2022/12/20 13:58:32 - 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: 1483300435 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: 0.3.2 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 ------------------------------------------------------------ 2022/12/20 13:58:32 - 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='AAGCN', graph_cfg=dict(layout='coco', mode='spatial'), stage_cfgs=dict(gcn_attention=False)), 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=['j']), 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=['j']), 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=['j']), 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=['j']), 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=['j']), 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=['j']), 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/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/12/20 13:58:32 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/modules_statistic_results.json 2022/12/20 13:58:33 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (BELOW_NORMAL) LoggerHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (NORMAL ) SyncBuffersHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- Name of parameter - Initialization information backbone.data_bn.weight - torch.Size([102]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.data_bn.bias - torch.Size([102]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.conv_d.0.weight - torch.Size([64, 3, 1, 1]): ConvBranchInit backbone.gcn.0.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_d.1.weight - torch.Size([64, 3, 1, 1]): ConvBranchInit backbone.gcn.0.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_d.2.weight - torch.Size([64, 3, 1, 1]): ConvBranchInit backbone.gcn.0.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.0.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.1.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.2.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.0.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.1.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.2.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.down.0.weight - torch.Size([64, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.down.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.down.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.0.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.conv_d.0.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.1.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_d.1.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.1.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_d.2.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.1.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.1.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.conv_d.0.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.2.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_d.1.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.2.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_d.2.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.2.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.2.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.conv_d.0.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.3.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_d.1.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.3.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_d.2.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.3.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.3.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.conv_d.0.weight - torch.Size([128, 64, 1, 1]): ConvBranchInit backbone.gcn.4.gcn.conv_d.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_d.1.weight - torch.Size([128, 64, 1, 1]): ConvBranchInit backbone.gcn.4.gcn.conv_d.1.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_d.2.weight - torch.Size([128, 64, 1, 1]): ConvBranchInit backbone.gcn.4.gcn.conv_d.2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.0.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.1.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.2.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.0.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.1.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.2.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.down.0.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.down.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.down.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.gcn.4.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.conv_d.0.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.5.gcn.conv_d.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_d.1.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.5.gcn.conv_d.1.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_d.2.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.5.gcn.conv_d.2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.gcn.5.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.conv_d.0.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.6.gcn.conv_d.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_d.1.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.6.gcn.conv_d.1.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_d.2.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.6.gcn.conv_d.2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.gcn.6.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.conv_d.0.weight - torch.Size([256, 128, 1, 1]): ConvBranchInit backbone.gcn.7.gcn.conv_d.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_d.1.weight - torch.Size([256, 128, 1, 1]): ConvBranchInit backbone.gcn.7.gcn.conv_d.1.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_d.2.weight - torch.Size([256, 128, 1, 1]): ConvBranchInit backbone.gcn.7.gcn.conv_d.2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.0.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.1.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.2.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.0.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.1.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.2.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.down.0.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.down.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.down.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.gcn.7.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.conv_d.0.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.8.gcn.conv_d.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_d.1.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.8.gcn.conv_d.1.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_d.2.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.8.gcn.conv_d.2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.gcn.8.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.conv_d.0.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.9.gcn.conv_d.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_d.1.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.9.gcn.conv_d.1.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_d.2.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.9.gcn.conv_d.2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.gcn.9.