2022/12/14 23:26:07 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] CUDA available: True numpy_random_seed: 699608983 GPU 0,1,2,3: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/cache/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 5.4.0 PyTorch: 1.12.1 PyTorch compiling details: PyTorch built with: - GCC 9.3 - 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 v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) - 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 8.3.2 (built against CUDA 11.5) - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -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-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 -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.1, 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: 0.13.1 OpenCV: 4.6.0 MMEngine: 0.3.2 Runtime environment: cudnn_benchmark: True mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None Distributed launcher: slurm Distributed training: True GPU number: 4 ------------------------------------------------------------ 2022/12/14 23:26:08 - mmengine - INFO - Config: file_client_args = dict(backend='disk') dictionary = dict( type='Dictionary', dict_file= 'configs/textrecog/aster/../../../dicts/english_digits_symbols.txt', with_padding=True, with_unknown=True, same_start_end=True, with_start=True, with_end=True) model = dict( type='ASTER', preprocessor=dict( type='STN', in_channels=3, resized_image_size=(32, 64), output_image_size=(32, 100), num_control_points=20), backbone=dict( type='ResNet', in_channels=3, stem_channels=[32], block_cfgs=dict(type='BasicBlock', use_conv1x1='True'), arch_layers=[3, 4, 6, 6, 3], arch_channels=[32, 64, 128, 256, 512], strides=[(2, 2), (2, 2), (2, 1), (2, 1), (2, 1)], init_cfg=[ dict(type='Kaiming', layer='Conv2d'), dict(type='Constant', val=1, layer='BatchNorm2d') ]), encoder=dict(type='ASTEREncoder', in_channels=512), decoder=dict( type='ASTERDecoder', max_seq_len=25, in_channels=512, emb_dims=512, attn_dims=512, hidden_size=512, postprocessor=dict(type='AttentionPostprocessor'), module_loss=dict( type='CEModuleLoss', flatten=True, ignore_first_char=True), dictionary=dict( type='Dictionary', dict_file= 'configs/textrecog/aster/../../../dicts/english_digits_symbols.txt', with_padding=True, with_unknown=True, same_start_end=True, with_start=True, with_end=True)), data_preprocessor=dict( type='TextRecogDataPreprocessor', mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5])) train_pipeline = [ dict( type='LoadImageFromFile', file_client_args=dict(backend='disk'), ignore_empty=True, min_size=5), dict(type='LoadOCRAnnotations', with_text=True), dict(type='Resize', scale=(256, 64)), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio')) ] test_pipeline = [ dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='Resize', scale=(256, 64)), dict(type='LoadOCRAnnotations', with_text=True), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio', 'instances')) ] mjsynth_textrecog_data_root = 'data/rec/Syn90k/' mjsynth_textrecog_test = dict( type='OCRDataset', data_root='data/rec/Syn90k/', data_prefix=dict(img_path='mnt/ramdisk/max/90kDICT32px'), ann_file='train_labels.json', test_mode=False, pipeline=None) mjsynth_sub_textrecog_train = dict( type='OCRDataset', data_root='data/rec/Syn90k/', data_prefix=dict(img_path='mnt/ramdisk/max/90kDICT32px'), ann_file='subset_train_labels.json', test_mode=False, pipeline=None) synthtext_textrecog_data_root = 'data/rec/SynthText/' synthtext_textrecog_train = dict( type='OCRDataset', data_root='data/rec/SynthText/', data_prefix=dict(img_path='synthtext/SynthText_patch_horizontal'), ann_file='train_labels.json', test_mode=False, pipeline=None) synthtext_an_textrecog_train = dict( type='OCRDataset', data_root='data/rec/SynthText/', data_prefix=dict(img_path='synthtext/SynthText_patch_horizontal'), ann_file='alphanumeric_train_labels.json', test_mode=False, pipeline=None) synthtext_sub_textrecog_train = dict( type='OCRDataset', data_root='data/rec/SynthText/', data_prefix=dict(img_path='synthtext/SynthText_patch_horizontal'), ann_file='subset_train_labels.json', test_mode=False, pipeline=None) cute80_textrecog_data_root = 'data/cute80' cute80_textrecog_test = dict( type='OCRDataset', data_root='data/cute80', ann_file='textrecog_test.json', test_mode=True, pipeline=None) iiit5k_textrecog_data_root = 'data/iiit5k' iiit5k_textrecog_train = dict( type='OCRDataset', data_root='data/iiit5k', ann_file='textrecog_train.json', pipeline=None) iiit5k_textrecog_test = dict( type='OCRDataset', data_root='data/iiit5k', ann_file='textrecog_test.json', test_mode=True, pipeline=None) svt_textrecog_data_root = 'data/svt' svt_textrecog_train = dict( type='OCRDataset', data_root='data/svt', ann_file='textrecog_train.json', pipeline=None) svt_textrecog_test = dict( type='OCRDataset', data_root='data/svt', ann_file='textrecog_test.json', test_mode=True, pipeline=None) svtp_textrecog_data_root = 'data/svtp' svtp_textrecog_train = dict( type='OCRDataset', data_root='data/svtp', ann_file='textrecog_train.json', pipeline=None) svtp_textrecog_test = dict( type='OCRDataset', data_root='data/svtp', ann_file='textrecog_test.json', test_mode=True, pipeline=None) icdar2013_textrecog_data_root = 'data/icdar2013' icdar2013_textrecog_train = dict( type='OCRDataset', data_root='data/icdar2013', ann_file='textrecog_train.json', pipeline=None) icdar2013_textrecog_test = dict( type='OCRDataset', data_root='data/icdar2013', ann_file='textrecog_test.json', test_mode=True, pipeline=None) icdar2013_857_textrecog_test = dict( type='OCRDataset', data_root='data/icdar2013', ann_file='textrecog_test_857.json', test_mode=True, pipeline=None) icdar2015_textrecog_data_root = 'data/icdar2015' icdar2015_textrecog_train = dict( type='OCRDataset', data_root='data/icdar2015', ann_file='textrecog_train.json', pipeline=None) icdar2015_textrecog_test = dict( type='OCRDataset', data_root='data/icdar2015', ann_file='textrecog_test.json', test_mode=True, pipeline=None) icdar2015_1811_textrecog_test = dict( type='OCRDataset', data_root='data/icdar2015', ann_file='textrecog_test_1811.json', test_mode=True, pipeline=None) default_scope = 'mmocr' env_cfg = dict( cudnn_benchmark=True, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) randomness = dict(seed=None) default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=50), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1), sampler_seed=dict(type='DistSamplerSeedHook'), sync_buffer=dict(type='SyncBuffersHook'), visualization=dict( type='VisualizationHook', interval=1, enable=False, show=False, draw_gt=False, draw_pred=False)) log_level = 'INFO' log_processor = dict(type='LogProcessor', window_size=10, by_epoch=True) load_from = None resume = False val_evaluator = dict( type='MultiDatasetsEvaluator', metrics=[ dict( type='WordMetric', mode=['exact', 'ignore_case', 'ignore_case_symbol']), dict(type='CharMetric') ], dataset_prefixes=['CUTE80', 'IIIT5K', 'SVT', 'SVTP', 'IC13', 'IC15']) test_evaluator = dict( type='MultiDatasetsEvaluator', metrics=[ dict( type='WordMetric', mode=['exact', 'ignore_case', 'ignore_case_symbol']), dict(type='CharMetric') ], dataset_prefixes=['CUTE80', 'IIIT5K', 'SVT', 'SVTP', 'IC13', 'IC15']) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='TextRecogLocalVisualizer', name='visualizer', vis_backends=[dict(type='LocalVisBackend')]) optim_wrapper = dict( type='OptimWrapper', optimizer=dict( type='AdamW', lr=0.0004, betas=(0.9, 0.999), eps=1e-08, weight_decay=0.05)) train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=6, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='CosineAnnealingLR', T_max=6, eta_min=4e-06, convert_to_iter_based=True) ] train_list = [ dict( type='OCRDataset', data_root='data/rec/Syn90k/', data_prefix=dict(img_path='mnt/ramdisk/max/90kDICT32px'), ann_file='train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root='data/rec/SynthText/', data_prefix=dict(img_path='synthtext/SynthText_patch_horizontal'), ann_file='train_labels.json', test_mode=False, pipeline=None) ] test_list = [ dict( type='OCRDataset', data_root='data/cute80', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/iiit5k', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/svt', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/svtp', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/icdar2013', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/icdar2015', ann_file='textrecog_test.json', test_mode=True, pipeline=None) ] train_dataset = dict( type='ConcatDataset', datasets=[ dict( type='OCRDataset', data_root='data/rec/Syn90k/', data_prefix=dict(img_path='mnt/ramdisk/max/90kDICT32px'), ann_file='train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root='data/rec/SynthText/', data_prefix=dict(img_path='synthtext/SynthText_patch_horizontal'), ann_file='train_labels.json', test_mode=False, pipeline=None) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='disk'), ignore_empty=True, min_size=5), dict(type='LoadOCRAnnotations', with_text=True), dict(type='Resize', scale=(256, 64)), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio')) ]) test_dataset = dict( type='ConcatDataset', datasets=[ dict( type='OCRDataset', data_root='data/cute80', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/iiit5k', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/svt', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/svtp', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/icdar2013', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/icdar2015', ann_file='textrecog_test.json', test_mode=True, pipeline=None) ], pipeline=[ dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='Resize', scale=(256, 64)), dict(type='LoadOCRAnnotations', with_text=True), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio', 'instances')) ]) train_dataloader = dict( batch_size=1024, num_workers=24, persistent_workers=True, pin_memory=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='ConcatDataset', datasets=[ dict( type='OCRDataset', data_root='openmmlab:s3://openmmlab/datasets/ocr/recog/Syn90k', data_prefix=dict(img_path='mnt/ramdisk/max/90kDICT32px'), ann_file='train_labels.json', test_mode=False, pipeline=None), dict( type='OCRDataset', data_root= 'openmmlab:s3://openmmlab/datasets/ocr/recog/SynthText', data_prefix=dict( img_path='synthtext/SynthText_patch_horizontal'), ann_file='train_labels.json', test_mode=False, pipeline=None) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='petrel'), ignore_empty=True, min_size=5), dict(type='LoadOCRAnnotations', with_text=True), dict(type='Resize', scale=(256, 64)), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio')) ])) auto_scale_lr = dict(base_batch_size=1024) test_dataloader = dict( batch_size=1, num_workers=4, persistent_workers=True, pin_memory=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='ConcatDataset', datasets=[ dict( type='OCRDataset', data_root='data/cute80', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/iiit5k', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/svt', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/svtp', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/icdar2013', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/icdar2015', ann_file='textrecog_test.json', test_mode=True, pipeline=None) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='Resize', scale=(256, 64)), dict(type='LoadOCRAnnotations', with_text=True), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio', 'instances')) ])) val_dataloader = dict( batch_size=1, num_workers=4, persistent_workers=True, pin_memory=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='ConcatDataset', datasets=[ dict( type='OCRDataset', data_root='data/cute80', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/iiit5k', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/svt', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/svtp', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/icdar2013', ann_file='textrecog_test.json', test_mode=True, pipeline=None), dict( type='OCRDataset', data_root='data/icdar2015', ann_file='textrecog_test.json', test_mode=True, pipeline=None) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='disk')), dict(type='Resize', scale=(256, 64)), dict(type='LoadOCRAnnotations', with_text=True), dict( type='PackTextRecogInputs', meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio', 'instances')) ])) launcher = 'slurm' work_dir = 'work_dirs/aster' 2022/12/14 23:26:08 - mmengine - INFO - Result has been saved to work_dirs/aster/modules_statistic_results.json 2022/12/14 23:26:10 - 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 (NORMAL ) VisualizationHook (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 (NORMAL ) VisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- Name of parameter - Initialization information preprocessor.stn_convnet.0.conv.weight - torch.Size([32, 3, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 preprocessor.stn_convnet.0.bn.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_convnet.0.bn.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_convnet.2.conv.weight - torch.Size([64, 32, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 preprocessor.stn_convnet.2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_convnet.2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_convnet.4.conv.weight - torch.Size([128, 64, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 preprocessor.stn_convnet.4.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_convnet.4.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_convnet.6.conv.weight - torch.Size([256, 128, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 preprocessor.stn_convnet.6.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_convnet.6.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_convnet.8.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 preprocessor.stn_convnet.8.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_convnet.8.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_convnet.10.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 preprocessor.stn_convnet.10.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_convnet.10.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_fc1.0.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_fc1.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_fc1.1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_fc1.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_fc2.weight - torch.Size([40, 512]): The value is the same before and after calling `init_weights` of ASTER preprocessor.stn_fc2.bias - torch.Size([40]): The value is the same before and after calling `init_weights` of ASTER backbone.stem_layers.0.conv.weight - torch.Size([32, 3, 3, 3]): Initialized by user-defined `init_weights` in ConvModule backbone.stem_layers.0.bn.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.stem_layers.0.bn.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.0.conv1.weight - torch.Size([32, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer1.0.conv2.weight - torch.Size([32, 32, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer1.0.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.0.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.0.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.0.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.0.downsample.conv.weight - torch.Size([32, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer1.0.downsample.bn.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.0.downsample.bn.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.1.conv1.weight - torch.Size([32, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer1.1.conv2.weight - torch.Size([32, 32, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer1.1.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.1.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.1.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.1.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.2.conv1.weight - torch.Size([32, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer1.2.conv2.weight - torch.Size([32, 32, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer1.2.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.2.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.2.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer1.2.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.0.conv1.weight - torch.Size([64, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer2.0.conv2.weight - torch.Size([64, 64, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer2.0.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.0.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.0.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.0.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.0.downsample.conv.weight - torch.Size([64, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer2.0.downsample.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.0.downsample.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.1.conv1.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer2.1.conv2.weight - torch.Size([64, 64, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer2.1.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.1.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.1.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.1.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.2.conv1.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer2.2.conv2.weight - torch.Size([64, 64, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer2.2.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.2.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.2.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.2.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.3.conv1.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer2.3.conv2.weight - torch.Size([64, 64, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer2.3.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.3.