/1567] lr: 9.5445e-02 eta: 0:12:29 time: 0.0345 data_time: 0.0059 memory: 1253 loss: 0.3950 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3950 2022/11/28 14:09:32 - mmengine - INFO - Epoch(train) [3][400/1567] lr: 9.5180e-02 eta: 0:12:25 time: 0.0342 data_time: 0.0062 memory: 1253 loss: 0.3970 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3970 2022/11/28 14:09:35 - mmengine - INFO - Epoch(train) [3][500/1567] lr: 9.4908e-02 eta: 0:12:22 time: 0.0335 data_time: 0.0062 memory: 1253 loss: 0.4666 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4666 2022/11/28 14:09:39 - mmengine - INFO - Epoch(train) [3][600/1567] lr: 9.4629e-02 eta: 0:12:18 time: 0.0340 data_time: 0.0064 memory: 1253 loss: 0.3603 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3603 2022/11/28 14:09:42 - mmengine - INFO - Epoch(train) [3][700/1567] lr: 9.4343e-02 eta: 0:12:15 time: 0.0347 data_time: 0.0061 memory: 1253 loss: 0.4291 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4291 2022/11/28 14:09:45 - mmengine - INFO - Epoch(train) [3][800/1567] lr: 9.4050e-02 eta: 0:12:11 time: 0.0334 data_time: 0.0063 memory: 1253 loss: 0.3233 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3233 2022/11/28 14:09:48 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:09:49 - mmengine - INFO - Epoch(train) [3][900/1567] lr: 9.3750e-02 eta: 0:12:07 time: 0.0333 data_time: 0.0061 memory: 1253 loss: 0.2989 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2989 2022/11/28 14:09:52 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:12:03 time: 0.0331 data_time: 0.0061 memory: 1253 loss: 0.4114 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4114 2022/11/28 14:09:55 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:11:59 time: 0.0348 data_time: 0.0061 memory: 1253 loss: 0.4458 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4458 2022/11/28 14:09:59 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:11:55 time: 0.0332 data_time: 0.0059 memory: 1253 loss: 0.2953 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2953 2022/11/28 14:10:02 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:11:52 time: 0.0366 data_time: 0.0062 memory: 1253 loss: 0.3327 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3327 2022/11/28 14:10:06 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:11:48 time: 0.0330 data_time: 0.0061 memory: 1253 loss: 0.3866 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3866 2022/11/28 14:10:09 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:11:44 time: 0.0343 data_time: 0.0065 memory: 1253 loss: 0.3130 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3130 2022/11/28 14:10:11 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:10:11 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:11:42 time: 0.0340 data_time: 0.0059 memory: 1253 loss: 0.4260 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4260 2022/11/28 14:10:11 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/11/28 14:10:13 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:00 time: 0.0149 data_time: 0.0059 memory: 262 2022/11/28 14:10:14 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.7337 acc/top5: 0.9707 acc/mean1: 0.7336 2022/11/28 14:10:14 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_2.pth is removed 2022/11/28 14:10:14 - mmengine - INFO - The best checkpoint with 0.7337 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2022/11/28 14:10:18 - mmengine - INFO - Epoch(train) [4][100/1567] lr: 9.1226e-02 eta: 0:11:39 time: 0.0349 data_time: 0.0061 memory: 1253 loss: 0.3457 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3457 2022/11/28 14:10:21 - mmengine - INFO - Epoch(train) [4][200/1567] lr: 9.0868e-02 eta: 0:11:36 time: 0.0347 data_time: 0.0062 memory: 1253 loss: 0.2712 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2712 2022/11/28 14:10:24 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:10:25 - mmengine - INFO - Epoch(train) [4][300/1567] lr: 9.0504e-02 eta: 0:11:32 time: 0.0345 data_time: 0.0061 memory: 1253 loss: 0.3489 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3489 2022/11/28 14:10:28 - mmengine - INFO - Epoch(train) [4][400/1567] lr: 9.0133e-02 eta: 0:11:29 time: 0.0342 data_time: 0.0061 memory: 1253 loss: 0.3817 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3817 2022/11/28 14:10:31 - mmengine - INFO - Epoch(train) [4][500/1567] lr: 8.9756e-02 eta: 0:11:25 time: 0.0340 data_time: 0.0062 memory: 1253 loss: 0.3366 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3366 2022/11/28 14:10:35 - mmengine - INFO - Epoch(train) [4][600/1567] lr: 8.9373e-02 eta: 0:11:22 time: 0.0337 data_time: 0.0061 memory: 1253 loss: 0.3073 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3073 2022/11/28 14:10:38 - mmengine - INFO - Epoch(train) [4][700/1567] lr: 8.8984e-02 eta: 0:11:18 time: 0.0335 data_time: 0.0060 memory: 1253 loss: 0.3149 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3149 2022/11/28 14:10:42 - mmengine - INFO - Epoch(train) [4][800/1567] lr: 8.8589e-02 eta: 0:11:14 time: 0.0337 data_time: 0.0061 memory: 1253 loss: 0.3185 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3185 2022/11/28 14:10:45 - mmengine - INFO - Epoch(train) [4][900/1567] lr: 8.8187e-02 eta: 0:11:11 time: 0.0332 data_time: 0.0060 memory: 1253 loss: 0.2759 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2759 2022/11/28 14:10:48 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:11:07 time: 0.0330 data_time: 0.0060 memory: 1253 loss: 0.3045 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3045 2022/11/28 14:10:52 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:11:03 time: 0.0333 data_time: 0.0061 memory: 1253 loss: 0.3083 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3083 2022/11/28 14:10:55 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:10:59 time: 0.0348 data_time: 0.0076 memory: 1253 loss: 0.3000 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3000 2022/11/28 14:10:59 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:10:59 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:10:56 time: 0.0342 data_time: 0.0061 memory: 1253 loss: 0.2593 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2593 2022/11/28 14:11:02 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:10:53 time: 0.0344 data_time: 0.0069 memory: 1253 loss: 0.2799 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2799 2022/11/28 14:11:05 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:10:49 time: 0.0335 data_time: 0.0063 memory: 1253 loss: 0.3478 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3478 2022/11/28 14:11:08 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:11:08 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:10:47 time: 0.0331 data_time: 0.0060 