2022/12/22 11:06:53 - 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: 485729613 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/share/cuda-11.1 NVCC: Cuda compilation tools, release 11.1, V11.1.74 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 ------------------------------------------------------------ 2022/12/22 11:06:53 - 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='nturgb+d', 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_3d.pkl' train_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['j']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] val_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', 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='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', 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_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', 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_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', 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_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', 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-3d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/12/22 11:06:53 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/modules_statistic_results.json 2022/12/22 11:06:53 - 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([150]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.data_bn.bias - torch.Size([150]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.A - torch.Size([3, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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 2022/12/22 11:07:31 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d. 2022/12/22 11:08:59 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 6:06:56 time: 0.5417 data_time: 0.0072 memory: 2111 loss: 2.6055 top1_acc: 0.3750 top5_acc: 0.5625 loss_cls: 2.6055 2022/12/22 11:09:53 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 4:55:44 time: 0.5443 data_time: 0.0073 memory: 2111 loss: 1.9648 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.9648 2022/12/22 11:10:48 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 4:31:31 time: 0.5463 data_time: 0.0072 memory: 2111 loss: 1.6698 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 1.6698 2022/12/22 11:11:43 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 4:19:01 time: 0.5478 data_time: 0.0069 memory: 2111 loss: 1.4223 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4223 2022/12/22 11:12:37 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 4:11:12 time: 0.5474 data_time: 0.0075 memory: 2111 loss: 1.3216 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.3216 2022/12/22 11:13:32 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 4:05:28 time: 0.5421 data_time: 0.0072 memory: 2111 loss: 1.2053 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 1.2053 2022/12/22 11:14:26 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 4:01:05 time: 0.5438 data_time: 0.0069 memory: 2111 loss: 1.1664 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 1.1664 2022/12/22 11:15:21 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 3:57:42 time: 0.5448 data_time: 0.0070 memory: 2111 loss: 0.9414 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9414 2022/12/22 11:16:15 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 3:54:47 time: 0.5469 data_time: 0.0070 memory: 2111 loss: 0.9237 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.9237 2022/12/22 11:17:10 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:17:10 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 3:52:19 time: 0.5436 data_time: 0.0072 memory: 2111 loss: 0.9252 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9252 2022/12/22 11:18:04 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 3:50:10 time: 0.5479 data_time: 0.0071 memory: 2111 loss: 0.9185 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9185 2022/12/22 11:18:59 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 3:48:13 time: 0.5446 data_time: 0.0070 memory: 2111 loss: 0.8701 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8701 2022/12/22 11:19:54 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 3:46:24 time: 0.5491 data_time: 0.0070 memory: 2111 loss: 0.7375 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7375 2022/12/22 11:20:48 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 3:44:41 time: 0.5469 data_time: 0.0072 memory: 2111 loss: 0.7264 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7264 2022/12/22 11:21:42 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 3:43:02 time: 0.5308 data_time: 0.0068 memory: 2111 loss: 0.6267 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.6267 2022/12/22 11:22:18 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:22:18 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 3:41:52 time: 0.5318 data_time: 0.0068 memory: 2111 loss: 0.8201 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.8201 2022/12/22 11:22:18 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/22 11:22:40 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:06 time: 0.1896 data_time: 0.0067 memory: 293 2022/12/22 11:22:46 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.5473 acc/top5: 0.8874 acc/mean1: 0.5471 2022/12/22 11:22:47 - mmengine - INFO - The best checkpoint with 0.5473 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/12/22 11:23:41 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 3:40:23 time: 0.5463 data_time: 0.0071 memory: 2111 loss: 0.6386 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.6386 2022/12/22 11:24:36 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 3:39:00 time: 0.5415 data_time: 0.0068 memory: 2111 loss: 0.6808 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6808 2022/12/22 11:25:30 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 3:37:37 time: 0.5362 data_time: 0.0071 memory: 2111 loss: 0.5651 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5651 2022/12/22 11:26:25 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 3:36:20 time: 0.5459 data_time: 0.0076 memory: 2111 loss: 0.6000 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6000 2022/12/22 11:26:42 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:27:19 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 3:35:06 time: 0.5475 data_time: 0.0073 memory: 2111 loss: 0.6658 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6658 2022/12/22 11:28:14 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 3:33:52 time: 0.5405 data_time: 0.0072 memory: 2111 loss: 0.5966 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5966 2022/12/22 11:29:08 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 3:32:41 time: 0.5464 data_time: 0.0073 memory: 2111 loss: 0.5914 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5914 2022/12/22 11:30:03 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 3:31:31 time: 0.5436 data_time: 0.0069 memory: 2111 loss: 0.6391 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6391 2022/12/22 11:30:57 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 3:30:21 time: 0.5446 data_time: 0.0072 memory: 2111 loss: 0.5055 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5055 2022/12/22 11:31:52 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 3:29:15 time: 0.5432 data_time: 0.0071 memory: 2111 loss: 0.5726 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5726 2022/12/22 11:32:46 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 3:28:09 time: 0.5489 data_time: 0.0068 memory: 2111 loss: 0.4554 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4554 2022/12/22 11:33:41 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 