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.3.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer2.3.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.0.conv1.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.0.conv2.weight - torch.Size([128, 128, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.0.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.0.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.0.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.0.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.0.downsample.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.0.downsample.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.0.downsample.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.1.conv1.weight - torch.Size([128, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.1.conv2.weight - torch.Size([128, 128, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.1.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.1.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.1.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.1.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.2.conv1.weight - torch.Size([128, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.2.conv2.weight - torch.Size([128, 128, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.2.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.2.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.2.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.2.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.3.conv1.weight - torch.Size([128, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.3.conv2.weight - torch.Size([128, 128, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.3.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.3.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.3.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.3.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.4.conv1.weight - torch.Size([128, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.4.conv2.weight - torch.Size([128, 128, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.4.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.4.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.4.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.4.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.5.conv1.weight - torch.Size([128, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.5.conv2.weight - torch.Size([128, 128, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer3.5.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.5.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.5.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer3.5.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.0.conv1.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.0.conv2.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.0.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.0.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.0.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.0.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.0.downsample.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.0.downsample.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.0.downsample.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.1.conv1.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.1.conv2.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.1.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.1.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.1.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.1.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.2.conv1.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.2.conv2.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.2.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.2.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.2.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.2.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.3.conv1.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.3.conv2.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.3.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.3.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.3.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.3.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.4.conv1.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.4.conv2.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.4.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.4.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.4.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.4.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.5.conv1.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.5.conv2.weight - torch.Size([256, 256, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer4.5.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.5.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.5.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer4.5.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.0.conv1.weight - torch.Size([512, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer5.0.conv2.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer5.0.bn1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.0.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.0.bn2.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.0.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.0.downsample.conv.weight - torch.Size([512, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer5.0.downsample.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.0.downsample.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.1.conv1.weight - torch.Size([512, 512, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer5.1.conv2.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer5.1.bn1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.1.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.1.bn2.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.1.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.2.conv1.weight - torch.Size([512, 512, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer5.2.conv2.weight - torch.Size([512, 512, 3, 3]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.layer5.2.bn1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.2.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.2.bn2.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER backbone.layer5.2.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.weight_ih_l0 - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.weight_hh_l0 - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.bias_ih_l0 - torch.Size([1024]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.bias_hh_l0 - torch.Size([1024]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.weight_ih_l0_reverse - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.weight_hh_l0_reverse - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.bias_ih_l0_reverse - torch.Size([1024]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.bias_hh_l0_reverse - torch.Size([1024]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.weight_ih_l1 - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.weight_hh_l1 - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.bias_ih_l1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.bias_hh_l1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.weight_ih_l1_reverse - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.weight_hh_l1_reverse - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.bias_ih_l1_reverse - torch.Size([1024]): The value is the same before and after calling `init_weights` of ASTER encoder.bilstm.bias_hh_l1_reverse - torch.Size([1024]): The value is the same before and after calling `init_weights` of ASTER decoder.proj_feat.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of ASTER decoder.proj_feat.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER decoder.proj_hidden.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of ASTER decoder.proj_hidden.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ASTER decoder.proj_sum.weight - torch.Size([1, 512]): The value is the same before and after calling `init_weights` of ASTER decoder.proj_sum.bias - torch.Size([1]): The value is the same before and after calling `init_weights` of ASTER decoder.embedding.weight - torch.Size([93, 512]): The value is the same before and after calling `init_weights` of ASTER decoder.gru.weight_ih_l0 - torch.Size([1536, 1024]): The value is the same before and after calling `init_weights` of ASTER decoder.gru.weight_hh_l0 - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of ASTER decoder.gru.bias_ih_l0 - torch.Size([1536]): The value is the same before and after calling `init_weights` of ASTER decoder.gru.bias_hh_l0 - torch.Size([1536]): The value is the same before and after calling `init_weights` of ASTER decoder.fc.weight - torch.Size([93, 512]): The value is the same before and after calling `init_weights` of ASTER decoder.fc.bias - torch.Size([93]): The value is the same before and after calling `init_weights` of ASTER 2022/12/14 23:29:17 - mmengine - INFO - Checkpoints will be saved to work_dirs/aster. 2022/12/14 23:42:19 - mmengine - INFO - Epoch(train) [1][ 50/3952] lr: 4.0000e-04 eta: 4 days, 6:50:22 time: 1.0938 data_time: 0.0028 memory: 17857 loss: 0.7780 loss_ce: 0.7780 2022/12/14 23:43:06 - mmengine - INFO - Epoch(train) [1][ 100/3952] lr: 3.9998e-04 eta: 2 days, 6:21:39 time: 0.9590 data_time: 0.0026 memory: 11985 loss: 0.6960 loss_ce: 0.6960 2022/12/14 23:43:50 - mmengine - INFO - Epoch(train) [1][ 150/3952] lr: 3.9996e-04 eta: 1 day, 14:05:49 time: 0.9084 data_time: 0.0025 memory: 11985 loss: 0.6606 loss_ce: 0.6606 2022/12/14 23:44:36 - mmengine - INFO - Epoch(train) [1][ 200/3952] lr: 3.9993e-04 eta: 1 day, 5:59:43 time: 0.9086 data_time: 0.0030 memory: 11985 loss: 0.6301 loss_ce: 0.6301 2022/12/14 23:45:20 - mmengine - INFO - Epoch(train) [1][ 250/3952] lr: 3.9989e-04 eta: 1 day, 1:06:47 time: 0.8995 data_time: 0.0024 memory: 11985 loss: 0.6111 loss_ce: 0.6111 2022/12/14 23:46:05 - mmengine - INFO - Epoch(train) [1][ 300/3952] lr: 3.9984e-04 eta: 21:51:36 time: 0.8851 data_time: 0.0028 memory: 11985 loss: 0.5827 loss_ce: 0.5827 2022/12/14 23:46:50 - mmengine - INFO - Epoch(train) [1][ 350/3952] lr: 3.9979e-04 eta: 19:31:49 time: 0.8752 data_time: 0.0024 memory: 11985 loss: 0.5366 loss_ce: 0.5366 2022/12/14 23:47:36 - mmengine - INFO - Epoch(train) [1][ 400/3952] lr: 3.9972e-04 eta: 17:47:15 time: 0.9168 data_time: 0.0027 memory: 11985 loss: 0.4654 loss_ce: 0.4654 2022/12/14 23:48:22 - mmengine - INFO - Epoch(train) [1][ 450/3952] lr: 3.9965e-04 eta: 16:26:41 time: 0.9017 data_time: 0.0027 memory: 11985 loss: 0.3618 loss_ce: 0.3618 2022/12/14 23:49:07 - mmengine - INFO - Epoch(train) [1][ 500/3952] lr: 3.9957e-04 eta: 15:20:57 time: 0.8723 data_time: 0.0026 memory: 11985 loss: 0.2648 loss_ce: 0.2648 2022/12/14 23:49:53 - mmengine - INFO - Epoch(train) [1][ 550/3952] lr: 3.9948e-04 eta: 14:27:40 time: 0.9376 data_time: 0.0025 memory: 11985 loss: 0.1960 loss_ce: 0.1960 2022/12/14 23:50:39 - mmengine - INFO - Epoch(train) [1][ 600/3952] lr: 3.9938e-04 eta: 13:42:58 time: 0.8799 data_time: 0.0027 memory: 11985 loss: 0.1577 loss_ce: 0.1577 2022/12/14 23:51:25 - mmengine - INFO - Epoch(train) [1][ 650/3952] lr: 3.9927e-04 eta: 13:05:25 time: 0.8747 data_time: 0.0036 memory: 11985 loss: 0.1334 loss_ce: 0.1334 2022/12/14 23:52:10 - mmengine - INFO - Epoch(train) [1][ 700/3952] lr: 3.9915e-04 eta: 12:32:28 time: 0.8603 data_time: 0.0025 memory: 11985 loss: 0.1190 loss_ce: 0.1190 2022/12/14 23:52:56 - mmengine - INFO - Epoch(train) [1][ 750/3952] lr: 3.9903e-04 eta: 12:03:54 time: 0.8824 data_time: 0.0025 memory: 11985 loss: 0.1119 loss_ce: 0.1119 2022/12/14 23:53:41 - mmengine - INFO - Epoch(train) [1][ 800/3952] lr: 3.9889e-04 eta: 11:38:49 time: 0.8717 data_time: 0.0025 memory: 11985 loss: 0.1005 loss_ce: 0.1005 2022/12/14 23:54:25 - mmengine - INFO - Epoch(train) [1][ 850/3952] lr: 3.9875e-04 eta: 11:15:57 time: 0.8868 data_time: 0.0026 memory: 11985 loss: 0.0984 loss_ce: 0.0984 2022/12/14 23:55:11 - mmengine - INFO - Epoch(train) [1][ 900/3952] lr: 3.9860e-04 eta: 10:56:19 time: 0.9250 data_time: 0.0024 memory: 11985 loss: 0.0930 loss_ce: 0.0930 2022/12/14 23:55:56 - mmengine - INFO - Epoch(train) [1][ 950/3952] lr: 3.9844e-04 eta: 10:38:22 time: 0.8990 data_time: 0.0031 memory: 11985 loss: 0.0834 loss_ce: 0.0834 2022/12/14 23:56:41 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/14 23:56:41 - mmengine - INFO - Epoch(train) [1][1000/3952] lr: 3.9827e-04 eta: 10:22:24 time: 0.8938 data_time: 0.0039 memory: 11985 loss: 0.0819 loss_ce: 0.0819 2022/12/14 23:57:27 - mmengine - INFO - Epoch(train) [1][1050/3952] lr: 3.9809e-04 eta: 10:07:45 time: 0.9073 data_time: 0.0025 memory: 11985 loss: 0.0784 loss_ce: 0.0784 2022/12/14 23:58:12 - mmengine - INFO - Epoch(train) [1][1100/3952] lr: 3.9790e-04 eta: 9:54:29 time: 0.9537 data_time: 0.0029 memory: 11985 loss: 0.0711 loss_ce: 0.0711 2022/12/14 23:58:57 - mmengine - INFO - Epoch(train) [1][1150/3952] lr: 3.9771e-04 eta: 9:41:58 time: 0.8743 data_time: 0.0026 memory: 11985 loss: 0.0754 loss_ce: 0.0754 2022/12/14 23:59:42 - mmengine - INFO - Epoch(train) [1][1200/3952] lr: 3.9751e-04 eta: 9:30:37 time: 0.9124 data_time: 0.0026 memory: 11985 loss: 0.0702 loss_ce: 0.0702 2022/12/15 00:00:27 - mmengine - INFO - Epoch(train) [1][1250/3952] lr: 3.9730e-04 eta: 9:19:57 time: 0.9057 data_time: 0.0027 memory: 11985 loss: 0.0726 loss_ce: 0.0726 2022/12/15 00:01:12 - mmengine - INFO - Epoch(train) [1][1300/3952] lr: 3.9707e-04 eta: 9:10:11 time: 0.8979 data_time: 0.0024 memory: 11985 loss: 0.0677 loss_ce: 0.0677 2022/12/15 00:01:57 - mmengine - INFO - Epoch(train) [1][1350/3952] lr: 3.9685e-04 eta: 9:01:10 time: 0.8861 data_time: 0.0041 memory: 11985 loss: 0.0675 loss_ce: 0.0675 2022/12/15 00:02:42 - mmengine - INFO - Epoch(train) [1][1400/3952] lr: 3.9661e-04 eta: 8:52:39 time: 0.8916 data_time: 0.0026 memory: 11985 loss: 0.0669 loss_ce: 0.0669 2022/12/15 00:03:27 - mmengine - INFO - Epoch(train) [1][1450/3952] lr: 3.9636e-04 eta: 8:44:26 time: 0.9185 data_time: 0.0028 memory: 11985 loss: 0.0599 loss_ce: 0.0599 2022/12/15 00:04:13 - mmengine - INFO - Epoch(train) [1][1500/3952] lr: 3.9611e-04 eta: 8:37:10 time: 0.9537 data_time: 0.0025 memory: 11985 loss: 0.0596 loss_ce: 0.0596 2022/12/15 00:04:59 - mmengine - INFO - Epoch(train) [1][1550/3952] lr: 3.9584e-04 eta: 8:30:28 time: 0.9401 data_time: 0.0027 memory: 11985 loss: 0.0594 loss_ce: 0.0594 2022/12/15 00:05:46 - mmengine - INFO - Epoch(train) [1][1600/3952] lr: 3.9557e-04 eta: 8:24:08 time: 0.9400 data_time: 0.0028 memory: 11985 loss: 0.0582 loss_ce: 0.0582 2022/12/15 00:06:31 - mmengine - INFO - Epoch(train) [1][1650/3952] lr: 3.9529e-04 eta: 8:17:52 time: 0.8981 data_time: 0.0026 memory: 11985 loss: 0.0551 loss_ce: 0.0551 2022/12/15 00:07:16 - mmengine - INFO - Epoch(train) [1][1700/3952] lr: 3.9500e-04 eta: 8:11:51 time: 0.8982 data_time: 0.0029 memory: 11985 loss: 0.0551 loss_ce: 0.0551 2022/12/15 00:08:01 - mmengine - INFO - Epoch(train) [1][1750/3952] lr: 3.9471e-04 eta: 8:05:58 time: 0.8708 data_time: 0.0025 memory: 11985 loss: 0.0552 loss_ce: 0.0552 2022/12/15 00:08:44 - mmengine - INFO - Epoch(train) [1][1800/3952] lr: 3.9440e-04 eta: 8:00:13 time: 0.8609 data_time: 0.0026 memory: 11985 loss: 0.0563 loss_ce: 0.0563 2022/12/15 00:09:28 - mmengine - INFO - Epoch(train) [1][1850/3952] lr: 3.9409e-04 eta: 7:54:53 time: 0.9272 data_time: 0.0025 memory: 11985 loss: 0.0532 loss_ce: 0.0532 2022/12/15 00:10:12 - mmengine - INFO - Epoch(train) [1][1900/3952] lr: 3.9377e-04 eta: 7:49:42 time: 0.8613 data_time: 0.0028 memory: 11985 loss: 0.0529 loss_ce: 0.0529 2022/12/15 00:10:57 - mmengine - INFO - Epoch(train) [1][1950/3952] lr: 3.9344e-04 eta: 7:44:56 time: 0.8404 data_time: 0.0030 memory: 11985 loss: 0.0525 loss_ce: 0.0525 2022/12/15 00:11:43 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 00:11:43 - mmengine - INFO - Epoch(train) [1][2000/3952] lr: 3.9310e-04 eta: 7:40:35 time: 0.9545 data_time: 0.0025 memory: 11985 loss: 0.0524 loss_ce: 0.0524 2022/12/15 00:12:29 - mmengine - INFO - Epoch(train) [1][2050/3952] lr: 3.9275e-04 eta: 7:36:25 time: 0.9536 data_time: 0.0026 memory: 11985 loss: 0.0486 loss_ce: 0.0486 2022/12/15 00:13:15 - mmengine - INFO - Epoch(train) [1][2100/3952] lr: 3.9239e-04 eta: 7:32:25 time: 0.8729 data_time: 0.0028 memory: 11985 loss: 0.0507 loss_ce: 0.0507 2022/12/15 00:14:01 - mmengine - INFO - Epoch(train) [1][2150/3952] lr: 3.9203e-04 eta: 7:28:32 time: 0.8570 data_time: 0.0031 memory: 11985 loss: 0.0490 loss_ce: 0.0490 2022/12/15 00:14:46 - mmengine - INFO - Epoch(train) [1][2200/3952] lr: 3.9166e-04 eta: 7:24:45 time: 0.8520 data_time: 0.0030 memory: 11985 loss: 0.0517 loss_ce: 0.0517 2022/12/15 00:15:32 - mmengine - INFO - Epoch(train) [1][2250/3952] lr: 3.9128e-04 eta: 7:21:06 time: 0.9000 data_time: 0.0025 memory: 11985 loss: 0.0503 loss_ce: 0.0503 2022/12/15 00:16:18 - mmengine - INFO - Epoch(train) [1][2300/3952] lr: 3.9089e-04 eta: 7:17:37 time: 0.9192 data_time: 0.0026 memory: 11985 loss: 0.0492 loss_ce: 0.0492 2022/12/15 00:17:04 - mmengine - INFO - Epoch(train) [1][2350/3952] lr: 3.9049e-04 eta: 7:14:16 time: 0.8813 data_time: 0.0037 memory: 11985 loss: 0.0483 loss_ce: 0.0483 2022/12/15 00:17:49 - mmengine - INFO - Epoch(train) [1][2400/3952] lr: 3.9008e-04 eta: 7:10:58 time: 0.8647 data_time: 0.0030 memory: 11985 loss: 0.0480 loss_ce: 0.0480 2022/12/15 00:18:34 - mmengine - INFO - Epoch(train) [1][2450/3952] lr: 3.8967e-04 eta: 7:07:42 time: 0.9443 data_time: 0.0043 memory: 11985 loss: 0.0449 loss_ce: 0.0449 2022/12/15 00:19:21 - mmengine - INFO - Epoch(train) [1][2500/3952] lr: 3.8925e-04 eta: 7:04:49 time: 0.9074 data_time: 0.0039 memory: 11985 loss: 0.0457 loss_ce: 0.0457 2022/12/15 00:20:06 - mmengine - INFO - Epoch(train) [1][2550/3952] lr: 3.8882e-04 eta: 7:01:43 time: 0.8730 data_time: 0.0026 memory: 11985 loss: 0.0448 loss_ce: 0.0448 2022/12/15 00:20:52 - mmengine - INFO - Epoch(train) [1][2600/3952] lr: 3.8838e-04 eta: 6:58:51 time: 0.9103 data_time: 0.0028 memory: 11985 loss: 0.0452 loss_ce: 0.0452 2022/12/15 00:21:38 - mmengine - INFO - Epoch(train) [1][2650/3952] lr: 3.8793e-04 eta: 6:56:06 time: 0.8717 data_time: 0.0039 memory: 11985 loss: 0.0464 loss_ce: 0.0464 2022/12/15 00:22:23 - mmengine - INFO - Epoch(train) [1][2700/3952] lr: 3.8748e-04 eta: 6:53:11 time: 0.8613 data_time: 0.0027 memory: 11985 loss: 0.0445 loss_ce: 0.0445 2022/12/15 00:23:08 - mmengine - INFO - Epoch(train) [1][2750/3952] lr: 3.8701e-04 eta: 6:50:26 time: 0.8893 data_time: 0.0027 memory: 11985 loss: 0.2193 loss_ce: 0.2193 2022/12/15 00:23:53 - mmengine - INFO - Epoch(train) [1][2800/3952] lr: 3.8654e-04 eta: 6:47:43 time: 0.8730 data_time: 0.0027 memory: 11985 loss: 0.0594 loss_ce: 0.0594 2022/12/15 00:24:38 - mmengine - INFO - Epoch(train) [1][2850/3952] lr: 3.8606e-04 eta: 6:45:10 time: 0.9066 data_time: 0.0025 memory: 11985 loss: 0.0511 loss_ce: 0.0511 2022/12/15 00:25:24 - mmengine - INFO - Epoch(train) [1][2900/3952] lr: 3.8557e-04 eta: 6:42:43 time: 0.8784 data_time: 0.0026 memory: 11985 loss: 0.0467 loss_ce: 0.0467 2022/12/15 00:26:09 - mmengine - INFO - Epoch(train) [1][2950/3952] lr: 3.8508e-04 eta: 6:40:16 time: 0.8247 data_time: 0.0026 memory: 11985 loss: 0.0488 loss_ce: 0.0488 2022/12/15 00:26:54 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 00:26:54 - mmengine - INFO - Epoch(train) [1][3000/3952] lr: 3.8457e-04 eta: 6:37:46 time: 0.8785 data_time: 0.0043 memory: 11985 loss: 0.0459 loss_ce: 0.0459 2022/12/15 00:27:39 - mmengine - INFO - Epoch(train) [1][3050/3952] lr: 3.8406e-04 eta: 6:35:21 time: 0.9126 data_time: 0.0028 memory: 11985 loss: 0.0460 loss_ce: 0.0460 2022/12/15 00:28:22 - mmengine - INFO - Epoch(train) [1][3100/3952] lr: 3.8354e-04 eta: 6:32:46 time: 0.8496 data_time: 0.0027 memory: 11985 loss: 0.0445 loss_ce: 0.0445 2022/12/15 00:29:08 - mmengine - INFO - Epoch(train) [1][3150/3952] lr: 3.8302e-04 eta: 6:30:36 time: 0.9694 data_time: 0.0026 memory: 11985 loss: 0.0419 loss_ce: 0.0419 2022/12/15 00:29:53 - mmengine - INFO - Epoch(train) [1][3200/3952] lr: 3.8248e-04 eta: 6:28:23 time: 0.9001 data_time: 0.0026 memory: 11985 loss: 0.0454 loss_ce: 0.0454 2022/12/15 00:30:37 - mmengine - INFO - Epoch(train) [1][3250/3952] lr: 3.8194e-04 eta: 6:26:11 time: 0.8747 data_time: 0.0026 memory: 11985 loss: 0.0450 loss_ce: 0.0450 2022/12/15 00:31:24 - mmengine - INFO - Epoch(train) [1][3300/3952] lr: 3.8139e-04 eta: 6:24:09 time: 0.9304 data_time: 0.0027 memory: 11985 loss: 0.0429 loss_ce: 0.0429 2022/12/15 00:32:09 - mmengine - INFO - Epoch(train) [1][3350/3952] lr: 3.8083e-04 eta: 6:22:06 time: 0.8957 data_time: 0.0028 memory: 11985 loss: 0.0429 loss_ce: 0.0429 2022/12/15 00:32:55 - mmengine - INFO - Epoch(train) [1][3400/3952] lr: 3.8026e-04 eta: 6:20:08 time: 0.9474 data_time: 0.0027 memory: 11985 loss: 0.0437 loss_ce: 0.0437 2022/12/15 00:33:41 - mmengine - INFO - Epoch(train) [1][3450/3952] lr: 3.7969e-04 eta: 6:18:14 time: 0.9493 data_time: 0.0031 memory: 11985 loss: 0.0403 loss_ce: 0.0403 2022/12/15 00:34:27 - mmengine - INFO - Epoch(train) [1][3500/3952] lr: 3.7910e-04 eta: 6:16:17 time: 0.8856 data_time: 0.0026 memory: 11985 loss: 0.0431 loss_ce: 0.0431 2022/12/15 00:35:12 - mmengine - INFO - Epoch(train) [1][3550/3952] lr: 3.7851e-04 eta: 6:14:18 time: 0.9133 data_time: 0.0029 memory: 11985 loss: 0.0437 loss_ce: 0.0437 2022/12/15 00:35:55 - mmengine - INFO - Epoch(train) [1][3600/3952] lr: 3.7791e-04 eta: 6:12:16 time: 0.8347 data_time: 0.0042 memory: 11985 loss: 0.0395 loss_ce: 0.0395 2022/12/15 00:36:40 - mmengine - INFO - Epoch(train) [1][3650/3952] lr: 3.7731e-04 eta: 6:10:21 time: 0.9219 data_time: 0.0027 memory: 11985 loss: 0.0391 loss_ce: 0.0391 2022/12/15 00:37:27 - mmengine - INFO - Epoch(train) [1][3700/3952] lr: 3.7669e-04 eta: 6:08:38 time: 0.9411 data_time: 0.0027 memory: 11985 loss: 0.0411 loss_ce: 0.0411 2022/12/15 00:38:12 - mmengine - INFO - Epoch(train) [1][3750/3952] lr: 3.7607e-04 eta: 6:06:50 time: 0.9012 data_time: 0.0028 memory: 11985 loss: 0.0386 loss_ce: 0.0386 2022/12/15 00:38:58 - mmengine - INFO - Epoch(train) [1][3800/3952] lr: 3.7544e-04 eta: 6:05:08 time: 0.9134 data_time: 0.0029 memory: 11985 loss: 0.0399 loss_ce: 0.0399 2022/12/15 00:39:43 - mmengine - INFO - Epoch(train) [1][3850/3952] lr: 3.7481e-04 eta: 6:03:19 time: 0.8226 data_time: 0.0040 memory: 11985 loss: 0.0421 loss_ce: 0.0421 2022/12/15 00:40:27 - mmengine - INFO - Epoch(train) [1][3900/3952] lr: 3.7416e-04 eta: 6:01:32 time: 0.8840 data_time: 0.0034 memory: 11985 loss: 0.0377 loss_ce: 0.0377 2022/12/15 00:40:58 - mmengine - INFO - Epoch(train) [1][3950/3952] lr: 3.7351e-04 eta: 5:58:38 time: 0.6203 data_time: 0.0030 memory: 11985 loss: 0.0394 loss_ce: 0.0394 2022/12/15 00:41:01 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 00:41:01 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/15 00:41:08 - mmengine - INFO - Epoch(val) [1][ 50/1918] eta: 0:02:39 time: 0.0501 data_time: 0.0001 memory: 11985 2022/12/15 00:41:11 - mmengine - INFO - Epoch(val) [1][ 100/1918] eta: 0:02:16 time: 0.0654 data_time: 0.0002 memory: 453 2022/12/15 00:41:14 - mmengine - INFO - Epoch(val) [1][ 150/1918] eta: 0:01:59 time: 0.0544 data_time: 0.0001 memory: 453 2022/12/15 00:41:16 - mmengine - INFO - Epoch(val) [1][ 200/1918] eta: 0:01:47 time: 0.0482 data_time: 0.0002 memory: 453 2022/12/15 00:41:19 - mmengine - INFO - Epoch(val) [1][ 250/1918] eta: 0:01:38 time: 0.0463 data_time: 0.0001 memory: 453 2022/12/15 00:41:21 - mmengine - INFO - Epoch(val) [1][ 300/1918] eta: 0:01:32 time: 0.0454 data_time: 0.0013 memory: 453 2022/12/15 00:41:23 - mmengine - INFO - Epoch(val) [1][ 350/1918] eta: 0:01:27 time: 0.0470 data_time: 0.0014 memory: 453 2022/12/15 00:41:26 - mmengine - INFO - Epoch(val) [1][ 400/1918] eta: 0:01:23 time: 0.0473 data_time: 0.0020 memory: 453 2022/12/15 00:41:28 - mmengine - INFO - Epoch(val) [1][ 450/1918] eta: 0:01:19 time: 0.0553 data_time: 0.0030 memory: 453 2022/12/15 00:41:31 - mmengine - INFO - Epoch(val) [1][ 500/1918] eta: 0:01:17 time: 0.0586 data_time: 0.0023 memory: 453 2022/12/15 00:41:34 - mmengine - INFO - Epoch(val) [1][ 550/1918] eta: 0:01:14 time: 0.0469 data_time: 0.0001 memory: 453 2022/12/15 00:41:36 - mmengine - INFO - Epoch(val) [1][ 600/1918] eta: 0:01:11 time: 0.0511 data_time: 0.0001 memory: 453 2022/12/15 00:41:39 - mmengine - INFO - Epoch(val) [1][ 650/1918] eta: 0:01:08 time: 0.0495 data_time: 0.0001 memory: 453 2022/12/15 00:41:41 - mmengine - INFO - Epoch(val) [1][ 700/1918] eta: 0:01:04 time: 0.0464 data_time: 0.0017 memory: 453 2022/12/15 00:41:44 - mmengine - INFO - Epoch(val) [1][ 750/1918] eta: 0:01:01 time: 0.0468 data_time: 0.0041 memory: 453 2022/12/15 00:41:46 - mmengine - INFO - Epoch(val) [1][ 800/1918] eta: 0:00:58 time: 0.0370 data_time: 0.0022 memory: 453 2022/12/15 00:41:48 - mmengine - INFO - Epoch(val) [1][ 850/1918] eta: 0:00:55 time: 0.0586 data_time: 0.0056 memory: 453 2022/12/15 00:41:51 - mmengine - INFO - Epoch(val) [1][ 900/1918] eta: 0:00:53 time: 0.0475 data_time: 0.0047 memory: 453 2022/12/15 00:41:54 - mmengine - INFO - Epoch(val) [1][ 950/1918] eta: 0:00:50 time: 0.0469 data_time: 0.0051 memory: 453 2022/12/15 00:41:56 - mmengine - INFO - Epoch(val) [1][1000/1918] eta: 0:00:48 time: 0.0742 data_time: 0.0035 memory: 453 2022/12/15 00:41:59 - mmengine - INFO - Epoch(val) [1][1050/1918] eta: 0:00:45 time: 0.0503 data_time: 0.0001 memory: 453 2022/12/15 00:42:02 - mmengine - INFO - Epoch(val) [1][1100/1918] eta: 0:00:42 time: 0.0545 data_time: 0.0052 memory: 453 2022/12/15 00:42:04 - mmengine - INFO - Epoch(val) [1][1150/1918] eta: 0:00:40 time: 0.0485 data_time: 0.0001 memory: 453 2022/12/15 00:42:07 - mmengine - INFO - Epoch(val) [1][1200/1918] eta: 0:00:37 time: 0.0480 data_time: 0.0027 memory: 453 2022/12/15 00:42:09 - mmengine - INFO - Epoch(val) [1][1250/1918] eta: 0:00:34 time: 0.0468 data_time: 0.0023 memory: 453 2022/12/15 00:42:12 - mmengine - INFO - Epoch(val) [1][1300/1918] eta: 0:00:32 time: 0.0483 data_time: 0.0025 memory: 453 2022/12/15 00:42:14 - mmengine - INFO - Epoch(val) [1][1350/1918] eta: 0:00:29 time: 0.0484 data_time: 0.0029 memory: 453 2022/12/15 00:42:17 - mmengine - INFO - Epoch(val) [1][1400/1918] eta: 0:00:26 time: 0.0570 data_time: 0.0016 memory: 453 2022/12/15 00:42:19 - mmengine - INFO - Epoch(val) [1][1450/1918] eta: 0:00:24 time: 0.0458 data_time: 0.0001 memory: 453 2022/12/15 00:42:21 - mmengine - INFO - Epoch(val) [1][1500/1918] eta: 0:00:21 time: 0.0461 data_time: 0.0001 memory: 453 2022/12/15 00:42:23 - mmengine - INFO - Epoch(val) [1][1550/1918] eta: 0:00:18 time: 0.0476 data_time: 0.0007 memory: 453 2022/12/15 00:42:26 - mmengine - INFO - Epoch(val) [1][1600/1918] eta: 0:00:16 time: 0.0535 data_time: 0.0012 memory: 453 2022/12/15 00:42:29 - mmengine - INFO - Epoch(val) [1][1650/1918] eta: 0:00:13 time: 0.0485 data_time: 0.0001 memory: 453 2022/12/15 00:42:31 - mmengine - INFO - Epoch(val) [1][1700/1918] eta: 0:00:11 time: 0.0463 data_time: 0.0001 memory: 453 2022/12/15 00:42:33 - mmengine - INFO - Epoch(val) [1][1750/1918] eta: 0:00:08 time: 0.0462 data_time: 0.0017 memory: 453 2022/12/15 00:42:36 - mmengine - INFO - Epoch(val) [1][1800/1918] eta: 0:00:06 time: 0.0458 data_time: 0.0012 memory: 453 2022/12/15 00:42:37 - mmengine - INFO - Epoch(val) [1][1850/1918] eta: 0:00:03 time: 0.0329 data_time: 0.0002 memory: 453 2022/12/15 00:42:38 - mmengine - INFO - Epoch(val) [1][1900/1918] eta: 0:00:00 time: 0.0208 data_time: 0.0001 memory: 453 2022/12/15 00:42:39 - mmengine - INFO - Epoch(val) [1][1918/1918] CUTE80/recog/word_acc: 0.6389 CUTE80/recog/word_acc_ignore_case: 0.7500 CUTE80/recog/word_acc_ignore_case_symbol: 0.7569 IIIT5K/recog/word_acc: 0.3603 IIIT5K/recog/word_acc_ignore_case: 0.7980 IIIT5K/recog/word_acc_ignore_case_symbol: 0.8787 SVT/recog/word_acc: 0.1221 SVT/recog/word_acc_ignore_case: 0.7790 SVT/recog/word_acc_ignore_case_symbol: 0.7975 SVTP/recog/word_acc: 0.3163 SVTP/recog/word_acc_ignore_case: 0.6992 SVTP/recog/word_acc_ignore_case_symbol: 0.7054 IC13/recog/word_acc: 0.8089 IC13/recog/word_acc_ignore_case: 0.8690 IC13/recog/word_acc_ignore_case_symbol: 0.8739 IC15/recog/word_acc: 0.4945 IC15/recog/word_acc_ignore_case: 0.6442 IC15/recog/word_acc_ignore_case_symbol: 0.6726 CUTE80/recog/char_recall: 0.8795 CUTE80/recog/char_precision: 0.9028 IIIT5K/recog/char_recall: 0.9577 IIIT5K/recog/char_precision: 0.9535 SVT/recog/char_recall: 0.9315 SVT/recog/char_precision: 0.9382 SVTP/recog/char_recall: 0.8725 SVTP/recog/char_precision: 0.9052 IC13/recog/char_recall: 0.9603 IC13/recog/char_precision: 0.9621 IC15/recog/char_recall: 0.8654 IC15/recog/char_precision: 0.8838 2022/12/15 00:43:36 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 00:43:38 - mmengine - INFO - Epoch(train) [2][ 50/3952] lr: 3.7283e-04 eta: 5:58:10 time: 0.9223 data_time: 0.0029 memory: 11986 loss: 0.0367 loss_ce: 0.0367 2022/12/15 00:44:24 - mmengine - INFO - Epoch(train) [2][ 100/3952] lr: 3.7216e-04 eta: 5:56:34 time: 0.9457 data_time: 0.0033 memory: 11981 loss: 0.0370 loss_ce: 0.0370 2022/12/15 00:45:11 - mmengine - INFO - Epoch(train) [2][ 150/3952] lr: 3.7149e-04 eta: 5:55:05 time: 0.9514 data_time: 0.0046 memory: 11981 loss: 0.0370 loss_ce: 0.0370 2022/12/15 00:45:58 - mmengine - INFO - Epoch(train) [2][ 200/3952] lr: 3.7080e-04 eta: 5:53:38 time: 0.9765 data_time: 0.0029 memory: 11981 loss: 0.0386 loss_ce: 0.0386 2022/12/15 00:46:44 - mmengine - INFO - Epoch(train) [2][ 250/3952] lr: 3.7011e-04 eta: 5:52:06 time: 0.8650 data_time: 0.0029 memory: 11981 loss: 0.0388 loss_ce: 0.0388 2022/12/15 00:47:30 - mmengine - INFO - Epoch(train) [2][ 300/3952] lr: 3.6942e-04 eta: 5:50:32 time: 0.8924 data_time: 0.0034 memory: 11981 loss: 0.0389 loss_ce: 0.0389 2022/12/15 00:48:15 - mmengine - INFO - Epoch(train) [2][ 350/3952] lr: 3.6871e-04 eta: 5:48:58 time: 0.8813 data_time: 0.0070 memory: 11981 loss: 0.0374 loss_ce: 0.0374 2022/12/15 00:49:00 - mmengine - INFO - Epoch(train) [2][ 400/3952] lr: 3.6800e-04 eta: 5:47:25 time: 0.9196 data_time: 0.0032 memory: 11981 loss: 0.0369 loss_ce: 0.0369 2022/12/15 00:49:45 - mmengine - INFO - Epoch(train) [2][ 450/3952] lr: 3.6728e-04 eta: 5:45:50 time: 0.8650 data_time: 0.0031 memory: 11981 loss: 0.0357 loss_ce: 0.0357 2022/12/15 00:50:30 - mmengine - INFO - Epoch(train) [2][ 500/3952] lr: 3.6656e-04 eta: 5:44:21 time: 0.9212 data_time: 0.0039 memory: 11981 loss: 0.0372 loss_ce: 0.0372 2022/12/15 00:51:15 - mmengine - INFO - Epoch(train) [2][ 550/3952] lr: 3.6583e-04 eta: 5:42:51 time: 0.8900 data_time: 0.0043 memory: 11981 loss: 0.0362 loss_ce: 0.0362 2022/12/15 00:52:02 - mmengine - INFO - Epoch(train) [2][ 600/3952] lr: 3.6508e-04 eta: 5:41:29 time: 0.8870 data_time: 0.0032 memory: 11981 loss: 0.0372 loss_ce: 0.0372 2022/12/15 00:52:46 - mmengine - INFO - Epoch(train) [2][ 650/3952] lr: 3.6434e-04 eta: 5:39:55 time: 0.9044 data_time: 0.0033 memory: 11981 loss: 0.0375 loss_ce: 0.0375 2022/12/15 00:53:32 - mmengine - INFO - Epoch(train) [2][ 700/3952] lr: 3.6358e-04 eta: 5:38:31 time: 0.9525 data_time: 0.0032 memory: 11981 loss: 0.0360 loss_ce: 0.0360 2022/12/15 00:54:17 - mmengine - INFO - Epoch(train) [2][ 750/3952] lr: 3.6282e-04 eta: 5:37:04 time: 0.8710 data_time: 0.0032 memory: 11981 loss: 0.0346 loss_ce: 0.0346 2022/12/15 00:55:02 - mmengine - INFO - Epoch(train) [2][ 800/3952] lr: 3.6205e-04 eta: 5:35:39 time: 0.8695 data_time: 0.0032 memory: 11981 loss: 0.0358 loss_ce: 0.0358 2022/12/15 00:55:47 - mmengine - INFO - Epoch(train) [2][ 850/3952] lr: 3.6128e-04 eta: 5:34:12 time: 0.8644 data_time: 0.0036 memory: 11981 loss: 0.0353 loss_ce: 0.0353 2022/12/15 00:56:31 - mmengine - INFO - Epoch(train) [2][ 900/3952] lr: 3.6049e-04 eta: 5:32:46 time: 0.8974 data_time: 0.0037 memory: 11981 loss: 0.0369 loss_ce: 0.0369 2022/12/15 00:57:17 - mmengine - INFO - Epoch(train) [2][ 950/3952] lr: 3.5970e-04 eta: 5:31:27 time: 0.9264 data_time: 0.0035 memory: 11981 loss: 0.0371 loss_ce: 0.0371 2022/12/15 00:58:04 - mmengine - INFO - Epoch(train) [2][1000/3952] lr: 3.5891e-04 eta: 5:30:10 time: 0.9254 data_time: 0.0037 memory: 11981 loss: 0.0335 loss_ce: 0.0335 2022/12/15 00:58:46 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 00:58:48 - mmengine - INFO - Epoch(train) [2][1050/3952] lr: 3.5810e-04 eta: 5:28:47 time: 0.8966 data_time: 0.0033 memory: 11981 loss: 0.0366 loss_ce: 0.0366 2022/12/15 00:59:34 - mmengine - INFO - Epoch(train) [2][1100/3952] lr: 3.5729e-04 eta: 5:27:27 time: 0.9026 data_time: 0.0035 memory: 11981 loss: 0.0368 loss_ce: 0.0368 2022/12/15 01:00:19 - mmengine - INFO - Epoch(train) [2][1150/3952] lr: 3.5648e-04 eta: 5:26:07 time: 0.9222 data_time: 0.0033 memory: 11981 loss: 0.0340 loss_ce: 0.0340 2022/12/15 01:01:04 - mmengine - INFO - Epoch(train) [2][1200/3952] lr: 3.5565e-04 eta: 5:24:47 time: 0.8625 data_time: 0.0032 memory: 11981 loss: 0.0329 loss_ce: 0.0329 2022/12/15 01:01:50 - mmengine - INFO - Epoch(train) [2][1250/3952] lr: 3.5482e-04 eta: 5:23:32 time: 0.9079 data_time: 0.0032 memory: 11981 loss: 0.0375 loss_ce: 0.0375 2022/12/15 01:02:34 - mmengine - INFO - Epoch(train) [2][1300/3952] lr: 3.5399e-04 eta: 5:22:11 time: 0.8789 data_time: 0.0032 memory: 11981 loss: 0.0345 loss_ce: 0.0345 2022/12/15 01:03:20 - mmengine - INFO - Epoch(train) [2][1350/3952] lr: 3.5314e-04 eta: 5:20:54 time: 0.8988 data_time: 0.0035 memory: 11981 loss: 0.0326 loss_ce: 0.0326 2022/12/15 01:04:05 - mmengine - INFO - Epoch(train) [2][1400/3952] lr: 3.5229e-04 eta: 5:19:38 time: 0.8804 data_time: 0.0030 memory: 11981 loss: 0.0346 loss_ce: 0.0346 2022/12/15 01:04:52 - mmengine - INFO - Epoch(train) [2][1450/3952] lr: 3.5143e-04 eta: 5:18:27 time: 0.9001 data_time: 0.0031 memory: 11981 loss: 0.0344 loss_ce: 0.0344 2022/12/15 01:05:38 - mmengine - INFO - Epoch(train) [2][1500/3952] lr: 3.5057e-04 eta: 5:17:16 time: 0.9138 data_time: 0.0033 memory: 11981 loss: 0.0324 loss_ce: 0.0324 2022/12/15 01:06:24 - mmengine - INFO - Epoch(train) [2][1550/3952] lr: 3.4970e-04 eta: 5:16:02 time: 0.8716 data_time: 0.0037 memory: 11981 loss: 0.0331 loss_ce: 0.0331 2022/12/15 01:07:10 - mmengine - INFO - Epoch(train) [2][1600/3952] lr: 3.4882e-04 eta: 5:14:50 time: 0.8950 data_time: 0.0038 memory: 11981 loss: 0.0337 loss_ce: 0.0337 2022/12/15 01:07:57 - mmengine - INFO - Epoch(train) [2][1650/3952] lr: 3.4794e-04 eta: 5:13:41 time: 0.9794 data_time: 0.0032 memory: 11981 loss: 0.0345 loss_ce: 0.0345 2022/12/15 01:08:44 - mmengine - INFO - Epoch(train) [2][1700/3952] lr: 3.4705e-04 eta: 5:12:33 time: 0.9785 data_time: 0.0037 memory: 11981 loss: 0.0320 loss_ce: 0.0320 2022/12/15 01:09:30 - mmengine - INFO - Epoch(train) [2][1750/3952] lr: 3.4615e-04 eta: 5:11:23 time: 0.9061 data_time: 0.0050 memory: 11981 loss: 0.0336 loss_ce: 0.0336 2022/12/15 01:10:16 - mmengine - INFO - Epoch(train) [2][1800/3952] lr: 3.4525e-04 eta: 5:10:13 time: 0.8490 data_time: 0.0037 memory: 11981 loss: 0.0310 loss_ce: 0.0310 2022/12/15 01:11:01 - mmengine - INFO - Epoch(train) [2][1850/3952] lr: 3.4434e-04 eta: 5:09:01 time: 0.9206 data_time: 0.0032 memory: 11981 loss: 0.0333 loss_ce: 0.0333 2022/12/15 01:11:48 - mmengine - INFO - Epoch(train) [2][1900/3952] lr: 3.4343e-04 eta: 5:07:55 time: 0.9593 data_time: 0.0031 memory: 11981 loss: 0.0324 loss_ce: 0.0324 2022/12/15 01:12:35 - mmengine - INFO - Epoch(train) [2][1950/3952] lr: 3.4251e-04 eta: 5:06:50 time: 0.9361 data_time: 0.0032 memory: 11981 loss: 0.0320 loss_ce: 0.0320 2022/12/15 01:13:22 - mmengine - INFO - Epoch(train) [2][2000/3952] lr: 3.4158e-04 eta: 5:05:42 time: 0.9238 data_time: 0.0034 memory: 11981 loss: 0.0331 loss_ce: 0.0331 2022/12/15 01:14:05 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 01:14:07 - mmengine - INFO - Epoch(train) [2][2050/3952] lr: 3.4065e-04 eta: 5:04:33 time: 0.9491 data_time: 0.0038 memory: 11981 loss: 0.0332 loss_ce: 0.0332 2022/12/15 01:14:52 - mmengine - INFO - Epoch(train) [2][2100/3952] lr: 3.3971e-04 eta: 5:03:22 time: 0.9428 data_time: 0.0037 memory: 11981 loss: 0.0310 loss_ce: 0.0310 2022/12/15 01:15:37 - mmengine - INFO - Epoch(train) [2][2150/3952] lr: 3.3876e-04 