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN cls_head.fc.weight - torch.Size([60, 256]): NormalInit: mean=0, std=0.01, bias=0 cls_head.fc.bias - torch.Size([60]): NormalInit: mean=0, std=0.01, bias=0 2022/12/20 13:59:15 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d. 2022/12/20 13:59:34 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 1:18:46 time: 0.1612 data_time: 0.0076 memory: 1461 loss: 3.3886 top1_acc: 0.1875 top5_acc: 0.3750 loss_cls: 3.3886 2022/12/20 13:59:49 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 1:10:30 time: 0.1480 data_time: 0.0070 memory: 1461 loss: 3.0437 top1_acc: 0.0000 top5_acc: 0.3125 loss_cls: 3.0437 2022/12/20 14:00:05 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 1:09:27 time: 0.1586 data_time: 0.0071 memory: 1461 loss: 2.7302 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 2.7302 2022/12/20 14:00:20 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 1:06:17 time: 0.1668 data_time: 0.0074 memory: 1461 loss: 1.9050 top1_acc: 0.3750 top5_acc: 0.7500 loss_cls: 1.9050 2022/12/20 14:00:35 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 1:05:31 time: 0.1323 data_time: 0.0068 memory: 1461 loss: 1.6637 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.6637 2022/12/20 14:00:49 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 1:03:46 time: 0.1365 data_time: 0.0073 memory: 1461 loss: 1.2438 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.2438 2022/12/20 14:01:01 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 1:01:32 time: 0.1871 data_time: 0.0091 memory: 1461 loss: 1.0598 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0598 2022/12/20 14:01:17 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 1:01:31 time: 0.1488 data_time: 0.0078 memory: 1461 loss: 0.8436 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8436 2022/12/20 14:01:31 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 1:00:51 time: 0.1554 data_time: 0.0072 memory: 1461 loss: 0.9071 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9071 2022/12/20 14:01:48 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:01:48 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 1:01:11 time: 0.1430 data_time: 0.0069 memory: 1461 loss: 0.7303 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7303 2022/12/20 14:02:01 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 1:00:22 time: 0.1263 data_time: 0.0069 memory: 1461 loss: 0.6125 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6125 2022/12/20 14:02:18 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 1:00:32 time: 0.1384 data_time: 0.0080 memory: 1461 loss: 0.7326 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7326 2022/12/20 14:02:32 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 0:59:55 time: 0.1326 data_time: 0.0075 memory: 1461 loss: 0.6529 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6529 2022/12/20 14:02:48 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 1:00:03 time: 0.1388 data_time: 0.0068 memory: 1461 loss: 0.4712 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4712 2022/12/20 14:03:03 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 0:59:38 time: 0.1541 data_time: 0.0080 memory: 1461 loss: 0.4878 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4878 2022/12/20 14:03:14 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:03:14 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 0:59:41 time: 0.1924 data_time: 0.0074 memory: 1461 loss: 0.7953 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7953 2022/12/20 14:03:14 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/20 14:03:20 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:01 time: 0.0594 data_time: 0.0068 memory: 215 2022/12/20 14:03:25 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.6683 acc/top5: 0.9486 acc/mean1: 0.6684 2022/12/20 14:03:26 - mmengine - INFO - The best checkpoint with 0.6683 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/12/20 14:03:40 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 0:59:21 time: 0.1882 data_time: 0.0071 memory: 1461 loss: 0.5873 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5873 2022/12/20 14:03:56 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 0:59:10 time: 0.1326 data_time: 0.0074 memory: 1461 loss: 0.4330 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4330 2022/12/20 14:04:10 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 0:58:39 time: 0.1409 data_time: 0.0067 memory: 1461 loss: 0.4391 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4391 2022/12/20 14:04:25 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 0:58:22 time: 0.1313 data_time: 0.0068 memory: 1461 loss: 0.4945 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4945 2022/12/20 14:04:30 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:04:39 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 0:57:50 time: 0.1414 data_time: 0.0064 memory: 1461 loss: 0.4437 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4437 2022/12/20 14:04:50 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 0:57:01 time: 0.1422 data_time: 0.0080 memory: 1461 loss: 0.4148 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4148 2022/12/20 14:05:08 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 0:57:10 time: 0.1495 data_time: 0.0077 memory: 1461 loss: 0.4023 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4023 2022/12/20 14:05:23 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 0:56:58 time: 0.1376 data_time: 0.0068 memory: 1461 loss: 0.4348 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.4348 2022/12/20 14:05:39 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 0:56:55 time: 0.1512 data_time: 0.0074 memory: 1461 loss: 0.4665 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4665 2022/12/20 14:05:55 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:56:41 time: 0.1341 data_time: 0.0068 memory: 1461 loss: 0.3013 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3013 2022/12/20 14:06:11 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:56:39 time: 0.1614 data_time: 0.0071 memory: 1461 loss: 0.3825 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.3825 2022/12/20 14:06:27 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:56:25 time: 0.1466 data_time: 0.0071 memory: 1461 loss: 0.3974 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3974 2022/12/20 14:06:42 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:56:14 time: 0.1627 data_time: 0.0069 memory: 1461 loss: 0.3810 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3810 2022/12/20 14:06:58 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:56:03 time: 0.1602 data_time: 0.0065 memory: 1461 loss: 0.4459 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4459 2022/12/20 14:07:03 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:07:14 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:55:55 time: 0.1996 data_time: 0.0071 memory: 1461 loss: 0.2735 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2735 2022/12/20 14:07:25 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:07:25 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:55:47 time: 0.1511 data_time: 0.0071 memory: 1461 loss: 0.5696 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5696 2022/12/20 14:07:25 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/20 14:07:32 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:01 time: 0.0497 data_time: 0.0061 memory: 215 2022/12/20 14:07:35 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.7755 acc/top5: 0.9699 acc/mean1: 0.7756 2022/12/20 14:07:35 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_1.pth is removed 2022/12/20 14:07:35 - mmengine - INFO - The best checkpoint with 0.7755 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/12/20 14:07:52 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 0:55:44 time: 0.1721 data_time: 0.0074 memory: 1461 loss: 0.3402 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3402 2022/12/20 14:08:07 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 0:55:23 time: 0.1295 data_time: 0.0066 memory: 1461 loss: 0.3016 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3016 2022/12/20 14:08:23 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 0:55:11 time: 0.1562 data_time: 0.0066 memory: 1461 loss: 0.3240 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3240 2022/12/20 14:08:37 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 0:54:52 time: 0.1283 data_time: 0.0069 memory: 1461 loss: 0.3001 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3001 2022/12/20 14:08:50 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 0:54:22 time: 0.0829 data_time: 0.0069 memory: 1461 loss: 0.3393 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3393 2022/12/20 14:09:05 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 0:54:06 time: 0.1651 data_time: 0.0065 memory: 1461 loss: 0.2772 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2772 2022/12/20 14:09:21 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 0:53:52 time: 0.1433 data_time: 0.0071 memory: 1461 loss: 0.3063 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3063 2022/12/20 14:09:37 