3:27:03 time: 0.5426 data_time: 0.0068 memory: 2111 loss: 0.4877 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4877 2022/12/22 11:34:35 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 3:25:58 time: 0.5392 data_time: 0.0073 memory: 2111 loss: 0.5226 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.5226 2022/12/22 11:35:30 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 3:24:55 time: 0.5475 data_time: 0.0069 memory: 2111 loss: 0.5415 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.5415 2022/12/22 11:35:48 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:36:24 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 3:23:51 time: 0.5413 data_time: 0.0070 memory: 2111 loss: 0.5513 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5513 2022/12/22 11:37:00 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:37:00 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 3:23:06 time: 0.5313 data_time: 0.0073 memory: 2111 loss: 0.7505 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7505 2022/12/22 11:37:00 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/22 11:37:21 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:05 time: 0.1879 data_time: 0.0073 memory: 293 2022/12/22 11:37:28 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.7544 acc/top5: 0.9400 acc/mean1: 0.7542 2022/12/22 11:37:28 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_1.pth is removed 2022/12/22 11:37:28 - mmengine - INFO - The best checkpoint with 0.7544 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/12/22 11:38:22 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 3:22:03 time: 0.5493 data_time: 0.0068 memory: 2111 loss: 0.4657 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4657 2022/12/22 11:39:17 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 3:21:00 time: 0.5423 data_time: 0.0072 memory: 2111 loss: 0.4489 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4489 2022/12/22 11:40:11 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 3:19:59 time: 0.5459 data_time: 0.0073 memory: 2111 loss: 0.4974 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4974 2022/12/22 11:41:06 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 3:18:57 time: 0.5416 data_time: 0.0071 memory: 2111 loss: 0.4711 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.4711 2022/12/22 11:42:00 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 3:17:56 time: 0.5469 data_time: 0.0070 memory: 2111 loss: 0.4951 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.4951 2022/12/22 11:42:54 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 3:16:53 time: 0.5445 data_time: 0.0077 memory: 2111 loss: 0.4758 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4758 2022/12/22 11:43:48 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 3:15:51 time: 0.5406 data_time: 0.0073 memory: 2111 loss: 0.4794 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4794 2022/12/22 11:44:43 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 3:14:51 time: 0.5434 data_time: 0.0071 memory: 2111 loss: 0.4399 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4399 2022/12/22 11:45:19 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:45:38 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 3:13:52 time: 0.5443 data_time: 0.0071 memory: 2111 loss: 0.4484 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4484 2022/12/22 11:46:32 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 3:12:52 time: 0.5477 data_time: 0.0071 memory: 2111 loss: 0.5675 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.5675 2022/12/22 11:47:26 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 3:11:52 time: 0.5387 data_time: 0.0071 memory: 2111 loss: 0.4689 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4689 2022/12/22 11:48:20 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 3:10:52 time: 0.5362 data_time: 0.0072 memory: 2111 loss: 0.4419 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4419 2022/12/22 11:49:15 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 3:09:54 time: 0.5481 data_time: 0.0073 memory: 2111 loss: 0.3949 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3949 2022/12/22 11:50:10 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 3:08:56 time: 0.5471 data_time: 0.0073 memory: 2111 loss: 0.3281 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3281 2022/12/22 11:51:04 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 3:07:58 time: 0.5467 data_time: 0.0072 memory: 2111 loss: 0.4802 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4802 2022/12/22 11:51:41 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:51:41 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 3:07:18 time: 0.5321 data_time: 0.0068 memory: 2111 loss: 0.5307 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5307 2022/12/22 11:51:41 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/12/22 11:52:01 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:05 time: 0.1791 data_time: 0.0070 memory: 293 2022/12/22 11:52:06 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.7702 acc/top5: 0.9555 acc/mean1: 0.7702 2022/12/22 11:52:06 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_2.pth is removed 2022/12/22 11:52:06 - mmengine - INFO - The best checkpoint with 0.7702 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2022/12/22 11:53:00 - mmengine - INFO - Epoch(train) [4][ 100/1567] lr: 9.1226e-02 eta: 3:06:19 time: 0.5462 data_time: 0.0071 memory: 2111 loss: 0.3799 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.3799 2022/12/22 11:53:54 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 3:05:19 time: 0.5385 data_time: 0.0068 memory: 2111 loss: 0.3404 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3404 2022/12/22 11:54:47 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:54:48 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 3:04:18 time: 0.5427 data_time: 0.0071 memory: 2111 loss: 0.2787 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2787 2022/12/22 11:55:42 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 3:03:18 time: 0.5356 data_time: 0.0069 memory: 2111 loss: 0.4466 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.4466 2022/12/22 11:56:36 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 3:02:20 time: 0.5393 data_time: 0.0070 memory: 2111 loss: 0.3671 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3671 2022/12/22 11:57:30 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 3:01:21 time: 0.5428 data_time: 0.0072 memory: 2111 loss: 0.4164 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4164 2022/12/22 11:58:24 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 3:00:21 time: 0.5360 data_time: 0.0067 memory: 2111 loss: 0.4362 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4362 2022/12/22 11:59:18 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 2:59:22 time: 0.5318 data_time: 0.0069 memory: 2111 loss: 0.4174 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4174 2022/12/22 12:00:11 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 2:58:22 time: 0.5274 data_time: 0.0068 memory: 2111 loss: 0.3847 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3847 2022/12/22 12:01:05 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 2:57:22 time: 0.5271 data_time: 0.0069 memory: 2111 loss: 0.3881 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3881 2022/12/22 12:01:58 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 2:56:22 time: 0.5254 data_time: 0.0070 memory: 2111 loss: 0.3845 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3845 2022/12/22 12:02:52 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 2:55:24 time: 0.5484 data_time: 0.0070 memory: 2111 loss: 0.3644 