memory: 1253 loss: 0.3982 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3982 2022/11/28 14:11:08 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/11/28 14:11:10 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:00 time: 0.0145 data_time: 0.0055 memory: 262 2022/11/28 14:11:10 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7732 acc/top5: 0.9682 acc/mean1: 0.7731 2022/11/28 14:11:10 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_3.pth is removed 2022/11/28 14:11:11 - mmengine - INFO - The best checkpoint with 0.7732 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2022/11/28 14:11:14 - mmengine - INFO - Epoch(train) [5][100/1567] lr: 8.4914e-02 eta: 0:10:44 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.2653 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2653 2022/11/28 14:11:18 - mmengine - INFO - Epoch(train) [5][200/1567] lr: 8.4463e-02 eta: 0:10:40 time: 0.0344 data_time: 0.0068 memory: 1253 loss: 0.2483 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2483 2022/11/28 14:11:21 - mmengine - INFO - Epoch(train) [5][300/1567] lr: 8.4006e-02 eta: 0:10:37 time: 0.0351 data_time: 0.0062 memory: 1253 loss: 0.2937 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2937 2022/11/28 14:11:24 - mmengine - INFO - Epoch(train) [5][400/1567] lr: 8.3544e-02 eta: 0:10:34 time: 0.0345 data_time: 0.0061 memory: 1253 loss: 0.2019 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2019 2022/11/28 14:11:28 - mmengine - INFO - Epoch(train) [5][500/1567] lr: 8.3077e-02 eta: 0:10:30 time: 0.0340 data_time: 0.0063 memory: 1253 loss: 0.2490 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2490 2022/11/28 14:11:31 - mmengine - INFO - Epoch(train) [5][600/1567] lr: 8.2605e-02 eta: 0:10:26 time: 0.0344 data_time: 0.0064 memory: 1253 loss: 0.2804 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2804 2022/11/28 14:11:35 - mmengine - INFO - Epoch(train) [5][700/1567] lr: 8.2127e-02 eta: 0:10:23 time: 0.0348 data_time: 0.0069 memory: 1253 loss: 0.2641 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2641 2022/11/28 14:11:36 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:11:38 - mmengine - INFO - Epoch(train) [5][800/1567] lr: 8.1645e-02 eta: 0:10:20 time: 0.0343 data_time: 0.0061 memory: 1253 loss: 0.2955 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2955 2022/11/28 14:11:42 - mmengine - INFO - Epoch(train) [5][900/1567] lr: 8.1157e-02 eta: 0:10:16 time: 0.0336 data_time: 0.0062 memory: 1253 loss: 0.2955 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2955 2022/11/28 14:11:45 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:10:13 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.2452 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2452 2022/11/28 14:11:49 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:10:09 time: 0.0347 data_time: 0.0063 memory: 1253 loss: 0.2631 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2631 2022/11/28 14:11:52 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:10:06 time: 0.0334 data_time: 0.0062 memory: 1253 loss: 0.2555 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2555 2022/11/28 14:11:55 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:10:02 time: 0.0353 data_time: 0.0061 memory: 1253 loss: 0.3454 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3454 2022/11/28 14:11:59 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:09:59 time: 0.0342 data_time: 0.0063 memory: 1253 loss: 0.2724 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2724 2022/11/28 14:12:02 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:09:56 time: 0.0339 data_time: 0.0062 memory: 1253 loss: 0.2506 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2506 2022/11/28 14:12:05 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:12:05 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:09:53 time: 0.0328 data_time: 0.0059 memory: 1253 loss: 0.4750 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4750 2022/11/28 14:12:05 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/11/28 14:12:06 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:00 time: 0.0151 data_time: 0.0058 memory: 262 2022/11/28 14:12:07 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7966 acc/top5: 0.9791 acc/mean1: 0.7966 2022/11/28 14:12:07 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_4.pth is removed 2022/11/28 14:12:07 - mmengine - INFO - The best checkpoint with 0.7966 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2022/11/28 14:12:11 - mmengine - INFO - Epoch(train) [6][100/1567] lr: 7.7261e-02 eta: 0:09:50 time: 0.0337 data_time: 0.0060 memory: 1253 loss: 0.2820 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.2820 2022/11/28 14:12:13 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:12:14 - mmengine - INFO - Epoch(train) [6][200/1567] lr: 7.6733e-02 eta: 0:09:46 time: 0.0338 data_time: 0.0062 memory: 1253 loss: 0.2503 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2503 2022/11/28 14:12:18 - mmengine - INFO - Epoch(train) [6][300/1567] lr: 7.6202e-02 eta: 0:09:43 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.2798 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2798 2022/11/28 14:12:21 - mmengine - INFO - Epoch(train) [6][400/1567] lr: 7.5666e-02 eta: 0:09:39 time: 0.0346 data_time: 0.0073 memory: 1253 loss: 0.2124 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2124 2022/11/28 14:12:25 - mmengine - INFO - Epoch(train) [6][500/1567] lr: 7.5126e-02 eta: 0:09:36 time: 0.0332 data_time: 0.0061 memory: 1253 loss: 0.2107 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2107 2022/11/28 14:12:28 - mmengine - INFO - Epoch(train) [6][600/1567] lr: 7.4583e-02 eta: 0:09:32 time: 0.0334 data_time: 0.0062 memory: 1253 loss: 0.1887 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1887 2022/11/28 14:12:31 - mmengine - INFO - Epoch(train) [6][700/1567] lr: 7.4035e-02 eta: 0:09:28 time: 0.0334 data_time: 0.0061 memory: 1253 loss: 0.3036 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3036 2022/11/28 14:12:35 - mmengine - INFO - Epoch(train) [6][800/1567] lr: 7.3484e-02 eta: 0:09:25 time: 0.0333 data_time: 0.0061 memory: 1253 loss: 0.2626 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2626 2022/11/28 14:12:38 - mmengine - INFO - Epoch(train) [6][900/1567] lr: 7.2929e-02 eta: 0:09:21 time: 0.0333 data_time: 0.0062 memory: 1253 loss: 0.1886 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1886 2022/11/28 14:12:41 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:09:18 time: 0.0339 data_time: 0.0063 memory: 1253 loss: 0.2305 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2305 2022/11/28 14:12:45 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:09:14 time: 0.0333 data_time: 0.0061 memory: 1253 