2021-12-01 19:55:16,012 - mmocr - INFO - Environment info: ------------------------------------------------------------ sys.platform: linux Python: 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: Tesla PG503-216 CUDA_HOME: /mnt/lustre/share/cuda-10.2 NVCC: Cuda compilation tools, release 10.2, V10.2.89 GCC: gcc (GCC) 5.4.0 PyTorch: 1.7.1 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.3-Product Build 20210617 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 10.2 - 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_37,code=compute_37 - CuDNN 7.6.5 - Magma 2.5.2 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, TorchVision: 0.8.2 OpenCV: 4.5.3 MMCV: 1.3.14 MMCV Compiler: GCC 5.4 MMCV CUDA Compiler: 10.2 MMOCR: 0.3.0+191e497 ------------------------------------------------------------ 2021-12-01 19:55:18,052 - mmocr - INFO - Distributed training: True 2021-12-01 19:55:19,884 - mmocr - INFO - Config: checkpoint_config = dict(interval=1) log_config = dict(interval=1000, hooks=[dict(type='TextLoggerHook')]) dist_params = dict(backend='nccl') log_level = 'INFO' load_from = None resume_from = None workflow = [('train', 1)] num_chars = 37 max_seq_len = 26 label_convertor = dict( type='AttnConvertor', dict_type='DICT36', with_unknown=False, with_padding=False, lower=True) model = dict( type='ABINet', backbone=dict( type='ResTransformer', n_layers=3, n_head=8, d_model=512, d_inner=2048, dropout=0.1, max_len=256), encoder=dict( type='ABIVisionEncoder', in_channels=512, num_channels=64, attn_height=8, attn_width=32, attn_mode='nearest', use_result='feature', num_chars=37, max_seq_len=26, init_cfg=dict(type='Xavier', layer='Conv2d')), loss=dict( type='ABILoss', enc_weight=1.0, dec_weight=1.0, fusion_weight=1.0), label_convertor=dict( type='AttnConvertor', dict_type='DICT36', with_unknown=False, with_padding=False, lower=True), max_seq_len=26, iter_size=1) optimizer = dict(type='Adam', lr=0.0001) optimizer_config = dict(grad_clip=dict(max_norm=20)) lr_config = dict( policy='step', step=[16, 18], warmup='linear', warmup_iters=1, warmup_ratio=0.001, warmup_by_epoch=True) total_epochs = 20 img_norm_cfg = dict(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) train_pipeline = [ dict(type='LoadImageFromFile', file_client_args=dict(backend='petrel')), dict( type='ResizeOCR', height=32, min_width=128, max_width=128, keep_aspect_ratio=False, width_downsample_ratio=0.25), dict( type='RandomWrapper', p=0.5, transforms=[ dict( type='OneOfWrapper', transforms=[ dict(type='RandomRotateTextDet', max_angle=15), dict( type='TorchVisionWrapper', op='RandomAffine', degrees=15, translate=(0.3, 0.3), scale=(0.5, 2.0), shear=(-45, 45)), dict( type='TorchVisionWrapper', op='RandomPerspective', distortion_scale=0.5, p=1) ]) ]), dict( type='RandomWrapper', p=0.25, transforms=[ dict(type='PyramidRescale'), dict( type='Albu', transforms=[ dict(type='GaussNoise', var_limit=(20, 20), p=1), dict(type='MotionBlur', blur_limit=12, p=1) ]) ]), dict( type='RandomWrapper', p=0.25, transforms=[ dict( type='TorchVisionWrapper', op='ColorJitter', brightness=0.5, saturation=0.5, contrast=0.5, hue=0.1) ]), dict(type='ToTensorOCR'), dict( type='NormalizeOCR', mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), dict( type='Collect', keys=['img'], meta_keys=[ 'filename', 'ori_shape', 'img_shape', 'text', 'valid_ratio', 'resize_shape' ]) ] test_pipeline = [ dict(type='LoadImageFromFile', file_client_args=dict(backend='petrel')), dict( type='MultiRotateAugOCR', rotate_degrees=[0, 90, 270], transforms=[ dict( type='ResizeOCR', height=32, min_width=128, max_width=128, keep_aspect_ratio=False, width_downsample_ratio=0.25), dict(type='ToTensorOCR'), dict( type='NormalizeOCR', mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), dict( type='Collect', keys=['img'], meta_keys=[ 'filename', 'ori_shape', 'img_shape', 'valid_ratio', 'resize_shape' ]) ]) ] dataset_type = 'OCRDataset' train_prefix = 's3://openmmlab/datasets/ocr/recog/' train_ann_file1 = 'data/SynthText/labels/alphanumeric.lmdb' train_img_prefix1 = 's3://openmmlab/datasets/ocr/recog/SynthText/synthtext/SynthText_patch_horizontal/' train_img_prefix2 = 's3://openmmlab/datasets/ocr/recog/mnt/ramdisk/max/90kDICT32px/' train_ann_file2 = 'data/mnt/ramdisk/max/90kDICT32px/full_labels.lmdb' train1 = dict( type='OCRDataset', img_prefix= 's3://openmmlab/datasets/ocr/recog/SynthText/synthtext/SynthText_patch_horizontal/', ann_file='data/SynthText/labels/alphanumeric.lmdb', loader=dict( type='LmdbLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=False) train2 = dict( type='OCRDataset', img_prefix= 's3://openmmlab/datasets/ocr/recog/mnt/ramdisk/max/90kDICT32px/', ann_file='data/mnt/ramdisk/max/90kDICT32px/full_labels.lmdb', loader=dict( type='LmdbLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=False) test_prefix = 'data/mixture/testset/' test_img_prefix1 = 'data/mixture/testset/IIIT5K/' test_img_prefix2 = 'data/mixture/testset/svt/' test_img_prefix3 = 'data/mixture/testset/icdar_2013/Challenge2_Test_Task3_Images/' test_img_prefix4 = 'data/mixture/testset/icdar_2015/ch4_test_word_images_gt/' test_img_prefix5 = 'data/mixture/testset/svtp/' test_img_prefix6 = 'data/mixture/testset/ct80/' test_ann_file1 = 'data/mixture/testset/IIIT5K/label.txt' test_ann_file2 = 'data/mixture/testset/svt/test_list.txt' test_ann_file3 = 'data/mixture/testset/icdar_2013/1015_test_label.txt' test_ann_file4 = 'data/mixture/testset/icdar_2015/test_label.txt' test_ann_file5 = 'data/mixture/testset/svtp/imagelist.txt' test_ann_file6 = 'data/mixture/testset/ct80/imagelist.txt' test1 = dict( type='OCRDataset', img_prefix='data/mixture/testset/IIIT5K/', ann_file='data/mixture/testset/IIIT5K/label.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True) test2 = dict( type='OCRDataset', img_prefix='data/mixture/testset/svt/', ann_file='data/mixture/testset/svt/test_list.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True) test3 = dict( type='OCRDataset', img_prefix='data/mixture/testset/icdar_2013/Challenge2_Test_Task3_Images/', ann_file='data/mixture/testset/icdar_2013/1015_test_label.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True) test4 = dict( type='OCRDataset', img_prefix='data/mixture/testset/icdar_2015/ch4_test_word_images_gt/', ann_file='data/mixture/testset/icdar_2015/test_label.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True) test5 = dict( type='OCRDataset', img_prefix='data/mixture/testset/svtp/', ann_file='data/mixture/testset/svtp/imagelist.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True) test6 = dict( type='OCRDataset', img_prefix='data/mixture/testset/ct80/', ann_file='data/mixture/testset/ct80/imagelist.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True) data = dict( samples_per_gpu=192, workers_per_gpu=8, val_dataloader=dict(samples_per_gpu=1), test_dataloader=dict(samples_per_gpu=1), train=dict( type='UniformConcatDataset', datasets=[ dict( type='OCRDataset', img_prefix= 's3://openmmlab/datasets/ocr/recog/SynthText/synthtext/SynthText_patch_horizontal/', ann_file='data/SynthText/labels/alphanumeric.lmdb', loader=dict( type='LmdbLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=False), dict( type='OCRDataset', img_prefix= 's3://openmmlab/datasets/ocr/recog/mnt/ramdisk/max/90kDICT32px/', ann_file='data/mnt/ramdisk/max/90kDICT32px/full_labels.lmdb', loader=dict( type='LmdbLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=False) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='petrel')), dict( type='ResizeOCR', height=32, min_width=128, max_width=128, keep_aspect_ratio=False, width_downsample_ratio=0.25), dict( type='RandomWrapper', p=0.5, transforms=[ dict( type='OneOfWrapper', transforms=[ dict(type='RandomRotateTextDet', max_angle=15), dict( type='TorchVisionWrapper', op='RandomAffine', degrees=15, translate=(0.3, 0.3), scale=(0.5, 2.0), shear=(-45, 45)), dict( type='TorchVisionWrapper', op='RandomPerspective', distortion_scale=0.5, p=1) ]) ]), dict( type='RandomWrapper', p=0.25, transforms=[ dict(type='PyramidRescale'), dict( type='Albu', transforms=[ dict(type='GaussNoise', var_limit=(20, 20), p=1), dict(type='MotionBlur', blur_limit=12, p=1) ]) ]), dict( type='RandomWrapper', p=0.25, transforms=[ dict( type='TorchVisionWrapper', op='ColorJitter', brightness=0.5, saturation=0.5, contrast=0.5, hue=0.1) ]), dict(type='ToTensorOCR'), dict( type='NormalizeOCR', mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), dict( type='Collect', keys=['img'], meta_keys=[ 'filename', 'ori_shape', 'img_shape', 'text', 'valid_ratio', 'resize_shape' ]) ]), val=dict( type='UniformConcatDataset', datasets=[ dict( type='OCRDataset', img_prefix='data/mixture/testset/IIIT5K/', ann_file='data/mixture/testset/IIIT5K/label.