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3644 2022/12/22 12:03:46 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:03:46 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 2:54:27 time: 0.5413 data_time: 0.0069 memory: 2111 loss: 0.4434 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4434 2022/12/22 12:04:40 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 2:53:28 time: 0.5283 data_time: 0.0069 memory: 2111 loss: 0.3599 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3599 2022/12/22 12:05:34 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 2:52:31 time: 0.5419 data_time: 0.0074 memory: 2111 loss: 0.3615 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3615 2022/12/22 12:06:10 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:06:10 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 2:51:50 time: 0.5095 data_time: 0.0072 memory: 2111 loss: 0.4972 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4972 2022/12/22 12:06:10 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/22 12:06:29 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:05 time: 0.1878 data_time: 0.0065 memory: 293 2022/12/22 12:06:36 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7982 acc/top5: 0.9547 acc/mean1: 0.7982 2022/12/22 12:06:36 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_3.pth is removed 2022/12/22 12:06:36 - mmengine - INFO - The best checkpoint with 0.7982 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2022/12/22 12:07:30 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 2:50:51 time: 0.5449 data_time: 0.0069 memory: 2111 loss: 0.4367 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4367 2022/12/22 12:08:24 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 2:49:54 time: 0.5417 data_time: 0.0070 memory: 2111 loss: 0.4326 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4326 2022/12/22 12:09:17 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 2:48:56 time: 0.5434 data_time: 0.0069 memory: 2111 loss: 0.3194 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3194 2022/12/22 12:10:11 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 2:47:59 time: 0.5391 data_time: 0.0072 memory: 2111 loss: 0.4075 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4075 2022/12/22 12:11:05 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 2:47:02 time: 0.5410 data_time: 0.0073 memory: 2111 loss: 0.3766 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3766 2022/12/22 12:11:59 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 2:46:04 time: 0.5277 data_time: 0.0068 memory: 2111 loss: 0.4236 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4236 2022/12/22 12:12:53 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 2:45:07 time: 0.5447 data_time: 0.0077 memory: 2111 loss: 0.2448 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2448 2022/12/22 12:13:10 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:13:46 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 2:44:10 time: 0.5365 data_time: 0.0069 memory: 2111 loss: 0.3502 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3502 2022/12/22 12:14:40 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 2:43:13 time: 0.5377 data_time: 0.0071 memory: 2111 loss: 0.3352 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3352 2022/12/22 12:15:34 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 2:42:17 time: 0.5455 data_time: 0.0069 memory: 2111 loss: 0.2362 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2362 2022/12/22 12:16:28 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 2:41:19 time: 0.5403 data_time: 0.0069 memory: 2111 loss: 0.3105 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3105 2022/12/22 12:17:21 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 2:40:22 time: 0.5170 data_time: 0.0073 memory: 2111 loss: 0.3412 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3412 2022/12/22 12:18:15 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 2:39:25 time: 0.5312 data_time: 0.0068 memory: 2111 loss: 0.3497 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3497 2022/12/22 12:19:09 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 2:38:29 time: 0.5383 data_time: 0.0069 memory: 2111 loss: 0.3173 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3173 2022/12/22 12:20:03 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 2:37:32 time: 0.5307 data_time: 0.0074 memory: 2111 loss: 0.3459 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3459 2022/12/22 12:20:38 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:20:38 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 2:36:52 time: 0.4833 data_time: 0.0074 memory: 2111 loss: 0.5227 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5227 2022/12/22 12:20:38 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/22 12:20:57 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:05 time: 0.1895 data_time: 0.0062 memory: 293 2022/12/22 12:21:05 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.8204 acc/top5: 0.9676 acc/mean1: 0.8203 2022/12/22 12:21:05 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_4.pth is removed 2022/12/22 12:21:05 - mmengine - INFO - The best checkpoint with 0.8204 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2022/12/22 12:21:58 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 2:35:55 time: 0.5364 data_time: 0.0067 memory: 2111 loss: 0.2630 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2630 2022/12/22 12:22:33 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:22:51 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 2:34:57 time: 0.5426 data_time: 0.0070 memory: 2111 loss: 0.3266 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3266 2022/12/22 12:23:45 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 2:34:01 time: 0.5322 data_time: 0.0070 memory: 2111 loss: 0.2838 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2838 2022/12/22 12:24:39 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 2:33:04 time: 0.5321 data_time: 0.0071 memory: 2111 loss: 0.2276 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2276 2022/12/22 12:25:33 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 2:32:09 time: 0.5432 data_time: 0.0073 memory: 2111 loss: 0.3457 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3457 2022/12/22 12:26:27 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 2:31:13 time: 0.5373 data_time: 0.0068 memory: 2111 loss: 0.2722 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2722 2022/12/22 12:27:20 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 2:30:15 time: 0.5431 data_time: 0.0069 memory: 2111 loss: 0.2901 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2901 2022/12/22 12:28:14 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 2:29:20 time: 0.5413 data_time: 0.0068 memory: 2111 loss: 0.2588 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2588 2022/12/22 12:29:08 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 2:28:24 time: 0.5445 data_time: 0.0072 memory: 2111 loss: 0.3267 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3267 2022/12/22 12:30:01 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 2:27:28 time: 0.5374 data_time: 0.0069 memory: 2111 loss: 0.3262 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3262 2022/12/22 12:30:55 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 2:26:33 time: 0.5374 data_time: 0.0069 memory: 2111 loss: 0.2611 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2611 2022/12/22 12:31:30 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:31:49 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 2:25:37 time: 0.5415 data_time: 0.0068 memory: 2111 loss: 0.2208 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2208 