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 0:53:41 time: 0.1802 data_time: 0.0071 memory: 1461 loss: 0.2763 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2763 2022/12/20 14:09:47 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:09:52 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 0:53:26 time: 0.1407 data_time: 0.0067 memory: 1461 loss: 0.3890 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3890 2022/12/20 14:10:07 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:53:11 time: 0.1864 data_time: 0.0073 memory: 1461 loss: 0.3515 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.3515 2022/12/20 14:10:24 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:53:01 time: 0.1478 data_time: 0.0074 memory: 1461 loss: 0.2736 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2736 2022/12/20 14:10:38 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:52:43 time: 0.1871 data_time: 0.0065 memory: 1461 loss: 0.3208 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3208 2022/12/20 14:10:55 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:52:36 time: 0.1623 data_time: 0.0067 memory: 1461 loss: 0.2850 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2850 2022/12/20 14:11:09 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:52:11 time: 0.1205 data_time: 0.0068 memory: 1461 loss: 0.3052 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3052 2022/12/20 14:11:26 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:52:06 time: 0.1631 data_time: 0.0064 memory: 1461 loss: 0.3558 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3558 2022/12/20 14:11:36 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:11:36 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:51:55 time: 0.1430 data_time: 0.0065 memory: 1461 loss: 0.4441 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.4441 2022/12/20 14:11:36 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/12/20 14:11:41 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:01 time: 0.0250 data_time: 0.0058 memory: 215 2022/12/20 14:11:47 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.7662 acc/top5: 0.9709 acc/mean1: 0.7661 2022/12/20 14:12:03 - mmengine - INFO - Epoch(train) [4][ 100/1567] lr: 9.1226e-02 eta: 0:51:44 time: 0.1439 data_time: 0.0066 memory: 1461 loss: 0.2984 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2984 2022/12/20 14:12:17 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 0:51:23 time: 0.1489 data_time: 0.0070 memory: 1461 loss: 0.2961 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2961 2022/12/20 14:12:32 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:12:32 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 0:51:07 time: 0.1293 data_time: 0.0066 memory: 1461 loss: 0.2054 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2054 2022/12/20 14:12:45 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 0:50:44 time: 0.1393 data_time: 0.0067 memory: 1461 loss: 0.2846 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2846 2022/12/20 14:12:57 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 0:50:13 time: 0.0971 data_time: 0.0083 memory: 1461 loss: 0.3357 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3357 2022/12/20 14:13:13 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 0:50:04 time: 0.1416 data_time: 0.0076 memory: 1461 loss: 0.2550 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2550 2022/12/20 14:13:28 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 0:49:48 time: 0.1379 data_time: 0.0067 memory: 1461 loss: 0.3009 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3009 2022/12/20 14:13:45 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 0:49:38 time: 0.1613 data_time: 0.0067 memory: 1461 loss: 0.2984 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2984 2022/12/20 14:14:01 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 0:49:24 time: 0.1531 data_time: 0.0067 memory: 1461 loss: 0.2841 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2841 2022/12/20 14:14:17 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:49:12 time: 0.1555 data_time: 0.0072 memory: 1461 loss: 0.2950 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2950 2022/12/20 14:14:32 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:48:58 time: 0.1460 data_time: 0.0077 memory: 1461 loss: 0.3064 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3064 2022/12/20 14:14:49 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:48:46 time: 0.2207 data_time: 0.0067 memory: 1461 loss: 0.2011 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2011 2022/12/20 14:15:04 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:15:04 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:48:33 time: 0.1376 data_time: 0.0071 memory: 1461 loss: 0.2690 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2690 2022/12/20 14:15:20 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:48:18 time: 0.1901 data_time: 0.0067 memory: 1461 loss: 0.2260 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2260 2022/12/20 14:15:37 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:48:09 time: 0.1974 data_time: 0.0076 memory: 1461 loss: 0.2498 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2498 2022/12/20 14:15:46 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:15:46 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:47:55 time: 0.1471 data_time: 0.0076 memory: 1461 loss: 0.4300 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4300 2022/12/20 14:15:46 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/20 14:15:56 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:02 time: 0.1161 data_time: 0.0063 memory: 215 2022/12/20 14:15:58 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.8021 acc/top5: 0.9756 acc/mean1: 0.8021 2022/12/20 14:15:58 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_2.pth is removed 2022/12/20 14:15:58 - mmengine - INFO - The best checkpoint with 0.8021 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2022/12/20 14:16:15 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 0:47:45 time: 0.1698 data_time: 0.0074 memory: 1461 loss: 0.2376 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2376 2022/12/20 14:16:29 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 0:47:26 time: 0.1658 data_time: 0.0068 memory: 1461 loss: 0.2261 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2261 2022/12/20 14:16:46 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 0:47:14 time: 0.1620 data_time: 0.0072 memory: 1461 loss: 0.2612 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2612 2022/12/20 14:16:59 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 0:46:54 time: 0.1391 data_time: 0.0071 memory: 1461 loss: 0.2405 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2405 2022/12/20 14:17:11 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 0:46:28 time: 0.0949 data_time: 0.0080 memory: 1461 loss: 0.1814 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1814 2022/12/20 14:17:27 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 0:46:15 time: 0.1438 data_time: 0.0072 memory: 1461 loss: 0.2067 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2067 2022/12/20 14:17:41 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 0:45:57 time: 0.1568 data_time: 0.0073 memory: 1461 loss: 0.2707 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2707 2022/12/20 14:17:46 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:17:58 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 0:45:45 time: 0.1641 data_time: 0.0066 memory: 1461 loss: 0.2364 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2364 2022/12/20 14:18:13 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 0:45:29 time: 0.1482 data_time: 0.0075 memory: 1461 loss: 0.2632 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2632 2022/12/20 14:18:29 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:45:16 time: 0.1522 data_time: 0.0068 memory: 1461 loss: 0.2135 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2135 2022/12/20 14:18:44 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:45:01 time: 0.1606 data_time: 0.0075 memory: 1461 loss: 0.2107 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2107 2022/12/20 14:19:00 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:44:48 