loss: 0.2266 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2266 2022/11/28 14:12:47 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:12:48 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:09:11 time: 0.0333 data_time: 0.0061 memory: 1253 loss: 0.2174 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2174 2022/11/28 14:12:52 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:09:07 time: 0.0350 data_time: 0.0061 memory: 1253 loss: 0.2062 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2062 2022/11/28 14:12:55 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:09:04 time: 0.0337 data_time: 0.0061 memory: 1253 loss: 0.2625 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2625 2022/11/28 14:12:58 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:09:00 time: 0.0336 data_time: 0.0062 memory: 1253 loss: 0.2460 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2460 2022/11/28 14:13:01 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:13:01 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:08:58 time: 0.0329 data_time: 0.0060 memory: 1253 loss: 0.3188 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3188 2022/11/28 14:13:01 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/11/28 14:13:03 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:00 time: 0.0156 data_time: 0.0064 memory: 262 2022/11/28 14:13:03 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.8243 acc/top5: 0.9858 acc/mean1: 0.8242 2022/11/28 14:13:03 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_5.pth is removed 2022/11/28 14:13:04 - mmengine - INFO - The best checkpoint with 0.8243 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2022/11/28 14:13:07 - mmengine - INFO - Epoch(train) [7][100/1567] lr: 6.8560e-02 eta: 0:08:54 time: 0.0335 data_time: 0.0062 memory: 1253 loss: 0.2560 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2560 2022/11/28 14:13:10 - mmengine - INFO - Epoch(train) [7][200/1567] lr: 6.7976e-02 eta: 0:08:51 time: 0.0357 data_time: 0.0063 memory: 1253 loss: 0.2576 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2576 2022/11/28 14:13:14 - mmengine - INFO - Epoch(train) [7][300/1567] lr: 6.7390e-02 eta: 0:08:48 time: 0.0337 data_time: 0.0062 memory: 1253 loss: 0.2070 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2070 2022/11/28 14:13:17 - mmengine - INFO - Epoch(train) [7][400/1567] lr: 6.6802e-02 eta: 0:08:44 time: 0.0340 data_time: 0.0061 memory: 1253 loss: 0.1484 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1484 2022/11/28 14:13:21 - mmengine - INFO - Epoch(train) [7][500/1567] lr: 6.6210e-02 eta: 0:08:41 time: 0.0348 data_time: 0.0066 memory: 1253 loss: 0.1974 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1974 2022/11/28 14:13:24 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:13:24 - mmengine - INFO - Epoch(train) [7][600/1567] lr: 6.5616e-02 eta: 0:08:37 time: 0.0342 data_time: 0.0064 memory: 1253 loss: 0.2532 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2532 2022/11/28 14:13:28 - mmengine - INFO - Epoch(train) [7][700/1567] lr: 6.5020e-02 eta: 0:08:34 time: 0.0334 data_time: 0.0061 memory: 1253 loss: 0.2074 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2074 2022/11/28 14:13:31 - mmengine - INFO - Epoch(train) [7][800/1567] lr: 6.4421e-02 eta: 0:08:30 time: 0.0336 data_time: 0.0062 memory: 1253 loss: 0.2016 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2016 2022/11/28 14:13:34 - mmengine - INFO - Epoch(train) [7][900/1567] lr: 6.3820e-02 eta: 0:08:27 time: 0.0346 data_time: 0.0064 memory: 1253 loss: 0.1902 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1902 2022/11/28 14:13:38 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:08:23 time: 0.0341 data_time: 0.0060 memory: 1253 loss: 0.2715 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2715 2022/11/28 14:13:41 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:08:20 time: 0.0345 data_time: 0.0063 memory: 1253 loss: 0.1568 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1568 2022/11/28 14:13:45 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:08:17 time: 0.0337 data_time: 0.0061 memory: 1253 loss: 0.1968 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1968 2022/11/28 14:13:48 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:08:13 time: 0.0344 data_time: 0.0062 memory: 1253 loss: 0.1603 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1603 2022/11/28 14:13:52 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:08:10 time: 0.0344 data_time: 0.0062 memory: 1253 loss: 0.1853 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1853 2022/11/28 14:13:55 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:08:07 time: 0.0360 data_time: 0.0068 memory: 1253 loss: 0.2350 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2350 2022/11/28 14:13:58 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:13:58 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:08:04 time: 0.0332 data_time: 0.0062 memory: 1253 loss: 0.3988 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3988 2022/11/28 14:13:58 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/11/28 14:13:59 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:00 time: 0.0148 data_time: 0.0057 memory: 262 2022/11/28 14:14:00 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.8519 acc/top5: 0.9862 acc/mean1: 0.8518 2022/11/28 14:14:00 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_6.pth is removed 2022/11/28 14:14:00 - mmengine - INFO - The best checkpoint with 0.8519 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2022/11/28 14:14:02 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:14:04 - mmengine - INFO - Epoch(train) [8][100/1567] lr: 5.9145e-02 eta: 0:08:01 time: 0.0345 data_time: 0.0068 memory: 1253 loss: 0.1999 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1999 2022/11/28 14:14:08 - mmengine - INFO - Epoch(train) [8][200/1567] lr: 5.8529e-02 eta: 0:07:58 time: 0.0340 data_time: 0.0062 memory: 1253 loss: 0.1575 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1575 2022/11/28 14:14:11 - mmengine - INFO - Epoch(train) [8][300/1567] lr: 5.7911e-02 eta: 0:07:54 time: 0.0355 data_time: 0.0060 memory: 1253 loss: 0.1938 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1938 2022/11/28 14:14:15 - mmengine - INFO - Epoch(train) [8][400/1567] lr: 5.7292e-02 eta: 0:07:51 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.1947 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1947 2022/11/28 14:14:18 - mmengine - INFO - Epoch(train) [8][500/1567] lr: 5.6671e-02 eta: 0:07:47 time: 0.0337 data_time: 0.0062 memory: 1253 loss: 0.2121 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2121 2022/11/28 14:14:21 - mmengine - INFO - Epoch(train) [8][600/1567] lr: 5.6050e-02 