2022/12/22 12:32:43 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 2:24:41 time: 0.5355 data_time: 0.0067 memory: 2111 loss: 0.2765 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2765 2022/12/22 12:33:37 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 2:23:46 time: 0.5422 data_time: 0.0068 memory: 2111 loss: 0.3125 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3125 2022/12/22 12:34:31 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 2:22:50 time: 0.5294 data_time: 0.0068 memory: 2111 loss: 0.2559 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2559 2022/12/22 12:35:05 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:35:05 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 2:22:10 time: 0.4450 data_time: 0.0066 memory: 2111 loss: 0.4254 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4254 2022/12/22 12:35:05 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/22 12:35:24 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:05 time: 0.1874 data_time: 0.0063 memory: 293 2022/12/22 12:35:32 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.8129 acc/top5: 0.9603 acc/mean1: 0.8128 2022/12/22 12:36:25 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 2:21:13 time: 0.5298 data_time: 0.0068 memory: 2111 loss: 0.2853 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2853 2022/12/22 12:37:19 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 2:20:18 time: 0.5412 data_time: 0.0068 memory: 2111 loss: 0.2183 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2183 2022/12/22 12:38:13 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 2:19:22 time: 0.5288 data_time: 0.0071 memory: 2111 loss: 0.2302 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2302 2022/12/22 12:39:07 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 2:18:27 time: 0.5412 data_time: 0.0071 memory: 2111 loss: 0.2019 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2019 2022/12/22 12:40:00 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 2:17:32 time: 0.5390 data_time: 0.0070 memory: 2111 loss: 0.3739 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3739 2022/12/22 12:40:53 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:40:54 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 2:16:37 time: 0.5452 data_time: 0.0068 memory: 2111 loss: 0.2327 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2327 2022/12/22 12:41:48 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 2:15:42 time: 0.5388 data_time: 0.0070 memory: 2111 loss: 0.2063 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2063 2022/12/22 12:42:42 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 2:14:47 time: 0.5434 data_time: 0.0068 memory: 2111 loss: 0.2348 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2348 2022/12/22 12:43:36 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 2:13:51 time: 0.5276 data_time: 0.0068 memory: 2111 loss: 0.2219 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2219 2022/12/22 12:44:30 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 2:12:56 time: 0.5442 data_time: 0.0071 memory: 2111 loss: 0.2658 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2658 2022/12/22 12:45:24 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 2:12:02 time: 0.5422 data_time: 0.0069 memory: 2111 loss: 0.2249 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2249 2022/12/22 12:46:18 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 2:11:07 time: 0.5379 data_time: 0.0068 memory: 2111 loss: 0.1666 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1666 2022/12/22 12:47:12 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 2:10:11 time: 0.5392 data_time: 0.0068 memory: 2111 loss: 0.1947 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1947 2022/12/22 12:48:06 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 2:09:16 time: 0.5416 data_time: 0.0072 memory: 2111 loss: 0.2036 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2036 2022/12/22 12:49:00 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 2:08:21 time: 0.5403 data_time: 0.0069 memory: 2111 loss: 0.1802 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1802 2022/12/22 12:49:33 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:49:33 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 2:07:42 time: 0.4221 data_time: 0.0066 memory: 2111 loss: 0.4186 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4186 2022/12/22 12:49:33 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/12/22 12:49:53 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:05 time: 0.1797 data_time: 0.0064 memory: 293 2022/12/22 12:50:01 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.7980 acc/top5: 0.9582 acc/mean1: 0.7980 2022/12/22 12:50:17 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:50:54 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 2:06:46 time: 0.5381 data_time: 0.0066 memory: 2111 loss: 0.1709 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1709 2022/12/22 12:51:48 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 2:05:51 time: 0.5354 data_time: 0.0069 memory: 2111 loss: 0.2208 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2208 2022/12/22 12:52:42 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 2:04:56 time: 0.5355 data_time: 0.0069 memory: 2111 loss: 0.2059 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2059 2022/12/22 12:53:35 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 2:04:01 time: 0.5355 data_time: 0.0069 memory: 2111 loss: 0.1759 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1759 2022/12/22 12:54:29 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 2:03:06 time: 0.5345 data_time: 0.0070 memory: 2111 loss: 0.2354 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2354 2022/12/22 12:55:23 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 2:02:11 time: 0.5439 data_time: 0.0069 memory: 2111 loss: 0.2333 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2333 2022/12/22 12:56:17 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 2:01:17 time: 0.5392 data_time: 0.0069 memory: 2111 loss: 0.1634 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1634 2022/12/22 12:57:11 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 2:00:22 time: 0.5428 data_time: 0.0069 memory: 2111 loss: 0.1822 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1822 2022/12/22 12:58:05 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 1:59:28 time: 0.5394 data_time: 0.0067 memory: 2111 loss: 0.1721 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1721 2022/12/22 12:58:59 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 1:58:33 time: 0.5401 data_time: 0.0067 memory: 2111 loss: 0.1583 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1583 2022/12/22 12:59:16 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:59:53 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 1:57:38 time: 0.5401 data_time: 0.0068 memory: 2111 loss: 0.1106 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1106 2022/12/22 13:00:47 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 1:56:43 time: 0.5399 data_time: 0.0069 memory: 2111 loss: 0.1653 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1653 2022/12/22 13:01:41 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 1:55:48 time: 0.5380 data_time: 0.0067 memory: 2111 loss: 0.1463 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.1463 2022/12/22 13:02:35 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 1:54:54 time: 0.5435 data_time: 0.0068 memory: 2111 loss: 0.1591 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1591 2022/12/22 13:03:28 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 1:53:59 time: 0.5389 data_time: 