time: 0.1935 data_time: 0.0069 memory: 1461 loss: 0.2431 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2431 2022/12/20 14:19:16 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:44:33 time: 0.1516 data_time: 0.0072 memory: 1461 loss: 0.2951 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2951 2022/12/20 14:19:31 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:44:17 time: 0.1764 data_time: 0.0068 memory: 1461 loss: 0.1989 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1989 2022/12/20 14:19:48 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:44:06 time: 0.1521 data_time: 0.0074 memory: 1461 loss: 0.1646 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1646 2022/12/20 14:19:57 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:19:57 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:43:54 time: 0.1261 data_time: 0.0066 memory: 1461 loss: 0.3920 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3920 2022/12/20 14:19:57 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/20 14:20:06 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:02 time: 0.0992 data_time: 0.0061 memory: 215 2022/12/20 14:20:08 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7987 acc/top5: 0.9744 acc/mean1: 0.7986 2022/12/20 14:20:24 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 0:43:40 time: 0.1396 data_time: 0.0071 memory: 1461 loss: 0.2448 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2448 2022/12/20 14:20:33 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:20:38 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 0:43:22 time: 0.1830 data_time: 0.0066 memory: 1461 loss: 0.1712 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1712 2022/12/20 14:20:53 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 0:43:06 time: 0.1364 data_time: 0.0070 memory: 1461 loss: 0.2168 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2168 2022/12/20 14:21:07 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 0:42:48 time: 0.1490 data_time: 0.0075 memory: 1461 loss: 0.1634 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1634 2022/12/20 14:21:20 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 0:42:28 time: 0.1857 data_time: 0.0074 memory: 1461 loss: 0.1598 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1598 2022/12/20 14:21:36 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 0:42:15 time: 0.1504 data_time: 0.0074 memory: 1461 loss: 0.1450 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1450 2022/12/20 14:21:51 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 0:42:01 time: 0.2172 data_time: 0.0066 memory: 1461 loss: 0.1694 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1694 2022/12/20 14:22:07 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 0:41:47 time: 0.1392 data_time: 0.0066 memory: 1461 loss: 0.1442 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1442 2022/12/20 14:22:22 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 0:41:31 time: 0.1764 data_time: 0.0071 memory: 1461 loss: 0.1803 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1803 2022/12/20 14:22:39 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:41:18 time: 0.1416 data_time: 0.0068 memory: 1461 loss: 0.1688 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1688 2022/12/20 14:22:53 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:41:01 time: 0.1383 data_time: 0.0066 memory: 1461 loss: 0.1429 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1429 2022/12/20 14:23:04 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:23:10 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:40:48 time: 0.1539 data_time: 0.0068 memory: 1461 loss: 0.1669 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1669 2022/12/20 14:23:23 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:40:30 time: 0.1282 data_time: 0.0066 memory: 1461 loss: 0.2020 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2020 2022/12/20 14:23:41 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:40:18 time: 0.1635 data_time: 0.0065 memory: 1461 loss: 0.1528 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1528 2022/12/20 14:23:55 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:40:01 time: 0.1338 data_time: 0.0066 memory: 1461 loss: 0.1519 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1519 2022/12/20 14:24:06 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:24:06 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:39:53 time: 0.1466 data_time: 0.0068 memory: 1461 loss: 0.3247 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3247 2022/12/20 14:24:06 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/20 14:24:12 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:01 time: 0.0552 data_time: 0.0059 memory: 215 2022/12/20 14:24:15 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.7859 acc/top5: 0.9770 acc/mean1: 0.7859 2022/12/20 14:24:30 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 0:39:36 time: 0.1483 data_time: 0.0069 memory: 1461 loss: 0.1427 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1427 2022/12/20 14:24:44 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 0:39:19 time: 0.1215 data_time: 0.0070 memory: 1461 loss: 0.1192 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1192 2022/12/20 14:24:58 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 0:39:01 time: 0.1451 data_time: 0.0074 memory: 1461 loss: 0.1679 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1679 2022/12/20 14:25:13 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 0:38:46 time: 0.1356 data_time: 0.0074 memory: 1461 loss: 0.1552 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1552 2022/12/20 14:25:32 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 0:38:36 time: 0.1593 data_time: 0.0067 memory: 1461 loss: 0.1301 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1301 2022/12/20 14:25:45 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:25:46 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 0:38:19 time: 0.1518 data_time: 0.0074 memory: 1461 loss: 0.1717 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1717 2022/12/20 14:26:03 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 0:38:06 time: 0.1685 data_time: 0.0063 memory: 1461 loss: 0.1677 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1677 2022/12/20 14:26:18 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 0:37:50 time: 0.1334 data_time: 0.0066 memory: 1461 loss: 0.1663 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1663 2022/12/20 14:26:35 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 0:37:38 time: 0.1732 data_time: 0.0069 memory: 1461 loss: 0.1338 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1338 2022/12/20 14:26:49 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:37:22 time: 0.1212 data_time: 0.0070 memory: 1461 loss: 0.1346 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1346 2022/12/20 14:27:06 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:37:07 time: 0.1709 data_time: 0.0068 memory: 1461 loss: 0.1561 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1561 2022/12/20 14:27:21 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:36:52 time: 0.1340 data_time: 0.0069 memory: 1461 loss: 0.1630 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1630 2022/12/20 14:27:38 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:36:39 time: 0.2092 data_time: 0.0065 memory: 1461 loss: 0.1368 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1368 2022/12/20 14:27:54 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:36:25 time: 0.1573 data_time: 0.0070 memory: 1461 loss: 0.1587 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1587 2022/12/20 14:28:09 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:36:09 time: 0.1783 data_time: 0.0065 memory: 1461 loss: 0.1419 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1419 2022/12/20 14:28:21 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:28:21 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:36:01 time: 0.1483 data_time: 0.0067 memory: 1461 loss: 0.3215 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3215 2022/12/20 14:28:21 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/12/20 14:28:27 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:01 time: 