eta: 0:07:44 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.1780 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1780 2022/11/28 14:14:25 - mmengine - INFO - Epoch(train) [8][700/1567] lr: 5.5427e-02 eta: 0:07:41 time: 0.0351 data_time: 0.0061 memory: 1253 loss: 0.1768 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1768 2022/11/28 14:14:28 - mmengine - INFO - Epoch(train) [8][800/1567] lr: 5.4804e-02 eta: 0:07:37 time: 0.0338 data_time: 0.0062 memory: 1253 loss: 0.2091 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2091 2022/11/28 14:14:32 - mmengine - INFO - Epoch(train) [8][900/1567] lr: 5.4180e-02 eta: 0:07:34 time: 0.0344 data_time: 0.0063 memory: 1253 loss: 0.1722 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1722 2022/11/28 14:14:35 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:07:30 time: 0.0336 data_time: 0.0063 memory: 1253 loss: 0.1737 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1737 2022/11/28 14:14:36 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:14:39 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:07:27 time: 0.0338 data_time: 0.0062 memory: 1253 loss: 0.1611 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1611 2022/11/28 14:14:42 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:07:23 time: 0.0335 data_time: 0.0062 memory: 1253 loss: 0.1501 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1501 2022/11/28 14:14:45 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:07:20 time: 0.0343 data_time: 0.0068 memory: 1253 loss: 0.1874 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1874 2022/11/28 14:14:49 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:07:16 time: 0.0353 data_time: 0.0062 memory: 1253 loss: 0.1373 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1373 2022/11/28 14:14:52 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:07:13 time: 0.0334 data_time: 0.0061 memory: 1253 loss: 0.1242 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1242 2022/11/28 14:14:55 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:14:55 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:07:11 time: 0.0336 data_time: 0.0059 memory: 1253 loss: 0.3048 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3048 2022/11/28 14:14:55 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/11/28 14:14:56 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:00 time: 0.0147 data_time: 0.0056 memory: 262 2022/11/28 14:14:57 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.8529 acc/top5: 0.9847 acc/mean1: 0.8526 2022/11/28 14:14:57 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_7.pth is removed 2022/11/28 14:14:57 - mmengine - INFO - The best checkpoint with 0.8529 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/11/28 14:15:01 - mmengine - INFO - Epoch(train) [9][100/1567] lr: 4.9380e-02 eta: 0:07:07 time: 0.0340 data_time: 0.0061 memory: 1253 loss: 0.1229 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1229 2022/11/28 14:15:04 - mmengine - INFO - Epoch(train) [9][200/1567] lr: 4.8753e-02 eta: 0:07:04 time: 0.0347 data_time: 0.0060 memory: 1253 loss: 0.1250 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1250 2022/11/28 14:15:08 - mmengine - INFO - Epoch(train) [9][300/1567] lr: 4.8127e-02 eta: 0:07:00 time: 0.0341 data_time: 0.0062 memory: 1253 loss: 0.1362 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1362 2022/11/28 14:15:11 - mmengine - INFO - Epoch(train) [9][400/1567] lr: 4.7501e-02 eta: 0:06:57 time: 0.0342 data_time: 0.0062 memory: 1253 loss: 0.1681 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1681 2022/11/28 14:15:14 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:15:15 - mmengine - INFO - Epoch(train) [9][500/1567] lr: 4.6876e-02 eta: 0:06:53 time: 0.0352 data_time: 0.0062 memory: 1253 loss: 0.1431 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1431 2022/11/28 14:15:18 - mmengine - INFO - Epoch(train) [9][600/1567] lr: 4.6251e-02 eta: 0:06:50 time: 0.0356 data_time: 0.0063 memory: 1253 loss: 0.1191 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1191 2022/11/28 14:15:22 - mmengine - INFO - Epoch(train) [9][700/1567] lr: 4.5626e-02 eta: 0:06:47 time: 0.0352 data_time: 0.0061 memory: 1253 loss: 0.1437 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1437 2022/11/28 14:15:25 - mmengine - INFO - Epoch(train) [9][800/1567] lr: 4.5003e-02 eta: 0:06:43 time: 0.0344 data_time: 0.0063 memory: 1253 loss: 0.1201 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1201 2022/11/28 14:15:29 - mmengine - INFO - Epoch(train) [9][900/1567] lr: 4.4380e-02 eta: 0:06:40 time: 0.0358 data_time: 0.0062 memory: 1253 loss: 0.1063 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1063 2022/11/28 14:15:33 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:06:37 time: 0.0362 data_time: 0.0065 memory: 1253 loss: 0.1065 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1065 2022/11/28 14:15:36 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:06:33 time: 0.0344 data_time: 0.0062 memory: 1253 loss: 0.0990 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0990 2022/11/28 14:15:40 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:06:30 time: 0.0350 data_time: 0.0062 memory: 1253 loss: 0.1508 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1508 2022/11/28 14:15:43 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:06:26 time: 0.0354 data_time: 0.0060 memory: 1253 loss: 0.1459 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1459 2022/11/28 14:15:47 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:06:23 time: 0.0342 data_time: 0.0062 memory: 1253 loss: 0.1347 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1347 2022/11/28 14:15:49 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:15:50 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:06:20 time: 0.0338 data_time: 0.0061 memory: 1253 loss: 0.1357 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1357 2022/11/28 14:15:52 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:15:52 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:06:17 time: 0.0339 data_time: 0.0059 memory: 1253 loss: 0.3418 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3418 2022/11/28 14:15:52 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/11/28 14:15:54 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:00 time: 0.0146 data_time: 0.0056 memory: 262 2022/11/28 14:15:55 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8537 acc/top5: 0.9859 acc/mean1: 0.8537 2022/11/28 14:15:55 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_8.pth is removed 2022/11/28 14:15:55 - mmengine - INFO - The best checkpoint with 0.8537 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2022/11/28 14:15:59 - mmengine - INFO - Epoch(train) [10][100/1567] lr: 3.9638e-02 eta: 0:06:14 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.1218 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1218 2022/11/28 14:16:02 - mmengine - INFO - Epoch(train) [10][200/1567] lr: 3.9026e-02 eta: 0:06:10 time: 0.0344 data_time: 0.0062 memory: 1253 loss: 0.0829 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0829 2022/11/28 14:16:06 - mmengine - INFO - Epoch(train) [10][300/1567] lr: 3.8415e-02 eta: 0:06:07 time: 0.0345 data_time: 0.0068 memory: 1253 loss: 0.1224 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1224 2022/11/28 14:16:09 - mmengine - INFO - Epoch(train) [10][400/1567] lr: 3.7807e-02 eta: 0:06:04 time: 0.0340 data_time: 0.0062 memory: 1253 loss: 0.1661 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1661 2022/11/28 14:16:13 - mmengine - INFO - Epoch(train) [10][500/1567] lr: 3.7200e-02 eta: 0:06:00 time: 0.0346 data_time: 0.0061 memory: 1253 loss: 0.0941 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0941 2022/11/28 14:16:16 - mmengine - INFO - Epoch(train) [10][600/1567] lr: 3.6596e-02 eta: 0:05:57 time: 0.0341 data_time: 0.0061 memory: 1253 loss: 0.1147 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1147 2022/11/28 14:16:19 - mmengine - INFO - Epoch(train) [10][700/1567] lr: 3.5993e-02 eta: 0:05:53 time: 0.0349 data_time: 0.0062 memory: 1253 loss: 0.0878 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0878 2022/11/28 14:16:23 - mmengine - INFO - Epoch(train) [10][800/1567] lr: 3.5393e-02 eta: 0:05:50 time: 0.0355 data_time: 0.0060 memory: 1253 loss: 0.0974 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0974 2022/11/28 14:16:26 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:16:26 - mmengine - INFO - Epoch(train) [10][900/1567] lr: 3.4795e-02 eta: 0:05:46 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.1057 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1057 2022/11/28 14:16:30 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:05:43 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.1027 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1027 2022/11/28 14:16:33 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:05:39 time: 0.0337 data_time: 0.0061 memory: 1253 loss: 0.0971 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0971 2022/11/28 14:16:37 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:05:36 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.1494 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1494 2022/11/28 14:16:40 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:05:32 time: 0.0339 data_time: 0.0060 memory: 1253 loss: 0.0997 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0997 2022/11/28 14:16:43 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:05:29 time: 0.0355 data_time: 0.0069 memory: 1253 loss: 0.1203 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1203 2022/11/28 14:16:47 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:05:26 time: 0.0346 data_time: 0.0066 memory: 1253 loss: 0.0684 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0684 2022/11/28 14:16:49 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:16:49 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:05:23 time: 0.0342 data_time: 0.0060 memory: 1253 loss: 0.3104 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3104 2022/11/28 14:16:49 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/11/28 14:16:51 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:00 time: 0.0147 data_time: 0.0057 memory: 262 2022/11/28 14:16:52 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8740 acc/top5: 0.9880 acc/mean1: 0.8739 2022/11/28 14:16:52 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_9.pth is removed 2022/11/28 14:16:52 - mmengine - INFO - The best checkpoint with 0.8740 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/11/28 14:16:56 - mmengine - INFO - Epoch(train) [11][100/1567] lr: 3.0294e-02 eta: 0:05:20 time: 0.0335 data_time: 0.0061 memory: 1253 loss: 0.0846 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0846 2022/11/28 14:16:59 - mmengine - INFO - Epoch(train) [11][200/1567] lr: 2.9720e-02 eta: 0:05:16 time: 0.0337 data_time: 0.0062 memory: 1253 loss: 0.0777 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0777 2022/11/28 14:17:02 - mmengine - INFO - Epoch(train) [11][300/1567] lr: 2.9149e-02 eta: 0:05:13 time: 0.0352 data_time: 0.0062 memory: 1253 loss: 0.1337 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1337 2022/11/28 14:17:03 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:17:06 - mmengine - INFO - Epoch(train) [11][400/1567] lr: 2.8581e-02 eta: 0:05:10 time: 0.0333 data_time: 0.0061 memory: 1253 loss: 0.0662 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0662 2022/11/28 14:17:09 - mmengine - INFO - Epoch(train) [11][500/1567] lr: 2.8017e-02 eta: 0:05:06 time: 0.0340 data_time: 0.0061 memory: 1253 loss: 0.0652 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0652 2022/11/28 14:17:13 - mmengine - INFO - Epoch(train) [11][600/1567] lr: 2.7456e-02 eta: 0:05:03 time: 0.0345 data_time: 0.0061 memory: 1253 loss: 0.0897 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0897 2022/11/28 14:17:16 - mmengine - INFO - Epoch(train) [11][700/1567] lr: 2.6898e-02 eta: 0:04:59 time: 0.0333 data_time: 0.0061 memory: 1253 loss: 0.0774 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0774 2022/11/28 14:17:19 - mmengine - INFO - Epoch(train) [11][800/1567] lr: 2.6345e-02 eta: 0:04:56 time: 0.0335 data_time: 0.0061 memory: 1253 loss: 0.0756 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0756 2022/11/28 14:17:23 - mmengine - INFO - Epoch(train) [11][900/1567] lr: 2.5794e-02 eta: 0:04:52 time: 0.0350 data_time: 0.0061 memory: 1253 loss: 0.0812 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0812 2022/11/28 14:17:26 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:04:49 time: 0.0334 data_time: 0.0061 memory: 1253 loss: 0.0609 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0609 2022/11/28 14:17:30 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:04:45 time: 0.0351 data_time: 0.0062 memory: 1253 loss: 0.0762 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0762 2022/11/28 14:17:33 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:04:42 time: 0.0360 data_time: 0.0061 memory: 1253 loss: 0.0799 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0799 2022/11/28 14:17:37 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:04:39 time: 0.0341 data_time: 0.0061 memory: 1253 loss: 0.0681 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0681 2022/11/28 14:17:38 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:17:40 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:04:35 time: 0.0349 data_time: 0.0061 memory: 