0.0069 memory: 2111 loss: 0.1252 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1252 2022/12/22 13:04:01 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:04:01 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 1:53:19 time: 0.4170 data_time: 0.0070 memory: 2111 loss: 0.3343 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3343 2022/12/22 13:04:01 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/12/22 13:04:22 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:05 time: 0.2227 data_time: 0.0064 memory: 293 2022/12/22 13:04:30 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.8271 acc/top5: 0.9628 acc/mean1: 0.8270 2022/12/22 13:04:30 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_5.pth is removed 2022/12/22 13:04:30 - mmengine - INFO - The best checkpoint with 0.8271 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/12/22 13:05:24 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 1:52:25 time: 0.5366 data_time: 0.0070 memory: 2111 loss: 0.1318 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1318 2022/12/22 13:06:18 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 1:51:30 time: 0.5387 data_time: 0.0069 memory: 2111 loss: 0.1233 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1233 2022/12/22 13:07:12 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 1:50:36 time: 0.5380 data_time: 0.0068 memory: 2111 loss: 0.1161 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1161 2022/12/22 13:08:05 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 1:49:41 time: 0.5398 data_time: 0.0070 memory: 2111 loss: 0.1149 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1149 2022/12/22 13:08:40 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:08:59 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 1:48:47 time: 0.5436 data_time: 0.0070 memory: 2111 loss: 0.1600 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1600 2022/12/22 13:09:53 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 1:47:52 time: 0.5443 data_time: 0.0071 memory: 2111 loss: 0.1372 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1372 2022/12/22 13:10:48 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 1:46:58 time: 0.5445 data_time: 0.0070 memory: 2111 loss: 0.1251 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1251 2022/12/22 13:11:42 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 1:46:03 time: 0.5405 data_time: 0.0069 memory: 2111 loss: 0.1208 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.1208 2022/12/22 13:12:35 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 1:45:09 time: 0.5349 data_time: 0.0067 memory: 2111 loss: 0.1479 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1479 2022/12/22 13:13:29 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 1:44:14 time: 0.5439 data_time: 0.0067 memory: 2111 loss: 0.1212 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1212 2022/12/22 13:14:24 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 1:43:20 time: 0.5409 data_time: 0.0068 memory: 2111 loss: 0.1190 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1190 2022/12/22 13:15:18 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 1:42:26 time: 0.5452 data_time: 0.0072 memory: 2111 loss: 0.1162 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1162 2022/12/22 13:16:12 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 1:41:31 time: 0.5472 data_time: 0.0068 memory: 2111 loss: 0.1191 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1191 2022/12/22 13:17:06 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 1:40:37 time: 0.5387 data_time: 0.0068 memory: 2111 loss: 0.0882 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0882 2022/12/22 13:17:41 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:18:00 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 1:39:43 time: 0.5421 data_time: 0.0069 memory: 2111 loss: 0.1497 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1497 2022/12/22 13:18:33 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:18:33 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 1:39:04 time: 0.4297 data_time: 0.0069 memory: 2111 loss: 0.2683 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2683 2022/12/22 13:18:33 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/12/22 13:18:54 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:05 time: 0.2321 data_time: 0.0063 memory: 293 2022/12/22 13:19:02 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8455 acc/top5: 0.9662 acc/mean1: 0.8454 2022/12/22 13:19:02 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_8.pth is removed 2022/12/22 13:19:02 - mmengine - INFO - The best checkpoint with 0.8455 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2022/12/22 13:19:56 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 1:38:10 time: 0.5323 data_time: 0.0068 memory: 2111 loss: 0.0834 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0834 2022/12/22 13:20:51 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 1:37:16 time: 0.5417 data_time: 0.0070 memory: 2111 loss: 0.1346 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1346 2022/12/22 13:21:45 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 1:36:22 time: 0.5398 data_time: 0.0069 memory: 2111 loss: 0.1161 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1161 2022/12/22 13:22:39 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 1:35:27 time: 0.5453 data_time: 0.0069 memory: 2111 loss: 0.0885 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0885 2022/12/22 13:23:32 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 1:34:33 time: 0.5347 data_time: 0.0071 memory: 2111 loss: 0.1534 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1534 2022/12/22 13:24:27 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 1:33:39 time: 0.5434 data_time: 0.0077 memory: 2111 loss: 0.0751 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0751 2022/12/22 13:25:21 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 1:32:44 time: 0.5424 data_time: 0.0071 memory: 2111 loss: 0.0754 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0754 2022/12/22 13:26:15 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 1:31:50 time: 0.5396 data_time: 0.0070 memory: 2111 loss: 0.1068 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1068 2022/12/22 13:27:07 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:27:09 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 1:30:56 time: 0.5382 data_time: 0.0069 memory: 2111 loss: 0.0860 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0860 2022/12/22 13:28:03 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 1:30:02 time: 0.5378 data_time: 0.0071 memory: 2111 loss: 0.0787 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0787 2022/12/22 13:28:57 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 1:29:07 time: 0.5328 data_time: 0.0069 memory: 2111 loss: 0.0791 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0791 2022/12/22 13:29:51 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 1:28:13 time: 0.5314 data_time: 0.0069 memory: 2111 loss: 0.0729 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0729 2022/12/22 13:30:46 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 1:27:19 time: 0.5464 data_time: 0.0070 memory: 2111 loss: 0.0731 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0731 2022/12/22 13:31:40 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 1:26:25 time: 0.5444 data_time: 0.0069 memory: 2111 loss: 0.0801 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0801 2022/12/22 13:32:34 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 1:25:30 time: 0.5453 data_time: 0.0070 memory: 2111 loss: 0.0946 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0946 