0.0528 data_time: 0.0063 memory: 215 2022/12/20 14:28:29 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.7969 acc/top5: 0.9720 acc/mean1: 0.7967 2022/12/20 14:28:33 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:28:45 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 0:35:47 time: 0.1799 data_time: 0.0068 memory: 1461 loss: 0.1321 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1321 2022/12/20 14:28:59 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 0:35:30 time: 0.1168 data_time: 0.0067 memory: 1461 loss: 0.1079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1079 2022/12/20 14:29:12 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 0:35:12 time: 0.1047 data_time: 0.0072 memory: 1461 loss: 0.1280 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1280 2022/12/20 14:29:27 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 0:34:57 time: 0.1848 data_time: 0.0073 memory: 1461 loss: 0.1400 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1400 2022/12/20 14:29:42 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 0:34:40 time: 0.1339 data_time: 0.0080 memory: 1461 loss: 0.1047 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1047 2022/12/20 14:29:58 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 0:34:26 time: 0.1543 data_time: 0.0068 memory: 1461 loss: 0.1112 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1112 2022/12/20 14:30:13 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 0:34:10 time: 0.1528 data_time: 0.0071 memory: 1461 loss: 0.1405 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1405 2022/12/20 14:30:29 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 0:33:55 time: 0.1758 data_time: 0.0071 memory: 1461 loss: 0.1403 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1403 2022/12/20 14:30:44 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 0:33:40 time: 0.1534 data_time: 0.0080 memory: 1461 loss: 0.1426 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1426 2022/12/20 14:30:59 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:33:25 time: 0.1708 data_time: 0.0071 memory: 1461 loss: 0.1092 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1092 2022/12/20 14:31:05 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:31:16 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:33:11 time: 0.1524 data_time: 0.0067 memory: 1461 loss: 0.1237 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1237 2022/12/20 14:31:30 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:32:55 time: 0.1658 data_time: 0.0075 memory: 1461 loss: 0.1063 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.1063 2022/12/20 14:31:47 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:32:41 time: 0.1622 data_time: 0.0070 memory: 1461 loss: 0.1048 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1048 2022/12/20 14:32:01 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:32:23 time: 0.1067 data_time: 0.0075 memory: 1461 loss: 0.1116 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1116 2022/12/20 14:32:17 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:32:09 time: 0.1582 data_time: 0.0071 memory: 1461 loss: 0.1118 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1118 2022/12/20 14:32:27 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:32:27 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:31:59 time: 0.1172 data_time: 0.0064 memory: 1461 loss: 0.3157 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3157 2022/12/20 14:32:27 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/12/20 14:32:33 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:01 time: 0.1159 data_time: 0.0064 memory: 215 2022/12/20 14:32:37 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.8256 acc/top5: 0.9790 acc/mean1: 0.8256 2022/12/20 14:32:37 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_4.pth is removed 2022/12/20 14:32:37 - mmengine - INFO - The best checkpoint with 0.8256 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/12/20 14:32:52 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 0:31:43 time: 0.1308 data_time: 0.0072 memory: 1461 loss: 0.1071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1071 2022/12/20 14:33:06 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 0:31:26 time: 0.1294 data_time: 0.0068 memory: 1461 loss: 0.0915 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0915 2022/12/20 14:33:19 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 0:31:09 time: 0.2241 data_time: 0.0082 memory: 1461 loss: 0.0832 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0832 2022/12/20 14:33:35 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 0:30:54 time: 0.1569 data_time: 0.0067 memory: 1461 loss: 0.1064 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1064 2022/12/20 14:33:44 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:33:50 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 0:30:39 time: 0.2084 data_time: 0.0079 memory: 1461 loss: 0.1008 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1008 2022/12/20 14:34:06 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 0:30:24 time: 0.1731 data_time: 0.0068 memory: 1461 loss: 0.1412 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1412 2022/12/20 14:34:20 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 0:30:08 time: 0.1510 data_time: 0.0069 memory: 1461 loss: 0.1179 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1179 2022/12/20 14:34:37 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 0:29:54 time: 0.1680 data_time: 0.0067 memory: 1461 loss: 0.1346 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1346 2022/12/20 14:34:51 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 0:29:37 time: 0.1105 data_time: 0.0073 memory: 1461 loss: 0.0931 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0931 2022/12/20 14:35:08 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:29:23 time: 0.1413 data_time: 0.0079 memory: 1461 loss: 0.1281 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1281 2022/12/20 14:35:22 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:29:07 time: 0.1256 data_time: 0.0071 memory: 1461 loss: 0.0883 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.0883 2022/12/20 14:35:39 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:28:54 time: 0.1265 data_time: 0.0080 memory: 1461 loss: 0.0939 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0939 2022/12/20 14:35:54 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:28:38 time: 0.1474 data_time: 0.0071 memory: 1461 loss: 0.0754 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0754 2022/12/20 14:36:10 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:28:23 time: 0.1744 data_time: 0.0068 memory: 1461 loss: 0.0491 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0491 2022/12/20 14:36:19 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:36:24 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:28:07 time: 0.1446 data_time: 0.0075 memory: 1461 loss: 0.0549 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0549 2022/12/20 14:36:35 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:36:35 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:27:57 time: 0.1781 data_time: 0.0071 memory: 1461 loss: 0.2543 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2543 2022/12/20 14:36:35 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/12/20 14:36:39 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:01 time: 0.0487 data_time: 0.0066 memory: 215 2022/12/20 14:36:44 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8453 acc/top5: 0.9791 acc/mean1: 0.8453 2022/12/20 14:36:44 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_8.pth is removed 2022/12/20 14:36:44 - mmengine - INFO - The best checkpoint with 0.8453 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2022/12/20 14:36:58 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 0:27:40 time: 0.1491 data_time: 0.0072 memory: 1461 loss: 0.0723 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0723 2022/12/20 14:37:11 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 0:27:23 time: 0.1812 data_time: 0.0086 memory: 1461 loss: 0.0712 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0712 2022/12/20 14:37:28 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 