eta: 5:02:11 time: 0.9088 data_time: 0.0030 memory: 11981 loss: 0.0320 loss_ce: 0.0320 2022/12/15 01:16:23 - mmengine - INFO - Epoch(train) [2][2200/3952] lr: 3.3781e-04 eta: 5:01:03 time: 0.8726 data_time: 0.0032 memory: 11981 loss: 0.0328 loss_ce: 0.0328 2022/12/15 01:17:08 - mmengine - INFO - Epoch(train) [2][2250/3952] lr: 3.3685e-04 eta: 4:59:54 time: 0.9040 data_time: 0.0033 memory: 11981 loss: 0.0320 loss_ce: 0.0320 2022/12/15 01:17:54 - mmengine - INFO - Epoch(train) [2][2300/3952] lr: 3.3589e-04 eta: 4:58:46 time: 0.8961 data_time: 0.0032 memory: 11981 loss: 0.0335 loss_ce: 0.0335 2022/12/15 01:18:40 - mmengine - INFO - Epoch(train) [2][2350/3952] lr: 3.3492e-04 eta: 4:57:40 time: 0.9579 data_time: 0.0032 memory: 11981 loss: 0.0308 loss_ce: 0.0308 2022/12/15 01:19:25 - mmengine - INFO - Epoch(train) [2][2400/3952] lr: 3.3395e-04 eta: 4:56:34 time: 0.9428 data_time: 0.0031 memory: 11981 loss: 0.0336 loss_ce: 0.0336 2022/12/15 01:20:12 - mmengine - INFO - Epoch(train) [2][2450/3952] lr: 3.3296e-04 eta: 4:55:29 time: 0.8852 data_time: 0.0031 memory: 11981 loss: 0.0337 loss_ce: 0.0337 2022/12/15 01:20:58 - mmengine - INFO - Epoch(train) [2][2500/3952] lr: 3.3198e-04 eta: 4:54:24 time: 0.9379 data_time: 0.0033 memory: 11981 loss: 0.0309 loss_ce: 0.0309 2022/12/15 01:21:43 - mmengine - INFO - Epoch(train) [2][2550/3952] lr: 3.3099e-04 eta: 4:53:18 time: 0.9076 data_time: 0.0035 memory: 11981 loss: 0.0313 loss_ce: 0.0313 2022/12/15 01:22:29 - mmengine - INFO - Epoch(train) [2][2600/3952] lr: 3.2999e-04 eta: 4:52:13 time: 0.8819 data_time: 0.0034 memory: 11981 loss: 0.0305 loss_ce: 0.0305 2022/12/15 01:23:15 - mmengine - INFO - Epoch(train) [2][2650/3952] lr: 3.2898e-04 eta: 4:51:08 time: 0.9386 data_time: 0.0040 memory: 11981 loss: 0.0306 loss_ce: 0.0306 2022/12/15 01:24:03 - mmengine - INFO - Epoch(train) [2][2700/3952] lr: 3.2797e-04 eta: 4:50:09 time: 0.9444 data_time: 0.0031 memory: 11981 loss: 0.0309 loss_ce: 0.0309 2022/12/15 01:24:49 - mmengine - INFO - Epoch(train) [2][2750/3952] lr: 3.2696e-04 eta: 4:49:06 time: 0.9354 data_time: 0.0032 memory: 11981 loss: 0.0318 loss_ce: 0.0318 2022/12/15 01:25:35 - mmengine - INFO - Epoch(train) [2][2800/3952] lr: 3.2594e-04 eta: 4:48:02 time: 0.8951 data_time: 0.0035 memory: 11981 loss: 0.0309 loss_ce: 0.0309 2022/12/15 01:26:21 - mmengine - INFO - Epoch(train) [2][2850/3952] lr: 3.2491e-04 eta: 4:46:59 time: 0.9368 data_time: 0.0052 memory: 11981 loss: 0.0318 loss_ce: 0.0318 2022/12/15 01:27:07 - mmengine - INFO - Epoch(train) [2][2900/3952] lr: 3.2388e-04 eta: 4:45:56 time: 0.9593 data_time: 0.0046 memory: 11981 loss: 0.0307 loss_ce: 0.0307 2022/12/15 01:27:53 - mmengine - INFO - Epoch(train) [2][2950/3952] lr: 3.2285e-04 eta: 4:44:53 time: 0.9356 data_time: 0.0035 memory: 11981 loss: 0.0309 loss_ce: 0.0309 2022/12/15 01:28:39 - mmengine - INFO - Epoch(train) [2][3000/3952] lr: 3.2181e-04 eta: 4:43:50 time: 0.9104 data_time: 0.0033 memory: 11981 loss: 0.0307 loss_ce: 0.0307 2022/12/15 01:29:24 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 01:29:26 - mmengine - INFO - Epoch(train) [2][3050/3952] lr: 3.2076e-04 eta: 4:42:51 time: 0.9728 data_time: 0.0033 memory: 11981 loss: 0.0303 loss_ce: 0.0303 2022/12/15 01:30:14 - mmengine - INFO - Epoch(train) [2][3100/3952] lr: 3.1971e-04 eta: 4:41:53 time: 0.9233 data_time: 0.0038 memory: 11981 loss: 0.0321 loss_ce: 0.0321 2022/12/15 01:31:01 - mmengine - INFO - Epoch(train) [2][3150/3952] lr: 3.1865e-04 eta: 4:40:55 time: 0.9698 data_time: 0.0034 memory: 11981 loss: 0.0299 loss_ce: 0.0299 2022/12/15 01:31:49 - mmengine - INFO - Epoch(train) [2][3200/3952] lr: 3.1759e-04 eta: 4:39:56 time: 0.9943 data_time: 0.0041 memory: 11981 loss: 0.0303 loss_ce: 0.0303 2022/12/15 01:32:36 - mmengine - INFO - Epoch(train) [2][3250/3952] lr: 3.1652e-04 eta: 4:38:58 time: 0.9421 data_time: 0.0050 memory: 11981 loss: 0.0329 loss_ce: 0.0329 2022/12/15 01:33:22 - mmengine - INFO - Epoch(train) [2][3300/3952] lr: 3.1545e-04 eta: 4:37:57 time: 0.9183 data_time: 0.0033 memory: 11981 loss: 0.0316 loss_ce: 0.0316 2022/12/15 01:34:09 - mmengine - INFO - Epoch(train) [2][3350/3952] lr: 3.1437e-04 eta: 4:36:56 time: 0.9340 data_time: 0.0030 memory: 11981 loss: 0.0284 loss_ce: 0.0284 2022/12/15 01:34:55 - mmengine - INFO - Epoch(train) [2][3400/3952] lr: 3.1329e-04 eta: 4:35:57 time: 0.9548 data_time: 0.0034 memory: 11981 loss: 0.0294 loss_ce: 0.0294 2022/12/15 01:35:40 - mmengine - INFO - Epoch(train) [2][3450/3952] lr: 3.1220e-04 eta: 4:34:54 time: 0.9493 data_time: 0.0051 memory: 11981 loss: 0.0292 loss_ce: 0.0292 2022/12/15 01:36:26 - mmengine - INFO - Epoch(train) [2][3500/3952] lr: 3.1111e-04 eta: 4:33:52 time: 0.8448 data_time: 0.0045 memory: 11981 loss: 0.0294 loss_ce: 0.0294 2022/12/15 01:37:11 - mmengine - INFO - Epoch(train) [2][3550/3952] lr: 3.1001e-04 eta: 4:32:50 time: 0.8907 data_time: 0.0051 memory: 11981 loss: 0.0277 loss_ce: 0.0277 2022/12/15 01:37:55 - mmengine - INFO - Epoch(train) [2][3600/3952] lr: 3.0891e-04 eta: 4:31:47 time: 0.8547 data_time: 0.0033 memory: 11981 loss: 0.0277 loss_ce: 0.0277 2022/12/15 01:38:40 - mmengine - INFO - Epoch(train) [2][3650/3952] lr: 3.0780e-04 eta: 4:30:44 time: 0.8687 data_time: 0.0031 memory: 11981 loss: 0.0281 loss_ce: 0.0281 2022/12/15 01:39:25 - mmengine - INFO - Epoch(train) [2][3700/3952] lr: 3.0669e-04 eta: 4:29:43 time: 0.9013 data_time: 0.0036 memory: 11981 loss: 0.0291 loss_ce: 0.0291 2022/12/15 01:40:10 - mmengine - INFO - Epoch(train) [2][3750/3952] lr: 3.0558e-04 eta: 4:28:40 time: 0.9052 data_time: 0.0033 memory: 11981 loss: 0.0311 loss_ce: 0.0311 2022/12/15 01:40:55 - mmengine - INFO - Epoch(train) [2][3800/3952] lr: 3.0446e-04 eta: 4:27:40 time: 0.9710 data_time: 0.0038 memory: 11981 loss: 0.0299 loss_ce: 0.0299 2022/12/15 01:41:41 - mmengine - INFO - Epoch(train) [2][3850/3952] lr: 3.0333e-04 eta: 4:26:40 time: 0.9133 data_time: 0.0037 memory: 11981 loss: 0.0267 loss_ce: 0.0267 2022/12/15 01:42:28 - mmengine - INFO - Epoch(train) [2][3900/3952] lr: 3.0220e-04 eta: 4:25:43 time: 0.9587 data_time: 0.0035 memory: 11981 loss: 0.0276 loss_ce: 0.0276 2022/12/15 01:42:59 - mmengine - INFO - Epoch(train) [2][3950/3952] lr: 3.0107e-04 eta: 4:24:14 time: 0.5852 data_time: 0.0035 memory: 11981 loss: 0.0298 loss_ce: 0.0298 2022/12/15 01:43:00 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 01:43:00 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/15 01:43:05 - mmengine - INFO - Epoch(val) [2][ 50/1918] eta: 0:01:52 time: 0.0594 data_time: 0.0001 memory: 11981 2022/12/15 01:43:08 - mmengine - INFO - Epoch(val) [2][ 100/1918] eta: 0:01:40 time: 0.0461 data_time: 0.0001 memory: 453 2022/12/15 01:43:10 - mmengine - INFO - Epoch(val) [2][ 150/1918] eta: 0:01:33 time: 0.0544 data_time: 0.0001 memory: 453 2022/12/15 01:43:13 - mmengine - INFO - Epoch(val) [2][ 200/1918] eta: 0:01:32 time: 0.0526 data_time: 0.0047 memory: 453 2022/12/15 01:43:16 - mmengine - INFO - Epoch(val) [2][ 250/1918] eta: 0:01:28 time: 0.0496 data_time: 0.0049 memory: 453 2022/12/15 01:43:18 - mmengine - INFO - Epoch(val) [2][ 300/1918] eta: 0:01:24 time: 0.0463 data_time: 0.0041 memory: 453 2022/12/15 01:43:21 - mmengine - INFO - Epoch(val) [2][ 350/1918] eta: 0:01:21 time: 0.0625 data_time: 0.0026 memory: 453 2022/12/15 01:43:24 - mmengine - INFO - Epoch(val) [2][ 400/1918] eta: 0:01:20 time: 0.0559 data_time: 0.0009 memory: 453 2022/12/15 01:43:26 - mmengine - INFO - Epoch(val) [2][ 450/1918] eta: 0:01:18 time: 0.0619 data_time: 0.0027 memory: 453 2022/12/15 01:43:29 - mmengine - INFO - Epoch(val) [2][ 500/1918] eta: 0:01:15 time: 0.0501 data_time: 0.0013 memory: 453 2022/12/15 01:43:32 - mmengine - INFO - Epoch(val) [2][ 550/1918] eta: 0:01:13 time: 0.0708 data_time: 0.0002 memory: 453 2022/12/15 01:43:35 - mmengine - INFO - Epoch(val) [2][ 600/1918] eta: 0:01:11 time: 0.0521 data_time: 0.0007 memory: 453 2022/12/15 01:43:37 - mmengine - INFO - Epoch(val) [2][ 650/1918] eta: 0:01:08 time: 0.0500 data_time: 0.0001 memory: 453 2022/12/15 01:43:40 - mmengine - INFO - Epoch(val) [2][ 700/1918] eta: 0:01:05 time: 0.0486 data_time: 0.0001 memory: 453 2022/12/15 01:43:42 - mmengine - INFO - Epoch(val) [2][ 750/1918] eta: 0:01:02 time: 0.0476 data_time: 0.0002 memory: 453 2022/12/15 01:43:45 - mmengine - INFO - Epoch(val) [2][ 800/1918] eta: 0:00:59 time: 0.0481 data_time: 0.0002 memory: 453 2022/12/15 01:43:47 - mmengine - INFO - Epoch(val) [2][ 850/1918] eta: 0:00:56 time: 0.0493 data_time: 0.0002 memory: 453 2022/12/15 01:43:50 - mmengine - INFO - Epoch(val) [2][ 900/1918] eta: 0:00:53 time: 0.0490 data_time: 0.0013 memory: 453 2022/12/15 01:43:52 - mmengine - INFO - Epoch(val) [2][ 950/1918] eta: 0:00:50 time: 0.0471 data_time: 0.0011 memory: 453 2022/12/15 01:43:54 - mmengine - INFO - Epoch(val) [2][1000/1918] eta: 0:00:47 time: 0.0476 data_time: 0.0018 memory: 453 2022/12/15 01:43:57 - mmengine - INFO - Epoch(val) [2][1050/1918] eta: 0:00:45 time: 0.0595 data_time: 0.0007 memory: 453 2022/12/15 01:44:00 - mmengine - INFO - Epoch(val) [2][1100/1918] eta: 0:00:42 time: 0.0507 data_time: 0.0008 memory: 453 2022/12/15 01:44:02 - mmengine - INFO - Epoch(val) [2][1150/1918] eta: 0:00:39 time: 0.0493 data_time: 0.0020 memory: 453 2022/12/15 01:44:05 - mmengine - INFO - Epoch(val) [2][1200/1918] eta: 0:00:37 time: 0.0587 data_time: 0.0025 memory: 453 2022/12/15 01:44:08 - mmengine - INFO - Epoch(val) [2][1250/1918] eta: 0:00:35 time: 0.0608 data_time: 0.0001 memory: 453 2022/12/15 01:44:11 - mmengine - INFO - Epoch(val) [2][1300/1918] eta: 0:00:32 time: 0.0491 data_time: 0.0001 memory: 453 2022/12/15 01:44:13 - mmengine - INFO - Epoch(val) [2][1350/1918] eta: 0:00:29 time: 0.0473 data_time: 0.0012 memory: 453 2022/12/15 01:44:16 - mmengine - INFO - Epoch(val) [2][1400/1918] eta: 0:00:27 time: 0.0483 data_time: 0.0028 memory: 453 2022/12/15 01:44:18 - mmengine - INFO - Epoch(val) [2][1450/1918] eta: 0:00:24 time: 0.0470 data_time: 0.0035 memory: 453 2022/12/15 01:44:20 - mmengine - INFO - Epoch(val) [2][1500/1918] eta: 0:00:21 time: 0.0475 data_time: 0.0042 memory: 453 2022/12/15 01:44:23 - mmengine - INFO - Epoch(val) [2][1550/1918] eta: 0:00:19 time: 0.0492 data_time: 0.0033 memory: 453 2022/12/15 01:44:25 - mmengine - INFO - Epoch(val) [2][1600/1918] eta: 0:00:16 time: 0.0502 data_time: 0.0043 memory: 453 2022/12/15 01:44:28 - mmengine - INFO - Epoch(val) [2][1650/1918] eta: 0:00:13 time: 0.0509 data_time: 0.0049 memory: 453 2022/12/15 01:44:30 - mmengine - INFO - Epoch(val) [2][1700/1918] eta: 0:00:11 time: 0.0376 data_time: 0.0005 memory: 453 2022/12/15 01:44:32 - mmengine - INFO - Epoch(val) [2][1750/1918] eta: 0:00:08 time: 0.0345 data_time: 0.0015 memory: 453 2022/12/15 01:44:34 - mmengine - INFO - Epoch(val) [2][1800/1918] eta: 0:00:05 time: 0.0211 data_time: 0.0001 memory: 453 2022/12/15 01:44:35 - mmengine - INFO - Epoch(val) [2][1850/1918] eta: 0:00:03 time: 0.0227 data_time: 0.0001 memory: 453 2022/12/15 01:44:36 - mmengine - INFO - Epoch(val) [2][1900/1918] eta: 0:00:00 time: 0.0225 data_time: 0.0002 memory: 453 2022/12/15 01:44:36 - mmengine - INFO - Epoch(val) [2][1918/1918] CUTE80/recog/word_acc: 0.6597 CUTE80/recog/word_acc_ignore_case: 0.7917 CUTE80/recog/word_acc_ignore_case_symbol: 0.8021 IIIT5K/recog/word_acc: 0.3717 IIIT5K/recog/word_acc_ignore_case: 0.8073 IIIT5K/recog/word_acc_ignore_case_symbol: 0.9050 SVT/recog/word_acc: 0.1453 SVT/recog/word_acc_ignore_case: 0.8176 SVT/recog/word_acc_ignore_case_symbol: 0.8485 SVTP/recog/word_acc: 0.3442 SVTP/recog/word_acc_ignore_case: 0.7364 SVTP/recog/word_acc_ignore_case_symbol: 0.7488 IC13/recog/word_acc: 0.8079 IC13/recog/word_acc_ignore_case: 0.8847 IC13/recog/word_acc_ignore_case_symbol: 0.8956 IC15/recog/word_acc: 0.5267 IC15/recog/word_acc_ignore_case: 0.6813 IC15/recog/word_acc_ignore_case_symbol: 0.7159 CUTE80/recog/char_recall: 0.8858 CUTE80/recog/char_precision: 0.9104 IIIT5K/recog/char_recall: 0.9668 IIIT5K/recog/char_precision: 0.9650 SVT/recog/char_recall: 0.9460 SVT/recog/char_precision: 0.9540 SVTP/recog/char_recall: 0.8960 SVTP/recog/char_precision: 0.9283 IC13/recog/char_recall: 0.9694 IC13/recog/char_precision: 0.9674 IC15/recog/char_recall: 0.8783 IC15/recog/char_precision: 0.8979 2022/12/15 01:45:38 - mmengine - INFO - Epoch(train) [3][ 50/3952] lr: 2.9988e-04 eta: 4:23:43 time: 0.9268 data_time: 0.0041 memory: 11981 loss: 0.0269 loss_ce: 0.0269 2022/12/15 01:46:19 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 01:46:23 - mmengine - INFO - Epoch(train) [3][ 100/3952] lr: 2.9874e-04 eta: 4:22:42 time: 0.8864 data_time: 0.0036 memory: 11981 loss: 0.0273 loss_ce: 0.0273 2022/12/15 01:47:08 - mmengine - INFO - Epoch(train) [3][ 150/3952] lr: 2.9760e-04 eta: 4:21:43 time: 0.9093 data_time: 0.0030 memory: 11981 loss: 0.0294 loss_ce: 0.0294 2022/12/15 01:47:53 - mmengine - INFO - Epoch(train) [3][ 200/3952] lr: 2.9645e-04 eta: 4:20:41 time: 0.8840 data_time: 0.0031 memory: 11981 loss: 0.0287 loss_ce: 0.0287 2022/12/15 01:48:38 - mmengine - INFO - Epoch(train) [3][ 250/3952] lr: 2.9529e-04 eta: 4:19:42 time: 0.8957 data_time: 0.0034 memory: 11981 loss: 0.0274 loss_ce: 0.0274 2022/12/15 01:49:23 - mmengine - INFO - Epoch(train) [3][ 300/3952] lr: 2.9413e-04 eta: 4:18:43 time: 0.9019 data_time: 0.0035 memory: 11981 loss: 0.0284 loss_ce: 0.0284 2022/12/15 01:50:09 - mmengine - INFO - Epoch(train) [3][ 350/3952] lr: 2.9297e-04 eta: 4:17:45 time: 0.8742 data_time: 0.0047 memory: 11981 loss: 0.0256 loss_ce: 0.0256 2022/12/15 01:50:54 - mmengine - INFO - Epoch(train) [3][ 400/3952] lr: 2.9180e-04 eta: 4:16:46 time: 0.8837 data_time: 0.0053 memory: 11981 loss: 0.0287 loss_ce: 0.0287 2022/12/15 01:51:41 - mmengine - INFO - Epoch(train) [3][ 450/3952] lr: 2.9063e-04 eta: 4:15:50 time: 0.9634 data_time: 0.0033 memory: 11981 loss: 0.0269 loss_ce: 0.0269 2022/12/15 01:52:28 - mmengine - INFO - Epoch(train) [3][ 500/3952] lr: 2.8946e-04 eta: 4:14:55 time: 0.9801 data_time: 0.0035 memory: 11981 loss: 0.0261 loss_ce: 0.0261 2022/12/15 01:53:15 - mmengine - INFO - Epoch(train) [3][ 550/3952] lr: 2.8828e-04 eta: 4:14:00 time: 1.0026 data_time: 0.0045 memory: 11981 loss: 0.0263 loss_ce: 0.0263 2022/12/15 01:54:01 - mmengine - INFO - Epoch(train) [3][ 600/3952] lr: 2.8709e-04 eta: 4:13:02 time: 0.9048 data_time: 0.0046 memory: 11981 loss: 0.0261 loss_ce: 0.0261 2022/12/15 01:54:46 - mmengine - INFO - Epoch(train) [3][ 650/3952] lr: 2.8591e-04 eta: 4:12:04 time: 0.8719 data_time: 0.0049 memory: 11981 loss: 0.0263 loss_ce: 0.0263 2022/12/15 01:55:30 - mmengine - INFO - Epoch(train) [3][ 700/3952] lr: 2.8472e-04 eta: 4:11:04 time: 0.8842 data_time: 0.0037 memory: 11981 loss: 0.0287 loss_ce: 0.0287 2022/12/15 01:56:16 - mmengine - INFO - Epoch(train) [3][ 750/3952] lr: 2.8352e-04 eta: 4:10:08 time: 1.0044 data_time: 0.0035 memory: 11981 loss: 0.0272 loss_ce: 0.0272 2022/12/15 01:57:02 - mmengine - INFO - Epoch(train) [3][ 800/3952] lr: 2.8233e-04 eta: 4:09:11 time: 0.9849 data_time: 0.0034 memory: 11981 loss: 0.0270 loss_ce: 0.0270 2022/12/15 01:57:48 - mmengine - INFO - Epoch(train) [3][ 850/3952] lr: 2.8113e-04 eta: 4:08:14 time: 0.9271 data_time: 0.0036 memory: 11981 loss: 0.0270 loss_ce: 0.0270 2022/12/15 01:58:33 - mmengine - INFO - Epoch(train) [3][ 900/3952] lr: 2.7992e-04 eta: 4:07:16 time: 0.9228 data_time: 0.0034 memory: 11981 loss: 0.0255 loss_ce: 0.0255 2022/12/15 01:59:18 - mmengine - INFO - Epoch(train) [3][ 950/3952] lr: 2.7872e-04 eta: 4:06:18 time: 0.9192 data_time: 0.0045 memory: 11981 loss: 0.0261 loss_ce: 0.0261 2022/12/15 02:00:03 - mmengine - INFO - Epoch(train) [3][1000/3952] lr: 2.7750e-04 eta: 4:05:21 time: 0.8836 data_time: 0.0035 memory: 11981 loss: 0.0274 loss_ce: 0.0274 2022/12/15 02:00:49 - mmengine - INFO - Epoch(train) [3][1050/3952] lr: 2.7629e-04 eta: 4:04:26 time: 0.9082 data_time: 0.0034 memory: 11981 loss: 0.0270 loss_ce: 0.0270 2022/12/15 02:01:33 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 02:01:36 - mmengine - INFO - Epoch(train) [3][1100/3952] lr: 2.7507e-04 eta: 4:03:31 time: 0.9379 data_time: 0.0038 memory: 11981 loss: 0.0269 loss_ce: 0.0269 2022/12/15 02:02:21 - mmengine - INFO - Epoch(train) [3][1150/3952] lr: 2.7385e-04 eta: 4:02:35 time: 0.8720 data_time: 0.0045 memory: 11981 loss: 0.0256 loss_ce: 0.0256 2022/12/15 02:03:08 - mmengine - INFO - Epoch(train) [3][1200/3952] lr: 2.7263e-04 eta: 4:01:39 time: 0.8952 data_time: 0.0040 memory: 11981 loss: 0.0273 loss_ce: 0.0273 2022/12/15 02:03:54 - mmengine - INFO - Epoch(train) [3][1250/3952] lr: 2.7140e-04 eta: 4:00:45 time: 0.9354 data_time: 0.0034 memory: 11981 loss: 0.0268 loss_ce: 0.0268 2022/12/15 02:04:41 - mmengine - INFO - Epoch(train) [3][1300/3952] lr: 2.7017e-04 eta: 3:59:51 time: 0.8821 data_time: 0.0039 memory: 11981 loss: 0.0255 loss_ce: 0.0255 2022/12/15 02:05:27 - mmengine - INFO - Epoch(train) [3][1350/3952] lr: 2.6894e-04 eta: 3:58:56 time: 0.8987 data_time: 0.0033 memory: 11981 loss: 0.0261 loss_ce: 0.0261 2022/12/15 02:06:13 - mmengine - INFO - Epoch(train) [3][1400/3952] lr: 2.6770e-04 eta: 3:58:01 time: 0.9310 data_time: 0.0039 memory: 11981 loss: 0.0250 loss_ce: 0.0250 2022/12/15 02:07:00 - mmengine - INFO - Epoch(train) [3][1450/3952] lr: 2.6646e-04 eta: 3:57:06 time: 0.9484 data_time: 0.0036 memory: 11981 loss: 0.0253 loss_ce: 0.0253 2022/12/15 02:07:46 - mmengine - INFO - Epoch(train) [3][1500/3952] lr: 2.6522e-04 eta: 3:56:12 time: 0.9172 data_time: 0.0046 memory: 11981 loss: 0.0245 loss_ce: 0.0245 2022/12/15 02:08:31 - mmengine - INFO - Epoch(train) [3][1550/3952] lr: 2.6398e-04 eta: 3:55:16 time: 0.8748 data_time: 0.0041 memory: 11981 loss: 0.0249 loss_ce: 0.0249 2022/12/15 02:09:18 - mmengine - INFO - Epoch(train) [3][1600/3952] lr: 2.6273e-04 eta: 3:54:22 time: 0.9061 data_time: 0.0036 memory: 11981 loss: 0.0264 loss_ce: 0.0264 2022/12/15 02:10:04 - mmengine - INFO - Epoch(train) [3][1650/3952] lr: 2.6148e-04 eta: 3:53:27 time: 0.9147 data_time: 0.0039 memory: 11981 loss: 0.0255 loss_ce: 0.0255 2022/12/15 02:10:49 - mmengine - INFO - Epoch(train) [3][1700/3952] lr: 2.6023e-04 eta: 3:52:32 time: 0.9195 data_time: 0.0033 memory: 11981 loss: 0.0275 loss_ce: 0.0275 2022/12/15 02:11:35 - mmengine - INFO - Epoch(train) [3][1750/3952] lr: 2.5897e-04 eta: 3:51:38 time: 0.9401 data_time: 0.0052 memory: 11981 loss: 0.0263 loss_ce: 0.0263 2022/12/15 02:12:22 - mmengine - INFO - Epoch(train) [3][1800/3952] lr: 2.5772e-04 eta: 3:50:44 time: 0.9632 data_time: 0.0037 memory: 11981 loss: 0.0257 loss_ce: 0.0257 2022/12/15 02:13:09 - mmengine - INFO - Epoch(train) [3][1850/3952] lr: 2.5646e-04 eta: 3:49:51 time: 0.9156 data_time: 0.0035 memory: 11981 loss: 0.0278 loss_ce: 0.0278 2022/12/15 02:13:55 - mmengine - INFO - Epoch(train) [3][1900/3952] lr: 2.5519e-04 eta: 3:48:57 time: 0.8748 data_time: 0.0033 memory: 11981 loss: 0.0252 loss_ce: 0.0252 2022/12/15 02:14:40 - mmengine - INFO - Epoch(train) [3][1950/3952] lr: 2.5393e-04 eta: 3:48:02 time: 0.8936 data_time: 0.0034 memory: 11981 loss: 0.0253 loss_ce: 0.0253 2022/12/15 02:15:27 - mmengine - INFO - Epoch(train) [3][2000/3952] lr: 2.5266e-04 eta: 3:47:08 time: 0.9562 data_time: 0.0033 memory: 11981 loss: 0.0252 loss_ce: 0.0252 2022/12/15 02:16:10 - mmengine - INFO - Epoch(train) [3][2050/3952] lr: 2.5139e-04 eta: 3:46:11 time: 0.8933 data_time: 0.0035 memory: 11981 loss: 0.0250 loss_ce: 0.0250 2022/12/15 02:16:51 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 02:16:55 - mmengine - INFO - Epoch(train) [3][2100/3952] lr: 2.5012e-04 eta: 3:45:15 time: 0.8501 data_time: 0.0035 memory: 11981 loss: 0.0260 loss_ce: 0.0260 2022/12/15 02:17:41 - mmengine - INFO - Epoch(train) [3][2150/3952] lr: 2.4885e-04 eta: 3:44:21 time: 0.9305 data_time: 0.0037 memory: 11981 loss: 0.0255 loss_ce: 0.0255 2022/12/15 02:18:26 - mmengine - INFO - Epoch(train) [3][2200/3952] lr: 2.4757e-04 eta: 3:43:26 time: 0.9194 data_time: 0.0036 memory: 11981 loss: 0.0264 loss_ce: 0.0264 2022/12/15 02:19:10 - mmengine - INFO - Epoch(train) [3][2250/3952] lr: 2.4630e-04 eta: 3:42:31 time: 0.9047 data_time: 0.0034 memory: 11981 loss: 0.0243 loss_ce: 0.0243 2022/12/15 02:19:56 - mmengine - INFO - Epoch(train) [3][2300/3952] lr: 2.4502e-04 eta: 3:41:37 time: 0.9020 data_time: 0.0036 memory: 11981 loss: 0.0243 loss_ce: 0.0243 2022/12/15 02:20:43 - mmengine - INFO - Epoch(train) [3][2350/3952] lr: 2.4374e-04 eta: 3:40:44 time: 0.9600 data_time: 0.0032 memory: 11981 loss: 0.0254 loss_ce: 0.0254 2022/12/15 02:21:27 - mmengine - INFO - Epoch(train) [3][2400/3952] lr: 2.4245e-04 eta: 3:39:49 time: 0.9370 data_time: 0.0031 memory: 11981 loss: 0.0241 loss_ce: 0.0241 2022/12/15 02:22:16 - mmengine - INFO - Epoch(train) [3][2450/3952] lr: 2.4117e-04 eta: 3:38:59 time: 0.9248 data_time: 0.0033 memory: 11981 loss: 0.0231 loss_ce: 0.0231 2022/12/15 02:23:04 - mmengine - INFO - Epoch(train) [3][2500/3952] lr: 2.3988e-04 eta: 3:38:08 time: 0.9796 data_time: 0.0034 memory: 11981 loss: 0.0247 loss_ce: 0.0247 2022/12/15 02:23:49 - mmengine - INFO - Epoch(train) [3][2550/3952] lr: 2.3859e-04 eta: 3:37:14 time: 0.9158 data_time: 0.0034 memory: 11981 loss: 0.0253 loss_ce: 0.0253 2022/12/15 02:24:35 - mmengine - INFO - Epoch(train) [3][2600/3952] lr: 2.3730e-04 eta: 3:36:21 time: 0.9530 data_time: 0.0033 memory: 11981 loss: 0.0259 loss_ce: 0.0259 2022/12/15 02:25:23 - mmengine - INFO - Epoch(train) [3][2650/3952] lr: 2.3601e-04 eta: 3:35:30 time: 0.9438 data_time: 0.0037 memory: 11981 loss: 0.0269 loss_ce: 0.0269 2022/12/15 02:26:09 - mmengine - INFO - Epoch(train) [3][2700/3952] lr: 2.3472e-04 eta: 3:34:37 time: 0.9298 data_time: 0.0032 memory: 11981 loss: 0.0245 loss_ce: 0.0245 2022/12/15 02:26:54 - mmengine - INFO - Epoch(train) [3][2750/3952] lr: 2.3342e-04 eta: 3:33:43 time: 0.8965 data_time: 0.0032 memory: 11981 loss: 0.0258 loss_ce: 0.0258 2022/12/15 02:27:41 - mmengine - INFO - Epoch(train) [3][2800/3952] lr: 2.3213e-04 eta: 3:32:51 time: 0.9225 data_time: 0.0040 memory: 11981 loss: 0.0249 loss_ce: 0.0249 2022/12/15 02:28:27 - mmengine - INFO - Epoch(train) [3][2850/3952] lr: 2.3083e-04 eta: 3:31:58 time: 0.8295 data_time: 0.0035 memory: 11981 loss: 0.0230 loss_ce: 0.0230 2022/12/15 02:29:14 - mmengine - INFO - Epoch(train) [3][2900/3952] lr: 2.2953e-04 eta: 3:31:07 time: 0.8901 data_time: 0.0040 memory: 11981 loss: 0.0222 loss_ce: 0.0222 2022/12/15 02:29:58 - mmengine - INFO - Epoch(train) [3][2950/3952] lr: 2.2823e-04 eta: 3:30:13 time: 0.9231 data_time: 0.0037 memory: 11981 loss: 0.0252 loss_ce: 0.0252 2022/12/15 02:30:45 - mmengine - INFO - Epoch(train) [3][3000/3952] lr: 2.2693e-04 eta: 3:29:20 time: 0.9454 data_time: 0.0040 memory: 11981 loss: 0.0238 loss_ce: 0.0238 2022/12/15 02:31:31 - mmengine - INFO - Epoch(train) [3][3050/3952] lr: 2.2563e-04 eta: 3:28:28 time: 0.9132 data_time: 0.0033 memory: 11981 loss: 0.0244 loss_ce: 0.0244 2022/12/15 02:32:13 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 02:32:17 - mmengine - INFO - Epoch(train) [3][3100/3952] lr: 2.2433e-04 eta: 3:27:35 time: 0.9486 data_time: 0.0036 memory: 11981 loss: 0.0252 loss_ce: 0.0252 2022/12/15 02:33:03 - mmengine - INFO - Epoch(train) [3][3150/3952] lr: 2.2303e-04 eta: 3:26:43 time: 0.8995 data_time: 0.0034 memory: 11981 loss: 0.0245 loss_ce: 0.0245 2022/12/15 02:33:49 - mmengine - INFO - Epoch(train) [3][3200/3952] lr: 2.2172e-04 eta: 3:25:51 time: 0.8621 data_time: 0.0040 memory: 11981 loss: 0.0249 loss_ce: 0.0249 2022/12/15 02:34:36 - mmengine - INFO - Epoch(train) [3][3250/3952] lr: 2.2042e-04 eta: 3:24:59 time: 0.9366 data_time: 0.0032 memory: 11981 loss: 0.0239 loss_ce: 0.0239 2022/12/15 02:35:22 - mmengine - INFO - Epoch(train) [3][3300/3952] lr: 2.1911e-04 eta: 3:24:08 time: 0.9688 data_time: 0.0033 memory: 11981 loss: 0.0234 loss_ce: 0.0234 2022/12/15 02:36:08 - mmengine - INFO - Epoch(train) [3][3350/3952] lr: 2.1780e-04 eta: 3:23:15 time: 0.8739 data_time: 0.0030 memory: 11981 loss: 0.0246 loss_ce: 0.0246 2022/12/15 02:36:54 - mmengine - INFO - Epoch(train) [3][3400/3952] lr: 2.1649e-04 eta: 3:22:23 time: 0.8803 data_time: 0.0032 memory: 11981 loss: 0.0237 loss_ce: 0.0237 2022/12/15 02:37:39 - mmengine - INFO - Epoch(train) [3][3450/3952] lr: 2.1519e-04 eta: 3:21:30 time: 0.9291 data_time: 0.0033 memory: 11981 loss: 0.0227 loss_ce: 0.0227 2022/12/15 02:38:25 - mmengine - INFO - Epoch(train) [3][3500/3952] lr: 2.1388e-04 eta: 3:20:37 time: 0.8867 data_time: 0.0038 memory: 11981 loss: 0.0232 loss_ce: 0.0232 2022/12/15 02:39:11 - mmengine - INFO - Epoch(train) [3][3550/3952] lr: 2.1257e-04 eta: 3:19:45 time: 0.9451 data_time: 0.0030 memory: 11981 loss: 0.0240 loss_ce: 0.0240 2022/12/15 02:39:57 - mmengine - INFO - Epoch(train) [3][3600/3952] lr: 2.1126e-04 eta: 3:18:54 time: 0.8986 data_time: 0.0038 memory: 11981 loss: 0.0239 loss_ce: 0.0239 2022/12/15 02:40:43 - mmengine - INFO - Epoch(train) [3][3650/3952] lr: 2.0995e-04 eta: 3:18:01 time: 0.9425 data_time: 0.0033 memory: 11981 loss: 0.0249 loss_ce: 0.0249 2022/12/15 02:41:29 - mmengine - INFO - Epoch(train) [3][3700/3952] lr: 2.0864e-04 eta: 3:17:09 time: 0.9401 data_time: 0.0039 memory: 11981 loss: 0.0227 loss_ce: 0.0227 2022/12/15 02:42:15 - mmengine - INFO - Epoch(train) [3][3750/3952] lr: 2.0732e-04 eta: 3:16:18 time: 0.8970 data_time: 0.0035 memory: 11981 loss: 0.0212 loss_ce: 0.0212 2022/12/15 02:43:01 - mmengine - INFO - Epoch(train) [3][3800/3952] lr: 2.0601e-04 eta: 3:15:26 time: 0.8959 data_time: 0.0033 memory: 11981 loss: 0.0242 loss_ce: 0.0242 2022/12/15 02:43:46 - mmengine - INFO - Epoch(train) [3][3850/3952] lr: 2.0470e-04 eta: 3:14:33 time: 0.8735 data_time: 0.0038 memory: 11981 loss: 0.0223 loss_ce: 0.0223 2022/12/15 02:44:31 - mmengine - INFO - Epoch(train) [3][3900/3952] lr: 2.0339e-04 eta: 3:13:41 time: 0.8898 data_time: 0.0033 memory: 11981 loss: 0.0244 loss_ce: 0.0244 2022/12/15 02:45:01 - mmengine - INFO - Epoch(train) [3][3950/3952] lr: 2.0208e-04 eta: 3:12:33 time: 0.5507 data_time: 0.0033 memory: 11981 loss: 0.0234 loss_ce: 0.0234 2022/12/15 02:45:02 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 02:45:02 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/12/15 02:45:07 - mmengine - INFO - Epoch(val) [3][ 50/1918] eta: 0:01:50 time: 0.0394 data_time: 0.0026 memory: 11981 2022/12/15 02:45:09 - mmengine - INFO - Epoch(val) [3][ 100/1918] eta: 0:01:26 time: 0.0325 data_time: 0.0006 memory: 453 2022/12/15 02:45:11 - mmengine - INFO - Epoch(val) [3][ 150/1918] eta: 0:01:17 time: 0.0400 data_time: 0.0013 memory: 453 2022/12/15 02:45:13 - mmengine - INFO - Epoch(val) [3][ 200/1918] eta: 0:01:12 time: 0.0438 data_time: 0.0015 memory: 453 2022/12/15 02:45:14 - mmengine - INFO - Epoch(val) [3][ 250/1918] eta: 0:01:08 time: 0.0358 data_time: 0.0007 memory: 453 2022/12/15 02:45:16 - mmengine - INFO - Epoch(val) [3][ 300/1918] eta: 0:01:05 time: 0.0466 data_time: 0.0010 memory: 453 2022/12/15 02:45:19 - mmengine - INFO - Epoch(val) [3][ 350/1918] eta: 0:01:05 time: 0.0526 data_time: 0.0015 memory: 453 2022/12/15 02:45:21 - mmengine - INFO - Epoch(val) [3][ 400/1918] eta: 0:01:04 time: 0.0494 data_time: 0.0028 memory: 453 2022/12/15 02:45:24 - mmengine - INFO - Epoch(val) [3][ 450/1918] eta: 0:01:03 time: 0.0486 data_time: 0.0032 memory: 453 2022/12/15 02:45:26 - mmengine - INFO - Epoch(val) [3][ 500/1918] eta: 0:01:02 time: 0.0493 data_time: 0.0032 memory: 453 2022/12/15 02:45:29 - mmengine - INFO - Epoch(val) [3][ 550/1918] eta: 0:01:00 time: 0.0488 data_time: 0.0040 memory: 453 2022/12/15 02:45:31 - mmengine - INFO - Epoch(val) [3][ 600/1918] eta: 0:00:58 time: 0.0498 data_time: 0.0047 memory: 453 2022/12/15 02:45:34 - mmengine - INFO - Epoch(val) [3][ 650/1918] eta: 0:00:57 time: 0.0487 data_time: 0.0025 memory: 453 2022/12/15 02:45:36 - mmengine - INFO - Epoch(val) [3][ 700/1918] eta: 0:00:55 time: 0.0508 data_time: 0.0042 memory: 453 2022/12/15 02:45:39 - mmengine - INFO - Epoch(val) [3][ 750/1918] eta: 0:00:53 time: 0.0477 data_time: 0.0031 memory: 453 2022/12/15 02:45:41 - mmengine - INFO - Epoch(val) [3][ 800/1918] eta: 0:00:51 time: 0.0500 data_time: 0.0040 memory: 453 2022/12/15 02:45:44 - mmengine - INFO - Epoch(val) [3][ 850/1918] eta: 0:00:49 time: 0.0536 data_time: 0.0001 memory: 453 2022/12/15 02:45:46 - mmengine - INFO - Epoch(val) [3][ 900/1918] eta: 0:00:47 time: 0.0535 data_time: 0.0002 memory: 453 2022/12/15 02:45:49 - mmengine - INFO - Epoch(val) [3][ 950/1918] eta: 0:00:45 time: 0.0526 data_time: 0.0010 memory: 453 2022/12/15 02:45:51 - mmengine - INFO - Epoch(val) [3][1000/1918] eta: 0:00:43 time: 0.0476 data_time: 0.0001 memory: 453 2022/12/15 02:45:54 - mmengine - INFO - Epoch(val) [3][1050/1918] eta: 0:00:40 time: 0.0474 data_time: 0.0001 memory: 453 2022/12/15 02:45:56 - mmengine - INFO - Epoch(val) [3][1100/1918] eta: 0:00:38 time: 0.0539 data_time: 0.0032 memory: 453 2022/12/15 02:45:59 - mmengine - INFO - Epoch(val) [3][1150/1918] eta: 0:00:36 time: 0.0468 data_time: 0.0042 memory: 453 2022/12/15 02:46:01 - mmengine - INFO - Epoch(val) [3][1200/1918] eta: 0:00:34 time: 0.0586 data_time: 0.0002 memory: 453 2022/12/15 02:46:04 - mmengine - INFO - Epoch(val) [3][1250/1918] eta: 0:00:31 time: 0.0487 data_time: 0.0011 memory: 453 2022/12/15 02:46:07 - mmengine - INFO - Epoch(val) [3][1300/1918] eta: 0:00:29 time: 0.0488 data_time: 0.0019 memory: 453 2022/12/15 02:46:09 - mmengine - INFO - Epoch(val) [3][1350/1918] eta: 0:00:27 time: 0.0507 data_time: 0.0008 memory: 453 2022/12/15 02:46:12 - mmengine - INFO - Epoch(val) [3][1400/1918] eta: 0:00:24 time: 0.0492 data_time: 0.0025 memory: 453 2022/12/15 02:46:14 - mmengine - INFO - Epoch(val) [3][1450/1918] eta: 0:00:22 time: 0.0503 data_time: 0.0025 memory: 453 2022/12/15 02:46:17 - mmengine - INFO - Epoch(val) [3][1500/1918] eta: 0:00:20 time: 0.0553 data_time: 0.0030 memory: 453 2022/12/15 02:46:20 - mmengine - INFO - Epoch(val) [3][1550/1918] eta: 0:00:18 time: 0.0719 data_time: 0.0053 memory: 453 2022/12/15 02:46:23 - mmengine - INFO - Epoch(val) [3][1600/1918] eta: 0:00:15 time: 0.0486 data_time: 0.0023 memory: 453 2022/12/15 02:46:26 - mmengine - INFO - Epoch(val) [3][1650/1918] eta: 0:00:13 time: 0.0479 data_time: 0.0025 memory: 453 2022/12/15 02:46:28 - mmengine - INFO - Epoch(val) [3][1700/1918] eta: 0:00:10 time: 0.0469 data_time: 0.0027 memory: 453 2022/12/15 02:46:30 - mmengine - INFO - Epoch(val) [3][1750/1918] eta: 0:00:08 time: 0.0487 data_time: 0.0041 memory: 453 2022/12/15 02:46:33 - mmengine - INFO - Epoch(val) [3][1800/1918] eta: 0:00:05 time: 0.0493 data_time: 0.0053 memory: 453 2022/12/15 02:46:35 - mmengine - INFO - Epoch(val) [3][1850/1918] eta: 0:00:03 time: 0.0258 data_time: 0.0002 memory: 453 2022/12/15 02:46:37 - mmengine - INFO - Epoch(val) [3][1900/1918] eta: 0:00:00 time: 0.0192 data_time: 0.0001 memory: 453 2022/12/15 02:46:39 - mmengine - INFO - Epoch(val) [3][1918/1918] CUTE80/recog/word_acc: 0.6667 CUTE80/recog/word_acc_ignore_case: 0.7882 CUTE80/recog/word_acc_ignore_case_symbol: 0.8021 IIIT5K/recog/word_acc: 0.3923 IIIT5K/recog/word_acc_ignore_case: 0.8253 IIIT5K/recog/word_acc_ignore_case_symbol: 0.9137 SVT/recog/word_acc: 0.1314 SVT/recog/word_acc_ignore_case: 0.8423 SVT/recog/word_acc_ignore_case_symbol: 0.8671 SVTP/recog/word_acc: 0.4093 SVTP/recog/word_acc_ignore_case: 0.7659 SVTP/recog/word_acc_ignore_case_symbol: 0.7752 IC13/recog/word_acc: 0.8345 IC13/recog/word_acc_ignore_case: 0.9005 IC13/recog/word_acc_ignore_case_symbol: 0.9103 IC15/recog/word_acc: 0.5763 IC15/recog/word_acc_ignore_case: 0.7053 IC15/recog/word_acc_ignore_case_symbol: 0.7323 CUTE80/recog/char_recall: 0.8946 CUTE80/recog/char_precision: 0.9176 IIIT5K/recog/char_recall: 0.9730 IIIT5K/recog/char_precision: 0.9699 SVT/recog/char_recall: 0.9547 SVT/recog/char_precision: 0.9651 SVTP/recog/char_recall: 0.9060 SVTP/recog/char_precision: 0.9382 IC13/recog/char_recall: 0.9753 IC13/recog/char_precision: 0.9721 IC15/recog/char_recall: 0.8906 IC15/recog/char_precision: 0.9076 2022/12/15 02:47:40 - mmengine - INFO - Epoch(train) [4][ 50/3952] lr: 2.0071e-04 eta: 3:11:53 time: 0.8851 data_time: 0.0029 memory: 11981 loss: 0.0215 loss_ce: 0.0215 2022/12/15 02:48:26 - mmengine - INFO - Epoch(train) [4][ 100/3952] lr: 1.9940e-04 eta: 3:11:02 time: 0.9086 data_time: 0.0031 memory: 11981 loss: 0.0222 loss_ce: 0.0222 2022/12/15 02:49:06 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 02:49:11 - mmengine - INFO - Epoch(train) [4][ 150/3952] lr: 1.9809e-04 eta: 3:10:09 time: 0.9250 data_time: 0.0037 memory: 11981 loss: 0.0216 loss_ce: 0.0216 2022/12/15 02:49:55 - mmengine - INFO - Epoch(train) [4][ 200/3952] lr: 1.9678e-04 eta: 3:09:16 time: 0.8510 data_time: 0.0039 memory: 11981 loss: 0.0216 loss_ce: 0.0216 2022/12/15 02:50:41 - mmengine - INFO - Epoch(train) [4][ 250/3952] lr: 1.9547e-04 eta: 3:08:25 time: 0.9331 data_time: 0.0034 memory: 11981 loss: 0.0209 loss_ce: 0.0209 2022/12/15 02:51:28 - mmengine - INFO - Epoch(train) [4][ 300/3952] lr: 1.9416e-04 eta: 3:07:35 time: 0.9360 data_time: 0.0033 memory: 11981 loss: 0.0219 loss_ce: 0.0219 2022/12/15 02:52:16 - mmengine - INFO - Epoch(train) [4][ 350/3952] lr: 1.9285e-04 eta: 3:06:45 time: 0.9524 data_time: 0.0037 memory: 11981 loss: 0.0222 loss_ce: 0.0222 2022/12/15 02:53:01 - mmengine - INFO - Epoch(train) [4][ 400/3952] lr: 1.9154e-04 eta: 3:05:53 time: 0.8812 data_time: 0.0033 memory: 11981 loss: 0.0209 loss_ce: 0.0209 2022/12/15 02:53:48 - mmengine - INFO - Epoch(train) [4][ 450/3952] lr: 1.9023e-04 eta: 3:05:03 time: 0.8809 data_time: 0.0039 memory: 11981 loss: 0.0221 loss_ce: 0.0221 2022/12/15 02:54:34 - mmengine - INFO - Epoch(train) [4][ 500/3952] lr: 1.8892e-04 eta: 3:04:11 time: 0.8773 data_time: 0.0035 memory: 11981 loss: 0.0217 loss_ce: 0.0217 2022/12/15 02:55:20 - mmengine - INFO - Epoch(train) [4][ 550/3952] lr: 1.8761e-04 eta: 3:03:20 time: 0.9625 data_time: 0.0035 memory: 11981 loss: 0.0236 loss_ce: 0.0236 2022/12/15 02:56:05 - mmengine - INFO - Epoch(train) [4][ 600/3952] lr: 1.8630e-04 eta: 3:02:29 time: 0.8610 data_time: 0.0033 memory: 11981 loss: 0.0217 loss_ce: 0.0217 2022/12/15 02:56:51 - mmengine - INFO - Epoch(train) [4][ 650/3952] lr: 1.8500e-04 eta: 3:01:37 time: 0.9144 data_time: 0.0031 memory: 11981 loss: 0.0220 loss_ce: 0.0220 2022/12/15 02:57:37 - mmengine - INFO - Epoch(train) [4][ 700/3952] lr: 1.8369e-04 eta: 3:00:47 time: 0.9206 data_time: 0.0037 memory: 11981 loss: 0.0208 loss_ce: 0.0208 2022/12/15 02:58:24 - mmengine - INFO - Epoch(train) [4][ 750/3952] lr: 1.8238e-04 eta: 2:59:57 time: 0.9434 data_time: 0.0032 memory: 11981 loss: 0.0218 loss_ce: 0.0218 2022/12/15 02:59:10 - mmengine - INFO - Epoch(train) [4][ 800/3952] lr: 1.8108e-04 eta: 2:59:05 time: 0.9533 data_time: 0.0036 memory: 11981 loss: 0.0220 loss_ce: 0.0220 2022/12/15 02:59:55 - mmengine - INFO - Epoch(train) [4][ 850/3952] lr: 1.7978e-04 eta: 2:58:14 time: 0.9128 data_time: 0.0038 memory: 11981 loss: 0.0221 loss_ce: 0.0221 2022/12/15 03:00:41 - mmengine - INFO - Epoch(train) [4][ 900/3952] lr: 1.7847e-04 eta: 2:57:23 time: 0.8954 data_time: 0.0041 memory: 11981 loss: 0.0220 loss_ce: 0.0220 2022/12/15 03:01:27 - mmengine - INFO - Epoch(train) [4][ 950/3952] lr: 1.7717e-04 eta: 2:56:32 time: 0.9166 data_time: 0.0033 memory: 11981 loss: 0.0211 loss_ce: 0.0211 2022/12/15 03:02:13 - mmengine - INFO - Epoch(train) [4][1000/3952] lr: 1.7587e-04 eta: 2:55:42 time: 0.8791 data_time: 0.0031 memory: 11981 loss: 0.0219 loss_ce: 0.0219 2022/12/15 03:02:59 - mmengine - INFO - Epoch(train) [4][1050/3952] lr: 1.7457e-04 eta: 2:54:51 time: 0.9351 data_time: 0.0034 memory: 11981 loss: 0.0214 loss_ce: 0.0214 2022/12/15 03:03:45 - mmengine - INFO - Epoch(train) [4][1100/3952] lr: 1.7327e-04 eta: 2:54:00 time: 0.9326 data_time: 0.0040 memory: 11981 loss: 0.0219 loss_ce: 0.0219 2022/12/15 03:04:24 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 03:04:30 - mmengine - INFO - Epoch(train) [4][1150/3952] lr: 1.7197e-04 eta: 2:53:08 time: 0.9256 data_time: 0.0035 memory: 11981 loss: 0.0233 loss_ce: 0.0233 2022/12/15 03:05:16 - mmengine - INFO - Epoch(train) [4][1200/3952] lr: 1.7068e-04 eta: 2:52:18 time: 0.9204 data_time: 0.0034 memory: 11981 loss: 0.0197 loss_ce: 0.0197 2022/12/15 03:06:02 - mmengine - INFO - Epoch(train) [4][1250/3952] lr: 1.6938e-04 eta: 2:51:28 time: 0.9471 data_time: 0.0037 memory: 11981 loss: 0.0228 loss_ce: 0.0228 2022/12/15 03:06:49 - mmengine - INFO - Epoch(train) [4][1300/3952] lr: 