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True), dict( type='OCRDataset', img_prefix='data/mixture/testset/svt/', ann_file='data/mixture/testset/svt/test_list.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True), dict( type='OCRDataset', img_prefix= 'data/mixture/testset/icdar_2013/Challenge2_Test_Task3_Images/', ann_file='data/mixture/testset/icdar_2013/1015_test_label.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True), dict( type='OCRDataset', img_prefix= 'data/mixture/testset/icdar_2015/ch4_test_word_images_gt/', ann_file='data/mixture/testset/icdar_2015/test_label.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True), dict( type='OCRDataset', img_prefix='data/mixture/testset/svtp/', ann_file='data/mixture/testset/svtp/imagelist.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True), dict( type='OCRDataset', img_prefix='data/mixture/testset/ct80/', ann_file='data/mixture/testset/ct80/imagelist.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='petrel')), dict( type='MultiRotateAugOCR', rotate_degrees=[0, 90, 270], transforms=[ dict( type='ResizeOCR', height=32, min_width=128, max_width=128, keep_aspect_ratio=False, width_downsample_ratio=0.25), dict(type='ToTensorOCR'), dict( type='NormalizeOCR', mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), dict( type='Collect', keys=['img'], meta_keys=[ 'filename', 'ori_shape', 'img_shape', 'valid_ratio', 'resize_shape' ]) ]) ]), test=dict( type='UniformConcatDataset', datasets=[ dict( type='OCRDataset', img_prefix='data/mixture/testset/IIIT5K/', ann_file='data/mixture/testset/IIIT5K/label.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True), dict( type='OCRDataset', img_prefix='data/mixture/testset/svt/', ann_file='data/mixture/testset/svt/test_list.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True), dict( type='OCRDataset', img_prefix= 'data/mixture/testset/icdar_2013/Challenge2_Test_Task3_Images/', ann_file='data/mixture/testset/icdar_2013/1015_test_label.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True), dict( type='OCRDataset', img_prefix= 'data/mixture/testset/icdar_2015/ch4_test_word_images_gt/', ann_file='data/mixture/testset/icdar_2015/test_label.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True), dict( type='OCRDataset', img_prefix='data/mixture/testset/svtp/', ann_file='data/mixture/testset/svtp/imagelist.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True), dict( type='OCRDataset', img_prefix='data/mixture/testset/ct80/', ann_file='data/mixture/testset/ct80/imagelist.txt', loader=dict( type='HardDiskLoader', repeat=1, parser=dict( type='LineStrParser', keys=['filename', 'text'], keys_idx=[0, 1], separator=' ')), pipeline=None, test_mode=True) ], pipeline=[ dict( type='LoadImageFromFile', file_client_args=dict(backend='petrel')), dict( type='MultiRotateAugOCR', rotate_degrees=[0, 90, 270], transforms=[ dict( type='ResizeOCR', height=32, min_width=128, max_width=128, keep_aspect_ratio=False, width_downsample_ratio=0.25), dict(type='ToTensorOCR'), dict( type='NormalizeOCR', mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), dict( type='Collect', keys=['img'], meta_keys=[ 'filename', 'ori_shape', 'img_shape', 'valid_ratio', 'resize_shape' ]) ]) ])) evaluation = dict(interval=1, metric='acc') work_dir = 'abinet_pretrain_vision_alphanumeric_reimplement_aug' gpu_ids = range(0, 8) 2021-12-01 19:55:20,734 - mmocr - INFO - initialize ResNetABI with init_cfg [{'type': 'Xavier', 'layer': 'Conv2d'}, {'type': 'Constant', 'val': 1, 'layer': 'BatchNorm2d'}] 2021-12-01 19:55:21,590 - mmocr - INFO - initialize ABIVisionEncoder with init_cfg {'type': 'Xavier', 'layer': 'Conv2d'} Name of parameter - Initialization information backbone.resnet.conv1.weight - torch.Size([32, 3, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.conv1.bias - torch.Size([32]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.0.conv1.weight - torch.Size([32, 32, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.0.0.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.0.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.0.0.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.0.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.0.downsample.0.weight - torch.Size([32, 32, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.0.0.downsample.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.0.downsample.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.1.conv1.weight - torch.Size([32, 32, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.0.1.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.1.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.0.1.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.1.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.2.conv1.weight - torch.Size([32, 32, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.0.2.bn1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.2.bn1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.0.2.bn2.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.0.2.bn2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.0.conv1.weight - torch.Size([64, 32, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.1.0.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.0.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.1.0.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.0.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.0.downsample.0.weight - torch.Size([64, 32, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.1.0.downsample.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.0.downsample.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.1.conv1.weight - torch.Size([64, 64, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.1.1.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.1.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.1.1.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.1.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.2.conv1.weight - torch.Size([64, 64, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.1.2.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.2.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.1.2.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.2.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.3.conv1.weight - torch.Size([64, 64, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.1.3.bn1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.3.bn1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.1.3.bn2.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.1.3.bn2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.0.conv1.weight - torch.Size([128, 64, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.0.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.0.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.0.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.0.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.0.downsample.0.weight - torch.Size([128, 64, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.0.downsample.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.0.downsample.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.1.conv1.weight - torch.Size([128, 128, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.1.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.1.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.1.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.1.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.2.conv1.weight - torch.Size([128, 128, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.2.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.2.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.2.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.2.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.3.conv1.weight - torch.Size([128, 128, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.3.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.3.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.3.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.3.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.4.conv1.weight - torch.Size([128, 128, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.4.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.4.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.4.conv2.weight - torch.Size([128, 128, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.4.