0:27:09 time: 0.1833 data_time: 0.0073 memory: 1461 loss: 0.0993 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0993 2022/12/20 14:37:43 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 0:26:54 time: 0.1468 data_time: 0.0081 memory: 1461 loss: 0.0813 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0813 2022/12/20 14:38:00 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 0:26:39 time: 0.1635 data_time: 0.0068 memory: 1461 loss: 0.0601 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0601 2022/12/20 14:38:15 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 0:26:25 time: 0.1389 data_time: 0.0075 memory: 1461 loss: 0.0346 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0346 2022/12/20 14:38:31 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 0:26:10 time: 0.1504 data_time: 0.0069 memory: 1461 loss: 0.0499 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0499 2022/12/20 14:38:48 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 0:25:55 time: 0.1398 data_time: 0.0075 memory: 1461 loss: 0.0446 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0446 2022/12/20 14:39:02 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:39:03 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 0:25:40 time: 0.1417 data_time: 0.0068 memory: 1461 loss: 0.0708 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0708 2022/12/20 14:39:20 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:25:26 time: 0.1638 data_time: 0.0067 memory: 1461 loss: 0.0500 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0500 2022/12/20 14:39:35 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:25:10 time: 0.1171 data_time: 0.0067 memory: 1461 loss: 0.0568 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0568 2022/12/20 14:39:53 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:24:56 time: 0.1881 data_time: 0.0071 memory: 1461 loss: 0.0953 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0953 2022/12/20 14:40:07 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:24:40 time: 0.1305 data_time: 0.0070 memory: 1461 loss: 0.0824 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0824 2022/12/20 14:40:24 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:24:26 time: 0.1970 data_time: 0.0066 memory: 1461 loss: 0.0578 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0578 2022/12/20 14:40:39 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:24:11 time: 0.1368 data_time: 0.0073 memory: 1461 loss: 0.0789 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0789 2022/12/20 14:40:49 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:40:49 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:24:00 time: 0.1803 data_time: 0.0065 memory: 1461 loss: 0.2160 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2160 2022/12/20 14:40:49 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/12/20 14:40:57 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:02 time: 0.0527 data_time: 0.0060 memory: 215 2022/12/20 14:41:00 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8347 acc/top5: 0.9802 acc/mean1: 0.8345 2022/12/20 14:41:14 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 0:23:44 time: 0.1426 data_time: 0.0072 memory: 1461 loss: 0.0359 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0359 2022/12/20 14:41:26 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 0:23:27 time: 0.0963 data_time: 0.0079 memory: 1461 loss: 0.0345 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0345 2022/12/20 14:41:43 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 0:23:12 time: 0.1369 data_time: 0.0075 memory: 1461 loss: 0.0306 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0306 2022/12/20 14:41:47 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:41:58 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 0:22:57 time: 0.1497 data_time: 0.0078 memory: 1461 loss: 0.0492 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0492 2022/12/20 14:42:14 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 0:22:42 time: 0.1502 data_time: 0.0072 memory: 1461 loss: 0.0316 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0316 2022/12/20 14:42:28 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 0:22:26 time: 0.1332 data_time: 0.0078 memory: 1461 loss: 0.0259 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0259 2022/12/20 14:42:45 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 0:22:11 time: 0.1554 data_time: 0.0075 memory: 1461 loss: 0.0438 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0438 2022/12/20 14:42:59 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 0:21:56 time: 0.1260 data_time: 0.0078 memory: 1461 loss: 0.0299 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0299 2022/12/20 14:43:16 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 0:21:41 time: 0.1735 data_time: 0.0070 memory: 1461 loss: 0.0401 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0401 2022/12/20 14:43:31 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:21:26 time: 0.1434 data_time: 0.0076 memory: 1461 loss: 0.0308 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0308 2022/12/20 14:43:47 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:21:11 time: 0.1746 data_time: 0.0073 memory: 1461 loss: 0.0323 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0323 2022/12/20 14:44:02 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:20:55 time: 0.1574 data_time: 0.0078 memory: 1461 loss: 0.0335 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0335 2022/12/20 14:44:18 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:20:40 time: 0.1622 data_time: 0.0067 memory: 1461 loss: 0.0212 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0212 2022/12/20 14:44:22 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:44:32 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:20:24 time: 0.1496 data_time: 0.0074 memory: 1461 loss: 0.0310 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0310 2022/12/20 14:44:48 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:20:09 time: 0.1676 data_time: 0.0072 memory: 1461 loss: 0.0259 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0259 2022/12/20 14:44:57 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:44:57 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:19:59 time: 0.1155 data_time: 0.0074 memory: 1461 loss: 0.1953 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1953 2022/12/20 14:44:57 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/12/20 14:45:02 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:01 time: 0.0590 data_time: 0.0061 memory: 215 2022/12/20 14:45:04 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8637 acc/top5: 0.9840 acc/mean1: 0.8636 2022/12/20 14:45:04 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_9.pth is removed 2022/12/20 14:45:04 - mmengine - INFO - The best checkpoint with 0.8637 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/12/20 14:45:18 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 0:19:42 time: 0.1851 data_time: 0.0082 memory: 1461 loss: 0.0248 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0248 2022/12/20 14:45:34 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 0:19:28 time: 0.1684 data_time: 0.0072 memory: 1461 loss: 0.0333 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0333 2022/12/20 14:45:49 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 0:19:12 time: 0.1917 data_time: 0.0074 memory: 1461 loss: 0.0194 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0194 2022/12/20 14:46:06 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 0:18:57 time: 0.1580 data_time: 0.0067 memory: 1461 loss: 0.0285 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0285 2022/12/20 14:46:20 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 0:18:42 time: 0.1152 data_time: 0.0068 memory: 1461 loss: 0.0147 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0147 2022/12/20 14:46:37 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 0:18:27 time: 0.1491 data_time: 0.0075 memory: 1461 loss: 0.0208 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0208 2022/12/20 14:46:53 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 0:18:12 time: 0.1496 data_time: 0.0071 memory: 1461 loss: 0.0149 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0149 