1253 loss: 0.0507 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0507 2022/11/28 14:17:44 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:04:32 time: 0.0350 data_time: 0.0061 memory: 1253 loss: 0.0492 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0492 2022/11/28 14:17:46 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:17:46 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:04:29 time: 0.0345 data_time: 0.0064 memory: 1253 loss: 0.2304 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2304 2022/11/28 14:17:46 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/11/28 14:17:48 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:00 time: 0.0148 data_time: 0.0057 memory: 262 2022/11/28 14:17:49 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8792 acc/top5: 0.9904 acc/mean1: 0.8791 2022/11/28 14:17:49 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_10.pth is removed 2022/11/28 14:17:49 - mmengine - INFO - The best checkpoint with 0.8792 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/11/28 14:17:52 - mmengine - INFO - Epoch(train) [12][100/1567] lr: 2.1708e-02 eta: 0:04:26 time: 0.0340 data_time: 0.0060 memory: 1253 loss: 0.0518 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0518 2022/11/28 14:17:56 - mmengine - INFO - Epoch(train) [12][200/1567] lr: 2.1194e-02 eta: 0:04:23 time: 0.0346 data_time: 0.0061 memory: 1253 loss: 0.0374 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0374 2022/11/28 14:17:59 - mmengine - INFO - Epoch(train) [12][300/1567] lr: 2.0684e-02 eta: 0:04:19 time: 0.0334 data_time: 0.0061 memory: 1253 loss: 0.0654 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0654 2022/11/28 14:18:03 - mmengine - INFO - Epoch(train) [12][400/1567] lr: 2.0179e-02 eta: 0:04:16 time: 0.0338 data_time: 0.0060 memory: 1253 loss: 0.0508 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0508 2022/11/28 14:18:06 - mmengine - INFO - Epoch(train) [12][500/1567] lr: 1.9678e-02 eta: 0:04:12 time: 0.0337 data_time: 0.0061 memory: 1253 loss: 0.0579 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0579 2022/11/28 14:18:09 - mmengine - INFO - Epoch(train) [12][600/1567] lr: 1.9182e-02 eta: 0:04:09 time: 0.0335 data_time: 0.0060 memory: 1253 loss: 0.0674 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0674 2022/11/28 14:18:13 - mmengine - INFO - Epoch(train) [12][700/1567] lr: 1.8691e-02 eta: 0:04:05 time: 0.0347 data_time: 0.0060 memory: 1253 loss: 0.0297 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0297 2022/11/28 14:18:15 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:18:16 - mmengine - INFO - Epoch(train) [12][800/1567] lr: 1.8205e-02 eta: 0:04:02 time: 0.0337 data_time: 0.0060 memory: 1253 loss: 0.0360 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0360 2022/11/28 14:18:20 - mmengine - INFO - Epoch(train) [12][900/1567] lr: 1.7724e-02 eta: 0:03:58 time: 0.0334 data_time: 0.0061 memory: 1253 loss: 0.0329 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0329 2022/11/28 14:18:23 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:03:55 time: 0.0339 data_time: 0.0060 memory: 1253 loss: 0.0353 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0353 2022/11/28 14:18:27 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:03:51 time: 0.0338 data_time: 0.0060 memory: 1253 loss: 0.0493 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0493 2022/11/28 14:18:30 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:03:48 time: 0.0350 data_time: 0.0063 memory: 1253 loss: 0.0265 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0265 2022/11/28 14:18:34 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:03:44 time: 0.0344 data_time: 0.0060 memory: 1253 loss: 0.0254 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0254 2022/11/28 14:18:37 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:03:41 time: 0.0339 data_time: 0.0064 memory: 1253 loss: 0.0248 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0248 2022/11/28 14:18:40 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:03:38 time: 0.0346 data_time: 0.0068 memory: 1253 loss: 0.0507 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0507 2022/11/28 14:18:43 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:18:43 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:03:35 time: 0.0338 data_time: 0.0061 memory: 1253 loss: 0.2108 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2108 2022/11/28 14:18:43 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/11/28 14:18:45 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:00 time: 0.0147 data_time: 0.0056 memory: 262 2022/11/28 14:18:45 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8892 acc/top5: 0.9911 acc/mean1: 0.8890 2022/11/28 14:18:45 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_11.pth is removed 2022/11/28 14:18:45 - mmengine - INFO - The best checkpoint with 0.8892 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/11/28 14:18:49 - mmengine - INFO - Epoch(train) [13][100/1567] lr: 1.4209e-02 eta: 0:03:32 time: 0.0353 data_time: 0.0061 memory: 1253 loss: 0.0295 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0295 2022/11/28 14:18:52 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:18:53 - mmengine - INFO - Epoch(train) [13][200/1567] lr: 1.3774e-02 eta: 0:03:28 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.0153 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0153 2022/11/28 14:18:56 - mmengine - INFO - Epoch(train) [13][300/1567] lr: 1.3345e-02 eta: 0:03:25 time: 0.0344 data_time: 0.0061 memory: 1253 loss: 0.0283 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0283 2022/11/28 14:18:59 - mmengine - INFO - Epoch(train) [13][400/1567] lr: 1.2922e-02 eta: 0:03:22 time: 0.0334 data_time: 0.0061 memory: 1253 loss: 0.0149 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0149 2022/11/28 14:19:03 - mmengine - INFO - Epoch(train) [13][500/1567] lr: 1.2505e-02 eta: 0:03:18 time: 0.0357 data_time: 0.0062 memory: 1253 loss: 0.0236 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0236 2022/11/28 14:19:06 - mmengine - INFO - Epoch(train) [13][600/1567] lr: 1.2093e-02 eta: 0:03:15 time: 0.0336 data_time: 0.0062 memory: 1253 loss: 0.0160 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0160 2022/11/28 14:19:10 - mmengine - INFO - Epoch(train) [13][700/1567] lr: 1.1687e-02 eta: 0:03:11 time: 0.0342 data_time: 0.0061 memory: 1253 loss: 0.0230 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0230 2022/11/28 14:19:13 - mmengine - INFO - Epoch(train) [13][800/1567] lr: 1.1288e-02 eta: 0:03:08 time: 0.0336 data_time: 0.0062 memory: 1253 loss: 0.0148 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0148 2022/11/28 14:19:16 - mmengine - INFO - Epoch(train) [13][900/1567] lr: 