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: 1741867977 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=['bm']), 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=['bm']), 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=['bm']), 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=['bm']), 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=['bm']), 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=['bm']), 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-bone-motion-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-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/modules_statistic_results.json 2022/12/22 11:06:54 - 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 11:08:09 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d. 2022/12/22 11:09:11 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 4:18:23 time: 0.5464 data_time: 0.0068 memory: 2111 loss: 3.1139 top1_acc: 0.0625 top5_acc: 0.2500 loss_cls: 3.1139 2022/12/22 11:10:05 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 4:01:08 time: 0.5423 data_time: 0.0070 memory: 2111 loss: 2.5941 top1_acc: 0.3125 top5_acc: 0.6875 loss_cls: 2.5941 2022/12/22 11:10:59 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 3:54:37 time: 0.5398 data_time: 0.0071 memory: 2111 loss: 2.0585 top1_acc: 0.5000 top5_acc: 0.7500 loss_cls: 2.0585 2022/12/22 11:11:53 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 3:51:09 time: 0.5447 data_time: 0.0068 memory: 2111 loss: 1.6993 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 1.6993 2022/12/22 11:12:48 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 3:48:55 time: 0.5450 data_time: 0.0070 memory: 2111 loss: 1.3955 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.3955 2022/12/22 11:13:42 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 3:46:47 time: 0.5355 data_time: 0.0072 memory: 2111 loss: 1.2079 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2079 2022/12/22 11:14:36 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 3:45:07 time: 0.5430 data_time: 0.0068 memory: 2111 loss: 1.1948 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.1948 2022/12/22 11:15:31 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 3:43:37 time: 0.5453 data_time: 0.0070 memory: 2111 loss: 0.9901 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.9901 2022/12/22 11:16:25 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 3:42:16 time: 0.5437 data_time: 0.0069 memory: 2111 loss: 1.0367 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 1.0367 2022/12/22 11:17:19 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:17:19 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 3:41:00 time: 0.5434 data_time: 0.0073 memory: 2111 loss: 0.9734 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.9734 2022/12/22 11:18:14 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 3:39:52 time: 0.5430 data_time: 0.0068 memory: 2111 loss: 0.9073 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9073 2022/12/22 11:19:08 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 3:38:45 time: 0.5465 data_time: 0.0070 memory: 2111 loss: 0.8837 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8837 2022/12/22 11:20:03 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 3:37:40 time: 0.5486 data_time: 0.0069 memory: 2111 loss: 0.7095 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7095 2022/12/22 11:20:57 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 3:36:31 time: 0.5345 data_time: 0.0082 memory: 2111 loss: 0.7175 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.7175 2022/12/22 11:21:51 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 3:35:19 time: 0.5261 data_time: 0.0096 memory: 2111 loss: 0.7499 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7499 2022/12/22 11:22:26 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:22:26 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 3:34:23 time: 0.4906 data_time: 0.0073 memory: 2111 loss: 0.8720 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.8720 2022/12/22 11:22:26 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/22 11:22:46 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:05 time: 0.1883 data_time: 0.0066 memory: 293 2022/12/22 11:22:53 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.6284 acc/top5: 0.9013 acc/mean1: 0.6283 2022/12/22 11:22:54 - mmengine - INFO - The best checkpoint with 0.6284 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/12/22 11:23:48 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 3:33:25 time: 0.5432 data_time: 0.0074 memory: 2111 loss: 0.7378 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7378 2022/12/22 11:24:42 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 3:32:26 time: 0.5430 data_time: 0.0070 memory: 2111 loss: 0.7282 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7282 2022/12/22 11:25:37 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 3:31:25 time: 0.5446 data_time: 0.0074 memory: 2111 loss: 0.7077 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7077 2022/12/22 11:26:31 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 3:30:24 time: 0.5431 data_time: 0.0072 memory: 2111 loss: 0.5987 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.5987 2022/12/22 11:26:49 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:27:25 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 3:29:27 time: 0.5459 data_time: 0.0076 memory: 2111 loss: 0.6515 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6515 2022/12/22 11:28:20 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 3:28:29 time: 0.5475 data_time: 0.0070 memory: 2111 loss: 0.6658 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.6658 2022/12/22 11:29:14 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 3:27:33 time: 0.5436 data_time: 0.0073 memory: 2111 loss: 0.6668 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.6668 2022/12/22 11:30:08 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 3:26:35 time: 0.5431 data_time: 0.0076 memory: 2111 loss: 0.5732 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5732 2022/12/22 11:31:03 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 3:25:37 time: 0.5415 data_time: 0.0071 memory: 2111 loss: 0.6797 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.6797 2022/12/22 11:31:57 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 3:24:41 time: 0.5456 data_time: 0.0072 memory: 2111 loss: 0.6378 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.6378 2022/12/22 11:32:51 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 3:23:46 time: 0.5482 data_time: 0.0079 memory: 2111 loss: 0.6658 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 0.6658 2022/12/22 11:33:46 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 3:22:49 time: 0.5428 data_time: 0.0070 memory: 2111 loss: 0.5639 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5639 2022/12/22 11:34:40 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 3:21:52 time: 0.5395 data_time: 0.0072 memory: 2111 loss: 0.5577 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5577 2022/12/22 11:35:34 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 3:20:55 time: 0.5420 data_time: 0.0070 memory: 2111 loss: 0.5629 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5629 2022/12/22 11:35:52 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:36:28 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 3:19:58 time: 0.5423 data_time: 0.0079 memory: 2111 loss: 0.6889 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6889 2022/12/22 11:37:04 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:37:04 