2022/12/20 14:47:03 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:47:10 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 0:17:57 time: 0.1599 data_time: 0.0071 memory: 1461 loss: 0.0164 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0164 2022/12/20 14:47:25 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 0:17:42 time: 0.1435 data_time: 0.0069 memory: 1461 loss: 0.0169 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0169 2022/12/20 14:47:42 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:17:27 time: 0.1694 data_time: 0.0069 memory: 1461 loss: 0.0117 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0117 2022/12/20 14:47:57 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:17:12 time: 0.1495 data_time: 0.0072 memory: 1461 loss: 0.0146 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0146 2022/12/20 14:48:13 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:16:57 time: 0.2006 data_time: 0.0069 memory: 1461 loss: 0.0205 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0205 2022/12/20 14:48:29 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:16:42 time: 0.1489 data_time: 0.0070 memory: 1461 loss: 0.0177 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0177 2022/12/20 14:48:44 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:16:26 time: 0.1632 data_time: 0.0080 memory: 1461 loss: 0.0137 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0137 2022/12/20 14:48:59 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:16:11 time: 0.1379 data_time: 0.0072 memory: 1461 loss: 0.0115 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0115 2022/12/20 14:49:08 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:49:08 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:16:00 time: 0.1296 data_time: 0.0072 memory: 1461 loss: 0.2186 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2186 2022/12/20 14:49:08 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/12/20 14:49:13 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:01 time: 0.0322 data_time: 0.0071 memory: 215 2022/12/20 14:49:14 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8623 acc/top5: 0.9830 acc/mean1: 0.8621 2022/12/20 14:49:30 - mmengine - INFO - Epoch(train) [13][ 100/1567] lr: 1.4209e-02 eta: 0:15:45 time: 0.1596 data_time: 0.0075 memory: 1461 loss: 0.0175 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0175 2022/12/20 14:49:45 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:49:46 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:15:30 time: 0.1517 data_time: 0.0074 memory: 1461 loss: 0.0090 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0090 2022/12/20 14:50:02 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:15:14 time: 0.1855 data_time: 0.0074 memory: 1461 loss: 0.0096 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0096 2022/12/20 14:50:18 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:14:59 time: 0.1510 data_time: 0.0067 memory: 1461 loss: 0.0171 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0171 2022/12/20 14:50:34 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:14:44 time: 0.1851 data_time: 0.0070 memory: 1461 loss: 0.0102 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0102 2022/12/20 14:50:49 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:14:29 time: 0.1527 data_time: 0.0076 memory: 1461 loss: 0.0070 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0070 2022/12/20 14:51:04 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:14:13 time: 0.1641 data_time: 0.0069 memory: 1461 loss: 0.0062 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0062 2022/12/20 14:51:21 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:13:58 time: 0.1523 data_time: 0.0074 memory: 1461 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/12/20 14:51:36 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:13:43 time: 0.2022 data_time: 0.0068 memory: 1461 loss: 0.0103 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0103 2022/12/20 14:51:52 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:13:28 time: 0.1695 data_time: 0.0071 memory: 1461 loss: 0.0074 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0074 2022/12/20 14:52:07 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:13:12 time: 0.1298 data_time: 0.0069 memory: 1461 loss: 0.0095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0095 2022/12/20 14:52:23 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:52:24 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:12:58 time: 0.1464 data_time: 0.0068 memory: 1461 loss: 0.0087 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0087 2022/12/20 14:52:38 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:12:42 time: 0.1339 data_time: 0.0067 memory: 1461 loss: 0.0089 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0089 2022/12/20 14:52:55 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:12:27 time: 0.1548 data_time: 0.0075 memory: 1461 loss: 0.0061 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0061 2022/12/20 14:53:08 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:12:11 time: 0.1390 data_time: 0.0076 memory: 1461 loss: 0.0120 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0120 2022/12/20 14:53:17 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:53:17 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:12:01 time: 0.0942 data_time: 0.0070 memory: 1461 loss: 0.1773 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1773 2022/12/20 14:53:17 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/12/20 14:53:21 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:00 time: 0.0341 data_time: 0.0087 memory: 215 2022/12/20 14:53:25 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8847 acc/top5: 0.9852 acc/mean1: 0.8846 2022/12/20 14:53:25 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_11.pth is removed 2022/12/20 14:53:25 - mmengine - INFO - The best checkpoint with 0.8847 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/12/20 14:53:41 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:11:45 time: 0.1344 data_time: 0.0074 memory: 1461 loss: 0.0096 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0096 2022/12/20 14:53:56 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:11:30 time: 0.1400 data_time: 0.0077 memory: 1461 loss: 0.0108 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0108 2022/12/20 14:54:13 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:11:15 time: 0.1581 data_time: 0.0068 memory: 1461 loss: 0.0070 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0070 2022/12/20 14:54:27 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:10:59 time: 0.1330 data_time: 0.0076 memory: 1461 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/12/20 14:54:45 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:10:44 time: 0.1866 data_time: 0.0073 memory: 1461 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/12/20 14:54:59 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:10:29 time: 0.1390 data_time: 0.0084 memory: 1461 loss: 0.0087 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0087 2022/12/20 14:55:03 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:55:15 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:10:14 time: 0.1566 data_time: 0.0070 memory: 1461 loss: 0.0158 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0158 2022/12/20 14:55:31 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:09:58 time: 0.1407 data_time: 0.0078 memory: 1461 loss: 0.0080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0080 2022/12/20 14:55:47 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:09:43 time: 0.1646 data_time: 0.0078 memory: 1461 loss: 0.0080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0080 2022/12/20 14:56:03 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:09:28 time: 0.1570 data_time: 0.0069 memory: 1461 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/12/20 14:56:19 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:09:13 time: 0.1969 data_time: 0.0068 memory: 1461 loss: 0.0062 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0062 2022/12/20 14:56:35 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:08:57 time: 0.1578 data_time: 0.0077 memory: 1461 loss: 0.0100 