1.6809e-04 eta: 2:50:38 time: 0.8836 data_time: 0.0038 memory: 11981 loss: 0.0206 loss_ce: 0.0206 2022/12/15 03:07:35 - mmengine - INFO - Epoch(train) [4][1350/3952] lr: 1.6680e-04 eta: 2:49:47 time: 0.9519 data_time: 0.0035 memory: 11981 loss: 0.0226 loss_ce: 0.0226 2022/12/15 03:08:22 - mmengine - INFO - Epoch(train) [4][1400/3952] lr: 1.6551e-04 eta: 2:48:58 time: 0.9589 data_time: 0.0039 memory: 11981 loss: 0.0206 loss_ce: 0.0206 2022/12/15 03:09:08 - mmengine - INFO - Epoch(train) [4][1450/3952] lr: 1.6422e-04 eta: 2:48:07 time: 0.8874 data_time: 0.0032 memory: 11981 loss: 0.0220 loss_ce: 0.0220 2022/12/15 03:09:53 - mmengine - INFO - Epoch(train) [4][1500/3952] lr: 1.6293e-04 eta: 2:47:17 time: 0.8572 data_time: 0.0039 memory: 11981 loss: 0.0203 loss_ce: 0.0203 2022/12/15 03:10:40 - mmengine - INFO - Epoch(train) [4][1550/3952] lr: 1.6165e-04 eta: 2:46:27 time: 0.9772 data_time: 0.0033 memory: 11981 loss: 0.0196 loss_ce: 0.0196 2022/12/15 03:11:26 - mmengine - INFO - Epoch(train) [4][1600/3952] lr: 1.6037e-04 eta: 2:45:36 time: 0.9222 data_time: 0.0032 memory: 11981 loss: 0.0208 loss_ce: 0.0208 2022/12/15 03:12:12 - mmengine - INFO - Epoch(train) [4][1650/3952] lr: 1.5909e-04 eta: 2:44:46 time: 0.9217 data_time: 0.0036 memory: 11981 loss: 0.0202 loss_ce: 0.0202 2022/12/15 03:12:59 - mmengine - INFO - Epoch(train) [4][1700/3952] lr: 1.5781e-04 eta: 2:43:56 time: 0.9474 data_time: 0.0042 memory: 11981 loss: 0.0209 loss_ce: 0.0209 2022/12/15 03:13:46 - mmengine - INFO - Epoch(train) [4][1750/3952] lr: 1.5653e-04 eta: 2:43:07 time: 1.0011 data_time: 0.0045 memory: 11981 loss: 0.0210 loss_ce: 0.0210 2022/12/15 03:14:31 - mmengine - INFO - Epoch(train) [4][1800/3952] lr: 1.5525e-04 eta: 2:42:16 time: 0.8897 data_time: 0.0032 memory: 11981 loss: 0.0215 loss_ce: 0.0215 2022/12/15 03:15:18 - mmengine - INFO - Epoch(train) [4][1850/3952] lr: 1.5398e-04 eta: 2:41:27 time: 0.9077 data_time: 0.0037 memory: 11981 loss: 0.0207 loss_ce: 0.0207 2022/12/15 03:16:07 - mmengine - INFO - Epoch(train) [4][1900/3952] lr: 1.5271e-04 eta: 2:40:39 time: 0.9759 data_time: 0.0044 memory: 11981 loss: 0.0226 loss_ce: 0.0226 2022/12/15 03:16:52 - mmengine - INFO - Epoch(train) [4][1950/3952] lr: 1.5144e-04 eta: 2:39:48 time: 0.8507 data_time: 0.0041 memory: 11981 loss: 0.0213 loss_ce: 0.0213 2022/12/15 03:17:39 - mmengine - INFO - Epoch(train) [4][2000/3952] lr: 1.5017e-04 eta: 2:38:58 time: 0.9387 data_time: 0.0035 memory: 11981 loss: 0.0224 loss_ce: 0.0224 2022/12/15 03:18:25 - mmengine - INFO - Epoch(train) [4][2050/3952] lr: 1.4891e-04 eta: 2:38:08 time: 0.9025 data_time: 0.0031 memory: 11981 loss: 0.0193 loss_ce: 0.0193 2022/12/15 03:19:11 - mmengine - INFO - Epoch(train) [4][2100/3952] lr: 1.4764e-04 eta: 2:37:18 time: 0.9069 data_time: 0.0035 memory: 11981 loss: 0.0191 loss_ce: 0.0191 2022/12/15 03:19:53 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 03:19:58 - mmengine - INFO - Epoch(train) [4][2150/3952] lr: 1.4638e-04 eta: 2:36:29 time: 0.8923 data_time: 0.0032 memory: 11981 loss: 0.0227 loss_ce: 0.0227 2022/12/15 03:20:44 - mmengine - INFO - Epoch(train) [4][2200/3952] lr: 1.4513e-04 eta: 2:35:39 time: 0.9158 data_time: 0.0035 memory: 11981 loss: 0.0216 loss_ce: 0.0216 2022/12/15 03:21:31 - mmengine - INFO - Epoch(train) [4][2250/3952] lr: 1.4387e-04 eta: 2:34:50 time: 0.9385 data_time: 0.0033 memory: 11981 loss: 0.0222 loss_ce: 0.0222 2022/12/15 03:22:18 - mmengine - INFO - Epoch(train) [4][2300/3952] lr: 1.4262e-04 eta: 2:34:01 time: 0.9515 data_time: 0.0045 memory: 11981 loss: 0.0225 loss_ce: 0.0225 2022/12/15 03:23:05 - mmengine - INFO - Epoch(train) [4][2350/3952] lr: 1.4137e-04 eta: 2:33:11 time: 0.9452 data_time: 0.0042 memory: 11981 loss: 0.0206 loss_ce: 0.0206 2022/12/15 03:23:51 - mmengine - INFO - Epoch(train) [4][2400/3952] lr: 1.4012e-04 eta: 2:32:21 time: 0.9521 data_time: 0.0047 memory: 11981 loss: 0.0198 loss_ce: 0.0198 2022/12/15 03:24:37 - mmengine - INFO - Epoch(train) [4][2450/3952] lr: 1.3888e-04 eta: 2:31:31 time: 0.8899 data_time: 0.0037 memory: 11981 loss: 0.0206 loss_ce: 0.0206 2022/12/15 03:25:24 - mmengine - INFO - Epoch(train) [4][2500/3952] lr: 1.3764e-04 eta: 2:30:42 time: 0.9398 data_time: 0.0038 memory: 11981 loss: 0.0215 loss_ce: 0.0215 2022/12/15 03:26:11 - mmengine - INFO - Epoch(train) [4][2550/3952] lr: 1.3640e-04 eta: 2:29:53 time: 0.9295 data_time: 0.0039 memory: 11981 loss: 0.0216 loss_ce: 0.0216 2022/12/15 03:26:58 - mmengine - INFO - Epoch(train) [4][2600/3952] lr: 1.3516e-04 eta: 2:29:04 time: 0.9016 data_time: 0.0038 memory: 11981 loss: 0.0220 loss_ce: 0.0220 2022/12/15 03:27:42 - mmengine - INFO - Epoch(train) [4][2650/3952] lr: 1.3393e-04 eta: 2:28:13 time: 0.8877 data_time: 0.0036 memory: 11981 loss: 0.0200 loss_ce: 0.0200 2022/12/15 03:28:27 - mmengine - INFO - Epoch(train) [4][2700/3952] lr: 1.3270e-04 eta: 2:27:22 time: 0.8525 data_time: 0.0033 memory: 11981 loss: 0.0228 loss_ce: 0.0228 2022/12/15 03:29:13 - mmengine - INFO - Epoch(train) [4][2750/3952] lr: 1.3147e-04 eta: 2:26:33 time: 0.9528 data_time: 0.0035 memory: 11981 loss: 0.0223 loss_ce: 0.0223 2022/12/15 03:29:58 - mmengine - INFO - Epoch(train) [4][2800/3952] lr: 1.3025e-04 eta: 2:25:42 time: 0.8907 data_time: 0.0034 memory: 11981 loss: 0.0201 loss_ce: 0.0201 2022/12/15 03:30:44 - mmengine - INFO - Epoch(train) [4][2850/3952] lr: 1.2902e-04 eta: 2:24:52 time: 0.9208 data_time: 0.0041 memory: 11981 loss: 0.0202 loss_ce: 0.0202 2022/12/15 03:31:30 - mmengine - INFO - Epoch(train) [4][2900/3952] lr: 1.2781e-04 eta: 2:24:03 time: 0.9733 data_time: 0.0031 memory: 11981 loss: 0.0206 loss_ce: 0.0206 2022/12/15 03:32:15 - mmengine - INFO - Epoch(train) [4][2950/3952] lr: 1.2659e-04 eta: 2:23:13 time: 0.8742 data_time: 0.0032 memory: 11981 loss: 0.0205 loss_ce: 0.0205 2022/12/15 03:33:00 - mmengine - INFO - Epoch(train) [4][3000/3952] lr: 1.2538e-04 eta: 2:22:23 time: 0.8836 data_time: 0.0032 memory: 11981 loss: 0.0213 loss_ce: 0.0213 2022/12/15 03:33:46 - mmengine - INFO - Epoch(train) [4][3050/3952] lr: 1.2417e-04 eta: 2:21:33 time: 0.9304 data_time: 0.0034 memory: 11981 loss: 0.0197 loss_ce: 0.0197 2022/12/15 03:34:32 - mmengine - INFO - Epoch(train) [4][3100/3952] lr: 1.2297e-04 eta: 2:20:43 time: 0.9308 data_time: 0.0032 memory: 11981 loss: 0.0196 loss_ce: 0.0196 2022/12/15 03:35:12 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 03:35:18 - mmengine - INFO - Epoch(train) [4][3150/3952] lr: 1.2177e-04 eta: 2:19:54 time: 0.9117 data_time: 0.0038 memory: 11981 loss: 0.0181 loss_ce: 0.0181 2022/12/15 03:36:03 - mmengine - INFO - Epoch(train) [4][3200/3952] lr: 1.2057e-04 eta: 2:19:04 time: 0.9445 data_time: 0.0031 memory: 11981 loss: 0.0201 loss_ce: 0.0201 2022/12/15 03:36:49 - mmengine - INFO - Epoch(train) [4][3250/3952] lr: 1.1938e-04 eta: 2:18:15 time: 0.9060 data_time: 0.0041 memory: 11981 loss: 0.0200 loss_ce: 0.0200 2022/12/15 03:37:34 - mmengine - INFO - Epoch(train) [4][3300/3952] lr: 1.1819e-04 eta: 2:17:25 time: 0.9064 data_time: 0.0033 memory: 11981 loss: 0.0200 loss_ce: 0.0200 2022/12/15 03:38:22 - mmengine - INFO - Epoch(train) [4][3350/3952] lr: 1.1700e-04 eta: 2:16:36 time: 0.8829 data_time: 0.0035 memory: 11981 loss: 0.0195 loss_ce: 0.0195 2022/12/15 03:39:08 - mmengine - INFO - Epoch(train) [4][3400/3952] lr: 1.1582e-04 eta: 2:15:47 time: 0.8887 data_time: 0.0036 memory: 11981 loss: 0.0209 loss_ce: 0.0209 2022/12/15 03:39:54 - mmengine - INFO - Epoch(train) [4][3450/3952] lr: 1.1464e-04 eta: 2:14:58 time: 0.9427 data_time: 0.0034 memory: 11981 loss: 0.0207 loss_ce: 0.0207 2022/12/15 03:40:40 - mmengine - INFO - Epoch(train) [4][3500/3952] lr: 1.1346e-04 eta: 2:14:08 time: 0.9640 data_time: 0.0032 memory: 11981 loss: 0.0201 loss_ce: 0.0201 2022/12/15 03:41:26 - mmengine - INFO - Epoch(train) [4][3550/3952] lr: 1.1229e-04 eta: 2:13:19 time: 0.8527 data_time: 0.0034 memory: 11981 loss: 0.0200 loss_ce: 0.0200 2022/12/15 03:42:12 - mmengine - INFO - Epoch(train) [4][3600/3952] lr: 1.1112e-04 eta: 2:12:29 time: 0.9418 data_time: 0.0036 memory: 11981 loss: 0.0195 loss_ce: 0.0195 2022/12/15 03:42:59 - mmengine - INFO - Epoch(train) [4][3650/3952] lr: 1.0996e-04 eta: 2:11:41 time: 0.9904 data_time: 0.0038 memory: 11981 loss: 0.0209 loss_ce: 0.0209 2022/12/15 03:43:45 - mmengine - INFO - Epoch(train) [4][3700/3952] lr: 1.0880e-04 eta: 2:10:51 time: 0.9047 data_time: 0.0035 memory: 11981 loss: 0.0203 loss_ce: 0.0203 2022/12/15 03:44:30 - mmengine - INFO - Epoch(train) [4][3750/3952] lr: 1.0765e-04 eta: 2:10:02 time: 0.8664 data_time: 0.0040 memory: 11981 loss: 0.0198 loss_ce: 0.0198 2022/12/15 03:45:17 - mmengine - INFO - Epoch(train) [4][3800/3952] lr: 1.0650e-04 eta: 2:09:13 time: 0.9512 data_time: 0.0036 memory: 11981 loss: 0.0197 loss_ce: 0.0197 2022/12/15 03:46:03 - mmengine - INFO - Epoch(train) [4][3850/3952] lr: 1.0535e-04 eta: 2:08:24 time: 0.9400 data_time: 0.0038 memory: 11981 loss: 0.0191 loss_ce: 0.0191 2022/12/15 03:46:49 - mmengine - INFO - Epoch(train) [4][3900/3952] lr: 1.0421e-04 eta: 2:07:35 time: 0.9406 data_time: 0.0034 memory: 11981 loss: 0.0201 loss_ce: 0.0201 2022/12/15 03:47:21 - mmengine - INFO - Epoch(train) [4][3950/3952] lr: 1.0307e-04 eta: 2:06:38 time: 0.6063 data_time: 0.0033 memory: 11981 loss: 0.0188 loss_ce: 0.0188 2022/12/15 03:47:22 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 03:47:22 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/15 03:47:27 - mmengine - INFO - Epoch(val) [4][ 50/1918] eta: 0:01:40 time: 0.0473 data_time: 0.0007 memory: 11981 2022/12/15 03:47:30 - mmengine - INFO - Epoch(val) [4][ 100/1918] eta: 0:01:32 time: 0.0467 data_time: 0.0031 memory: 453 2022/12/15 03:47:32 - mmengine - INFO - Epoch(val) [4][ 150/1918] eta: 0:01:28 time: 0.0481 data_time: 0.0050 memory: 453 2022/12/15 03:47:34 - mmengine - INFO - Epoch(val) [4][ 200/1918] eta: 0:01:25 time: 0.0491 data_time: 0.0052 memory: 453 2022/12/15 03:47:37 - mmengine - INFO - Epoch(val) [4][ 250/1918] eta: 0:01:22 time: 0.0483 data_time: 0.0050 memory: 453 2022/12/15 03:47:39 - mmengine - INFO - Epoch(val) [4][ 300/1918] eta: 0:01:19 time: 0.0493 data_time: 0.0049 memory: 453 2022/12/15 03:47:42 - mmengine - INFO - Epoch(val) [4][ 350/1918] eta: 0:01:18 time: 0.0671 data_time: 0.0027 memory: 453 2022/12/15 03:47:45 - mmengine - INFO - Epoch(val) [4][ 400/1918] eta: 0:01:16 time: 0.0620 data_time: 0.0001 memory: 453 2022/12/15 03:47:47 - mmengine - INFO - Epoch(val) [4][ 450/1918] eta: 0:01:13 time: 0.0295 data_time: 0.0003 memory: 453 2022/12/15 03:47:49 - mmengine - INFO - Epoch(val) [4][ 500/1918] eta: 0:01:09 time: 0.0399 data_time: 0.0006 memory: 453 2022/12/15 03:47:51 - mmengine - INFO - Epoch(val) [4][ 550/1918] eta: 0:01:05 time: 0.0289 data_time: 0.0003 memory: 453 2022/12/15 03:47:53 - mmengine - INFO - Epoch(val) [4][ 600/1918] eta: 0:01:01 time: 0.0403 data_time: 0.0007 memory: 453 2022/12/15 03:47:55 - mmengine - INFO - Epoch(val) [4][ 650/1918] eta: 0:00:59 time: 0.0471 data_time: 0.0014 memory: 453 2022/12/15 03:47:57 - mmengine - INFO - Epoch(val) [4][ 700/1918] eta: 0:00:57 time: 0.0490 data_time: 0.0028 memory: 453 2022/12/15 03:48:00 - mmengine - INFO - Epoch(val) [4][ 750/1918] eta: 0:00:54 time: 0.0467 data_time: 0.0008 memory: 453 2022/12/15 03:48:02 - mmengine - INFO - Epoch(val) [4][ 800/1918] eta: 0:00:52 time: 0.0465 data_time: 0.0007 memory: 453 2022/12/15 03:48:04 - mmengine - INFO - Epoch(val) [4][ 850/1918] eta: 0:00:50 time: 0.0461 data_time: 0.0017 memory: 453 2022/12/15 03:48:07 - mmengine - INFO - Epoch(val) [4][ 900/1918] eta: 0:00:47 time: 0.0458 data_time: 0.0001 memory: 453 2022/12/15 03:48:09 - mmengine - INFO - Epoch(val) [4][ 950/1918] eta: 0:00:45 time: 0.0457 data_time: 0.0027 memory: 453 2022/12/15 03:48:11 - mmengine - INFO - Epoch(val) [4][1000/1918] eta: 0:00:42 time: 0.0457 data_time: 0.0025 memory: 453 2022/12/15 03:48:14 - mmengine - INFO - Epoch(val) [4][1050/1918] eta: 0:00:40 time: 0.0462 data_time: 0.0032 memory: 453 2022/12/15 03:48:16 - mmengine - INFO - Epoch(val) [4][1100/1918] eta: 0:00:38 time: 0.0458 data_time: 0.0036 memory: 453 2022/12/15 03:48:18 - mmengine - INFO - Epoch(val) [4][1150/1918] eta: 0:00:35 time: 0.0458 data_time: 0.0041 memory: 453 2022/12/15 03:48:21 - mmengine - INFO - Epoch(val) [4][1200/1918] eta: 0:00:33 time: 0.0465 data_time: 0.0050 memory: 453 2022/12/15 03:48:23 - mmengine - INFO - Epoch(val) [4][1250/1918] eta: 0:00:31 time: 0.0463 data_time: 0.0036 memory: 453 2022/12/15 03:48:25 - mmengine - INFO - Epoch(val) [4][1300/1918] eta: 0:00:28 time: 0.0471 data_time: 0.0049 memory: 453 2022/12/15 03:48:28 - mmengine - INFO - Epoch(val) [4][1350/1918] eta: 0:00:26 time: 0.0484 data_time: 0.0047 memory: 453 2022/12/15 03:48:30 - mmengine - INFO - Epoch(val) [4][1400/1918] eta: 0:00:24 time: 0.0472 data_time: 0.0007 memory: 453 2022/12/15 03:48:33 - mmengine - INFO - Epoch(val) [4][1450/1918] eta: 0:00:21 time: 0.0541 data_time: 0.0031 memory: 453 2022/12/15 03:48:35 - mmengine - INFO - Epoch(val) [4][1500/1918] eta: 0:00:19 time: 0.0489 data_time: 0.0023 memory: 453 2022/12/15 03:48:38 - mmengine - INFO - Epoch(val) [4][1550/1918] eta: 0:00:17 time: 0.0497 data_time: 0.0013 memory: 453 2022/12/15 03:48:40 - mmengine - INFO - Epoch(val) [4][1600/1918] eta: 0:00:15 time: 0.0520 data_time: 0.0026 memory: 453 2022/12/15 03:48:43 - mmengine - INFO - Epoch(val) [4][1650/1918] eta: 0:00:12 time: 0.0538 data_time: 0.0001 memory: 453 2022/12/15 03:48:45 - mmengine - INFO - Epoch(val) [4][1700/1918] eta: 0:00:10 time: 0.0350 data_time: 0.0002 memory: 453 2022/12/15 03:48:47 - mmengine - INFO - Epoch(val) [4][1750/1918] eta: 0:00:07 time: 0.0200 data_time: 0.0001 memory: 453 2022/12/15 03:48:48 - mmengine - INFO - Epoch(val) [4][1800/1918] eta: 0:00:05 time: 0.0194 data_time: 0.0001 memory: 453 2022/12/15 03:48:49 - mmengine - INFO - Epoch(val) [4][1850/1918] eta: 0:00:03 time: 0.0196 data_time: 0.0001 memory: 453 2022/12/15 03:48:50 - mmengine - INFO - Epoch(val) [4][1900/1918] eta: 0:00:00 time: 0.0197 data_time: 0.0001 memory: 453 2022/12/15 03:48:51 - mmengine - INFO - Epoch(val) [4][1918/1918] CUTE80/recog/word_acc: 0.6319 CUTE80/recog/word_acc_ignore_case: 0.8264 CUTE80/recog/word_acc_ignore_case_symbol: 0.8437 IIIT5K/recog/word_acc: 0.3403 IIIT5K/recog/word_acc_ignore_case: 0.8300 IIIT5K/recog/word_acc_ignore_case_symbol: 0.9303 SVT/recog/word_acc: 0.2148 SVT/recog/word_acc_ignore_case: 0.8532 SVT/recog/word_acc_ignore_case_symbol: 0.8810 SVTP/recog/word_acc: 0.3240 SVTP/recog/word_acc_ignore_case: 0.7783 SVTP/recog/word_acc_ignore_case_symbol: 0.7907 IC13/recog/word_acc: 0.8089 IC13/recog/word_acc_ignore_case: 0.9163 IC13/recog/word_acc_ignore_case_symbol: 0.9261 IC15/recog/word_acc: 0.5277 IC15/recog/word_acc_ignore_case: 0.7111 IC15/recog/word_acc_ignore_case_symbol: 0.7468 CUTE80/recog/char_recall: 0.9046 CUTE80/recog/char_precision: 0.9291 IIIT5K/recog/char_recall: 0.9765 IIIT5K/recog/char_precision: 0.9764 SVT/recog/char_recall: 0.9618 SVT/recog/char_precision: 0.9695 SVTP/recog/char_recall: 0.9107 SVTP/recog/char_precision: 0.9400 IC13/recog/char_recall: 0.9792 IC13/recog/char_precision: 0.9776 IC15/recog/char_recall: 0.8947 IC15/recog/char_precision: 0.9083 2022/12/15 03:49:51 - mmengine - INFO - Epoch(train) [5][ 50/3952] lr: 1.0189e-04 eta: 2:05:54 time: 0.8691 data_time: 0.0031 memory: 11981 loss: 0.0181 loss_ce: 0.0181 2022/12/15 03:50:35 - mmengine - INFO - Epoch(train) [5][ 100/3952] lr: 1.0076e-04 eta: 2:05:04 time: 0.8947 data_time: 0.0033 memory: 11981 loss: 0.0193 loss_ce: 0.0193 2022/12/15 03:51:19 - mmengine - INFO - Epoch(train) [5][ 150/3952] lr: 9.9634e-05 eta: 2:04:14 time: 0.9161 data_time: 0.0037 memory: 11981 loss: 0.0185 loss_ce: 0.0185 2022/12/15 03:51:57 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 03:52:04 - mmengine - INFO - Epoch(train) [5][ 200/3952] lr: 9.8514e-05 eta: 2:03:24 time: 0.8484 data_time: 0.0039 memory: 11981 loss: 0.0193 loss_ce: 0.0193 2022/12/15 03:52:50 - mmengine - INFO - Epoch(train) [5][ 250/3952] lr: 9.7398e-05 eta: 2:02:35 time: 0.8694 data_time: 0.0036 memory: 11981 loss: 0.0206 loss_ce: 0.0206 2022/12/15 03:53:36 - mmengine - INFO - Epoch(train) [5][ 300/3952] lr: 9.6287e-05 eta: 2:01:46 time: 0.9330 data_time: 0.0042 memory: 11981 loss: 0.0189 loss_ce: 0.0189 2022/12/15 03:54:21 - mmengine - INFO - Epoch(train) [5][ 350/3952] lr: 9.5180e-05 eta: 2:00:57 time: 0.8834 data_time: 0.0044 memory: 11981 loss: 0.0194 loss_ce: 0.0194 2022/12/15 03:55:06 - mmengine - INFO - Epoch(train) [5][ 400/3952] lr: 9.4078e-05 eta: 2:00:07 time: 0.8869 data_time: 0.0038 memory: 11981 loss: 0.0188 loss_ce: 0.0188 2022/12/15 03:55:53 - mmengine - INFO - Epoch(train) [5][ 450/3952] lr: 9.2981e-05 eta: 1:59:19 time: 0.9055 data_time: 0.0031 memory: 11981 loss: 0.0173 loss_ce: 0.0173 2022/12/15 03:56:39 - mmengine - INFO - Epoch(train) [5][ 500/3952] lr: 9.1888e-05 eta: 1:58:30 time: 0.8905 data_time: 0.0046 memory: 11981 loss: 0.0194 loss_ce: 0.0194 2022/12/15 03:57:25 - mmengine - INFO - Epoch(train) [5][ 550/3952] lr: 9.0800e-05 eta: 1:57:41 time: 0.8853 data_time: 0.0032 memory: 11981 loss: 0.0178 loss_ce: 0.0178 2022/12/15 03:58:11 - mmengine - INFO - Epoch(train) [5][ 600/3952] lr: 8.9718e-05 eta: 1:56:52 time: 0.9222 data_time: 0.0034 memory: 11981 loss: 0.0187 loss_ce: 0.0187 2022/12/15 03:58:56 - mmengine - INFO - Epoch(train) [5][ 650/3952] lr: 8.8640e-05 eta: 1:56:03 time: 0.8588 data_time: 0.0032 memory: 11981 loss: 0.0200 loss_ce: 0.0200 2022/12/15 03:59:43 - mmengine - INFO - Epoch(train) [5][ 700/3952] lr: 8.7567e-05 eta: 1:55:14 time: 0.9562 data_time: 0.0034 memory: 11981 loss: 0.0199 loss_ce: 0.0199 2022/12/15 04:00:27 - mmengine - INFO - Epoch(train) [5][ 750/3952] lr: 8.6499e-05 eta: 1:54:24 time: 0.9366 data_time: 0.0034 memory: 11981 loss: 0.0188 loss_ce: 0.0188 2022/12/15 04:01:12 - mmengine - INFO - Epoch(train) [5][ 800/3952] lr: 8.5436e-05 eta: 1:53:35 time: 0.9028 data_time: 0.0038 memory: 11981 loss: 0.0184 loss_ce: 0.0184 2022/12/15 04:01:58 - mmengine - INFO - Epoch(train) [5][ 850/3952] lr: 8.4378e-05 eta: 1:52:47 time: 0.9442 data_time: 0.0041 memory: 11981 loss: 0.0198 loss_ce: 0.0198 2022/12/15 04:02:44 - mmengine - INFO - Epoch(train) [5][ 900/3952] lr: 8.3326e-05 eta: 1:51:58 time: 0.9182 data_time: 0.0032 memory: 11981 loss: 0.0187 loss_ce: 0.0187 2022/12/15 04:03:29 - mmengine - INFO - Epoch(train) [5][ 950/3952] lr: 8.2279e-05 eta: 1:51:08 time: 0.9425 data_time: 0.0030 memory: 11981 loss: 0.0176 loss_ce: 0.0176 2022/12/15 04:04:16 - mmengine - INFO - Epoch(train) [5][1000/3952] lr: 8.1236e-05 eta: 1:50:20 time: 0.8882 data_time: 0.0032 memory: 11981 loss: 0.0175 loss_ce: 0.0175 2022/12/15 04:05:02 - mmengine - INFO - Epoch(train) [5][1050/3952] lr: 8.0200e-05 eta: 1:49:31 time: 0.8844 data_time: 0.0038 memory: 11981 loss: 0.0190 loss_ce: 0.0190 2022/12/15 04:05:48 - mmengine - INFO - Epoch(train) [5][1100/3952] lr: 7.9168e-05 eta: 1:48:42 time: 0.9635 data_time: 0.0033 memory: 11981 loss: 0.0172 loss_ce: 0.0172 2022/12/15 04:06:33 - mmengine - INFO - Epoch(train) [5][1150/3952] lr: 7.8142e-05 eta: 1:47:54 time: 0.9438 data_time: 0.0039 memory: 11981 loss: 0.0196 loss_ce: 0.0196 2022/12/15 04:07:11 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 04:07:18 - mmengine - INFO - Epoch(train) [5][1200/3952] lr: 7.7122e-05 eta: 1:47:05 time: 0.9081 data_time: 0.0031 memory: 11981 loss: 0.0182 loss_ce: 0.0182 2022/12/15 04:08:06 - mmengine - INFO - Epoch(train) [5][1250/3952] lr: 7.6106e-05 eta: 1:46:16 time: 0.9054 data_time: 0.0039 memory: 11981 loss: 0.0176 loss_ce: 0.0176 2022/12/15 04:08:52 - mmengine - INFO - Epoch(train) [5][1300/3952] lr: 7.5097e-05 eta: 1:45:28 time: 0.9565 data_time: 0.0041 memory: 11981 loss: 0.0171 loss_ce: 0.0171 2022/12/15 04:09:39 - mmengine - INFO - Epoch(train) [5][1350/3952] lr: 7.4093e-05 eta: 1:44:39 time: 0.9337 data_time: 0.0034 memory: 11981 loss: 0.0179 loss_ce: 0.0179 2022/12/15 04:10:26 - mmengine - INFO - Epoch(train) [5][1400/3952] lr: 7.3094e-05 eta: 1:43:51 time: 0.9792 data_time: 0.0037 memory: 11981 loss: 0.0167 loss_ce: 0.0167 2022/12/15 04:11:13 - mmengine - INFO - Epoch(train) [5][1450/3952] lr: 7.2102e-05 eta: 1:43:03 time: 0.9168 data_time: 0.0035 memory: 11981 loss: 0.0185 loss_ce: 0.0185 2022/12/15 04:12:00 - mmengine - INFO - Epoch(train) [5][1500/3952] lr: 7.1115e-05 eta: 1:42:15 time: 0.9379 data_time: 0.0033 memory: 11981 loss: 0.0176 loss_ce: 0.0176 2022/12/15 04:12:48 - mmengine - INFO - Epoch(train) [5][1550/3952] lr: 7.0133e-05 eta: 1:41:27 time: 0.9325 data_time: 0.0036 memory: 11981 loss: 0.0181 loss_ce: 0.0181 2022/12/15 04:13:34 - mmengine - INFO - Epoch(train) [5][1600/3952] lr: 6.9158e-05 eta: 1:40:38 time: 0.9429 data_time: 0.0042 memory: 11981 loss: 0.0176 loss_ce: 0.0176 2022/12/15 04:14:21 - mmengine - INFO - Epoch(train) [5][1650/3952] lr: 6.8188e-05 eta: 1:39:50 time: 0.9628 data_time: 0.0049 memory: 11981 loss: 0.0162 loss_ce: 0.0162 2022/12/15 04:15:09 - mmengine - INFO - Epoch(train) [5][1700/3952] lr: 6.7224e-05 eta: 1:39:02 time: 0.9766 data_time: 0.0049 memory: 11981 loss: 0.0179 loss_ce: 0.0179 2022/12/15 04:15:56 - mmengine - INFO - Epoch(train) [5][1750/3952] lr: 6.6266e-05 eta: 1:38:14 time: 0.8628 data_time: 0.0043 memory: 11981 loss: 0.0187 loss_ce: 0.0187 2022/12/15 04:16:42 - mmengine - INFO - Epoch(train) [5][1800/3952] lr: 6.5314e-05 eta: 1:37:26 time: 0.9408 data_time: 0.0042 memory: 11981 loss: 0.0191 loss_ce: 0.0191 2022/12/15 04:17:27 - mmengine - INFO - Epoch(train) [5][1850/3952] lr: 6.4368e-05 eta: 1:36:37 time: 0.8404 data_time: 0.0048 memory: 11981 loss: 0.0176 loss_ce: 0.0176 2022/12/15 04:18:14 - mmengine - INFO - Epoch(train) [5][1900/3952] lr: 6.3428e-05 eta: 1:35:48 time: 0.9324 data_time: 0.0037 memory: 11981 loss: 0.0184 loss_ce: 0.0184 2022/12/15 04:19:01 - mmengine - INFO - Epoch(train) [5][1950/3952] lr: 6.2495e-05 eta: 1:35:00 time: 0.9574 data_time: 0.0035 memory: 11981 loss: 0.0180 loss_ce: 0.0180 2022/12/15 04:19:46 - mmengine - INFO - Epoch(train) [5][2000/3952] lr: 6.1567e-05 eta: 1:34:12 time: 0.9064 data_time: 0.0036 memory: 11981 loss: 0.0182 loss_ce: 0.0182 2022/12/15 04:20:31 - mmengine - INFO - Epoch(train) [5][2050/3952] lr: 6.0645e-05 eta: 1:33:23 time: 0.8743 data_time: 0.0034 memory: 11981 loss: 0.0182 loss_ce: 0.0182 2022/12/15 04:21:17 - mmengine - INFO - Epoch(train) [5][2100/3952] lr: 5.9730e-05 eta: 1:32:34 time: 0.8866 data_time: 0.0035 memory: 11981 loss: 0.0184 loss_ce: 0.0184 2022/12/15 04:22:01 - mmengine - INFO - Epoch(train) [5][2150/3952] lr: 5.8821e-05 eta: 1:31:45 time: 0.8457 data_time: 0.0037 memory: 11981 loss: 0.0173 loss_ce: 0.0173 2022/12/15 04:22:39 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 04:22:46 - mmengine - INFO - Epoch(train) [5][2200/3952] lr: 5.7918e-05 eta: 1:30:56 time: 0.9159 data_time: 0.0038 memory: 11981 loss: 0.0189 loss_ce: 0.0189 2022/12/15 04:23:31 - mmengine - INFO - Epoch(train) [5][2250/3952] lr: 5.7022e-05 eta: 1:30:08 time: 0.9070 data_time: 0.0040 memory: 11981 loss: 0.0171 loss_ce: 0.0171 2022/12/15 04:24:14 - mmengine - INFO - Epoch(train) [5][2300/3952] lr: 5.6131e-05 eta: 1:29:18 time: 0.8251 data_time: 0.0034 memory: 11981 loss: 0.0185 loss_ce: 0.0185 2022/12/15 04:24:59 - mmengine - INFO - Epoch(train) [5][2350/3952] lr: 5.5248e-05 eta: 1:28:29 time: 0.8471 data_time: 0.0032 memory: 11981 loss: 0.0181 loss_ce: 0.0181 2022/12/15 04:25:44 - mmengine - INFO - Epoch(train) [5][2400/3952] lr: 5.4370e-05 eta: 1:27:41 time: 0.8708 data_time: 0.0033 memory: 11981 loss: 0.0185 loss_ce: 0.0185 2022/12/15 04:26:29 - mmengine - INFO - Epoch(train) [5][2450/3952] lr: 5.3500e-05 eta: 1:26:52 time: 0.8871 data_time: 0.0040 memory: 11981 loss: 0.0172 loss_ce: 0.0172 2022/12/15 04:27:15 - mmengine - INFO - Epoch(train) [5][2500/3952] lr: 5.2635e-05 eta: 1:26:04 time: 0.9460 data_time: 0.0037 memory: 11981 loss: 0.0172 loss_ce: 0.0172 2022/12/15 04:28:03 - mmengine - INFO - Epoch(train) [5][2550/3952] lr: 5.1777e-05 eta: 1:25:16 time: 0.9409 data_time: 0.0035 memory: 11981 loss: 0.0191 loss_ce: 0.0191 2022/12/15 04:28:49 - mmengine - INFO - Epoch(train) [5][2600/3952] lr: 5.0926e-05 eta: 1:24:28 time: 0.9439 data_time: 0.0035 memory: 11981 loss: 0.0173 loss_ce: 0.0173 2022/12/15 04:29:33 - mmengine - INFO - Epoch(train) [5][2650/3952] lr: 5.0082e-05 eta: 1:23:39 time: 0.8858 data_time: 0.0037 memory: 11981 loss: 0.0186 loss_ce: 0.0186 2022/12/15 04:30:19 - mmengine - INFO - Epoch(train) [5][2700/3952] lr: 4.9244e-05 eta: 1:22:51 time: 0.9101 data_time: 0.0031 memory: 11981 loss: 0.0178 loss_ce: 0.0178 2022/12/15 04:31:07 - mmengine - INFO - Epoch(train) [5][2750/3952] lr: 4.8413e-05 eta: 1:22:03 time: 0.9884 data_time: 0.0045 memory: 11981 loss: 0.0195 loss_ce: 0.0195 2022/12/15 04:31:55 - mmengine - INFO - Epoch(train) [5][2800/3952] lr: 4.7588e-05 eta: 1:21:15 time: 1.0211 data_time: 0.0036 memory: 11981 loss: 0.0183 loss_ce: 0.0183 2022/12/15 04:32:42 - mmengine - INFO - Epoch(train) [5][2850/3952] lr: 4.6771e-05 eta: 1:20:27 time: 0.8808 data_time: 0.0033 memory: 11981 loss: 0.0176 loss_ce: 0.0176 2022/12/15 04:33:30 - mmengine - INFO - Epoch(train) [5][2900/3952] lr: 4.5960e-05 eta: 1:19:40 time: 0.9392 data_time: 0.0033 memory: 11981 loss: 0.0175 loss_ce: 0.0175 2022/12/15 04:34:14 - mmengine - INFO - Epoch(train) [5][2950/3952] lr: 4.5156e-05 eta: 1:18:51 time: 0.8684 data_time: 0.0031 memory: 11981 loss: 0.0177 loss_ce: 0.0177 2022/12/15 04:34:59 - mmengine - INFO - Epoch(train) [5][3000/3952] lr: 4.4359e-05 eta: 1:18:03 time: 0.9049 data_time: 0.0047 memory: 11981 loss: 0.0169 loss_ce: 0.0169 2022/12/15 04:35:45 - mmengine - INFO - Epoch(train) [5][3050/3952] lr: 4.3569e-05 eta: 1:17:14 time: 0.8987 data_time: 0.0035 memory: 11981 loss: 0.0176 loss_ce: 0.0176 2022/12/15 04:36:31 - mmengine - INFO - Epoch(train) [5][3100/3952] lr: 4.2785e-05 eta: 1:16:26 time: 0.8709 data_time: 0.0035 memory: 11981 loss: 0.0170 loss_ce: 0.0170 2022/12/15 04:37:19 - mmengine - INFO - Epoch(train) [5][3150/3952] lr: 4.2009e-05 eta: 1:15:38 time: 0.9189 data_time: 0.0034 memory: 11981 loss: 0.0184 loss_ce: 0.0184 2022/12/15 04:37:59 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 04:38:06 - mmengine - INFO - Epoch(train) [5][3200/3952] lr: 4.1240e-05 eta: 1:14:51 time: 0.9293 data_time: 0.0036 memory: 11981 loss: 0.0174 loss_ce: 0.0174 2022/12/15 04:38:53 - mmengine - INFO - Epoch(train) [5][3250/3952] lr: 4.0478e-05 eta: 1:14:03 time: 0.9520 data_time: 0.0051 memory: 11981 loss: 0.0192 loss_ce: 0.0192 2022/12/15 04:39:39 - mmengine - INFO - Epoch(train) [5][3300/3952] lr: 3.9723e-05 eta: 1:13:14 time: 0.9196 data_time: 0.0036 memory: 11981 loss: 0.0187 loss_ce: 0.0187 2022/12/15 04:40:24 - mmengine - INFO - Epoch(train) [5][3350/3952] lr: 3.8975e-05 eta: 1:12:26 time: 0.8879 data_time: 0.0038 memory: 11981 loss: 0.0174 loss_ce: 0.0174 2022/12/15 04:41:10 - mmengine - INFO - Epoch(train) [5][3400/3952] lr: 3.8234e-05 eta: 1:11:38 time: 0.9033 data_time: 0.0040 memory: 11981 loss: 0.0183 loss_ce: 0.0183 2022/12/15 04:41:55 - mmengine - INFO - Epoch(train) [5][3450/3952] lr: 3.7500e-05 eta: 1:10:50 time: 0.9214 data_time: 0.0033 memory: 11981 loss: 0.0192 loss_ce: 0.0192 2022/12/15 04:42:39 - mmengine - INFO - Epoch(train) [5][3500/3952] lr: 3.6774e-05 eta: 1:10:01 time: 0.9127 data_time: 0.0032 memory: 11981 loss: 0.0180 loss_ce: 0.0180 2022/12/15 04:43:24 - mmengine - INFO - Epoch(train) [5][3550/3952] lr: 3.6055e-05 eta: 1:09:13 time: 0.8782 data_time: 0.0033 memory: 11981 loss: 0.0163 loss_ce: 0.0163 2022/12/15 04:44:09 - mmengine - INFO - Epoch(train) [5][3600/3952] lr: 3.5343e-05 eta: 1:08:25 time: 0.8992 data_time: 0.0037 memory: 11981 loss: 0.0181 loss_ce: 0.0181 2022/12/15 04:44:54 - mmengine - INFO - Epoch(train) [5][3650/3952] lr: 3.4638e-05 eta: 1:07:36 time: 0.8678 data_time: 0.0037 memory: 11981 loss: 0.0171 loss_ce: 0.0171 2022/12/15 04:45:39 - mmengine - INFO - Epoch(train) [5][3700/3952] lr: 3.3941e-05 eta: 1:06:48 time: 0.9392 data_time: 0.0035 memory: 11981 loss: 0.0174 loss_ce: 0.0174 2022/12/15 04:46:26 - mmengine - INFO - Epoch(train) [5][3750/3952] lr: 3.3251e-05 eta: 1:06:00 time: 0.9814 data_time: 0.0036 memory: 11981 loss: 0.0187 loss_ce: 0.0187 2022/12/15 04:47:15 - mmengine - INFO - Epoch(train) [5][3800/3952] lr: 3.2569e-05 eta: 1:05:13 time: 0.9682 data_time: 0.0036 memory: 11981 loss: 0.0172 loss_ce: 0.0172 2022/12/15 04:48:02 - mmengine - INFO - Epoch(train) [5][3850/3952] lr: 3.1894e-05 eta: 1:04:25 time: 0.9349 data_time: 0.0036 memory: 11981 loss: 0.0186 loss_ce: 0.0186 2022/12/15 04:48:48 - mmengine - INFO - Epoch(train) [5][3900/3952] lr: 3.1226e-05 eta: 1:03:37 time: 0.9261 data_time: 0.0034 memory: 11981 loss: 0.0174 loss_ce: 0.0174 2022/12/15 04:49:19 - mmengine - INFO - Epoch(train) [5][3950/3952] lr: 3.0566e-05 eta: 1:02:46 time: 0.6117 data_time: 0.0046 memory: 11981 loss: 0.0175 loss_ce: 0.0175 2022/12/15 04:49:20 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 04:49:20 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/15 04:49:25 - mmengine - INFO - Epoch(val) [5][ 50/1918] eta: 0:01:44 time: 0.0448 data_time: 0.0015 memory: 11981 2022/12/15 04:49:27 - mmengine - INFO - Epoch(val) [5][ 100/1918] eta: 0:01:21 time: 0.0357 data_time: 0.0008 memory: 453 2022/12/15 04:49:29 - mmengine - INFO - Epoch(val) [5][ 150/1918] eta: 0:01:11 time: 0.0259 data_time: 0.0002 memory: 453 2022/12/15 04:49:31 - mmengine - INFO - Epoch(val) [5][ 200/1918] eta: 0:01:07 time: 0.0397 data_time: 0.0002 memory: 453 2022/12/15 04:49:33 - mmengine - INFO - Epoch(val) [5][ 250/1918] eta: 0:01:08 time: 0.0482 data_time: 0.0001 memory: 453 2022/12/15 04:49:35 - mmengine - INFO - Epoch(val) [5][ 300/1918] eta: 0:01:08 time: 0.0485 data_time: 0.0018 memory: 453 2022/12/15 04:49:38 - mmengine - INFO - Epoch(val) [5][ 350/1918] eta: 0:01:07 time: 0.0505 data_time: 0.0036 memory: 453 2022/12/15 04:49:40 - mmengine - INFO - Epoch(val) [5][ 400/1918] eta: 0:01:06 time: 0.0475 data_time: 0.0007 memory: 453 2022/12/15 04:49:43 - mmengine - INFO - Epoch(val) [5][ 450/1918] eta: 0:01:05 time: 0.0515 data_time: 0.0002 memory: 453 2022/12/15 04:49:45 - mmengine - INFO - Epoch(val) [5][ 500/1918] eta: 0:01:04 time: 0.0480 data_time: 0.0013 memory: 453 2022/12/15 04:49:48 - mmengine - INFO - Epoch(val) [5][ 550/1918] eta: 0:01:02 time: 0.0477 data_time: 0.0020 memory: 453 2022/12/15 04:49:50 - mmengine - INFO - Epoch(val) [5][ 600/1918] eta: 0:01:00 time: 0.0491 data_time: 0.0020 memory: 453 2022/12/15 04:49:53 - mmengine - INFO - Epoch(val) [5][ 650/1918] eta: 0:00:58 time: 0.0500 data_time: 0.0032 memory: 453 2022/12/15 04:49:55 - mmengine - INFO - Epoch(val) [5][ 700/1918] eta: 0:00:56 time: 0.0510 data_time: 0.0019 memory: 453 2022/12/15 04:49:58 - mmengine - INFO - Epoch(val) [5][ 750/1918] eta: 0:00:54 time: 0.0510 data_time: 0.0038 memory: 453 2022/12/15 04:50:00 - mmengine - INFO - Epoch(val) [5][ 800/1918] eta: 0:00:52 time: 0.0511 data_time: 0.0024 memory: 453 2022/12/15 04:50:03 - mmengine - INFO - Epoch(val) [5][ 850/1918] eta: 0:00:50 time: 0.0491 data_time: 0.0033 memory: 453 2022/12/15 04:50:05 - mmengine - INFO - Epoch(val) [5][ 900/1918] eta: 0:00:48 time: 0.0472 data_time: 0.0024 memory: 453 2022/12/15 04:50:08 - mmengine - INFO - Epoch(val) [5][ 950/1918] eta: 0:00:45 time: 0.0490 data_time: 0.0046 memory: 453 2022/12/15 04:50:10 - mmengine - INFO - Epoch(val) [5][1000/1918] eta: 0:00:43 time: 0.0477 data_time: 0.0024 memory: 453 2022/12/15 04:50:13 - mmengine - INFO - Epoch(val) [5][1050/1918] eta: 0:00:41 time: 0.0505 data_time: 0.0044 memory: 453 2022/12/15 04:50:15 - mmengine - INFO - Epoch(val) [5][1100/1918] eta: 0:00:39 time: 0.0489 data_time: 0.0002 memory: 453 2022/12/15 04:50:18 - mmengine - INFO - Epoch(val) [5][1150/1918] eta: 0:00:36 time: 0.0487 data_time: 0.0038 memory: 453 2022/12/15 04:50:20 - mmengine - INFO - Epoch(val) [5][1200/1918] eta: 0:00:34 time: 0.0485 data_time: 0.0037 memory: 453 2022/12/15 04:50:23 - mmengine - INFO - Epoch(val) [5][1250/1918] eta: 0:00:32 time: 0.0511 data_time: 0.0046 memory: 453 2022/12/15 04:50:25 - mmengine - INFO - Epoch(val) [5][1300/1918] eta: 0:00:29 time: 0.0524 data_time: 0.0039 memory: 453 2022/12/15 04:50:28 - mmengine - INFO - Epoch(val) [5][1350/1918] eta: 0:00:27 time: 0.0615 data_time: 0.0005 memory: 453 2022/12/15 04:50:31 - mmengine - INFO - Epoch(val) [5][1400/1918] eta: 0:00:25 time: 0.0487 data_time: 0.0010 memory: 453 2022/12/15 04:50:33 - mmengine - INFO - Epoch(val) [5][1450/1918] eta: 0:00:22 time: 0.0561 data_time: 0.0002 memory: 453 2022/12/15 04:50:36 - mmengine - INFO - Epoch(val) [5][1500/1918] eta: 0:00:20 time: 0.0585 data_time: 0.0007 memory: 453 2022/12/15 04:50:39 - mmengine - INFO - Epoch(val) [5][1550/1918] eta: 0:00:18 time: 0.0546 data_time: 0.0011 memory: 453 2022/12/15 04:50:42 - mmengine - INFO - Epoch(val) [5][1600/1918] eta: 0:00:15 time: 0.0558 data_time: 0.0019 memory: 453 2022/12/15 04:50:45 - mmengine - INFO - Epoch(val) [5][1650/1918] eta: 0:00:13 time: 0.0497 data_time: 0.0022 memory: 453 2022/12/15 04:50:46 - mmengine - INFO - Epoch(val) [5][1700/1918] eta: 0:00:10 time: 0.0349 data_time: 0.0014 memory: 453 2022/12/15 04:50:48 - mmengine - INFO - Epoch(val) [5][1750/1918] eta: 0:00:08 time: 0.0306 data_time: 0.0013 memory: 453 2022/12/15 04:50:50 - mmengine - INFO - Epoch(val) [5][1800/1918] eta: 0:00:05 time: 0.0277 data_time: 0.0003 memory: 453 2022/12/15 04:50:51 - mmengine - INFO - Epoch(val) [5][1850/1918] eta: 0:00:03 time: 0.0246 data_time: 0.0003 memory: 453 2022/12/15 04:50:52 - mmengine - INFO - Epoch(val) [5][1900/1918] eta: 0:00:00 time: 0.0236 data_time: 0.0002 memory: 453 2022/12/15 04:50:54 - mmengine - INFO - Epoch(val) [5][1918/1918] CUTE80/recog/word_acc: 0.6667 CUTE80/recog/word_acc_ignore_case: 0.8160 CUTE80/recog/word_acc_ignore_case_symbol: 0.8333 IIIT5K/recog/word_acc: 0.3773 IIIT5K/recog/word_acc_ignore_case: 0.8363 IIIT5K/recog/word_acc_ignore_case_symbol: 0.9310 SVT/recog/word_acc: 0.1777 SVT/recog/word_acc_ignore_case: 0.8702 SVT/recog/word_acc_ignore_case_symbol: 0.9011 SVTP/recog/word_acc: 0.3442 SVTP/recog/word_acc_ignore_case: 0.7829 SVTP/recog/word_acc_ignore_case_symbol: 0.7953 IC13/recog/word_acc: 0.8325 IC13/recog/word_acc_ignore_case: 0.9202 IC13/recog/word_acc_ignore_case_symbol: 0.9291 IC15/recog/word_acc: 0.5566 IC15/recog/word_acc_ignore_case: 0.7222 IC15/recog/word_acc_ignore_case_symbol: 0.7525 CUTE80/recog/char_recall: 0.9103 CUTE80/recog/char_precision: 0.9361 IIIT5K/recog/char_recall: 0.9782 IIIT5K/recog/char_precision: 0.9774 SVT/recog/char_recall: 0.9668 SVT/recog/char_precision: 0.9748 SVTP/recog/char_recall: 0.9097 SVTP/recog/char_precision: 0.9382 IC13/recog/char_recall: 0.9796 IC13/recog/char_precision: 0.9771 IC15/recog/char_recall: 0.9007 IC15/recog/char_precision: 0.9128 2022/12/15 04:51:54 - mmengine - INFO - Epoch(train) [6][ 50/3952] lr: 2.9888e-05 eta: 1:01:59 time: 0.9103 data_time: 0.0032 memory: 11981 loss: 0.0175 loss_ce: 0.0175 2022/12/15 04:52:38 - mmengine - INFO - Epoch(train) [6][ 100/3952] lr: 2.9243e-05 eta: 1:01:10 time: 0.9213 data_time: 0.0037 memory: 11981 loss: 0.0170 loss_ce: 0.0170 2022/12/15 04:53:24 - mmengine - INFO - Epoch(train) [6][ 150/3952] lr: 2.8606e-05 eta: 1:00:22 time: 0.8683 data_time: 0.0034 memory: 11981 loss: 0.0152 loss_ce: 0.0152 2022/12/15 04:54:10 - mmengine - INFO - Epoch(train) [6][ 200/3952] lr: 2.7977e-05 eta: 0:59:34 time: 0.8612 data_time: 0.0038 memory: 11981 loss: 0.0159 loss_ce: 0.0159 2022/12/15 04:54:48 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 04:54:57 - mmengine - INFO - Epoch(train) [6][ 250/3952] lr: 2.7355e-05 eta: 0:58:47 time: 0.9615 data_time: 0.0038 memory: 11981 loss: 0.0172 loss_ce: 0.0172 2022/12/15 04:55:43 - mmengine - INFO - Epoch(train) [6][ 300/3952] lr: 2.6741e-05 eta: 0:57:59 time: 0.9525 data_time: 0.0031 memory: 11981 loss: 0.0165 loss_ce: 0.0165 2022/12/15 04:56:29 - mmengine - INFO - Epoch(train) [6][ 350/3952] lr: 2.6134e-05 eta: 0:57:11 time: 0.8812 data_time: 0.0036 memory: 11981 loss: 0.0159 loss_ce: 0.0159 2022/12/15 04:57:16 - mmengine - INFO - Epoch(train) [6][ 400/3952] lr: 2.5535e-05 eta: 0:56:23 time: 0.9339 data_time: 0.0034 memory: 11981 loss: 0.0181 loss_ce: 0.0181 2022/12/15 04:58:03 - mmengine - INFO - Epoch(train) [6][ 450/3952] lr: 