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.4.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.5.conv1.weight - torch.Size([128, 128, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.5.bn1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.5.bn1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.5.conv2.weight - torch.Size([128, 128, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.2.5.bn2.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.2.5.bn2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.0.conv1.weight - torch.Size([256, 128, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.0.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.0.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.0.conv2.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.0.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.0.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.0.downsample.0.weight - torch.Size([256, 128, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.0.downsample.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.0.downsample.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.1.conv1.weight - torch.Size([256, 256, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.1.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.1.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.1.conv2.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.1.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.1.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.2.conv1.weight - torch.Size([256, 256, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.2.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.2.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.2.conv2.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.2.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.2.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.3.conv1.weight - torch.Size([256, 256, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.3.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.3.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.3.conv2.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.3.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.3.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.4.conv1.weight - torch.Size([256, 256, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.4.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.4.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.4.conv2.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.4.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.4.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.5.conv1.weight - torch.Size([256, 256, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.5.bn1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.5.bn1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.5.conv2.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.3.5.bn2.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.3.5.bn2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.0.conv1.weight - torch.Size([512, 256, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.4.0.bn1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.0.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.0.conv2.weight - torch.Size([512, 512, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.4.0.bn2.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.0.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.0.downsample.0.weight - torch.Size([512, 256, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.4.0.downsample.1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.0.downsample.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.1.conv1.weight - torch.Size([512, 512, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.4.1.bn1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.1.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.1.conv2.weight - torch.Size([512, 512, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.4.1.bn2.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.1.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.2.conv1.weight - torch.Size([512, 512, 1, 1]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.4.2.bn1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.2.bn1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.2.conv2.weight - torch.Size([512, 512, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 backbone.resnet.layers.4.2.bn2.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.resnet.layers.4.2.bn2.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.0.attentions.0.attn.in_proj_weight - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.0.attentions.0.attn.in_proj_bias - torch.Size([1536]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.0.attentions.0.attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.0.attentions.0.attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.0.ffns.0.layers.0.0.weight - torch.Size([2048, 512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.0.ffns.0.layers.0.0.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.0.ffns.0.layers.1.weight - torch.Size([512, 2048]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.0.ffns.0.layers.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.0.norms.0.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.0.norms.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.0.norms.1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.0.norms.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.1.attentions.0.attn.in_proj_weight - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.1.attentions.0.attn.in_proj_bias - torch.Size([1536]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.1.attentions.0.attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.1.attentions.0.attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.1.ffns.0.layers.0.0.weight - torch.Size([2048, 512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.1.ffns.0.layers.0.0.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.1.ffns.0.layers.1.weight - torch.Size([512, 2048]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.1.ffns.0.layers.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.1.norms.0.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.1.norms.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.1.norms.1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.1.norms.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.2.attentions.0.attn.in_proj_weight - torch.Size([1536, 512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.2.attentions.0.attn.in_proj_bias - torch.Size([1536]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.2.attentions.0.attn.out_proj.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.2.attentions.0.attn.out_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.2.ffns.0.layers.0.0.weight - torch.Size([2048, 512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.2.ffns.0.layers.0.0.bias - torch.Size([2048]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.2.ffns.0.layers.1.weight - torch.Size([512, 2048]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.2.ffns.0.layers.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.2.norms.0.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.2.norms.0.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.2.norms.1.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet backbone.transformer.2.norms.1.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_encoder.0.conv.weight - torch.Size([64, 512, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 encoder.attention.k_encoder.0.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_encoder.0.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_encoder.1.conv.weight - torch.Size([64, 64, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 encoder.attention.k_encoder.1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_encoder.1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_encoder.2.conv.weight - torch.Size([64, 64, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 encoder.attention.k_encoder.2.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_encoder.2.