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0100 2022/12/20 14:56:49 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:08:42 time: 0.1841 data_time: 0.0077 memory: 1461 loss: 0.0060 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0060 2022/12/20 14:57:04 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:08:26 time: 0.1362 data_time: 0.0072 memory: 1461 loss: 0.0068 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0068 2022/12/20 14:57:18 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:08:11 time: 0.1369 data_time: 0.0089 memory: 1461 loss: 0.0057 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0057 2022/12/20 14:57:26 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:57:26 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:08:00 time: 0.1838 data_time: 0.0074 memory: 1461 loss: 0.2267 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2267 2022/12/20 14:57:26 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/12/20 14:57:33 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:01 time: 0.1161 data_time: 0.0062 memory: 215 2022/12/20 14:57:39 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8812 acc/top5: 0.9857 acc/mean1: 0.8811 2022/12/20 14:57:47 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 14:57:53 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:07:45 time: 0.1591 data_time: 0.0071 memory: 1461 loss: 0.0067 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0067 2022/12/20 14:58:10 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:07:30 time: 0.1620 data_time: 0.0073 memory: 1461 loss: 0.0065 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0065 2022/12/20 14:58:26 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:07:14 time: 0.1690 data_time: 0.0068 memory: 1461 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/12/20 14:58:41 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:06:59 time: 0.1918 data_time: 0.0075 memory: 1461 loss: 0.0076 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0076 2022/12/20 14:58:57 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:06:44 time: 0.1676 data_time: 0.0069 memory: 1461 loss: 0.0087 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0087 2022/12/20 14:59:13 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:06:28 time: 0.1743 data_time: 0.0075 memory: 1461 loss: 0.0059 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0059 2022/12/20 14:59:29 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:06:13 time: 0.1654 data_time: 0.0070 memory: 1461 loss: 0.0086 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0086 2022/12/20 14:59:44 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:05:58 time: 0.1456 data_time: 0.0073 memory: 1461 loss: 0.0070 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0070 2022/12/20 15:00:01 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:05:43 time: 0.1321 data_time: 0.0075 memory: 1461 loss: 0.0059 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0059 2022/12/20 15:00:16 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:05:27 time: 0.2166 data_time: 0.0074 memory: 1461 loss: 0.0055 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0055 2022/12/20 15:00:26 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 15:00:33 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:05:12 time: 0.1699 data_time: 0.0071 memory: 1461 loss: 0.0053 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0053 2022/12/20 15:00:47 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:04:57 time: 0.1456 data_time: 0.0068 memory: 1461 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2022/12/20 15:01:03 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:04:41 time: 0.1442 data_time: 0.0077 memory: 1461 loss: 0.0062 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0062 2022/12/20 15:01:16 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:04:26 time: 0.1419 data_time: 0.0069 memory: 1461 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/12/20 15:01:28 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:04:10 time: 0.1278 data_time: 0.0078 memory: 1461 loss: 0.0055 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0055 2022/12/20 15:01:41 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 15:01:41 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:04:00 time: 0.1578 data_time: 0.0065 memory: 1461 loss: 0.2047 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2047 2022/12/20 15:01:41 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/12/20 15:01:45 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:01 time: 0.0413 data_time: 0.0067 memory: 215 2022/12/20 15:01:49 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8826 acc/top5: 0.9854 acc/mean1: 0.8825 2022/12/20 15:02:04 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:03:45 time: 0.1691 data_time: 0.0071 memory: 1461 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/12/20 15:02:20 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:03:29 time: 0.1378 data_time: 0.0090 memory: 1461 loss: 0.0072 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0072 2022/12/20 15:02:35 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:03:14 time: 0.1545 data_time: 0.0069 memory: 1461 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/12/20 15:02:51 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:02:59 time: 0.1282 data_time: 0.0072 memory: 1461 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2022/12/20 15:03:05 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 15:03:05 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:02:43 time: 0.1946 data_time: 0.0069 memory: 1461 loss: 0.0064 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0064 2022/12/20 15:03:22 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:02:28 time: 0.1382 data_time: 0.0070 memory: 1461 loss: 0.0074 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0074 2022/12/20 15:03:36 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:02:13 time: 0.1514 data_time: 0.0081 memory: 1461 loss: 0.0066 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0066 2022/12/20 15:03:53 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:01:57 time: 0.1595 data_time: 0.0077 memory: 1461 loss: 0.0054 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0054 2022/12/20 15:04:07 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:01:42 time: 0.1098 data_time: 0.0070 memory: 1461 loss: 0.0082 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0082 2022/12/20 15:04:25 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:01:27 time: 0.1774 data_time: 0.0079 memory: 1461 loss: 0.0067 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0067 2022/12/20 15:04:38 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:01:11 time: 0.1378 data_time: 0.0069 memory: 1461 loss: 0.0064 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0064 2022/12/20 15:04:55 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:56 time: 0.1593 data_time: 0.0068 memory: 1461 loss: 0.0062 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0062 2022/12/20 15:05:08 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:40 time: 0.1258 data_time: 0.0074 memory: 1461 loss: 0.0054 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0054 2022/12/20 15:05:24 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:25 time: 0.2161 data_time: 0.0069 memory: 1461 loss: 0.0072 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0072 2022/12/20 15:05:34 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 15:05:35 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:10 time: 0.1233 data_time: 0.0071 memory: 1461 loss: 0.0078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0078 2022/12/20 15:05:46 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20221220_135823 2022/12/20 15:05:46 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.2039 data_time: 0.0070 memory: 1461 loss: 0.2154 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2154 2022/12/20 15:05:46 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/12/20 15:05:52 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:01 time: 0.0300 data_time: 0.0065 memory: 215 2022/12/20 15:05:56 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8827 acc/top5: 0.9851 acc/mean1: 0.8826