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 3:19:16 time: 0.5087 data_time: 0.0071 memory: 2111 loss: 0.6996 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6996 2022/12/22 11:37:04 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/22 11:37:24 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:05 time: 0.1877 data_time: 0.0066 memory: 293 2022/12/22 11:37:31 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.7093 acc/top5: 0.9338 acc/mean1: 0.7090 2022/12/22 11:37:31 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_1.pth is removed 2022/12/22 11:37:31 - mmengine - INFO - The best checkpoint with 0.7093 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/12/22 11:38:25 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 3:18:18 time: 0.5425 data_time: 0.0070 memory: 2111 loss: 0.5226 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5226 2022/12/22 11:39:19 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 3:17:21 time: 0.5411 data_time: 0.0072 memory: 2111 loss: 0.4581 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4581 2022/12/22 11:40:14 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 3:16:27 time: 0.5432 data_time: 0.0073 memory: 2111 loss: 0.5217 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5217 2022/12/22 11:41:08 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 3:15:31 time: 0.5424 data_time: 0.0070 memory: 2111 loss: 0.4346 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4346 2022/12/22 11:42:02 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 3:14:35 time: 0.5412 data_time: 0.0072 memory: 2111 loss: 0.4497 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4497 2022/12/22 11:42:56 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 3:13:39 time: 0.5408 data_time: 0.0079 memory: 2111 loss: 0.5339 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5339 2022/12/22 11:43:50 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 3:12:41 time: 0.5350 data_time: 0.0070 memory: 2111 loss: 0.5158 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5158 2022/12/22 11:44:44 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 3:11:46 time: 0.5404 data_time: 0.0071 memory: 2111 loss: 0.4399 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4399 2022/12/22 11:45:20 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:45:39 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 3:10:50 time: 0.5436 data_time: 0.0071 memory: 2111 loss: 0.4625 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4625 2022/12/22 11:46:33 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 3:09:55 time: 0.5433 data_time: 0.0072 memory: 2111 loss: 0.4633 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4633 2022/12/22 11:47:27 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 3:08:59 time: 0.5388 data_time: 0.0082 memory: 2111 loss: 0.4375 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4375 2022/12/22 11:48:21 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 3:08:03 time: 0.5331 data_time: 0.0077 memory: 2111 loss: 0.4428 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4428 2022/12/22 11:49:15 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 3:07:08 time: 0.5456 data_time: 0.0079 memory: 2111 loss: 0.4038 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4038 2022/12/22 11:50:10 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 3:06:13 time: 0.5420 data_time: 0.0078 memory: 2111 loss: 0.5115 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.5115 2022/12/22 11:51:04 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 3:05:19 time: 0.5475 data_time: 0.0069 memory: 2111 loss: 0.5437 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.5437 2022/12/22 11:51:40 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:51:40 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 3:04:42 time: 0.5296 data_time: 0.0071 memory: 2111 loss: 0.6328 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.6328 2022/12/22 11:51:40 - 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: 0.1774 data_time: 0.0071 memory: 293 2022/12/22 11:52:05 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.7537 acc/top5: 0.9468 acc/mean1: 0.7536 2022/12/22 11:52:05 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_2.pth is removed 2022/12/22 11:52:05 - mmengine - INFO - The best checkpoint with 0.7537 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: 3:03:46 time: 0.5462 data_time: 0.0081 memory: 2111 loss: 0.4555 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4555 2022/12/22 11:53:53 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 3:02:50 time: 0.5393 data_time: 0.0073 memory: 2111 loss: 0.4604 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4604 2022/12/22 11:54:46 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:54:47 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 3:01:51 time: 0.5335 data_time: 0.0078 memory: 2111 loss: 0.4860 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4860 2022/12/22 11:55:40 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 3:00:54 time: 0.5341 data_time: 0.0070 memory: 2111 loss: 0.5250 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.5250 2022/12/22 11:56:34 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 2:59:57 time: 0.5348 data_time: 0.0071 memory: 2111 loss: 0.5065 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5065 2022/12/22 11:57:28 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 2:59:01 time: 0.5336 data_time: 0.0071 memory: 2111 loss: 0.4888 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4888 2022/12/22 11:58:21 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 2:58:03 time: 0.5357 data_time: 0.0069 memory: 2111 loss: 0.4194 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4194 2022/12/22 11:59:15 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 2:57:07 time: 0.5409 data_time: 0.0074 memory: 2111 loss: 0.4284 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4284 2022/12/22 12:00:09 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 2:56:10 time: 0.5275 data_time: 0.0070 memory: 2111 loss: 0.4370 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4370 2022/12/22 12:01:02 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 2:55:13 time: 0.5297 data_time: 0.0069 memory: 2111 loss: 0.3372 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3372 2022/12/22 12:01:56 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 2:54:16 time: 0.5373 data_time: 0.0069 memory: 2111 loss: 0.3897 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3897 2022/12/22 12:02:49 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 2:53:19 time: 0.5452 data_time: 0.0071 memory: 2111 loss: 0.4789 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4789 2022/12/22 12:03:43 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:03:43 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 2:52:24 time: 0.5410 data_time: 0.0075 memory: 2111 loss: 0.4140 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4140 2022/12/22 12:04:37 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 2:51:28 time: 0.5412 data_time: 0.0072 memory: 2111 loss: 0.3770 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3770 2022/12/22 12:05:31 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 2:50:33 time: 0.5436 data_time: 0.0070 memory: 2111 loss: 0.4098 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4098 2022/12/22 12:06:06 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:06:06 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 2:49:54 time: 0.5108 data_time: 0.0070 memory: 2111 loss: 0.6476 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.6476 