2022/12/22 13:33:06 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:33:06 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 1:24:52 time: 0.4289 data_time: 0.0066 memory: 2111 loss: 0.2239 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2239 2022/12/22 13:33:06 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/12/22 13:33:28 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:06 time: 0.2439 data_time: 0.0063 memory: 293 2022/12/22 13:33:36 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8483 acc/top5: 0.9681 acc/mean1: 0.8482 2022/12/22 13:33:36 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_9.pth is removed 2022/12/22 13:33:36 - mmengine - INFO - The best checkpoint with 0.8483 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/12/22 13:34:30 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 1:23:58 time: 0.5401 data_time: 0.0068 memory: 2111 loss: 0.0539 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0539 2022/12/22 13:35:24 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 1:23:04 time: 0.5456 data_time: 0.0073 memory: 2111 loss: 0.0335 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0335 2022/12/22 13:36:19 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 1:22:10 time: 0.5468 data_time: 0.0070 memory: 2111 loss: 0.0466 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0466 2022/12/22 13:36:35 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:37:13 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 1:21:15 time: 0.5422 data_time: 0.0068 memory: 2111 loss: 0.0813 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0813 2022/12/22 13:38:07 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 1:20:21 time: 0.5414 data_time: 0.0070 memory: 2111 loss: 0.0569 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0569 2022/12/22 13:39:01 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 1:19:27 time: 0.5404 data_time: 0.0072 memory: 2111 loss: 0.0481 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0481 2022/12/22 13:39:55 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 1:18:33 time: 0.5400 data_time: 0.0070 memory: 2111 loss: 0.0582 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0582 2022/12/22 13:40:50 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 1:17:39 time: 0.5395 data_time: 0.0072 memory: 2111 loss: 0.0665 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0665 2022/12/22 13:41:44 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 1:16:45 time: 0.5460 data_time: 0.0071 memory: 2111 loss: 0.0632 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0632 2022/12/22 13:42:38 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 1:15:51 time: 0.5399 data_time: 0.0069 memory: 2111 loss: 0.0634 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0634 2022/12/22 13:43:32 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 1:14:56 time: 0.5467 data_time: 0.0070 memory: 2111 loss: 0.0556 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0556 2022/12/22 13:44:27 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 1:14:02 time: 0.5435 data_time: 0.0070 memory: 2111 loss: 0.0371 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0371 2022/12/22 13:45:20 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 1:13:08 time: 0.5466 data_time: 0.0070 memory: 2111 loss: 0.0269 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0269 2022/12/22 13:45:37 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:46:15 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 1:12:14 time: 0.5415 data_time: 0.0068 memory: 2111 loss: 0.0297 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0297 2022/12/22 13:47:09 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 1:11:20 time: 0.5393 data_time: 0.0070 memory: 2111 loss: 0.0399 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0399 2022/12/22 13:47:42 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:47:42 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 1:10:42 time: 0.4314 data_time: 0.0067 memory: 2111 loss: 0.2115 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2115 2022/12/22 13:47:42 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/12/22 13:48:03 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:06 time: 0.2455 data_time: 0.0065 memory: 293 2022/12/22 13:48:11 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8572 acc/top5: 0.9698 acc/mean1: 0.8571 2022/12/22 13:48:11 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_10.pth is removed 2022/12/22 13:48:11 - mmengine - INFO - The best checkpoint with 0.8572 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/12/22 13:49:05 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 1:09:47 time: 0.5414 data_time: 0.0067 memory: 2111 loss: 0.0392 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0392 2022/12/22 13:49:59 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 1:08:53 time: 0.5365 data_time: 0.0068 memory: 2111 loss: 0.0499 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0499 2022/12/22 13:50:54 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 1:07:59 time: 0.5427 data_time: 0.0070 memory: 2111 loss: 0.0450 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0450 2022/12/22 13:51:48 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 1:07:05 time: 0.5417 data_time: 0.0070 memory: 2111 loss: 0.0558 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0558 2022/12/22 13:52:42 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 1:06:11 time: 0.5474 data_time: 0.0077 memory: 2111 loss: 0.0392 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0392 2022/12/22 13:53:36 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 1:05:17 time: 0.5407 data_time: 0.0072 memory: 2111 loss: 0.0205 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0205 2022/12/22 13:54:30 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 1:04:23 time: 0.5386 data_time: 0.0067 memory: 2111 loss: 0.0228 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0228 2022/12/22 13:55:04 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:55:24 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 1:03:28 time: 0.5356 data_time: 0.0068 memory: 2111 loss: 0.0172 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0172 2022/12/22 13:56:19 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 1:02:34 time: 0.5464 data_time: 0.0068 memory: 2111 loss: 0.0248 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0248 2022/12/22 13:57:13 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 1:01:40 time: 0.5409 data_time: 0.0069 memory: 2111 loss: 0.0270 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0270 2022/12/22 13:58:07 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 1:00:46 time: 0.5440 data_time: 0.0072 memory: 2111 loss: 0.0132 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0132 2022/12/22 13:59:01 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:59:52 time: 0.5402 data_time: 0.0074 memory: 2111 loss: 0.0254 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0254 2022/12/22 13:59:55 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:58:58 time: 0.5427 data_time: 0.0069 memory: 2111 loss: 0.0163 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0163 2022/12/22 14:00:49 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:58:04 time: 0.5374 data_time: 0.0072 memory: 2111 loss: 0.0144 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0144 2022/12/22 14:01:44 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:57:10 time: 0.5420 data_time: 0.0068 memory: 2111 loss: 0.0138 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0138 2022/12/22 14:02:16 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:02:16 