1.0894e-02 eta: 0:03:04 time: 0.0335 data_time: 0.0062 memory: 1253 loss: 0.0132 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0132 2022/11/28 14:19:20 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:03:01 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.0236 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0236 2022/11/28 14:19:23 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:02:57 time: 0.0339 data_time: 0.0062 memory: 1253 loss: 0.0078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0078 2022/11/28 14:19:27 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:19:27 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:02:54 time: 0.0350 data_time: 0.0074 memory: 1253 loss: 0.0236 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0236 2022/11/28 14:19:30 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:02:51 time: 0.0348 data_time: 0.0061 memory: 1253 loss: 0.0143 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0143 2022/11/28 14:19:34 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:02:47 time: 0.0351 data_time: 0.0063 memory: 1253 loss: 0.0164 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0164 2022/11/28 14:19:37 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:02:44 time: 0.0333 data_time: 0.0061 memory: 1253 loss: 0.0118 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0118 2022/11/28 14:19:40 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:19:40 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:02:41 time: 0.0355 data_time: 0.0060 memory: 1253 loss: 0.1724 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1724 2022/11/28 14:19:40 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/11/28 14:19:41 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:00 time: 0.0154 data_time: 0.0061 memory: 262 2022/11/28 14:19:42 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.9080 acc/top5: 0.9927 acc/mean1: 0.9079 2022/11/28 14:19:42 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_12.pth is removed 2022/11/28 14:19:42 - mmengine - INFO - The best checkpoint with 0.9080 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/11/28 14:19:46 - mmengine - INFO - Epoch(train) [14][100/1567] lr: 8.0851e-03 eta: 0:02:38 time: 0.0341 data_time: 0.0062 memory: 1253 loss: 0.0107 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0107 2022/11/28 14:19:49 - mmengine - INFO - Epoch(train) [14][200/1567] lr: 7.7469e-03 eta: 0:02:34 time: 0.0349 data_time: 0.0062 memory: 1253 loss: 0.0134 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0134 2022/11/28 14:19:53 - mmengine - INFO - Epoch(train) [14][300/1567] lr: 7.4152e-03 eta: 0:02:31 time: 0.0355 data_time: 0.0062 memory: 1253 loss: 0.0116 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0116 2022/11/28 14:19:56 - mmengine - INFO - Epoch(train) [14][400/1567] lr: 7.0902e-03 eta: 0:02:28 time: 0.0343 data_time: 0.0061 memory: 1253 loss: 0.0115 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0115 2022/11/28 14:20:00 - mmengine - INFO - Epoch(train) [14][500/1567] lr: 6.7720e-03 eta: 0:02:24 time: 0.0355 data_time: 0.0062 memory: 1253 loss: 0.0065 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0065 2022/11/28 14:20:03 - mmengine - INFO - Epoch(train) [14][600/1567] lr: 6.4606e-03 eta: 0:02:21 time: 0.0340 data_time: 0.0062 memory: 1253 loss: 0.0100 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0100 2022/11/28 14:20:04 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:20:07 - mmengine - INFO - Epoch(train) [14][700/1567] lr: 6.1560e-03 eta: 0:02:17 time: 0.0339 data_time: 0.0061 memory: 1253 loss: 0.0076 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0076 2022/11/28 14:20:10 - mmengine - INFO - Epoch(train) [14][800/1567] lr: 5.8582e-03 eta: 0:02:14 time: 0.0343 data_time: 0.0061 memory: 1253 loss: 0.0075 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0075 2022/11/28 14:20:14 - mmengine - INFO - Epoch(train) [14][900/1567] lr: 5.5675e-03 eta: 0:02:10 time: 0.0337 data_time: 0.0062 memory: 1253 loss: 0.0078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0078 2022/11/28 14:20:17 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:02:07 time: 0.0344 data_time: 0.0061 memory: 1253 loss: 0.0094 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0094 2022/11/28 14:20:21 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:02:04 time: 0.0336 data_time: 0.0062 memory: 1253 loss: 0.0077 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0077 2022/11/28 14:20:24 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:02:00 time: 0.0354 data_time: 0.0069 memory: 1253 loss: 0.0055 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0055 2022/11/28 14:20:28 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:01:57 time: 0.0350 data_time: 0.0061 memory: 1253 loss: 0.0097 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0097 2022/11/28 14:20:31 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:01:53 time: 0.0351 data_time: 0.0062 memory: 1253 loss: 0.0114 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0114 2022/11/28 14:20:35 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:01:50 time: 0.0351 data_time: 0.0062 memory: 1253 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/11/28 14:20:37 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:20:37 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:01:47 time: 0.0329 data_time: 0.0059 memory: 1253 loss: 0.1686 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1686 2022/11/28 14:20:37 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/11/28 14:20:39 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:00 time: 0.0148 data_time: 0.0057 memory: 262 2022/11/28 14:20:41 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.9118 acc/top5: 0.9926 acc/mean1: 0.9117 2022/11/28 14:20:41 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_13.pth is removed 2022/11/28 14:20:41 - mmengine - INFO - The best checkpoint with 0.9118 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/11/28 14:20:44 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:20:45 - mmengine - INFO - Epoch(train) [15][100/1567] lr: 3.5722e-03 eta: 0:01:44 time: 0.0335 data_time: 0.0061 memory: 1253 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/11/28 14:20:49 - mmengine - INFO - Epoch(train) [15][200/1567] lr: 3.3433e-03 eta: 0:01:41 time: 0.0352 data_time: 0.0062 memory: 1253 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/11/28 14:20:52 - mmengine - INFO - Epoch(train) [15][300/1567] lr: 3.1217e-03 eta: 0:01:37 time: 0.0338 data_time: 0.0062 memory: 1253 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/11/28 14:20:55 - mmengine - INFO - Epoch(train) [15][400/1567] lr: 2.9075e-03 eta: 0:01:34 time: 0.0354 data_time: 0.0062 