2022/12/22 12:06:06 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/22 12:06:27 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:05 time: 0.1885 data_time: 0.0064 memory: 293 2022/12/22 12:06:33 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7151 acc/top5: 0.9333 acc/mean1: 0.7150 2022/12/22 12:07:26 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 2:48:55 time: 0.5321 data_time: 0.0069 memory: 2111 loss: 0.3615 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3615 2022/12/22 12:08:20 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 2:48:00 time: 0.5404 data_time: 0.0074 memory: 2111 loss: 0.2843 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2843 2022/12/22 12:09:14 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 2:47:04 time: 0.5400 data_time: 0.0071 memory: 2111 loss: 0.3964 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3964 2022/12/22 12:10:07 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 2:46:08 time: 0.5383 data_time: 0.0071 memory: 2111 loss: 0.4032 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4032 2022/12/22 12:11:01 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 2:45:13 time: 0.5347 data_time: 0.0072 memory: 2111 loss: 0.4134 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4134 2022/12/22 12:11:54 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 2:44:17 time: 0.5391 data_time: 0.0069 memory: 2111 loss: 0.3688 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3688 2022/12/22 12:12:47 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 2:43:20 time: 0.5319 data_time: 0.0070 memory: 2111 loss: 0.3886 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3886 2022/12/22 12:13:05 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:13:41 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 2:42:25 time: 0.5367 data_time: 0.0069 memory: 2111 loss: 0.3542 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3542 2022/12/22 12:14:35 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 2:41:30 time: 0.5357 data_time: 0.0071 memory: 2111 loss: 0.4308 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.4308 2022/12/22 12:15:29 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 2:40:35 time: 0.5287 data_time: 0.0074 memory: 2111 loss: 0.4681 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4681 2022/12/22 12:16:22 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 2:39:39 time: 0.5389 data_time: 0.0081 memory: 2111 loss: 0.3788 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3788 2022/12/22 12:17:15 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 2:38:43 time: 0.5385 data_time: 0.0071 memory: 2111 loss: 0.3660 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3660 2022/12/22 12:18:09 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 2:37:47 time: 0.5362 data_time: 0.0069 memory: 2111 loss: 0.3958 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.3958 2022/12/22 12:19:02 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 2:36:52 time: 0.5417 data_time: 0.0072 memory: 2111 loss: 0.4271 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4271 2022/12/22 12:19:56 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 2:35:57 time: 0.5387 data_time: 0.0069 memory: 2111 loss: 0.3278 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3278 2022/12/22 12:20:32 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:20:32 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 2:35:20 time: 0.5239 data_time: 0.0069 memory: 2111 loss: 0.5380 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.5380 2022/12/22 12:20:32 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/22 12:20:53 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:06 time: 0.1888 data_time: 0.0071 memory: 293 2022/12/22 12:20:59 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7565 acc/top5: 0.9472 acc/mean1: 0.7564 2022/12/22 12:20:59 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_3.pth is removed 2022/12/22 12:21:00 - mmengine - INFO - The best checkpoint with 0.7565 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2022/12/22 12:21:52 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 2:34:22 time: 0.5297 data_time: 0.0070 memory: 2111 loss: 0.2873 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2873 2022/12/22 12:22:26 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:22:45 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 2:33:25 time: 0.5274 data_time: 0.0070 memory: 2111 loss: 0.3366 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3366 2022/12/22 12:23:38 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 2:32:30 time: 0.5382 data_time: 0.0070 memory: 2111 loss: 0.4007 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4007 2022/12/22 12:24:32 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 2:31:35 time: 0.5336 data_time: 0.0076 memory: 2111 loss: 0.3308 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3308 2022/12/22 12:25:25 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 2:30:40 time: 0.5348 data_time: 0.0071 memory: 2111 loss: 0.3270 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3270 2022/12/22 12:26:19 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 2:29:46 time: 0.5359 data_time: 0.0070 memory: 2111 loss: 0.2619 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2619 2022/12/22 12:27:12 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 2:28:49 time: 0.5414 data_time: 0.0078 memory: 2111 loss: 0.3672 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3672 2022/12/22 12:28:06 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 2:27:55 time: 0.5428 data_time: 0.0075 memory: 2111 loss: 0.3700 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3700 2022/12/22 12:28:59 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 2:27:00 time: 0.5395 data_time: 0.0081 memory: 2111 loss: 0.3145 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3145 2022/12/22 12:29:53 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 2:26:05 time: 0.5366 data_time: 0.0071 memory: 2111 loss: 0.4439 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4439 2022/12/22 12:30:46 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 2:25:10 time: 0.5367 data_time: 0.0070 memory: 2111 loss: 0.3472 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3472 2022/12/22 12:31:21 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:31:40 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 2:24:16 time: 0.5322 data_time: 0.0069 memory: 2111 loss: 0.2828 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2828 2022/12/22 12:32:34 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 2:23:21 time: 0.5344 data_time: 0.0071 memory: 2111 loss: 0.3307 top1_acc: 0.5625 top5_acc: 0.7500 loss_cls: 0.3307 2022/12/22 12:33:27 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 2:22:27 time: 0.5359 data_time: 0.0074 memory: 2111 loss: 0.3238 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3238 2022/12/22 12:34:21 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 2:21:32 time: 0.5337 data_time: 0.0069 memory: 2111 loss: 0.3037 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3037 2022/12/22 12:34:57 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:34:57 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 2:20:55 time: 0.5155 data_time: 0.0069 memory: 2111 loss: 0.3961 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3961 2022/12/22 12:34:57 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/22 12:35:18 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:06 time: 0.1897 data_time: 0.0065 memory: 293 2022/12/22 