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_encoder.3.conv.weight - torch.Size([64, 64, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 encoder.attention.k_encoder.3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_encoder.3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_decoder.0.1.conv.weight - torch.Size([64, 64, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 encoder.attention.k_decoder.0.1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_decoder.0.1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_decoder.1.1.conv.weight - torch.Size([64, 64, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 encoder.attention.k_decoder.1.1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_decoder.1.1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_decoder.2.1.conv.weight - torch.Size([64, 64, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 encoder.attention.k_decoder.2.1.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_decoder.2.1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_decoder.3.1.conv.weight - torch.Size([512, 64, 3, 3]): XavierInit: gain=1, distribution=normal, bias=0 encoder.attention.k_decoder.3.1.bn.weight - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.k_decoder.3.1.bn.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.project.weight - torch.Size([512, 512]): The value is the same before and after calling `init_weights` of ABINet encoder.attention.project.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of ABINet encoder.cls.weight - torch.Size([37, 512]): The value is the same before and after calling `init_weights` of ABINet encoder.cls.bias - torch.Size([37]): The value is the same before and after calling `init_weights` of ABINet 2021-12-01 19:55:23,064 - mmocr - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) StepLrUpdaterHook (NORMAL ) CheckpointHook (NORMAL ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_epoch: (VERY_HIGH ) StepLrUpdaterHook (NORMAL ) DistSamplerSeedHook (NORMAL ) DistEvalHook (LOW ) IterTimerHook (VERY_LOW ) TextLoggerHook -------------------- before_train_iter: (VERY_HIGH ) StepLrUpdaterHook (NORMAL ) DistEvalHook (LOW ) IterTimerHook -------------------- after_train_iter: (ABOVE_NORMAL) OptimizerHook (NORMAL ) CheckpointHook (NORMAL ) DistEvalHook (LOW ) IterTimerHook (VERY_LOW ) TextLoggerHook -------------------- after_train_epoch: (NORMAL ) CheckpointHook (NORMAL ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_val_epoch: (NORMAL ) DistSamplerSeedHook (LOW ) IterTimerHook (VERY_LOW ) TextLoggerHook -------------------- before_val_iter: (LOW ) IterTimerHook -------------------- after_val_iter: (LOW ) IterTimerHook -------------------- after_val_epoch: (VERY_LOW ) TextLoggerHook -------------------- 2021-12-01 19:55:23,064 - mmocr - INFO - workflow: [('train', 1)], max: 20 epochs 2021-12-01 20:20:13,345 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-01 20:20:13,359 - mmocr - INFO - Epoch [1][1000/10520] lr: 9.587e-06, eta: 3 days, 14:40:59, time: 1.490, data_time: 0.625, memory: 16118, loss_visual: 2.9352, loss: 2.9352, grad_norm: 1.3556 2021-12-01 20:34:44,806 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-01 20:34:44,807 - mmocr - INFO - Epoch [1][2000/10520] lr: 1.908e-05, eta: 2 days, 20:21:28, time: 0.871, data_time: 0.005, memory: 16118, loss_visual: 2.7264, loss: 2.7264, grad_norm: 1.0636 2021-12-01 20:49:18,938 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-01 20:49:18,939 - mmocr - INFO - Epoch [1][3000/10520] lr: 2.858e-05, eta: 2 days, 14:08:15, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 2.5589, loss: 2.5589, grad_norm: 1.3170 2021-12-01 21:03:51,786 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-01 21:03:51,788 - mmocr - INFO - Epoch [1][4000/10520] lr: 3.808e-05, eta: 2 days, 10:53:27, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 1.8075, loss: 1.8075, grad_norm: 2.4161 2021-12-01 21:18:25,958 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-01 21:18:25,960 - mmocr - INFO - Epoch [1][5000/10520] lr: 4.757e-05, eta: 2 days, 8:51:34, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 1.3359, loss: 1.3359, grad_norm: 2.4779 2021-12-01 21:32:58,427 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-01 21:32:58,429 - mmocr - INFO - Epoch [1][6000/10520] lr: 5.707e-05, eta: 2 days, 7:24:30, time: 0.872, data_time: 0.004, memory: 16118, loss_visual: 1.1192, loss: 1.1192, grad_norm: 2.3165 2021-12-01 21:47:33,636 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-01 21:47:33,637 - mmocr - INFO - Epoch [1][7000/10520] lr: 6.656e-05, eta: 2 days, 6:19:29, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.9903, loss: 0.9903, grad_norm: 2.2367 2021-12-01 22:02:09,850 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-01 22:02:09,859 - mmocr - INFO - Epoch [1][8000/10520] lr: 7.606e-05, eta: 2 days, 5:27:29, time: 0.876, data_time: 0.005, memory: 16118, loss_visual: 0.9032, loss: 0.9032, grad_norm: 2.1490 2021-12-01 22:16:45,422 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-01 22:16:45,430 - mmocr - INFO - Epoch [1][9000/10520] lr: 8.556e-05, eta: 2 days, 4:43:33, time: 0.876, data_time: 0.004, memory: 16118, loss_visual: 0.8364, loss: 0.8364, grad_norm: 2.0793 2021-12-01 22:31:21,621 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-01 22:31:21,623 - mmocr - INFO - Epoch [1][10000/10520] lr: 9.505e-05, eta: 2 days, 4:05:43, time: 0.876, data_time: 0.005, memory: 16118, loss_visual: 0.7860, loss: 0.7860, grad_norm: 2.0762 2021-12-01 22:39:01,208 - mmocr - INFO - Saving checkpoint at 1 epochs 2021-12-01 22:49:21,359 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-01 22:49:21,419 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-01 22:49:21,430 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-01 22:49:21,444 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-01 22:49:21,477 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-01 22:49:21,488 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-01 22:49:21,494 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-01 22:49:21,494 - mmocr - INFO - Epoch(val) [1][959] 0_word_acc: 0.0593, 0_word_acc_ignore_case: 0.7920, 0_word_acc_ignore_case_symbol: 0.7920, 0_char_recall: 0.9312, 0_char_precision: 0.9263, 0_1-N.E.D: 0.9244, 1_word_acc: 0.7496, 1_word_acc_ignore_case: 0.7496, 1_word_acc_ignore_case_symbol: 0.7496, 1_char_recall: 0.9202, 1_char_precision: 0.9241, 1_1-N.E.D: 0.9122, 2_word_acc: 0.2502, 2_word_acc_ignore_case: 0.8108, 2_word_acc_ignore_case_symbol: 0.8108, 2_char_recall: 0.9483, 2_char_precision: 0.9418, 2_1-N.E.D: 0.9098, 3_word_acc: 0.0939, 3_word_acc_ignore_case: 0.5797, 3_word_acc_ignore_case_symbol: 0.6042, 3_char_recall: 0.8778, 3_char_precision: 0.8646, 3_1-N.E.D: 0.8479, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.6047, 4_word_acc_ignore_case_symbol: 0.6047, 4_char_recall: 0.8614, 4_char_precision: 0.8795, 4_1-N.E.D: 0.8498, 5_word_acc: 0.1007, 5_word_acc_ignore_case: 0.6354, 5_word_acc_ignore_case_symbol: 0.6354, 5_char_recall: 0.8263, 5_char_precision: 0.8542, 5_1-N.E.D: 0.8267 2021-12-01 23:14:05,450 - mmocr - INFO - Epoch [2][1000/10520] lr: 1.000e-04, eta: 2 days, 3:59:41, time: 1.484, data_time: 0.620, memory: 16118, loss_visual: 0.7296, loss: 0.7296, grad_norm: 2.0126 2021-12-01 23:28:37,347 - mmocr - INFO - Epoch [2][2000/10520] lr: 1.000e-04, eta: 2 days, 3:25:45, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.6925, loss: 0.6925, grad_norm: 1.9262 2021-12-01 23:43:08,392 - mmocr - INFO - Epoch [2][3000/10520] lr: 1.000e-04, eta: 2 days, 2:54:28, time: 0.871, data_time: 0.005, memory: 16118, loss_visual: 0.6647, loss: 0.6647, grad_norm: 1.9084 2021-12-01 23:57:40,214 - mmocr - INFO - Epoch [2][4000/10520] lr: 1.000e-04, eta: 2 days, 2:25:41, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.6429, loss: 0.6429, grad_norm: 1.9150 2021-12-02 00:12:13,423 - mmocr - INFO - Epoch [2][5000/10520] lr: 1.000e-04, eta: 2 days, 1:59:01, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.6206, loss: 0.6206, grad_norm: 1.9161 2021-12-02 00:26:43,961 - mmocr - INFO - Epoch [2][6000/10520] lr: 1.000e-04, eta: 2 days, 1:33:18, time: 0.871, data_time: 0.005, memory: 16118, loss_visual: 0.6041, loss: 0.6041, grad_norm: 1.8756 2021-12-02 00:41:17,314 - mmocr - INFO - Epoch [2][7000/10520] lr: 1.000e-04, eta: 2 days, 1:09:23, time: 0.873, data_time: 0.006, memory: 16118, loss_visual: 0.5896, loss: 0.5896, grad_norm: 1.8422 2021-12-02 00:55:46,407 - mmocr - INFO - Epoch [2][8000/10520] lr: 1.000e-04, eta: 2 days, 0:45:43, time: 0.869, data_time: 0.005, memory: 16118, loss_visual: 0.5749, loss: 0.5749, grad_norm: 1.8021 2021-12-02 01:10:15,372 - mmocr - INFO - Epoch [2][9000/10520] lr: 1.000e-04, eta: 2 days, 0:23:00, time: 0.869, data_time: 0.004, memory: 16118, loss_visual: 0.5625, loss: 0.5625, grad_norm: 1.8461 2021-12-02 01:24:46,227 - mmocr - INFO - Epoch [2][10000/10520] lr: 1.000e-04, eta: 2 days, 