memory: 1253 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/11/28 14:20:59 - mmengine - INFO - Epoch(train) [15][500/1567] lr: 2.7007e-03 eta: 0:01:30 time: 0.0359 data_time: 0.0062 memory: 1253 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2022/11/28 14:21:03 - mmengine - INFO - Epoch(train) [15][600/1567] lr: 2.5013e-03 eta: 0:01:27 time: 0.0349 data_time: 0.0065 memory: 1253 loss: 0.0113 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0113 2022/11/28 14:21:06 - mmengine - INFO - Epoch(train) [15][700/1567] lr: 2.3093e-03 eta: 0:01:23 time: 0.0335 data_time: 0.0061 memory: 1253 loss: 0.0067 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0067 2022/11/28 14:21:09 - mmengine - INFO - Epoch(train) [15][800/1567] lr: 2.1249e-03 eta: 0:01:20 time: 0.0342 data_time: 0.0062 memory: 1253 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/11/28 14:21:13 - mmengine - INFO - Epoch(train) [15][900/1567] lr: 1.9479e-03 eta: 0:01:16 time: 0.0342 data_time: 0.0062 memory: 1253 loss: 0.0076 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0076 2022/11/28 14:21:16 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:01:13 time: 0.0361 data_time: 0.0063 memory: 1253 loss: 0.0056 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0056 2022/11/28 14:21:19 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:21:20 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:01:10 time: 0.0344 data_time: 0.0062 memory: 1253 loss: 0.0059 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0059 2022/11/28 14:21:23 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:01:06 time: 0.0341 data_time: 0.0062 memory: 1253 loss: 0.0077 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0077 2022/11/28 14:21:27 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:01:03 time: 0.0346 data_time: 0.0064 memory: 1253 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2022/11/28 14:21:30 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:00:59 time: 0.0340 data_time: 0.0062 memory: 1253 loss: 0.0065 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0065 2022/11/28 14:21:34 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:00:56 time: 0.0338 data_time: 0.0063 memory: 1253 loss: 0.0084 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0084 2022/11/28 14:21:36 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:21:36 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:00:54 time: 0.0332 data_time: 0.0060 memory: 1253 loss: 0.1569 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1569 2022/11/28 14:21:36 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/11/28 14:21:39 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:00 time: 0.0148 data_time: 0.0058 memory: 262 2022/11/28 14:21:39 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.9140 acc/top5: 0.9933 acc/mean1: 0.9139 2022/11/28 14:21:39 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_14.pth is removed 2022/11/28 14:21:40 - mmengine - INFO - The best checkpoint with 0.9140 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/11/28 14:21:43 - mmengine - INFO - Epoch(train) [16][100/1567] lr: 8.4351e-04 eta: 0:00:50 time: 0.0356 data_time: 0.0062 memory: 1253 loss: 0.0072 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0072 2022/11/28 14:21:47 - mmengine - INFO - Epoch(train) [16][200/1567] lr: 7.3277e-04 eta: 0:00:47 time: 0.0344 data_time: 0.0064 memory: 1253 loss: 0.0059 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0059 2022/11/28 14:21:50 - mmengine - INFO - Epoch(train) [16][300/1567] lr: 6.2978e-04 eta: 0:00:43 time: 0.0357 data_time: 0.0063 memory: 1253 loss: 0.0072 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0072 2022/11/28 14:21:54 - mmengine - INFO - Epoch(train) [16][400/1567] lr: 5.3453e-04 eta: 0:00:40 time: 0.0351 data_time: 0.0067 memory: 1253 loss: 0.0064 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0064 2022/11/28 14:21:57 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:21:57 - mmengine - INFO - Epoch(train) [16][500/1567] lr: 4.4705e-04 eta: 0:00:36 time: 0.0344 data_time: 0.0068 memory: 1253 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2022/11/28 14:22:01 - mmengine - INFO - Epoch(train) [16][600/1567] lr: 3.6735e-04 eta: 0:00:33 time: 0.0344 data_time: 0.0068 memory: 1253 loss: 0.0063 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0063 2022/11/28 14:22:04 - mmengine - INFO - Epoch(train) [16][700/1567] lr: 2.9544e-04 eta: 0:00:29 time: 0.0336 data_time: 0.0061 memory: 1253 loss: 0.0069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0069 2022/11/28 14:22:08 - mmengine - INFO - Epoch(train) [16][800/1567] lr: 2.3134e-04 eta: 0:00:26 time: 0.0354 data_time: 0.0062 memory: 1253 loss: 0.0052 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0052 2022/11/28 14:22:11 - mmengine - INFO - Epoch(train) [16][900/1567] lr: 1.7505e-04 eta: 0:00:23 time: 0.0341 data_time: 0.0062 memory: 1253 loss: 0.0106 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0106 2022/11/28 14:22:15 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:00:19 time: 0.0349 data_time: 0.0061 memory: 1253 loss: 0.0104 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0104 2022/11/28 14:22:18 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:00:16 time: 0.0337 data_time: 0.0062 memory: 1253 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/11/28 14:22:22 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:12 time: 0.0339 data_time: 0.0062 memory: 1253 loss: 0.0080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0080 2022/11/28 14:22:25 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:09 time: 0.0350 data_time: 0.0069 memory: 1253 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2022/11/28 14:22:28 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:05 time: 0.0344 data_time: 0.0070 memory: 1253 loss: 0.0060 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0060 2022/11/28 14:22:32 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:22:32 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:02 time: 0.0357 data_time: 0.0076 memory: 1253 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2022/11/28 14:22:34 - mmengine - INFO - Exp name: stgcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-2d_20221128_140645 2022/11/28 14:22:34 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.0343 data_time: 0.0072 memory: 1253 loss: 0.1834 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1834 2022/11/28 14:22:34 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/11/28 14:22:37 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:00 time: 0.0147 data_time: 0.0056 memory: 262 2022/11/28 14:22:37 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.9133 acc/top5: 0.9932 acc/mean1: 0.9132