12:35:24 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.7713 acc/top5: 0.9463 acc/mean1: 0.7712 2022/12/22 12:35:24 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_5.pth is removed 2022/12/22 12:35:25 - mmengine - INFO - The best checkpoint with 0.7713 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2022/12/22 12:36:17 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 2:19:58 time: 0.5339 data_time: 0.0075 memory: 2111 loss: 0.3572 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3572 2022/12/22 12:37:10 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 2:19:03 time: 0.5353 data_time: 0.0073 memory: 2111 loss: 0.2829 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2829 2022/12/22 12:38:04 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 2:18:09 time: 0.5367 data_time: 0.0071 memory: 2111 loss: 0.3154 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3154 2022/12/22 12:38:57 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 2:17:14 time: 0.5404 data_time: 0.0072 memory: 2111 loss: 0.2915 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2915 2022/12/22 12:39:51 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 2:16:20 time: 0.5362 data_time: 0.0071 memory: 2111 loss: 0.3416 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3416 2022/12/22 12:40:44 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:40:45 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 2:15:26 time: 0.5366 data_time: 0.0073 memory: 2111 loss: 0.3102 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3102 2022/12/22 12:41:38 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 2:14:31 time: 0.5398 data_time: 0.0079 memory: 2111 loss: 0.2878 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2878 2022/12/22 12:42:32 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 2:13:37 time: 0.5370 data_time: 0.0074 memory: 2111 loss: 0.3142 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3142 2022/12/22 12:43:26 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 2:12:43 time: 0.5378 data_time: 0.0072 memory: 2111 loss: 0.2232 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2232 2022/12/22 12:44:19 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 2:11:49 time: 0.5330 data_time: 0.0075 memory: 2111 loss: 0.2848 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2848 2022/12/22 12:45:13 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 2:10:55 time: 0.5376 data_time: 0.0078 memory: 2111 loss: 0.2522 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2522 2022/12/22 12:46:07 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 2:10:00 time: 0.5392 data_time: 0.0075 memory: 2111 loss: 0.2652 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2652 2022/12/22 12:47:00 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 2:09:06 time: 0.5233 data_time: 0.0069 memory: 2111 loss: 0.3030 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3030 2022/12/22 12:47:54 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 2:08:11 time: 0.5346 data_time: 0.0074 memory: 2111 loss: 0.2374 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2374 2022/12/22 12:48:47 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 2:07:17 time: 0.5379 data_time: 0.0070 memory: 2111 loss: 0.3859 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3859 2022/12/22 12:49:23 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:49:23 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 2:06:40 time: 0.5192 data_time: 0.0069 memory: 2111 loss: 0.5087 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5087 2022/12/22 12:49:23 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/12/22 12:49:45 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:06 time: 0.1940 data_time: 0.0119 memory: 293 2022/12/22 12:49:51 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.7908 acc/top5: 0.9534 acc/mean1: 0.7908 2022/12/22 12:49:51 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_6.pth is removed 2022/12/22 12:49:52 - mmengine - INFO - The best checkpoint with 0.7908 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2022/12/22 12:50:06 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:50:42 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 2:05:43 time: 0.5173 data_time: 0.0071 memory: 2111 loss: 0.2668 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.2668 2022/12/22 12:51:36 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 2:04:49 time: 0.5344 data_time: 0.0076 memory: 2111 loss: 0.2965 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2965 2022/12/22 12:52:30 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 2:03:54 time: 0.5387 data_time: 0.0076 memory: 2111 loss: 0.2583 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2583 2022/12/22 12:53:23 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 2:02:59 time: 0.5312 data_time: 0.0071 memory: 2111 loss: 0.2482 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2482 2022/12/22 12:54:16 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 2:02:05 time: 0.5422 data_time: 0.0075 memory: 2111 loss: 0.2119 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2119 2022/12/22 12:55:10 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 2:01:11 time: 0.5330 data_time: 0.0072 memory: 2111 loss: 0.3141 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3141 2022/12/22 12:56:04 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 2:00:18 time: 0.5393 data_time: 0.0076 memory: 2111 loss: 0.2537 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2537 2022/12/22 12:56:58 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 1:59:24 time: 0.5343 data_time: 0.0070 memory: 2111 loss: 0.1921 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1921 2022/12/22 12:57:51 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 1:58:30 time: 0.5310 data_time: 0.0074 memory: 2111 loss: 0.2471 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2471 2022/12/22 12:58:45 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 1:57:36 time: 0.5286 data_time: 0.0073 memory: 2111 loss: 0.2399 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2399 2022/12/22 12:59:02 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:59:39 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 1:56:41 time: 0.5315 data_time: 0.0071 memory: 2111 loss: 0.3073 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3073 2022/12/22 13:00:32 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 1:55:47 time: 0.5363 data_time: 0.0075 memory: 2111 loss: 0.2031 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2031 2022/12/22 13:01:26 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 1:54:53 time: 0.5292 data_time: 0.0077 memory: 2111 loss: 0.2073 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2073 2022/12/22 13:02:20 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 1:53:59 time: 0.5383 data_time: 0.0071 memory: 2111 loss: 0.2313 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2313 2022/12/22 13:03:13 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 1:53:05 time: 0.5276 data_time: 0.0071 memory: 2111 loss: 0.2148 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.2148 2022/12/22 13:03:49 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:03:49 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 1:52:29 time: 0.5193 data_time: 0.0069 memory: 2111 loss: 0.4017 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4017 2022/12/22 13:03:49 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/12/22 13:04:11 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:06 time: 0.1901 data_time: 0.0076 memory: 293 2022/12/22 