0:01:22, time: 0.871, data_time: 0.005, memory: 16118, loss_visual: 0.5534, loss: 0.5534, grad_norm: 1.7506 2021-12-02 01:32:28,188 - mmocr - INFO - Saving checkpoint at 2 epochs 2021-12-02 01:42:43,982 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-02 01:42:44,038 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-02 01:42:44,048 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-02 01:42:44,063 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-02 01:42:44,095 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-02 01:42:44,106 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-02 01:42:44,118 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-02 01:42:44,119 - mmocr - INFO - Epoch(val) [2][959] 0_word_acc: 0.0670, 0_word_acc_ignore_case: 0.8637, 0_word_acc_ignore_case_symbol: 0.8637, 0_char_recall: 0.9589, 0_char_precision: 0.9567, 0_1-N.E.D: 0.9537, 1_word_acc: 0.8346, 1_word_acc_ignore_case: 0.8346, 1_word_acc_ignore_case_symbol: 0.8346, 1_char_recall: 0.9494, 1_char_precision: 0.9532, 1_1-N.E.D: 0.9442, 2_word_acc: 0.2601, 2_word_acc_ignore_case: 0.8512, 2_word_acc_ignore_case_symbol: 0.8512, 2_char_recall: 0.9605, 2_char_precision: 0.9566, 2_1-N.E.D: 0.9258, 3_word_acc: 0.1112, 3_word_acc_ignore_case: 0.6832, 3_word_acc_ignore_case_symbol: 0.7188, 3_char_recall: 0.9190, 3_char_precision: 0.9050, 3_1-N.E.D: 0.8955, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.7364, 4_word_acc_ignore_case_symbol: 0.7364, 4_char_recall: 0.9068, 4_char_precision: 0.9189, 4_1-N.E.D: 0.8975, 5_word_acc: 0.1354, 5_word_acc_ignore_case: 0.7535, 5_word_acc_ignore_case_symbol: 0.7535, 5_char_recall: 0.8947, 5_char_precision: 0.9118, 5_1-N.E.D: 0.8939 2021-12-02 02:07:30,402 - mmocr - INFO - Epoch [3][1000/10520] lr: 1.000e-04, eta: 1 day, 23:52:52, time: 1.486, data_time: 0.618, memory: 16118, loss_visual: 0.5335, loss: 0.5335, grad_norm: 1.7707 2021-12-02 02:22:01,956 - mmocr - INFO - Epoch [3][2000/10520] lr: 1.000e-04, eta: 1 day, 23:31:43, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.5258, loss: 0.5258, grad_norm: 1.8281 2021-12-02 02:36:32,268 - mmocr - INFO - Epoch [3][3000/10520] lr: 1.000e-04, eta: 1 day, 23:10:57, time: 0.870, data_time: 0.005, memory: 16118, loss_visual: 0.5196, loss: 0.5196, grad_norm: 1.8139 2021-12-02 02:51:03,442 - mmocr - INFO - Epoch [3][4000/10520] lr: 1.000e-04, eta: 1 day, 22:50:47, time: 0.871, data_time: 0.005, memory: 16118, loss_visual: 0.5115, loss: 0.5115, grad_norm: 1.7499 2021-12-02 03:05:33,881 - mmocr - INFO - Epoch [3][5000/10520] lr: 1.000e-04, eta: 1 day, 22:30:58, time: 0.870, data_time: 0.005, memory: 16118, loss_visual: 0.5032, loss: 0.5032, grad_norm: 1.7731 2021-12-02 03:20:03,303 - mmocr - INFO - Epoch [3][6000/10520] lr: 1.000e-04, eta: 1 day, 22:11:26, time: 0.869, data_time: 0.005, memory: 16118, loss_visual: 0.4978, loss: 0.4978, grad_norm: 1.7907 2021-12-02 03:34:32,734 - mmocr - INFO - Epoch [3][7000/10520] lr: 1.000e-04, eta: 1 day, 21:52:16, time: 0.869, data_time: 0.004, memory: 16118, loss_visual: 0.4922, loss: 0.4922, grad_norm: 1.7585 2021-12-02 03:49:03,727 - mmocr - INFO - Epoch [3][8000/10520] lr: 1.000e-04, eta: 1 day, 21:33:34, time: 0.871, data_time: 0.005, memory: 16118, loss_visual: 0.4861, loss: 0.4861, grad_norm: 1.7130 2021-12-02 04:03:33,378 - mmocr - INFO - Epoch [3][9000/10520] lr: 1.000e-04, eta: 1 day, 21:15:02, time: 0.870, data_time: 0.005, memory: 16118, loss_visual: 0.4817, loss: 0.4817, grad_norm: 1.7325 2021-12-02 04:18:01,945 - mmocr - INFO - Epoch [3][10000/10520] lr: 1.000e-04, eta: 1 day, 20:56:38, time: 0.869, data_time: 0.005, memory: 16118, loss_visual: 0.4767, loss: 0.4767, grad_norm: 1.7081 2021-12-02 04:25:37,264 - mmocr - INFO - Saving checkpoint at 3 epochs 2021-12-02 04:35:53,537 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-02 04:35:53,593 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-02 04:35:53,608 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-02 04:35:53,623 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-02 04:35:53,655 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-02 04:35:53,666 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-02 04:35:53,672 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-02 04:35:53,672 - mmocr - INFO - Epoch(val) [3][959] 0_word_acc: 0.0717, 0_word_acc_ignore_case: 0.9047, 0_word_acc_ignore_case_symbol: 0.9047, 0_char_recall: 0.9712, 0_char_precision: 0.9685, 0_1-N.E.D: 0.9693, 1_word_acc: 0.8485, 1_word_acc_ignore_case: 0.8485, 1_word_acc_ignore_case_symbol: 0.8485, 1_char_recall: 0.9592, 1_char_precision: 0.9625, 1_1-N.E.D: 0.9528, 2_word_acc: 0.2778, 2_word_acc_ignore_case: 0.8847, 2_word_acc_ignore_case_symbol: 0.8847, 2_char_recall: 0.9696, 2_char_precision: 0.9673, 2_1-N.E.D: 0.9456, 3_word_acc: 0.1122, 3_word_acc_ignore_case: 0.7034, 3_word_acc_ignore_case_symbol: 0.7448, 3_char_recall: 0.9270, 3_char_precision: 0.9154, 3_1-N.E.D: 0.9034, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.7705, 4_word_acc_ignore_case_symbol: 0.7705, 4_char_recall: 0.9152, 4_char_precision: 0.9282, 4_1-N.E.D: 0.9081, 5_word_acc: 0.1458, 5_word_acc_ignore_case: 0.7882, 5_word_acc_ignore_case_symbol: 0.7917, 5_char_recall: 0.9129, 5_char_precision: 0.9387, 5_1-N.E.D: 0.9174 2021-12-02 05:00:37,936 - mmocr - INFO - Epoch [4][1000/10520] lr: 1.000e-04, eta: 1 day, 20:44:05, time: 1.484, data_time: 0.619, memory: 16118, loss_visual: 0.4674, loss: 0.4674, grad_norm: 1.6954 2021-12-02 05:15:09,131 - mmocr - INFO - Epoch [4][2000/10520] lr: 1.000e-04, eta: 1 day, 20:25:58, time: 0.871, data_time: 0.006, memory: 16118, loss_visual: 0.4623, loss: 0.4623, grad_norm: 1.6633 2021-12-02 05:29:39,507 - mmocr - INFO - Epoch [4][3000/10520] lr: 1.000e-04, eta: 1 day, 20:07:59, time: 0.870, data_time: 0.005, memory: 16118, loss_visual: 0.4581, loss: 0.4581, grad_norm: 1.6740 2021-12-02 05:44:09,302 - mmocr - INFO - Epoch [4][4000/10520] lr: 1.000e-04, eta: 1 day, 19:50:10, time: 0.870, data_time: 0.004, memory: 16118, loss_visual: 0.4536, loss: 0.4536, grad_norm: 1.6930 2021-12-02 05:58:42,474 - mmocr - INFO - Epoch [4][5000/10520] lr: 1.000e-04, eta: 1 day, 19:32:47, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.4500, loss: 0.4500, grad_norm: 1.7034 2021-12-02 06:13:14,521 - mmocr - INFO - Epoch [4][6000/10520] lr: 1.000e-04, eta: 1 day, 19:15:28, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.4476, loss: 0.4476, grad_norm: 1.6824 2021-12-02 06:27:46,801 - mmocr - INFO - Epoch [4][7000/10520] lr: 1.000e-04, eta: 1 day, 18:58:20, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.4444, loss: 0.4444, grad_norm: 1.6520 2021-12-02 06:42:17,711 - mmocr - INFO - Epoch [4][8000/10520] lr: 1.000e-04, eta: 1 day, 18:41:13, time: 0.871, data_time: 0.004, memory: 16118, loss_visual: 0.4420, loss: 0.4420, grad_norm: 1.6422 2021-12-02 06:56:47,803 - mmocr - INFO - Epoch [4][9000/10520] lr: 1.000e-04, eta: 1 day, 18:24:10, time: 0.870, data_time: 0.005, memory: 16118, loss_visual: 0.4369, loss: 0.4369, grad_norm: 1.6114 2021-12-02 07:11:18,241 - mmocr - INFO - Epoch [4][10000/10520] lr: 1.000e-04, eta: 1 day, 18:07:16, time: 0.870, data_time: 0.005, memory: 16118, loss_visual: 0.4346, loss: 0.4346, grad_norm: 1.6427 2021-12-02 07:18:53,296 - mmocr - INFO - Saving checkpoint at 4 epochs 2021-12-02 07:29:12,117 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-02 07:29:12,172 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-02 07:29:12,183 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-02 07:29:12,198 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-02 07:29:12,229 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-02 07:29:12,239 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-02 07:29:12,245 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-02 07:29:12,245 - mmocr - INFO - Epoch(val) [4][959] 0_word_acc: 0.0723, 0_word_acc_ignore_case: 0.9157, 0_word_acc_ignore_case_symbol: 0.9157, 0_char_recall: 0.9743, 0_char_precision: 0.9718, 0_1-N.E.D: 0.9721, 1_word_acc: 0.8532, 1_word_acc_ignore_case: 0.8532, 1_word_acc_ignore_case_symbol: 0.8532, 1_char_recall: 0.9610, 1_char_precision: 0.9641, 1_1-N.E.D: 0.9548, 2_word_acc: 0.2818, 2_word_acc_ignore_case: 0.8946, 2_word_acc_ignore_case_symbol: 0.8946, 2_char_recall: 0.9744, 2_char_precision: 0.9724, 2_1-N.E.D: 0.9527, 3_word_acc: 0.1175, 3_word_acc_ignore_case: 0.7260, 3_word_acc_ignore_case_symbol: 0.7689, 3_char_recall: 0.9382, 3_char_precision: 0.9235, 3_1-N.E.D: 0.9134, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.7829, 4_word_acc_ignore_case_symbol: 0.7829, 