2.4944e-05 eta: 0:55:35 time: 0.9573 data_time: 0.0034 memory: 11981 loss: 0.0167 loss_ce: 0.0167 2022/12/15 04:58:49 - mmengine - INFO - Epoch(train) [6][ 500/3952] lr: 2.4361e-05 eta: 0:54:47 time: 0.9549 data_time: 0.0034 memory: 11981 loss: 0.0170 loss_ce: 0.0170 2022/12/15 04:59:35 - mmengine - INFO - Epoch(train) [6][ 550/3952] lr: 2.3786e-05 eta: 0:53:59 time: 0.8550 data_time: 0.0034 memory: 11981 loss: 0.0166 loss_ce: 0.0166 2022/12/15 05:00:21 - mmengine - INFO - Epoch(train) [6][ 600/3952] lr: 2.3218e-05 eta: 0:53:12 time: 0.9057 data_time: 0.0033 memory: 11981 loss: 0.0162 loss_ce: 0.0162 2022/12/15 05:01:06 - mmengine - INFO - Epoch(train) [6][ 650/3952] lr: 2.2658e-05 eta: 0:52:24 time: 0.8798 data_time: 0.0040 memory: 11981 loss: 0.0174 loss_ce: 0.0174 2022/12/15 05:01:53 - mmengine - INFO - Epoch(train) [6][ 700/3952] lr: 2.2106e-05 eta: 0:51:36 time: 0.9479 data_time: 0.0035 memory: 11981 loss: 0.0164 loss_ce: 0.0164 2022/12/15 05:02:39 - mmengine - INFO - Epoch(train) [6][ 750/3952] lr: 2.1562e-05 eta: 0:50:48 time: 0.8582 data_time: 0.0038 memory: 11981 loss: 0.0175 loss_ce: 0.0175 2022/12/15 05:03:26 - mmengine - INFO - Epoch(train) [6][ 800/3952] lr: 2.1026e-05 eta: 0:50:00 time: 0.9469 data_time: 0.0039 memory: 11981 loss: 0.0178 loss_ce: 0.0178 2022/12/15 05:04:14 - mmengine - INFO - Epoch(train) [6][ 850/3952] lr: 2.0498e-05 eta: 0:49:13 time: 0.9819 data_time: 0.0035 memory: 11981 loss: 0.0169 loss_ce: 0.0169 2022/12/15 05:04:59 - mmengine - INFO - Epoch(train) [6][ 900/3952] lr: 1.9978e-05 eta: 0:48:25 time: 0.9016 data_time: 0.0040 memory: 11981 loss: 0.0155 loss_ce: 0.0155 2022/12/15 05:05:44 - mmengine - INFO - Epoch(train) [6][ 950/3952] lr: 1.9466e-05 eta: 0:47:37 time: 0.8950 data_time: 0.0034 memory: 11981 loss: 0.0163 loss_ce: 0.0163 2022/12/15 05:06:29 - mmengine - INFO - Epoch(train) [6][1000/3952] lr: 1.8962e-05 eta: 0:46:49 time: 0.8981 data_time: 0.0042 memory: 11981 loss: 0.0162 loss_ce: 0.0162 2022/12/15 05:07:16 - mmengine - INFO - Epoch(train) [6][1050/3952] lr: 1.8465e-05 eta: 0:46:01 time: 0.9314 data_time: 0.0035 memory: 11981 loss: 0.0158 loss_ce: 0.0158 2022/12/15 05:08:02 - mmengine - INFO - Epoch(train) [6][1100/3952] lr: 1.7977e-05 eta: 0:45:13 time: 0.9301 data_time: 0.0037 memory: 11981 loss: 0.0179 loss_ce: 0.0179 2022/12/15 05:08:49 - mmengine - INFO - Epoch(train) [6][1150/3952] lr: 1.7497e-05 eta: 0:44:26 time: 0.9665 data_time: 0.0035 memory: 11981 loss: 0.0159 loss_ce: 0.0159 2022/12/15 05:09:35 - mmengine - INFO - Epoch(train) [6][1200/3952] lr: 1.7025e-05 eta: 0:43:38 time: 0.9423 data_time: 0.0040 memory: 11981 loss: 0.0164 loss_ce: 0.0164 2022/12/15 05:10:12 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 05:10:21 - mmengine - INFO - Epoch(train) [6][1250/3952] lr: 1.6562e-05 eta: 0:42:50 time: 0.8770 data_time: 0.0038 memory: 11981 loss: 0.0165 loss_ce: 0.0165 2022/12/15 05:11:08 - mmengine - INFO - Epoch(train) [6][1300/3952] lr: 1.6106e-05 eta: 0:42:02 time: 0.9446 data_time: 0.0051 memory: 11981 loss: 0.0190 loss_ce: 0.0190 2022/12/15 05:11:53 - mmengine - INFO - Epoch(train) [6][1350/3952] lr: 1.5658e-05 eta: 0:41:15 time: 0.9548 data_time: 0.0039 memory: 11981 loss: 0.0162 loss_ce: 0.0162 2022/12/15 05:12:38 - mmengine - INFO - Epoch(train) [6][1400/3952] lr: 1.5219e-05 eta: 0:40:27 time: 0.9040 data_time: 0.0033 memory: 11981 loss: 0.0168 loss_ce: 0.0168 2022/12/15 05:13:25 - mmengine - INFO - Epoch(train) [6][1450/3952] lr: 1.4788e-05 eta: 0:39:39 time: 0.9350 data_time: 0.0035 memory: 11981 loss: 0.0167 loss_ce: 0.0167 2022/12/15 05:14:12 - mmengine - INFO - Epoch(train) [6][1500/3952] lr: 1.4365e-05 eta: 0:38:52 time: 0.9246 data_time: 0.0036 memory: 11981 loss: 0.0159 loss_ce: 0.0159 2022/12/15 05:14:58 - mmengine - INFO - Epoch(train) [6][1550/3952] lr: 1.3950e-05 eta: 0:38:04 time: 0.8501 data_time: 0.0036 memory: 11981 loss: 0.0158 loss_ce: 0.0158 2022/12/15 05:15:43 - mmengine - INFO - Epoch(train) [6][1600/3952] lr: 1.3544e-05 eta: 0:37:16 time: 0.9262 data_time: 0.0035 memory: 11981 loss: 0.0165 loss_ce: 0.0165 2022/12/15 05:16:30 - mmengine - INFO - Epoch(train) [6][1650/3952] lr: 1.3146e-05 eta: 0:36:28 time: 0.9028 data_time: 0.0042 memory: 11981 loss: 0.0175 loss_ce: 0.0175 2022/12/15 05:17:16 - mmengine - INFO - Epoch(train) [6][1700/3952] lr: 1.2756e-05 eta: 0:35:41 time: 0.8814 data_time: 0.0050 memory: 11981 loss: 0.0186 loss_ce: 0.0186 2022/12/15 05:18:02 - mmengine - INFO - Epoch(train) [6][1750/3952] lr: 1.2374e-05 eta: 0:34:53 time: 0.8771 data_time: 0.0040 memory: 11981 loss: 0.0161 loss_ce: 0.0161 2022/12/15 05:18:50 - mmengine - INFO - Epoch(train) [6][1800/3952] lr: 1.2001e-05 eta: 0:34:05 time: 0.9601 data_time: 0.0035 memory: 11981 loss: 0.0165 loss_ce: 0.0165 2022/12/15 05:19:35 - mmengine - INFO - Epoch(train) [6][1850/3952] lr: 1.1636e-05 eta: 0:33:18 time: 0.8827 data_time: 0.0046 memory: 11981 loss: 0.0160 loss_ce: 0.0160 2022/12/15 05:20:22 - mmengine - INFO - Epoch(train) [6][1900/3952] lr: 1.1279e-05 eta: 0:32:30 time: 0.9056 data_time: 0.0045 memory: 11981 loss: 0.0155 loss_ce: 0.0155 2022/12/15 05:21:10 - mmengine - INFO - Epoch(train) [6][1950/3952] lr: 1.0931e-05 eta: 0:31:43 time: 0.9203 data_time: 0.0037 memory: 11981 loss: 0.0163 loss_ce: 0.0163 2022/12/15 05:21:56 - mmengine - INFO - Epoch(train) [6][2000/3952] lr: 1.0591e-05 eta: 0:30:55 time: 0.9099 data_time: 0.0039 memory: 11981 loss: 0.0156 loss_ce: 0.0156 2022/12/15 05:22:41 - mmengine - INFO - Epoch(train) [6][2050/3952] lr: 1.0260e-05 eta: 0:30:07 time: 0.9351 data_time: 0.0053 memory: 11981 loss: 0.0177 loss_ce: 0.0177 2022/12/15 05:23:26 - mmengine - INFO - Epoch(train) [6][2100/3952] lr: 9.9370e-06 eta: 0:29:20 time: 0.9198 data_time: 0.0035 memory: 11981 loss: 0.0167 loss_ce: 0.0167 2022/12/15 05:24:15 - mmengine - INFO - Epoch(train) [6][2150/3952] lr: 9.6224e-06 eta: 0:28:32 time: 0.9891 data_time: 0.0035 memory: 11981 loss: 0.0169 loss_ce: 0.0169 2022/12/15 05:25:03 - mmengine - INFO - Epoch(train) [6][2200/3952] lr: 9.3163e-06 eta: 0:27:45 time: 0.9796 data_time: 0.0035 memory: 11981 loss: 0.0155 loss_ce: 0.0155 2022/12/15 05:25:40 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 05:25:49 - mmengine - INFO - Epoch(train) [6][2250/3952] lr: 9.0186e-06 eta: 0:26:57 time: 0.8735 data_time: 0.0036 memory: 11981 loss: 0.0167 loss_ce: 0.0167 2022/12/15 05:26:37 - mmengine - INFO - Epoch(train) [6][2300/3952] lr: 8.7294e-06 eta: 0:26:09 time: 0.9972 data_time: 0.0038 memory: 11981 loss: 0.0166 loss_ce: 0.0166 2022/12/15 05:27:23 - mmengine - INFO - Epoch(train) [6][2350/3952] lr: 8.4487e-06 eta: 0:25:22 time: 0.9493 data_time: 0.0041 memory: 11981 loss: 0.0166 loss_ce: 0.0166 2022/12/15 05:28:10 - mmengine - INFO - Epoch(train) [6][2400/3952] lr: 8.1765e-06 eta: 0:24:34 time: 0.9533 data_time: 0.0039 memory: 11981 loss: 0.0167 loss_ce: 0.0167 2022/12/15 05:28:55 - mmengine - INFO - Epoch(train) [6][2450/3952] lr: 7.9127e-06 eta: 0:23:47 time: 0.8820 data_time: 0.0038 memory: 11981 loss: 0.0159 loss_ce: 0.0159 2022/12/15 05:29:42 - mmengine - INFO - Epoch(train) [6][2500/3952] lr: 7.6575e-06 eta: 0:22:59 time: 0.9414 data_time: 0.0041 memory: 11981 loss: 0.0156 loss_ce: 0.0156 2022/12/15 05:30:28 - mmengine - INFO - Epoch(train) [6][2550/3952] lr: 7.4109e-06 eta: 0:22:11 time: 0.9668 data_time: 0.0031 memory: 11981 loss: 0.0174 loss_ce: 0.0174 2022/12/15 05:31:14 - mmengine - INFO - Epoch(train) [6][2600/3952] lr: 7.1727e-06 eta: 0:21:24 time: 0.9438 data_time: 0.0036 memory: 11981 loss: 0.0179 loss_ce: 0.0179 2022/12/15 05:31:59 - mmengine - INFO - Epoch(train) [6][2650/3952] lr: 6.9431e-06 eta: 0:20:36 time: 0.9118 data_time: 0.0036 memory: 11981 loss: 0.0165 loss_ce: 0.0165 2022/12/15 05:32:44 - mmengine - INFO - Epoch(train) [6][2700/3952] lr: 6.7221e-06 eta: 0:19:49 time: 0.9071 data_time: 0.0032 memory: 11981 loss: 0.0176 loss_ce: 0.0176 2022/12/15 05:33:29 - mmengine - INFO - Epoch(train) [6][2750/3952] lr: 6.5096e-06 eta: 0:19:01 time: 0.9038 data_time: 0.0039 memory: 11981 loss: 0.0160 loss_ce: 0.0160 2022/12/15 05:34:15 - mmengine - INFO - Epoch(train) [6][2800/3952] lr: 6.3058e-06 eta: 0:18:13 time: 0.9261 data_time: 0.0034 memory: 11981 loss: 0.0163 loss_ce: 0.0163 2022/12/15 05:35:01 - mmengine - INFO - Epoch(train) [6][2850/3952] lr: 6.1105e-06 eta: 0:17:26 time: 0.9251 data_time: 0.0033 memory: 11981 loss: 0.0164 loss_ce: 0.0164 2022/12/15 05:35:47 - mmengine - INFO - Epoch(train) [6][2900/3952] lr: 5.9238e-06 eta: 0:16:38 time: 0.9437 data_time: 0.0032 memory: 11981 loss: 0.0166 loss_ce: 0.0166 2022/12/15 05:36:34 - mmengine - INFO - Epoch(train) [6][2950/3952] lr: 5.7457e-06 eta: 0:15:51 time: 0.9403 data_time: 0.0044 memory: 11981 loss: 0.0166 loss_ce: 0.0166 2022/12/15 05:37:19 - mmengine - INFO - Epoch(train) [6][3000/3952] lr: 5.5762e-06 eta: 0:15:03 time: 0.8476 data_time: 0.0047 memory: 11981 loss: 0.0168 loss_ce: 0.0168 2022/12/15 05:38:05 - mmengine - INFO - Epoch(train) [6][3050/3952] lr: 5.4153e-06 eta: 0:14:16 time: 0.8849 data_time: 0.0031 memory: 11981 loss: 0.0166 loss_ce: 0.0166 2022/12/15 05:38:51 - mmengine - INFO - Epoch(train) [6][3100/3952] lr: 5.2631e-06 eta: 0:13:28 time: 0.9052 data_time: 0.0040 memory: 11981 loss: 0.0162 loss_ce: 0.0162 2022/12/15 05:39:36 - mmengine - INFO - Epoch(train) [6][3150/3952] lr: 5.1195e-06 eta: 0:12:41 time: 0.8744 data_time: 0.0035 memory: 11981 loss: 0.0156 loss_ce: 0.0156 2022/12/15 05:40:23 - mmengine - INFO - Epoch(train) [6][3200/3952] lr: 4.9845e-06 eta: 0:11:53 time: 0.9238 data_time: 0.0034 memory: 11981 loss: 0.0162 loss_ce: 0.0162 2022/12/15 05:41:00 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 05:41:09 - mmengine - INFO - Epoch(train) [6][3250/3952] lr: 4.8582e-06 eta: 0:11:06 time: 0.8959 data_time: 0.0036 memory: 11981 loss: 0.0159 loss_ce: 0.0159 2022/12/15 05:41:54 - mmengine - INFO - Epoch(train) [6][3300/3952] lr: 4.7405e-06 eta: 0:10:18 time: 0.8998 data_time: 0.0036 memory: 11981 loss: 0.0171 loss_ce: 0.0171 2022/12/15 05:42:40 - mmengine - INFO - Epoch(train) [6][3350/3952] lr: 4.6315e-06 eta: 0:09:31 time: 0.8719 data_time: 0.0035 memory: 11981 loss: 0.0153 loss_ce: 0.0153 2022/12/15 05:43:25 - mmengine - INFO - Epoch(train) [6][3400/3952] lr: 4.5312e-06 eta: 0:08:43 time: 0.8597 data_time: 0.0032 memory: 11981 loss: 0.0154 loss_ce: 0.0154 2022/12/15 05:44:11 - mmengine - INFO - Epoch(train) [6][3450/3952] lr: 4.4395e-06 eta: 0:07:56 time: 0.9310 data_time: 0.0034 memory: 11981 loss: 0.0176 loss_ce: 0.0176 2022/12/15 05:44:56 - mmengine - INFO - Epoch(train) [6][3500/3952] lr: 4.3565e-06 eta: 0:07:08 time: 0.8928 data_time: 0.0031 memory: 11981 loss: 0.0148 loss_ce: 0.0148 2022/12/15 05:45:42 - mmengine - INFO - Epoch(train) [6][3550/3952] lr: 4.2822e-06 eta: 0:06:21 time: 0.9343 data_time: 0.0036 memory: 11981 loss: 0.0155 loss_ce: 0.0155 2022/12/15 05:46:28 - mmengine - INFO - Epoch(train) [6][3600/3952] lr: 4.2165e-06 eta: 0:05:33 time: 0.9501 data_time: 0.0041 memory: 11981 loss: 0.0164 loss_ce: 0.0164 2022/12/15 05:47:15 - mmengine - INFO - Epoch(train) [6][3650/3952] lr: 4.1595e-06 eta: 0:04:46 time: 0.9230 data_time: 0.0049 memory: 11981 loss: 0.0170 loss_ce: 0.0170 2022/12/15 05:48:03 - mmengine - INFO - Epoch(train) [6][3700/3952] lr: 4.1112e-06 eta: 0:03:59 time: 0.9852 data_time: 0.0048 memory: 11981 loss: 0.0147 loss_ce: 0.0147 2022/12/15 05:48:47 - mmengine - INFO - Epoch(train) [6][3750/3952] lr: 4.0716e-06 eta: 0:03:11 time: 0.9032 data_time: 0.0035 memory: 11981 loss: 0.0160 loss_ce: 0.0160 2022/12/15 05:49:33 - mmengine - INFO - Epoch(train) [6][3800/3952] lr: 4.0407e-06 eta: 0:02:24 time: 0.9313 data_time: 0.0034 memory: 11981 loss: 0.0158 loss_ce: 0.0158 2022/12/15 05:50:20 - mmengine - INFO - Epoch(train) [6][3850/3952] lr: 4.0184e-06 eta: 0:01:36 time: 0.9778 data_time: 0.0034 memory: 11981 loss: 0.0152 loss_ce: 0.0152 2022/12/15 05:51:07 - mmengine - INFO - Epoch(train) [6][3900/3952] lr: 4.0049e-06 eta: 0:00:49 time: 0.9787 data_time: 0.0032 memory: 11981 loss: 0.0165 loss_ce: 0.0165 2022/12/15 05:51:37 - mmengine - INFO - Epoch(train) [6][3950/3952] lr: 4.0000e-06 eta: 0:00:01 time: 0.5585 data_time: 0.0039 memory: 11981 loss: 0.0175 loss_ce: 0.0175 2022/12/15 05:51:38 - mmengine - INFO - Exp name: aster_6e_st_mj_20221214_232605 2022/12/15 05:51:38 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/15 05:51:44 - mmengine - INFO - Epoch(val) [6][ 50/1918] eta: 0:01:54 time: 0.0659 data_time: 0.0036 memory: 11981 2022/12/15 05:51:47 - mmengine - INFO - Epoch(val) [6][ 100/1918] eta: 0:01:39 time: 0.0479 data_time: 0.0007 memory: 453 2022/12/15 05:51:49 - mmengine - INFO - Epoch(val) [6][ 150/1918] eta: 0:01:33 time: 0.0509 data_time: 0.0007 memory: 453 2022/12/15 05:51:52 - mmengine - INFO - Epoch(val) [6][ 200/1918] eta: 0:01:29 time: 0.0503 data_time: 0.0010 memory: 453 2022/12/15 05:51:54 - mmengine - INFO - Epoch(val) [6][ 250/1918] eta: 0:01:27 time: 0.0482 data_time: 0.0001 memory: 453 2022/12/15 05:51:57 - mmengine - INFO - Epoch(val) [6][ 300/1918] eta: 0:01:24 time: 0.0482 data_time: 0.0008 memory: 453 2022/12/15 05:51:59 - mmengine - INFO - Epoch(val) [6][ 350/1918] eta: 0:01:20 time: 0.0475 data_time: 0.0001 memory: 453 2022/12/15 05:52:02 - mmengine - INFO - Epoch(val) [6][ 400/1918] eta: 0:01:17 time: 0.0486 data_time: 0.0020 memory: 453 2022/12/15 05:52:04 - mmengine - INFO - Epoch(val) [6][ 450/1918] eta: 0:01:14 time: 0.0472 data_time: 0.0015 memory: 453 2022/12/15 05:52:06 - mmengine - INFO - Epoch(val) [6][ 500/1918] eta: 0:01:11 time: 0.0462 data_time: 0.0012 memory: 453 2022/12/15 05:52:09 - mmengine - INFO - Epoch(val) [6][ 550/1918] eta: 0:01:09 time: 0.0493 data_time: 0.0018 memory: 453 2022/12/15 05:52:11 - mmengine - INFO - Epoch(val) [6][ 600/1918] eta: 0:01:06 time: 0.0489 data_time: 0.0012 memory: 453 2022/12/15 05:52:14 - mmengine - INFO - Epoch(val) [6][ 650/1918] eta: 0:01:03 time: 0.0476 data_time: 0.0053 memory: 453 2022/12/15 05:52:16 - mmengine - INFO - Epoch(val) [6][ 700/1918] eta: 0:01:01 time: 0.0484 data_time: 0.0051 memory: 453 2022/12/15 05:52:19 - mmengine - INFO - Epoch(val) [6][ 750/1918] eta: 0:00:58 time: 0.0480 data_time: 0.0044 memory: 453 2022/12/15 05:52:21 - mmengine - INFO - Epoch(val) [6][ 800/1918] eta: 0:00:55 time: 0.0483 data_time: 0.0052 memory: 453 2022/12/15 05:52:23 - mmengine - INFO - Epoch(val) [6][ 850/1918] eta: 0:00:53 time: 0.0469 data_time: 0.0038 memory: 453 2022/12/15 05:52:26 - mmengine - INFO - Epoch(val) [6][ 900/1918] eta: 0:00:50 time: 0.0482 data_time: 0.0054 memory: 453 2022/12/15 05:52:28 - mmengine - INFO - Epoch(val) [6][ 950/1918] eta: 0:00:48 time: 0.0357 data_time: 0.0003 memory: 453 2022/12/15 05:52:30 - mmengine - INFO - Epoch(val) [6][1000/1918] eta: 0:00:45 time: 0.0290 data_time: 0.0006 memory: 453 2022/12/15 05:52:32 - mmengine - INFO - Epoch(val) [6][1050/1918] eta: 0:00:42 time: 0.0378 data_time: 0.0017 memory: 453 2022/12/15 05:52:34 - mmengine - INFO - Epoch(val) [6][1100/1918] eta: 0:00:39 time: 0.0271 data_time: 0.0003 memory: 453 2022/12/15 05:52:36 - mmengine - INFO - Epoch(val) [6][1150/1918] eta: 0:00:36 time: 0.0539 data_time: 0.0002 memory: 453 2022/12/15 05:52:39 - mmengine - INFO - Epoch(val) [6][1200/1918] eta: 0:00:34 time: 0.0501 data_time: 0.0001 memory: 453 2022/12/15 05:52:42 - mmengine - INFO - Epoch(val) [6][1250/1918] eta: 0:00:32 time: 0.0506 data_time: 0.0001 memory: 453 2022/12/15 05:52:44 - mmengine - INFO - Epoch(val) [6][1300/1918] eta: 0:00:29 time: 0.0510 data_time: 0.0001 memory: 453 2022/12/15 05:52:47 - mmengine - INFO - Epoch(val) [6][1350/1918] eta: 0:00:27 time: 0.0630 data_time: 0.0002 memory: 453 2022/12/15 05:52:50 - mmengine - INFO - Epoch(val) [6][1400/1918] eta: 0:00:25 time: 0.0504 data_time: 0.0001 memory: 453 2022/12/15 05:52:53 - mmengine - INFO - Epoch(val) [6][1450/1918] eta: 0:00:23 time: 0.0546 data_time: 0.0001 memory: 453 2022/12/15 05:52:55 - mmengine - INFO - Epoch(val) [6][1500/1918] eta: 0:00:20 time: 0.0501 data_time: 0.0001 memory: 453 2022/12/15 05:52:58 - mmengine - INFO - Epoch(val) [6][1550/1918] eta: 0:00:18 time: 0.0777 data_time: 0.0002 memory: 453 2022/12/15 05:53:00 - mmengine - INFO - Epoch(val) [6][1600/1918] eta: 0:00:15 time: 0.0369 data_time: 0.0006 memory: 453 2022/12/15 05:53:02 - mmengine - INFO - Epoch(val) [6][1650/1918] eta: 0:00:13 time: 0.0564 data_time: 0.0076 memory: 453 2022/12/15 05:53:05 - mmengine - INFO - Epoch(val) [6][1700/1918] eta: 0:00:10 time: 0.0517 data_time: 0.0055 memory: 453 2022/12/15 05:53:08 - mmengine - INFO - Epoch(val) [6][1750/1918] eta: 0:00:08 time: 0.0516 data_time: 0.0047 memory: 453 2022/12/15 05:53:10 - mmengine - INFO - Epoch(val) [6][1800/1918] eta: 0:00:05 time: 0.0491 data_time: 0.0052 memory: 453 2022/12/15 05:53:12 - mmengine - INFO - Epoch(val) [6][1850/1918] eta: 0:00:03 time: 0.0190 data_time: 0.0001 memory: 453 2022/12/15 05:53:13 - mmengine - INFO - Epoch(val) [6][1900/1918] eta: 0:00:00 time: 0.0191 data_time: 0.0001 memory: 453 2022/12/15 05:53:15 - mmengine - INFO - Epoch(val) [6][1918/1918] CUTE80/recog/word_acc: 0.6944 CUTE80/recog/word_acc_ignore_case: 0.8333 CUTE80/recog/word_acc_ignore_case_symbol: 0.8507 IIIT5K/recog/word_acc: 0.3877 IIIT5K/recog/word_acc_ignore_case: 0.8417 IIIT5K/recog/word_acc_ignore_case_symbol: 0.9357 SVT/recog/word_acc: 0.1716 SVT/recog/word_acc_ignore_case: 0.8686 SVT/recog/word_acc_ignore_case_symbol: 0.8949 SVTP/recog/word_acc: 0.3612 SVTP/recog/word_acc_ignore_case: 0.7953 SVTP/recog/word_acc_ignore_case_symbol: 0.8062 IC13/recog/word_acc: 0.8286 IC13/recog/word_acc_ignore_case: 0.9182 IC13/recog/word_acc_ignore_case_symbol: 0.9281 IC15/recog/word_acc: 0.5749 IC15/recog/word_acc_ignore_case: 0.7333 IC15/recog/word_acc_ignore_case_symbol: 0.7665 CUTE80/recog/char_recall: 0.9153 CUTE80/recog/char_precision: 0.9419 IIIT5K/recog/char_recall: 0.9796 IIIT5K/recog/char_precision: 0.9783 SVT/recog/char_recall: 0.9660 SVT/recog/char_precision: 0.9753 SVTP/recog/char_recall: 0.9160 SVTP/recog/char_precision: 0.9460 IC13/recog/char_recall: 0.9807 IC13/recog/char_precision: 0.9807 IC15/recog/char_recall: 0.9032 IC15/recog/char_precision: 0.9161