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:56:32 time: 0.4216 data_time: 0.0068 memory: 2111 loss: 0.2176 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2176 2022/12/22 14:02:16 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/12/22 14:02:37 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:06 time: 0.2446 data_time: 0.0062 memory: 293 2022/12/22 14:02:45 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8602 acc/top5: 0.9692 acc/mean1: 0.8601 2022/12/22 14:02:45 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_11.pth is removed 2022/12/22 14:02:45 - mmengine - INFO - The best checkpoint with 0.8602 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/12/22 14:03:40 - mmengine - INFO - Epoch(train) [13][ 100/1567] lr: 1.4209e-02 eta: 0:55:38 time: 0.5450 data_time: 0.0068 memory: 2111 loss: 0.0134 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0134 2022/12/22 14:04:32 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:04:34 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:54:44 time: 0.5482 data_time: 0.0071 memory: 2111 loss: 0.0114 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0114 2022/12/22 14:05:28 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:53:50 time: 0.5469 data_time: 0.0070 memory: 2111 loss: 0.0114 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0114 2022/12/22 14:06:22 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:52:55 time: 0.5373 data_time: 0.0068 memory: 2111 loss: 0.0127 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0127 2022/12/22 14:07:16 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:52:01 time: 0.5434 data_time: 0.0070 memory: 2111 loss: 0.0101 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0101 2022/12/22 14:08:11 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:51:07 time: 0.5487 data_time: 0.0075 memory: 2111 loss: 0.0138 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0138 2022/12/22 14:09:05 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:50:13 time: 0.5413 data_time: 0.0076 memory: 2111 loss: 0.0115 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0115 2022/12/22 14:09:59 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:49:19 time: 0.5320 data_time: 0.0071 memory: 2111 loss: 0.0145 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0145 2022/12/22 14:10:53 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:48:25 time: 0.5468 data_time: 0.0069 memory: 2111 loss: 0.0111 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0111 2022/12/22 14:11:47 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:47:31 time: 0.5468 data_time: 0.0071 memory: 2111 loss: 0.0098 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0098 2022/12/22 14:12:42 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:46:37 time: 0.5453 data_time: 0.0070 memory: 2111 loss: 0.0116 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0116 2022/12/22 14:13:34 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:13:36 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:45:43 time: 0.5463 data_time: 0.0068 memory: 2111 loss: 0.0127 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0127 2022/12/22 14:14:31 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:44:49 time: 0.5450 data_time: 0.0070 memory: 2111 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/12/22 14:15:25 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:43:55 time: 0.5441 data_time: 0.0070 memory: 2111 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/12/22 14:16:19 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:43:00 time: 0.5403 data_time: 0.0071 memory: 2111 loss: 0.0115 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0115 2022/12/22 14:16:51 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:16:51 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:42:23 time: 0.4219 data_time: 0.0074 memory: 2111 loss: 0.1977 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.1977 2022/12/22 14:16:51 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/12/22 14:17:13 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:06 time: 0.2431 data_time: 0.0063 memory: 293 2022/12/22 14:17:21 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8719 acc/top5: 0.9722 acc/mean1: 0.8718 2022/12/22 14:17:21 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_12.pth is removed 2022/12/22 14:17:21 - mmengine - INFO - The best checkpoint with 0.8719 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/12/22 14:18:16 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:41:29 time: 0.5404 data_time: 0.0069 memory: 2111 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/12/22 14:19:10 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:40:35 time: 0.5445 data_time: 0.0070 memory: 2111 loss: 0.0119 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0119 2022/12/22 14:20:04 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:39:41 time: 0.5441 data_time: 0.0069 memory: 2111 loss: 0.0088 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0088 2022/12/22 14:20:59 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:38:47 time: 0.5414 data_time: 0.0068 memory: 2111 loss: 0.0090 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0090 2022/12/22 14:21:53 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:37:53 time: 0.5403 data_time: 0.0070 memory: 2111 loss: 0.0088 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0088 2022/12/22 14:22:47 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:36:59 time: 0.5417 data_time: 0.0071 memory: 2111 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/12/22 14:23:03 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:23:41 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:36:05 time: 0.5404 data_time: 0.0071 memory: 2111 loss: 0.0089 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0089 2022/12/22 14:24:35 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:35:10 time: 0.5437 data_time: 0.0071 memory: 2111 loss: 0.0103 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0103 2022/12/22 14:25:29 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:34:16 time: 0.5383 data_time: 0.0071 memory: 2111 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/12/22 14:26:23 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:33:22 time: 0.5444 data_time: 0.0072 memory: 2111 loss: 0.0069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0069 2022/12/22 14:27:17 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:32:28 time: 0.5380 data_time: 0.0072 memory: 2111 loss: 0.0069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0069 2022/12/22 14:28:11 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:31:34 time: 0.5371 data_time: 0.0069 memory: 2111 loss: 0.0098 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0098 2022/12/22 14:29:05 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:30:40 time: 0.5334 data_time: 0.0069 memory: 2111 loss: 0.0059 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0059 2022/12/22 14:29:59 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:29:46 time: 0.5387 data_time: 0.0073 memory: 2111 loss: 0.0082 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0082 2022/12/22 14:30:52 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:28:51 time: 0.5355 data_time: 0.0069 memory: 2111 loss: 0.0064 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0064 2022/12/22 14:31:24 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:31:24 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:28:14 time: 0.4264 data_time: 0.0070 memory: 2111 loss: 0.1821 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1821 2022/12/22 14:31:24 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/12/22 14:31:46 