4_char_recall: 0.9181, 4_char_precision: 0.9307, 4_1-N.E.D: 0.9112, 5_word_acc: 0.1389, 5_word_acc_ignore_case: 0.8021, 5_word_acc_ignore_case_symbol: 0.8056, 5_char_recall: 0.9166, 5_char_precision: 0.9330, 5_1-N.E.D: 0.9184 2021-12-02 07:53:57,028 - mmocr - INFO - Epoch [5][1000/10520] lr: 1.000e-04, eta: 1 day, 17:52:15, time: 1.485, data_time: 0.620, memory: 16118, loss_visual: 0.4273, loss: 0.4273, grad_norm: 1.6133 2021-12-02 08:08:29,026 - mmocr - INFO - Epoch [5][2000/10520] lr: 1.000e-04, eta: 1 day, 17:35:25, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.4260, loss: 0.4260, grad_norm: 1.6587 2021-12-02 08:23:01,658 - mmocr - INFO - Epoch [5][3000/10520] lr: 1.000e-04, eta: 1 day, 17:18:44, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.4235, loss: 0.4235, grad_norm: 1.6127 2021-12-02 08:37:34,526 - mmocr - INFO - Epoch [5][4000/10520] lr: 1.000e-04, eta: 1 day, 17:02:09, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.4204, loss: 0.4204, grad_norm: 1.6619 2021-12-02 08:52:04,871 - mmocr - INFO - Epoch [5][5000/10520] lr: 1.000e-04, eta: 1 day, 16:45:30, time: 0.870, data_time: 0.005, memory: 16118, loss_visual: 0.4186, loss: 0.4186, grad_norm: 1.6062 2021-12-02 09:06:38,116 - mmocr - INFO - Epoch [5][6000/10520] lr: 1.000e-04, eta: 1 day, 16:29:07, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.4165, loss: 0.4165, grad_norm: 1.6210 2021-12-02 09:21:08,006 - mmocr - INFO - Epoch [5][7000/10520] lr: 1.000e-04, eta: 1 day, 16:12:37, time: 0.870, data_time: 0.005, memory: 16118, loss_visual: 0.4129, loss: 0.4129, grad_norm: 1.5958 2021-12-02 09:35:40,528 - mmocr - INFO - Epoch [5][8000/10520] lr: 1.000e-04, eta: 1 day, 15:56:20, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.4106, loss: 0.4106, grad_norm: 1.6232 2021-12-02 09:50:11,389 - mmocr - INFO - Epoch [5][9000/10520] lr: 1.000e-04, eta: 1 day, 15:40:02, time: 0.871, data_time: 0.005, memory: 16118, loss_visual: 0.4088, loss: 0.4088, grad_norm: 1.5957 2021-12-02 10:04:43,398 - mmocr - INFO - Epoch [5][10000/10520] lr: 1.000e-04, eta: 1 day, 15:23:52, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.4068, loss: 0.4068, grad_norm: 1.5736 2021-12-02 10:12:19,466 - mmocr - INFO - Saving checkpoint at 5 epochs 2021-12-02 10:22:34,778 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-02 10:22:34,836 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-02 10:22:34,846 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-02 10:22:34,861 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-02 10:22:34,891 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-02 10:22:34,901 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-02 10:22:34,907 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-02 10:22:34,907 - mmocr - INFO - Epoch(val) [5][959] 0_word_acc: 0.0750, 0_word_acc_ignore_case: 0.9220, 0_word_acc_ignore_case_symbol: 0.9220, 0_char_recall: 0.9773, 0_char_precision: 0.9749, 0_1-N.E.D: 0.9738, 1_word_acc: 0.8748, 1_word_acc_ignore_case: 0.8748, 1_word_acc_ignore_case_symbol: 0.8748, 1_char_recall: 0.9642, 1_char_precision: 0.9657, 1_1-N.E.D: 0.9592, 2_word_acc: 0.2847, 2_word_acc_ignore_case: 0.9044, 2_word_acc_ignore_case_symbol: 0.9044, 2_char_recall: 0.9776, 2_char_precision: 0.9745, 2_1-N.E.D: 0.9564, 3_word_acc: 0.1160, 3_word_acc_ignore_case: 0.7352, 3_word_acc_ignore_case_symbol: 0.7790, 3_char_recall: 0.9360, 3_char_precision: 0.9239, 3_1-N.E.D: 0.9136, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.7969, 4_word_acc_ignore_case_symbol: 0.7969, 4_char_recall: 0.9276, 4_char_precision: 0.9373, 4_1-N.E.D: 0.9198, 5_word_acc: 0.1354, 5_word_acc_ignore_case: 0.8090, 5_word_acc_ignore_case_symbol: 0.8125, 5_char_recall: 0.9260, 5_char_precision: 0.9366, 5_1-N.E.D: 0.9213 2021-12-02 10:47:18,598 - mmocr - INFO - Epoch [6][1000/10520] lr: 1.000e-04, eta: 1 day, 15:07:07, time: 1.484, data_time: 0.620, memory: 16118, loss_visual: 0.4036, loss: 0.4036, grad_norm: 1.5502 2021-12-02 11:01:47,141 - mmocr - INFO - Epoch [6][2000/10520] lr: 1.000e-04, eta: 1 day, 14:50:44, time: 0.869, data_time: 0.004, memory: 16118, loss_visual: 0.4022, loss: 0.4022, grad_norm: 1.5556 2021-12-02 11:16:19,657 - mmocr - INFO - Epoch [6][3000/10520] lr: 1.000e-04, eta: 1 day, 14:34:37, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3989, loss: 0.3989, grad_norm: 1.6152 2021-12-02 11:30:51,100 - mmocr - INFO - Epoch [6][4000/10520] lr: 1.000e-04, eta: 1 day, 14:18:30, time: 0.871, data_time: 0.005, memory: 16118, loss_visual: 0.3964, loss: 0.3964, grad_norm: 1.5685 2021-12-02 11:45:23,202 - mmocr - INFO - Epoch [6][5000/10520] lr: 1.000e-04, eta: 1 day, 14:02:28, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.3940, loss: 0.3940, grad_norm: 1.5439 2021-12-02 11:59:56,682 - mmocr - INFO - Epoch [6][6000/10520] lr: 1.000e-04, eta: 1 day, 13:46:33, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3936, loss: 0.3936, grad_norm: 1.5623 2021-12-02 12:14:29,713 - mmocr - INFO - Epoch [6][7000/10520] lr: 1.000e-04, eta: 1 day, 13:30:39, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3908, loss: 0.3908, grad_norm: 1.5910 2021-12-02 12:29:08,965 - mmocr - INFO - Epoch [6][8000/10520] lr: 1.000e-04, eta: 1 day, 13:15:03, time: 0.879, data_time: 0.005, memory: 16118, loss_visual: 0.3904, loss: 0.3904, grad_norm: 1.5821 2021-12-02 12:43:43,717 - mmocr - INFO - Epoch [6][9000/10520] lr: 1.000e-04, eta: 1 day, 12:59:19, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3885, loss: 0.3885, grad_norm: 1.5744 2021-12-02 12:58:17,230 - mmocr - INFO - Epoch [6][10000/10520] lr: 1.000e-04, eta: 1 day, 12:43:33, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.3866, loss: 0.3866, grad_norm: 1.5851 2021-12-02 13:05:55,175 - mmocr - INFO - Saving checkpoint at 6 epochs 2021-12-02 13:16:14,797 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-02 13:16:14,856 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-02 13:16:14,867 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-02 13:16:14,881 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-02 13:16:14,913 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-02 13:16:14,923 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-02 13:16:14,929 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-02 13:16:14,929 - mmocr - INFO - Epoch(val) [6][959] 0_word_acc: 0.0753, 0_word_acc_ignore_case: 0.9247, 0_word_acc_ignore_case_symbol: 0.9247, 0_char_recall: 0.9781, 0_char_precision: 0.9767, 0_1-N.E.D: 0.9760, 1_word_acc: 0.8810, 1_word_acc_ignore_case: 0.8810, 1_word_acc_ignore_case_symbol: 0.8810, 1_char_recall: 0.9636, 1_char_precision: 0.9690, 1_1-N.E.D: 0.9602, 2_word_acc: 0.2818, 2_word_acc_ignore_case: 0.9084, 2_word_acc_ignore_case_symbol: 0.9084, 2_char_recall: 0.9763, 2_char_precision: 0.9748, 2_1-N.E.D: 0.9573, 3_word_acc: 0.1204, 3_word_acc_ignore_case: 0.7453, 3_word_acc_ignore_case_symbol: 0.7896, 3_char_recall: 0.9390, 3_char_precision: 0.9317, 3_1-N.E.D: 0.9185, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.7984, 4_word_acc_ignore_case_symbol: 0.7984, 4_char_recall: 0.9258, 4_char_precision: 0.9399, 4_1-N.E.D: 0.9172, 5_word_acc: 0.1458, 5_word_acc_ignore_case: 0.8299, 5_word_acc_ignore_case_symbol: 0.8333, 5_char_recall: 0.9266, 5_char_precision: 0.9474, 5_1-N.E.D: 0.9282 2021-12-02 13:40:59,146 - mmocr - INFO - Epoch [7][1000/10520] lr: 1.000e-04, eta: 1 day, 12:25:38, time: 1.484, data_time: 0.619, memory: 16118, loss_visual: 0.3837, loss: 0.3837, grad_norm: 1.5694 2021-12-02 13:55:31,406 - mmocr - INFO - Epoch [7][2000/10520] lr: 1.000e-04, eta: 1 day, 12:09:47, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.3805, loss: 0.3805, grad_norm: 1.5682 2021-12-02 14:10:05,939 - mmocr - INFO - Epoch [7][3000/10520] lr: 1.000e-04, eta: 1 day, 11:54:04, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3796, loss: 0.3796, grad_norm: 1.5621 2021-12-02 14:24:37,947 - mmocr - INFO - Epoch [7][4000/10520] lr: 1.000e-04, eta: 1 day, 11:38:17, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.3783, loss: 0.3783, grad_norm: 1.4934 2021-12-02 14:39:12,799 - mmocr - INFO - Epoch [7][5000/10520] lr: 1.000e-04, eta: 1 day, 11:22:39, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3762, loss: 0.3762, grad_norm: 1.5395 2021-12-02 14:53:46,523 - mmocr - INFO - Epoch [7][6000/10520] lr: 1.000e-04, eta: 1 day, 11:07:00, time: 0.874, data_time: 0.004, memory: 16118, loss_visual: 0.3759, loss: 0.3759, grad_norm: 1.4884 2021-12-02 15:08:20,729 - mmocr - INFO - Epoch [7][7000/10520] lr: 1.000e-04, eta: 1 day, 10:51:24, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.3743, loss: 