13:04:17 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.7824 acc/top5: 0.9531 acc/mean1: 0.7823 2022/12/22 13:05:08 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 1:51:32 time: 0.5356 data_time: 0.0073 memory: 2111 loss: 0.1829 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1829 2022/12/22 13:06:02 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 1:50:38 time: 0.5399 data_time: 0.0071 memory: 2111 loss: 0.1617 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1617 2022/12/22 13:06:56 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 1:49:44 time: 0.5330 data_time: 0.0070 memory: 2111 loss: 0.1718 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1718 2022/12/22 13:07:49 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 1:48:50 time: 0.5322 data_time: 0.0074 memory: 2111 loss: 0.2549 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2549 2022/12/22 13:08:24 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:08:43 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 1:47:56 time: 0.5407 data_time: 0.0071 memory: 2111 loss: 0.2511 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2511 2022/12/22 13:09:37 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 1:47:02 time: 0.5405 data_time: 0.0082 memory: 2111 loss: 0.1836 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1836 2022/12/22 13:10:31 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 1:46:09 time: 0.5426 data_time: 0.0070 memory: 2111 loss: 0.1546 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1546 2022/12/22 13:11:25 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 1:45:15 time: 0.5295 data_time: 0.0072 memory: 2111 loss: 0.1624 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1624 2022/12/22 13:12:18 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 1:44:21 time: 0.5395 data_time: 0.0084 memory: 2111 loss: 0.2377 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2377 2022/12/22 13:13:12 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 1:43:27 time: 0.5311 data_time: 0.0079 memory: 2111 loss: 0.1982 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1982 2022/12/22 13:14:06 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 1:42:34 time: 0.5466 data_time: 0.0081 memory: 2111 loss: 0.1459 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1459 2022/12/22 13:15:00 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 1:41:40 time: 0.5394 data_time: 0.0076 memory: 2111 loss: 0.1859 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1859 2022/12/22 13:15:54 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 1:40:46 time: 0.5466 data_time: 0.0077 memory: 2111 loss: 0.2141 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2141 2022/12/22 13:16:48 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 1:39:53 time: 0.5359 data_time: 0.0074 memory: 2111 loss: 0.1264 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1264 2022/12/22 13:17:23 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:17:42 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 1:38:59 time: 0.5383 data_time: 0.0073 memory: 2111 loss: 0.1050 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1050 2022/12/22 13:18:18 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:18:18 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 1:38:23 time: 0.5222 data_time: 0.0076 memory: 2111 loss: 0.3465 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3465 2022/12/22 13:18:18 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/12/22 13:18:41 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:06 time: 0.1884 data_time: 0.0079 memory: 293 2022/12/22 13:18:47 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8050 acc/top5: 0.9552 acc/mean1: 0.8049 2022/12/22 13:18:47 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_7.pth is removed 2022/12/22 13:18:48 - mmengine - INFO - The best checkpoint with 0.8050 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2022/12/22 13:19:39 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 1:37:27 time: 0.5411 data_time: 0.0072 memory: 2111 loss: 0.1280 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1280 2022/12/22 13:20:33 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 1:36:33 time: 0.5453 data_time: 0.0075 memory: 2111 loss: 0.1485 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1485 2022/12/22 13:21:26 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 1:35:39 time: 0.5401 data_time: 0.0074 memory: 2111 loss: 0.1715 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1715 2022/12/22 13:22:20 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 1:34:45 time: 0.5278 data_time: 0.0074 memory: 2111 loss: 0.1684 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1684 2022/12/22 13:23:14 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 1:33:51 time: 0.5240 data_time: 0.0092 memory: 2111 loss: 0.1027 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1027 2022/12/22 13:24:07 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 1:32:57 time: 0.5428 data_time: 0.0070 memory: 2111 loss: 0.0977 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0977 2022/12/22 13:25:01 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 1:32:04 time: 0.5403 data_time: 0.0076 memory: 2111 loss: 0.0863 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0863 2022/12/22 13:25:56 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 1:31:10 time: 0.5317 data_time: 0.0072 memory: 2111 loss: 0.1212 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1212 2022/12/22 13:26:48 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:26:50 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 1:30:17 time: 0.5436 data_time: 0.0073 memory: 2111 loss: 0.1518 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1518 2022/12/22 13:27:44 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 1:29:23 time: 0.5441 data_time: 0.0075 memory: 2111 loss: 0.1385 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1385 2022/12/22 13:28:37 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 1:28:29 time: 0.5415 data_time: 0.0076 memory: 2111 loss: 0.1264 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1264 2022/12/22 13:29:31 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 1:27:35 time: 0.5362 data_time: 0.0073 memory: 2111 loss: 0.1191 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1191 2022/12/22 13:30:25 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 1:26:42 time: 0.5418 data_time: 0.0072 memory: 2111 loss: 0.1033 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1033 2022/12/22 13:31:19 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 1:25:48 time: 0.5428 data_time: 0.0076 memory: 2111 loss: 0.1188 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1188 2022/12/22 13:32:13 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 1:24:54 time: 0.5414 data_time: 0.0070 memory: 2111 loss: 0.1033 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1033 2022/12/22 13:32:49 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:32:49 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 1:24:18 time: 0.5183 data_time: 0.0074 memory: 2111 loss: 0.2510 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2510 2022/12/22 13:32:49 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/12/22 13:33:13 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:06 time: 0.1858 data_time: 0.0075 memory: 293 2022/12/22 13:33:19 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8075 acc/top5: 0.9594 acc/mean1: 0.8074 2022/12/22 13:33:19 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_9.pth is removed 2022/12/22 13:33:19 - mmengine - INFO - The best checkpoint with 0.8075 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/12/22 13:34:10 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 1:23:23 time: 0.5428 data_time: 0.0073 memory: 2111 loss: 0.1058 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1058 2022/12/22 13:35:04 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 1:22:29 time: 0.5413 data_time: 0.0075 memory: 2111 loss: 0.1016 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1016 2022/12/22 13:35:59 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 1:21:35 time: 0.5384 data_time: 0.0074 memory: 2111 loss: 0.1048 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1048 2022/12/22 13:36:15 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:36:53 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 1:20:42 time: 0.5411 data_time: 0.0072 memory: 2111 loss: 0.1487 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1487 2022/12/22 13:37:47 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 1:19:48 time: 0.5390 data_time: 0.0073 memory: 2111 loss: 0.1160 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1160 2022/12/22 13:38:41 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 1:18:54 time: 0.5346 data_time: 0.0074 memory: 2111 loss: 0.0709 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0709 2022/12/22 13:39:35 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 1:18:01 time: 0.5416 data_time: 0.0074 memory: 2111 loss: 0.1001 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1001 2022/12/22 13:40:29 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 1:17:07 time: 0.5422 data_time: 0.0071 memory: 2111 loss: 0.0845 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0845 2022/12/22 13:41:23 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 1:16:13 time: 0.5501 data_time: 0.0082 memory: 2111 loss: 0.0500 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0500 2022/12/22 13:42:17 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 1:15:20 time: 0.5418 data_time: 0.0073 memory: 2111 loss: 0.0817 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0817 2022/12/22 13:43:11 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 1:14:26 time: 0.5429 data_time: 0.0076 memory: 2111 loss: 0.1030 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1030 2022/12/22 13:44:05 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 1:13:33 time: 0.5395 data_time: 0.0074 memory: 2111 loss: 0.0703 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0703 2022/12/22 13:44:59 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 1:12:39 time: 0.5399 data_time: 0.0077 memory: 2111 loss: 0.0609 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0609 2022/12/22 13:45:15 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:45:53 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 1:11:45 time: 0.5400 data_time: 0.0072 memory: 2111 loss: 0.0641 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0641 2022/12/22 13:46:47 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 1:10:51 time: 0.5436 data_time: 0.0071 memory: 2111 loss: 0.0553 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0553 2022/12/22 13:47:23 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:47:23 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 1:10:15 time: 0.5231 data_time: 0.0070 memory: 2111 loss: 0.2557 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2557 2022/12/22 13:47:23 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/12/22 13:47:47 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:06 time: 0.1908 data_time: 0.0070 memory: 293 2022/12/22 13:47:53 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8324 acc/top5: 0.9639 acc/mean1: 0.8323 2022/12/22 13:47:53 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_10.pth is removed 2022/12/22 13:47:53 - mmengine - INFO - The best checkpoint with 0.8324 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/12/22 13:48:44 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 1:09:20 time: 0.5389 data_time: 0.0070 memory: 2111 loss: 0.0470 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0470 2022/12/22 13:49:38 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 1:08:26 time: 0.5357 data_time: 0.0075 memory: 2111 loss: 0.0429 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0429 2022/12/22 13:50:32 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 1:07:33 time: 0.5433 data_time: 0.0079 memory: 2111 loss: 0.0575 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0575 2022/12/22 13:51:26 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 1:06:39 time: 0.5402 data_time: 0.0081 memory: 2111 loss: 0.0691 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0691 2022/12/22 13:52:20 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 1:05:45 time: 0.5420 data_time: 0.0078 memory: 2111 loss: 0.0633 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0633 2022/12/22 13:53:15 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 1:04:52 time: 0.5448 data_time: 0.0074 memory: 2111 loss: 0.0534 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0534 2022/12/22 13:54:08 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 1:03:58 time: 0.5320 data_time: 0.0072 memory: 2111 loss: 0.0663 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0663 2022/12/22 13:54:42 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:55:02 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 1:03:04 time: 0.5451 data_time: 0.0079 memory: 2111 loss: 0.0498 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0498 2022/12/22 13:55:56 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 1:02:10 time: 0.5417 data_time: 0.0079 memory: 2111 loss: 0.0600 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0600 2022/12/22 13:56:50 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 1:01:17 time: 0.5409 data_time: 0.0086 memory: 2111 loss: 0.0512 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0512 2022/12/22 13:57:44 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 1:00:23 time: 0.5414 data_time: 0.0077 memory: 2111 loss: 0.0683 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0683 2022/12/22 13:58:38 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:59:29 time: 0.5315 data_time: 0.0074 memory: 2111 loss: 0.0548 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0548 2022/12/22 13:59:32 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:58:35 time: 0.5381 data_time: 0.0075 memory: 2111 loss: 0.0400 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0400 2022/12/22 14:00:26 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:57:42 time: 0.5444 data_time: 0.0079 memory: 2111 loss: 0.0382 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0382 2022/12/22 14:01:20 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:56:48 time: 0.5430 data_time: 0.0078 memory: 2111 loss: 0.0437 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0437 2022/12/22 14:01:56 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:01:56 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:56:12 time: 0.5246 data_time: 0.0079 memory: 2111 loss: 0.2318 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2318 2022/12/22 14:01:56 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/12/22 14:02:20 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:06 time: 0.1971 data_time: 0.0080 memory: 293 2022/12/22 14:02:26 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8410 acc/top5: 0.9659 acc/mean1: 0.8410 2022/12/22 14:02:26 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_11.pth is removed 2022/12/22 14:02:26 - mmengine - INFO - The best checkpoint with 0.8410 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/12/22 14:03:16 - mmengine - INFO - Epoch(train) [13][ 100/1567] lr: 1.4209e-02 eta: 0:55:17 time: 0.5437 data_time: 0.0079 memory: 2111 loss: 0.0203 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0203 2022/12/22 14:04:09 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:04:11 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:54:23 time: 0.5428 data_time: 0.0078 memory: 2111 loss: 0.0311 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0311 2022/12/22 14:05:05 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:53:29 time: 0.5412 data_time: 0.0080 memory: 2111 loss: 0.0358 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0358 2022/12/22 14:05:59 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:52:36 time: 0.5425 data_time: 0.0075 memory: 2111 loss: 0.0538 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0538 2022/12/22 14:06:53 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:51:42 time: 0.5441 data_time: 0.0080 memory: 2111 loss: 0.0308 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0308 2022/12/22 14:07:47 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:50:48 time: 0.5413 data_time: 0.0075 memory: 2111 loss: 0.0218 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0218 2022/12/22 14:08:41 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:49:55 time: 0.5393 data_time: 0.0076 memory: 2111 loss: 0.0284 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0284 2022/12/22 14:09:35 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:49:01 time: 0.5418 data_time: 0.0081 memory: 2111 loss: 0.0196 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0196 2022/12/22 14:10:29 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:48:07 time: 0.5401 data_time: 0.0077 memory: 2111 loss: 0.0228 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0228 2022/12/22 14:11:23 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:47:13 time: 0.5389 data_time: 0.0072 memory: 2111 loss: 0.0286 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0286 2022/12/22 14:12:17 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:46:20 time: 0.5464 data_time: 0.0071 memory: 2111 loss: 0.0246 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0246 2022/12/22 14:13:09 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:13:11 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:45:26 time: 0.5422 data_time: 0.0071 memory: 2111 loss: 0.0276 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0276 2022/12/22 14:14:05 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:44:32 time: 0.5391 data_time: 0.0074 memory: 2111 loss: 0.0253 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0253 2022/12/22 14:14:59 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:43:39 time: 0.5413 data_time: 0.0073 memory: 2111 loss: 0.0329 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0329 2022/12/22 14:15:53 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:42:45 time: 0.5389 data_time: 0.0071 memory: 2111 loss: 0.0180 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0180 2022/12/22 14:16:29 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:16:29 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:42:09 time: 0.5206 data_time: 0.0073 memory: 2111 loss: 0.2016 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2016 2022/12/22 14:16:29 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/12/22 14:16:54 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:07 time: 0.1939 data_time: 0.0076 memory: 293 2022/12/22 14:17:00 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8427 acc/top5: 0.9663 acc/mean1: 0.8426 2022/12/22 14:17:00 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_12.pth is removed 2022/12/22 14:17:00 - mmengine - INFO - The best checkpoint with 0.8427 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/12/22 14:17:51 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:41:14 time: 0.5381 data_time: 0.0086 memory: 2111 loss: 0.0137 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0137 2022/12/22 14:18:45 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:40:20 time: 0.5453 data_time: 0.0088 memory: 2111 loss: 0.0127 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0127 2022/12/22 14:19:39 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:39:27 time: 0.5406 data_time: 0.0090 memory: 2111 loss: 0.0170 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0170 2022/12/22 14:20:33 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:38:33 time: 0.5455 data_time: 0.0072 memory: 2111 loss: 0.0098 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0098 2022/12/22 14:21:28 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:37:39 time: 0.5389 data_time: 0.0079 memory: 2111 loss: 0.0108 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0108 2022/12/22 14:22:21 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:36:46 time: 0.5405 data_time: 0.0091 memory: 2111 loss: 0.0175 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0175 2022/12/22 14:22:37 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:23:16 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:35:52 time: 0.5395 data_time: 0.0078 memory: 2111 loss: 0.0157 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0157 2022/12/22 14:24:09 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:34:58 time: 0.5415 data_time: 0.0075 memory: 2111 loss: 0.0129 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0129 2022/12/22 14:25:03 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:34:04 time: 0.5329 data_time: 0.0078 memory: 2111 loss: 0.0157 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0157 2022/12/22 14:25:57 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:33:10 time: 0.5403 data_time: 0.0077 memory: 2111 loss: 0.0098 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0098 2022/12/22 14:26:51 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:32:17 time: 0.5391 data_time: 0.0079 memory: 2111 loss: 0.0116 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0116 2022/12/22 14:27:45 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:31:23 time: 0.5434 data_time: 0.0073 memory: 2111 loss: 0.0199 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0199 2022/12/22 14:28:39 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:30:29 time: 0.5380 data_time: 0.0072 memory: 2111 loss: 0.0095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0095 2022/12/22 14:29:32 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:29:35 time: 0.5315 data_time: 0.0073 memory: 2111 loss: 0.0154 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0154 2022/12/22 14:30:25 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:28:41 time: 0.5313 data_time: 0.0071 memory: 2111 loss: 0.0167 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0167 2022/12/22 14:31:01 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:31:01 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:28:05 time: 0.5177 data_time: 0.0078 memory: 2111 loss: 0.2107 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2107 2022/12/22 14:31:01 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/12/22 14:31:26 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:07 time: 0.2227 data_time: 0.0070 memory: 293 2022/12/22 14:31:32 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8505 acc/top5: 0.9683 acc/mean1: 0.8504 2022/12/22 14:31:32 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_13.pth is removed 2022/12/22 14:31:32 - mmengine - INFO - The best checkpoint with 0.8505 