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:06 time: 0.2410 data_time: 0.0065 memory: 293 2022/12/22 14:31:54 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8770 acc/top5: 0.9730 acc/mean1: 0.8769 2022/12/22 14:31:54 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_13.pth is removed 2022/12/22 14:31:54 - mmengine - INFO - The best checkpoint with 0.8770 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/12/22 14:32:28 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:32:48 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:27:20 time: 0.5384 data_time: 0.0110 memory: 2111 loss: 0.0061 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0061 2022/12/22 14:33:42 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:26:26 time: 0.5315 data_time: 0.0089 memory: 2111 loss: 0.0067 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0067 2022/12/22 14:34:36 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:25:32 time: 0.5487 data_time: 0.0093 memory: 2111 loss: 0.0077 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0077 2022/12/22 14:35:31 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:24:38 time: 0.5424 data_time: 0.0092 memory: 2111 loss: 0.0092 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0092 2022/12/22 14:36:25 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:23:44 time: 0.5475 data_time: 0.0086 memory: 2111 loss: 0.0088 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0088 2022/12/22 14:37:20 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:22:50 time: 0.5326 data_time: 0.0110 memory: 2111 loss: 0.0070 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0070 2022/12/22 14:38:14 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:21:56 time: 0.5388 data_time: 0.0092 memory: 2111 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/12/22 14:39:08 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:21:02 time: 0.5336 data_time: 0.0107 memory: 2111 loss: 0.0062 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0062 2022/12/22 14:40:03 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:20:08 time: 0.5471 data_time: 0.0093 memory: 2111 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2022/12/22 14:40:57 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:19:14 time: 0.5418 data_time: 0.0105 memory: 2111 loss: 0.0094 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0094 2022/12/22 14:41:31 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:41:52 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:18:20 time: 0.5422 data_time: 0.0100 memory: 2111 loss: 0.0078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0078 2022/12/22 14:42:46 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:17:26 time: 0.5472 data_time: 0.0104 memory: 2111 loss: 0.0059 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0059 2022/12/22 14:43:41 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:16:32 time: 0.5429 data_time: 0.0103 memory: 2111 loss: 0.0064 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0064 2022/12/22 14:44:35 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:15:38 time: 0.5287 data_time: 0.0102 memory: 2111 loss: 0.0072 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0072 2022/12/22 14:45:30 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:14:44 time: 0.5434 data_time: 0.0107 memory: 2111 loss: 0.0067 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0067 2022/12/22 14:46:01 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:46:01 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:14:07 time: 0.4287 data_time: 0.0098 memory: 2111 loss: 0.2040 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2040 2022/12/22 14:46:01 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/12/22 14:46:24 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:06 time: 0.2457 data_time: 0.0078 memory: 293 2022/12/22 14:46:32 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8764 acc/top5: 0.9740 acc/mean1: 0.8764 2022/12/22 14:47:26 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:13:13 time: 0.5411 data_time: 0.0108 memory: 2111 loss: 0.0070 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0070 2022/12/22 14:48:20 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:12:19 time: 0.5332 data_time: 0.0085 memory: 2111 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/12/22 14:49:14 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:11:25 time: 0.5417 data_time: 0.0105 memory: 2111 loss: 0.0095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0095 2022/12/22 14:50:09 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:10:31 time: 0.5453 data_time: 0.0086 memory: 2111 loss: 0.0061 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0061 2022/12/22 14:51:01 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:51:04 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:09:37 time: 0.5458 data_time: 0.0102 memory: 2111 loss: 0.0086 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0086 2022/12/22 14:51:58 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:08:43 time: 0.5358 data_time: 0.0089 memory: 2111 loss: 0.0074 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0074 2022/12/22 14:52:52 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:07:48 time: 0.5458 data_time: 0.0105 memory: 2111 loss: 0.0085 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0085 2022/12/22 14:53:46 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:06:54 time: 0.5316 data_time: 0.0100 memory: 2111 loss: 0.0065 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0065 2022/12/22 14:54:40 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:06:00 time: 0.5461 data_time: 0.0095 memory: 2111 loss: 0.0086 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0086 2022/12/22 14:55:35 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:05:06 time: 0.5437 data_time: 0.0090 memory: 2111 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/12/22 14:56:29 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:04:12 time: 0.5492 data_time: 0.0085 memory: 2111 loss: 0.0113 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0113 2022/12/22 14:57:23 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:03:18 time: 0.5358 data_time: 0.0102 memory: 2111 loss: 0.0069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0069 2022/12/22 14:58:18 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:02:24 time: 0.5520 data_time: 0.0086 memory: 2111 loss: 0.0077 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0077 2022/12/22 14:59:12 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:01:30 time: 0.5369 data_time: 0.0114 memory: 2111 loss: 0.0089 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0089 2022/12/22 15:00:04 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 15:00:07 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:36 time: 0.5488 data_time: 0.0095 memory: 2111 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/12/22 15:00:38 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 15:00:38 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.4276 data_time: 0.0092 memory: 2111 loss: 0.2133 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2133 2022/12/22 15:00:38 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/12/22 15:00:54 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:04 time: 0.1248 data_time: 0.0095 memory: 293 2022/12/22 15:00:59 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8774 acc/top5: 0.9738 acc/mean1: 0.8773 2022/12/22 15:00:59 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_14.pth is removed 2022/12/22 15:00:59 - mmengine - INFO - The best checkpoint with 0.8774 acc/top1 at 16 epoch is saved to best_acc/top1_epoch_16.pth.