0.3743, grad_norm: 1.4998 2021-12-02 15:22:55,425 - mmocr - INFO - Epoch [7][8000/10520] lr: 1.000e-04, eta: 1 day, 10:35:51, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3729, loss: 0.3729, grad_norm: 1.4990 2021-12-02 15:37:28,684 - mmocr - INFO - Epoch [7][9000/10520] lr: 1.000e-04, eta: 1 day, 10:20:16, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3717, loss: 0.3717, grad_norm: 1.4961 2021-12-02 15:52:00,880 - mmocr - INFO - Epoch [7][10000/10520] lr: 1.000e-04, eta: 1 day, 10:04:41, time: 0.872, data_time: 0.004, memory: 16118, loss_visual: 0.3703, loss: 0.3703, grad_norm: 1.5256 2021-12-02 15:59:39,070 - mmocr - INFO - Saving checkpoint at 7 epochs 2021-12-02 16:09:57,230 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-02 16:09:57,332 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-02 16:09:57,343 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-02 16:09:57,357 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-02 16:09:57,388 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-02 16:09:57,399 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-02 16:09:57,404 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-02 16:09:57,404 - mmocr - INFO - Epoch(val) [7][959] 0_word_acc: 0.0720, 0_word_acc_ignore_case: 0.9260, 0_word_acc_ignore_case_symbol: 0.9260, 0_char_recall: 0.9783, 0_char_precision: 0.9770, 0_1-N.E.D: 0.9742, 1_word_acc: 0.8903, 1_word_acc_ignore_case: 0.8903, 1_word_acc_ignore_case_symbol: 0.8903, 1_char_recall: 0.9700, 1_char_precision: 0.9738, 1_1-N.E.D: 0.9637, 2_word_acc: 0.2808, 2_word_acc_ignore_case: 0.9133, 2_word_acc_ignore_case_symbol: 0.9133, 2_char_recall: 0.9783, 2_char_precision: 0.9752, 2_1-N.E.D: 0.9584, 3_word_acc: 0.1204, 3_word_acc_ignore_case: 0.7468, 3_word_acc_ignore_case_symbol: 0.7939, 3_char_recall: 0.9396, 3_char_precision: 0.9274, 3_1-N.E.D: 0.9185, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8062, 4_word_acc_ignore_case_symbol: 0.8062, 4_char_recall: 0.9324, 4_char_precision: 0.9446, 4_1-N.E.D: 0.9278, 5_word_acc: 0.1458, 5_word_acc_ignore_case: 0.8264, 5_word_acc_ignore_case_symbol: 0.8299, 5_char_recall: 0.9279, 5_char_precision: 0.9385, 5_1-N.E.D: 0.9272 2021-12-02 16:34:42,309 - mmocr - INFO - Epoch [8][1000/10520] lr: 1.000e-04, eta: 1 day, 9:45:53, time: 1.485, data_time: 0.623, memory: 16118, loss_visual: 0.3668, loss: 0.3668, grad_norm: 1.4654 2021-12-02 16:49:14,807 - mmocr - INFO - Epoch [8][2000/10520] lr: 1.000e-04, eta: 1 day, 9:30:17, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.3674, loss: 0.3674, grad_norm: 1.4932 2021-12-02 17:03:49,507 - mmocr - INFO - Epoch [8][3000/10520] lr: 1.000e-04, eta: 1 day, 9:14:46, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3657, loss: 0.3657, grad_norm: 1.4981 2021-12-02 17:18:23,562 - mmocr - INFO - Epoch [8][4000/10520] lr: 1.000e-04, eta: 1 day, 8:59:16, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.3634, loss: 0.3634, grad_norm: 1.5041 2021-12-02 17:33:00,695 - mmocr - INFO - Epoch [8][5000/10520] lr: 1.000e-04, eta: 1 day, 8:43:52, time: 0.877, data_time: 0.005, memory: 16118, loss_visual: 0.3622, loss: 0.3622, grad_norm: 1.4891 2021-12-02 17:47:36,577 - mmocr - INFO - Epoch [8][6000/10520] lr: 1.000e-04, eta: 1 day, 8:28:28, time: 0.876, data_time: 0.004, memory: 16118, loss_visual: 0.3627, loss: 0.3627, grad_norm: 1.4922 2021-12-02 18:02:11,420 - mmocr - INFO - Epoch [8][7000/10520] lr: 1.000e-04, eta: 1 day, 8:13:03, time: 0.875, data_time: 0.004, memory: 16118, loss_visual: 0.3609, loss: 0.3609, grad_norm: 1.4607 2021-12-02 18:16:47,706 - mmocr - INFO - Epoch [8][8000/10520] lr: 1.000e-04, eta: 1 day, 7:57:41, time: 0.876, data_time: 0.004, memory: 16118, loss_visual: 0.3593, loss: 0.3593, grad_norm: 1.4523 2021-12-02 18:31:22,757 - mmocr - INFO - Epoch [8][9000/10520] lr: 1.000e-04, eta: 1 day, 7:42:19, time: 0.875, data_time: 0.004, memory: 16118, loss_visual: 0.3587, loss: 0.3587, grad_norm: 1.4971 2021-12-02 18:45:56,467 - mmocr - INFO - Epoch [8][10000/10520] lr: 1.000e-04, eta: 1 day, 7:26:56, time: 0.874, data_time: 0.004, memory: 16118, loss_visual: 0.3572, loss: 0.3572, grad_norm: 1.4659 2021-12-02 18:53:41,335 - mmocr - INFO - Saving checkpoint at 8 epochs 2021-12-02 19:03:58,575 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-02 19:03:58,695 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-02 19:03:58,705 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-02 19:03:58,719 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-02 19:03:58,750 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-02 19:03:58,760 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-02 19:03:58,765 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-02 19:03:58,765 - mmocr - INFO - Epoch(val) [8][959] 0_word_acc: 0.0743, 0_word_acc_ignore_case: 0.9313, 0_word_acc_ignore_case_symbol: 0.9313, 0_char_recall: 0.9790, 0_char_precision: 0.9784, 0_1-N.E.D: 0.9771, 1_word_acc: 0.8856, 1_word_acc_ignore_case: 0.8856, 1_word_acc_ignore_case_symbol: 0.8856, 1_char_recall: 0.9652, 1_char_precision: 0.9727, 1_1-N.E.D: 0.9604, 2_word_acc: 0.2847, 2_word_acc_ignore_case: 0.9153, 2_word_acc_ignore_case_symbol: 0.9153, 2_char_recall: 0.9796, 2_char_precision: 0.9783, 2_1-N.E.D: 0.9596, 3_word_acc: 0.1237, 3_word_acc_ignore_case: 0.7525, 3_word_acc_ignore_case_symbol: 0.7983, 3_char_recall: 0.9413, 3_char_precision: 0.9341, 3_1-N.E.D: 0.9204, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8062, 4_word_acc_ignore_case_symbol: 0.8062, 4_char_recall: 0.9266, 4_char_precision: 0.9405, 4_1-N.E.D: 0.9201, 5_word_acc: 0.1528, 5_word_acc_ignore_case: 0.8368, 5_word_acc_ignore_case_symbol: 0.8403, 5_char_recall: 0.9273, 5_char_precision: 0.9390, 5_1-N.E.D: 0.9295 2021-12-02 19:28:40,458 - mmocr - INFO - Epoch [9][1000/10520] lr: 1.000e-04, eta: 1 day, 7:07:20, time: 1.482, data_time: 0.620, memory: 16118, loss_visual: 0.3553, loss: 0.3553, grad_norm: 1.4566 2021-12-02 19:43:09,881 - mmocr - INFO - Epoch [9][2000/10520] lr: 1.000e-04, eta: 1 day, 6:51:50, time: 0.869, data_time: 0.005, memory: 16118, loss_visual: 0.3547, loss: 0.3547, grad_norm: 1.4466 2021-12-02 19:57:40,700 - mmocr - INFO - Epoch [9][3000/10520] lr: 1.000e-04, eta: 1 day, 6:36:22, time: 0.871, data_time: 0.004, memory: 16118, loss_visual: 0.3530, loss: 0.3530, grad_norm: 1.4265 2021-12-02 20:12:13,291 - mmocr - INFO - Epoch [9][4000/10520] lr: 1.000e-04, eta: 1 day, 6:20:58, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.3515, loss: 0.3515, grad_norm: 1.4605 2021-12-02 20:26:48,148 - mmocr - INFO - Epoch [9][5000/10520] lr: 1.000e-04, eta: 1 day, 6:05:39, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3515, loss: 0.3515, grad_norm: 1.4536 2021-12-02 20:41:26,843 - mmocr - INFO - Epoch [9][6000/10520] lr: 1.000e-04, eta: 1 day, 5:50:25, time: 0.879, data_time: 0.005, memory: 16118, loss_visual: 0.3511, loss: 0.3511, grad_norm: 1.4266 2021-12-02 20:55:59,351 - mmocr - INFO - Epoch [9][7000/10520] lr: 1.000e-04, eta: 1 day, 5:35:04, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3487, loss: 0.3487, grad_norm: 1.4367 2021-12-02 21:10:35,469 - mmocr - INFO - Epoch [9][8000/10520] lr: 1.000e-04, eta: 1 day, 5:19:49, time: 0.876, data_time: 0.005, memory: 16118, loss_visual: 0.3490, loss: 0.3490, grad_norm: 1.3902 2021-12-02 21:25:08,775 - mmocr - INFO - Epoch [9][9000/10520] lr: 1.000e-04, eta: 1 day, 5:04:31, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3470, loss: 0.3470, grad_norm: 1.4579 2021-12-02 21:39:41,349 - mmocr - INFO - Epoch [9][10000/10520] lr: 1.000e-04, eta: 1 day, 4:49:14, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3473, loss: 0.3473, grad_norm: 1.4755 2021-12-02 21:47:25,675 - mmocr - INFO - Saving checkpoint at 9 epochs 2021-12-02 21:57:44,731 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-02 21:57:44,786 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-02 21:57:44,797 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-02 21:57:44,811 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-02 21:57:44,842 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-02 21:57:44,852 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-02 21:57:44,858 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-02 21:57:44,858 - mmocr - INFO - Epoch(val) [9][959] 0_word_acc: 0.0753, 0_word_acc_ignore_case: 0.9387, 0_word_acc_ignore_case_symbol: 0.9387, 0_char_recall: 0.9793, 0_char_precision: 0.9795, 0_1-N.E.D: 0.9787, 1_word_acc: 0.9026, 1_word_acc_ignore_case: 0.9026, 1_word_acc_ignore_case_symbol: 0.9026, 1_char_recall: 0.9700, 1_char_precision: 