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/12/22 14:32:01 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:32:22 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:27:11 time: 0.5366 data_time: 0.0091 memory: 2111 loss: 0.0126 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0126 2022/12/22 14:33:16 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:26:17 time: 0.5360 data_time: 0.0100 memory: 2111 loss: 0.0078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0078 2022/12/22 14:34:09 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:25:23 time: 0.5445 data_time: 0.0104 memory: 2111 loss: 0.0351 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0351 2022/12/22 14:35:04 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:24:30 time: 0.5475 data_time: 0.0096 memory: 2111 loss: 0.0118 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0118 2022/12/22 14:35:58 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:23:36 time: 0.5430 data_time: 0.0100 memory: 2111 loss: 0.0102 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0102 2022/12/22 14:36:53 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:22:42 time: 0.5326 data_time: 0.0105 memory: 2111 loss: 0.0368 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0368 2022/12/22 14:37:47 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:21:49 time: 0.5498 data_time: 0.0110 memory: 2111 loss: 0.0099 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0099 2022/12/22 14:38:41 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:20:55 time: 0.5377 data_time: 0.0106 memory: 2111 loss: 0.0100 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0100 2022/12/22 14:39:35 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:20:01 time: 0.5480 data_time: 0.0091 memory: 2111 loss: 0.0141 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0141 2022/12/22 14:40:30 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:19:07 time: 0.5436 data_time: 0.0104 memory: 2111 loss: 0.0090 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0090 2022/12/22 14:41:03 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:41:24 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:18:14 time: 0.5474 data_time: 0.0088 memory: 2111 loss: 0.0096 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0096 2022/12/22 14:42:18 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:17:20 time: 0.5418 data_time: 0.0105 memory: 2111 loss: 0.0068 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0068 2022/12/22 14:43:13 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:16:26 time: 0.5370 data_time: 0.0087 memory: 2111 loss: 0.0087 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0087 2022/12/22 14:44:07 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:15:32 time: 0.5366 data_time: 0.0085 memory: 2111 loss: 0.0120 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0120 2022/12/22 14:45:01 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:14:39 time: 0.5403 data_time: 0.0086 memory: 2111 loss: 0.0194 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0194 2022/12/22 14:45:37 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:45:37 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:14:03 time: 0.5264 data_time: 0.0094 memory: 2111 loss: 0.2023 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2023 2022/12/22 14:45:37 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/12/22 14:46:02 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:07 time: 0.2320 data_time: 0.0105 memory: 293 2022/12/22 14:46:08 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8540 acc/top5: 0.9692 acc/mean1: 0.8539 2022/12/22 14:46:08 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_14.pth is removed 2022/12/22 14:46:09 - mmengine - INFO - The best checkpoint with 0.8540 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/12/22 14:46:58 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:13:08 time: 0.5448 data_time: 0.0104 memory: 2111 loss: 0.0062 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0062 2022/12/22 14:47:53 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:12:15 time: 0.5477 data_time: 0.0108 memory: 2111 loss: 0.0123 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0123 2022/12/22 14:48:47 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:11:21 time: 0.5415 data_time: 0.0090 memory: 2111 loss: 0.0148 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0148 2022/12/22 14:49:41 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:10:27 time: 0.5454 data_time: 0.0086 memory: 2111 loss: 0.0116 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0116 2022/12/22 14:50:32 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:50:35 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:09:33 time: 0.5424 data_time: 0.0093 memory: 2111 loss: 0.0134 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0134 2022/12/22 14:51:29 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:08:40 time: 0.5468 data_time: 0.0090 memory: 2111 loss: 0.0090 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0090 2022/12/22 14:52:23 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:07:46 time: 0.5389 data_time: 0.0104 memory: 2111 loss: 0.0122 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0122 2022/12/22 14:53:18 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:06:52 time: 0.5508 data_time: 0.0096 memory: 2111 loss: 0.0089 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0089 2022/12/22 14:54:12 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:05:58 time: 0.5395 data_time: 0.0113 memory: 2111 loss: 0.0128 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0128 2022/12/22 14:55:06 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:05:05 time: 0.5464 data_time: 0.0092 memory: 2111 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/12/22 14:56:00 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:04:11 time: 0.5426 data_time: 0.0108 memory: 2111 loss: 0.0133 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0133 2022/12/22 14:56:54 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:03:17 time: 0.5410 data_time: 0.0100 memory: 2111 loss: 0.0126 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0126 2022/12/22 14:57:48 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:02:23 time: 0.5434 data_time: 0.0113 memory: 2111 loss: 0.0063 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0063 2022/12/22 14:58:43 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:01:29 time: 0.5448 data_time: 0.0091 memory: 2111 loss: 0.0096 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0096 2022/12/22 14:59:34 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:59:37 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:36 time: 0.5503 data_time: 0.0109 memory: 2111 loss: 0.0143 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0143 2022/12/22 15:00:13 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 15:00:13 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.5330 data_time: 0.0095 memory: 2111 loss: 0.1890 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1890 2022/12/22 15:00:13 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/12/22 15:00:39 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:07 time: 0.2381 data_time: 0.0085 memory: 293 2022/12/22 15:00:45 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8566 acc/top5: 0.9691 acc/mean1: 0.8565 2022/12/22 15:00:45 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_15.pth is removed 2022/12/22 15:00:45 - mmengine - INFO - The best checkpoint with 0.8566 acc/top1 at 16 epoch is saved to best_acc/top1_epoch_16.pth.