0.9767, 1_1-N.E.D: 0.9656, 2_word_acc: 0.2857, 2_word_acc_ignore_case: 0.9251, 2_word_acc_ignore_case_symbol: 0.9251, 2_char_recall: 0.9798, 2_char_precision: 0.9798, 2_1-N.E.D: 0.9608, 3_word_acc: 0.1261, 3_word_acc_ignore_case: 0.7622, 3_word_acc_ignore_case_symbol: 0.8113, 3_char_recall: 0.9440, 3_char_precision: 0.9378, 3_1-N.E.D: 0.9235, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8233, 4_word_acc_ignore_case_symbol: 0.8233, 4_char_recall: 0.9340, 4_char_precision: 0.9508, 4_1-N.E.D: 0.9299, 5_word_acc: 0.1424, 5_word_acc_ignore_case: 0.8299, 5_word_acc_ignore_case_symbol: 0.8333, 5_char_recall: 0.9223, 5_char_precision: 0.9423, 5_1-N.E.D: 0.9301 2021-12-02 22:22:29,401 - mmocr - INFO - Epoch [10][1000/10520] lr: 1.000e-04, eta: 1 day, 4:29:10, time: 1.484, data_time: 0.623, memory: 16118, loss_visual: 0.3430, loss: 0.3430, grad_norm: 1.4143 2021-12-02 22:37:00,031 - mmocr - INFO - Epoch [10][2000/10520] lr: 1.000e-04, eta: 1 day, 4:13:49, time: 0.871, data_time: 0.006, memory: 16118, loss_visual: 0.3437, loss: 0.3437, grad_norm: 1.4008 2021-12-02 22:51:34,583 - mmocr - INFO - Epoch [10][3000/10520] lr: 1.000e-04, eta: 1 day, 3:58:33, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3423, loss: 0.3423, grad_norm: 1.4224 2021-12-02 23:06:09,356 - mmocr - INFO - Epoch [10][4000/10520] lr: 1.000e-04, eta: 1 day, 3:43:18, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3401, loss: 0.3401, grad_norm: 1.4037 2021-12-02 23:20:43,033 - mmocr - INFO - Epoch [10][5000/10520] lr: 1.000e-04, eta: 1 day, 3:28:03, time: 0.874, data_time: 0.004, memory: 16118, loss_visual: 0.3414, loss: 0.3414, grad_norm: 1.4504 2021-12-02 23:36:37,761 - mmocr - INFO - Epoch [10][6000/10520] lr: 1.000e-04, eta: 1 day, 3:14:17, time: 0.955, data_time: 0.004, memory: 16118, loss_visual: 0.3405, loss: 0.3405, grad_norm: 1.4059 2021-12-02 23:51:10,908 - mmocr - INFO - Epoch [10][7000/10520] lr: 1.000e-04, eta: 1 day, 2:59:01, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3381, loss: 0.3381, grad_norm: 1.4207 2021-12-03 00:05:43,950 - mmocr - INFO - Epoch [10][8000/10520] lr: 1.000e-04, eta: 1 day, 2:43:47, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3386, loss: 0.3386, grad_norm: 1.4431 2021-12-03 00:20:15,237 - mmocr - INFO - Epoch [10][9000/10520] lr: 1.000e-04, eta: 1 day, 2:28:31, time: 0.871, data_time: 0.004, memory: 16118, loss_visual: 0.3380, loss: 0.3380, grad_norm: 1.4138 2021-12-03 00:34:47,071 - mmocr - INFO - Epoch [10][10000/10520] lr: 1.000e-04, eta: 1 day, 2:13:16, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.3364, loss: 0.3364, grad_norm: 1.3878 2021-12-03 00:42:24,419 - mmocr - INFO - Saving checkpoint at 10 epochs 2021-12-03 00:52:42,820 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-03 00:52:42,875 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-03 00:52:42,885 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-03 00:52:42,899 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-03 00:52:42,930 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-03 00:52:42,940 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-03 00:52:42,945 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-03 00:52:42,945 - mmocr - INFO - Epoch(val) [10][959] 0_word_acc: 0.0733, 0_word_acc_ignore_case: 0.9373, 0_word_acc_ignore_case_symbol: 0.9373, 0_char_recall: 0.9811, 0_char_precision: 0.9801, 0_1-N.E.D: 0.9788, 1_word_acc: 0.8872, 1_word_acc_ignore_case: 0.8872, 1_word_acc_ignore_case_symbol: 0.8872, 1_char_recall: 0.9687, 1_char_precision: 0.9738, 1_1-N.E.D: 0.9633, 2_word_acc: 0.2877, 2_word_acc_ignore_case: 0.9163, 2_word_acc_ignore_case_symbol: 0.9163, 2_char_recall: 0.9818, 2_char_precision: 0.9795, 2_1-N.E.D: 0.9616, 3_word_acc: 0.1213, 3_word_acc_ignore_case: 0.7535, 3_word_acc_ignore_case_symbol: 0.8012, 3_char_recall: 0.9429, 3_char_precision: 0.9348, 3_1-N.E.D: 0.9224, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8186, 4_word_acc_ignore_case_symbol: 0.8186, 4_char_recall: 0.9319, 4_char_precision: 0.9451, 4_1-N.E.D: 0.9261, 5_word_acc: 0.1562, 5_word_acc_ignore_case: 0.8507, 5_word_acc_ignore_case_symbol: 0.8542, 5_char_recall: 0.9367, 5_char_precision: 0.9480, 5_1-N.E.D: 0.9403 2021-12-03 01:17:24,499 - mmocr - INFO - Epoch [11][1000/10520] lr: 1.000e-04, eta: 1 day, 1:52:41, time: 1.481, data_time: 0.620, memory: 16118, loss_visual: 0.3346, loss: 0.3346, grad_norm: 1.3886 2021-12-03 01:31:48,794 - mmocr - INFO - Epoch [11][2000/10520] lr: 1.000e-04, eta: 1 day, 1:37:18, time: 0.864, data_time: 0.005, memory: 16118, loss_visual: 0.3325, loss: 0.3325, grad_norm: 1.3673 2021-12-03 01:46:15,658 - mmocr - INFO - Epoch [11][3000/10520] lr: 1.000e-04, eta: 1 day, 1:21:59, time: 0.867, data_time: 0.005, memory: 16118, loss_visual: 0.3334, loss: 0.3334, grad_norm: 1.3989 2021-12-03 02:00:49,015 - mmocr - INFO - Epoch [11][4000/10520] lr: 1.000e-04, eta: 1 day, 1:06:47, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.3311, loss: 0.3311, grad_norm: 1.4001 2021-12-03 02:15:23,552 - mmocr - INFO - Epoch [11][5000/10520] lr: 1.000e-04, eta: 1 day, 0:51:36, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.3320, loss: 0.3320, grad_norm: 1.3946 2021-12-03 02:29:56,097 - mmocr - INFO - Epoch [11][6000/10520] lr: 1.000e-04, eta: 1 day, 0:36:25, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.3298, loss: 0.3298, grad_norm: 1.3917 2021-12-03 02:44:28,793 - mmocr - INFO - Epoch [11][7000/10520] lr: 1.000e-04, eta: 1 day, 0:21:14, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3296, loss: 0.3296, grad_norm: 1.3762 2021-12-03 02:59:01,511 - mmocr - INFO - Epoch [11][8000/10520] lr: 1.000e-04, eta: 1 day, 0:06:04, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3302, loss: 0.3302, grad_norm: 1.3996 2021-12-03 03:13:34,339 - mmocr - INFO - Epoch [11][9000/10520] lr: 1.000e-04, eta: 23:50:54, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.3274, loss: 0.3274, grad_norm: 1.3810 2021-12-03 03:28:06,134 - mmocr - INFO - Epoch [11][10000/10520] lr: 1.000e-04, eta: 23:35:45, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.3276, loss: 0.3276, grad_norm: 1.3729 2021-12-03 03:35:47,879 - mmocr - INFO - Saving checkpoint at 11 epochs 2021-12-03 03:46:09,407 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-03 03:46:09,491 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-03 03:46:09,501 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-03 03:46:09,515 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-03 03:46:09,546 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-03 03:46:09,556 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-03 03:46:09,561 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-03 03:46:09,562 - mmocr - INFO - Epoch(val) [11][959] 0_word_acc: 0.0740, 0_word_acc_ignore_case: 0.9410, 0_word_acc_ignore_case_symbol: 0.9410, 0_char_recall: 0.9835, 0_char_precision: 0.9834, 0_1-N.E.D: 0.9799, 1_word_acc: 0.9104, 1_word_acc_ignore_case: 0.9104, 1_word_acc_ignore_case_symbol: 0.9104, 1_char_recall: 0.9739, 1_char_precision: 0.9801, 1_1-N.E.D: 0.9713, 2_word_acc: 0.2837, 2_word_acc_ignore_case: 0.9241, 2_word_acc_ignore_case_symbol: 0.9241, 2_char_recall: 0.9831, 2_char_precision: 0.9806, 2_1-N.E.D: 0.9628, 3_word_acc: 0.1247, 3_word_acc_ignore_case: 0.7646, 3_word_acc_ignore_case_symbol: 0.8127, 3_char_recall: 0.9449, 3_char_precision: 0.9370, 3_1-N.E.D: 0.9256, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8403, 4_word_acc_ignore_case_symbol: 0.8403, 4_char_recall: 0.9374, 4_char_precision: 0.9510, 4_1-N.E.D: 0.9324, 5_word_acc: 0.1493, 5_word_acc_ignore_case: 0.8507, 5_word_acc_ignore_case_symbol: 0.8542, 5_char_recall: 0.9323, 5_char_precision: 0.9508, 5_1-N.E.D: 0.9365 2021-12-03 04:10:53,014 - mmocr - INFO - Epoch [12][1000/10520] lr: 1.000e-04, eta: 23:14:51, time: 1.483, data_time: 0.621, memory: 16118, loss_visual: 0.3248, loss: 0.3248, grad_norm: 1.3535 2021-12-03 04:25:21,944 - mmocr - INFO - Epoch [12][2000/10520] lr: 1.000e-04, eta: 22:59:38, time: 0.869, data_time: 0.004, memory: 16118, loss_visual: 0.3238, loss: 0.3238, grad_norm: 1.3271 2021-12-03 04:39:55,296 - mmocr - INFO - Epoch [12][3000/10520] lr: 1.000e-04, eta: 22:44:29, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.3239, loss: 0.3239, grad_norm: 1.3427 2021-12-03 04:54:30,436 - mmocr - INFO - Epoch [12][4000/10520] lr: 1.000e-04, eta: 22:29:23, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3231, loss: 0.3231, grad_norm: 1.3509 2021-12-03 05:09:04,036 - mmocr - INFO - Epoch [12][5000/10520] lr: 1.000e-04, eta: 22:14:16, time: 0.874, data_time: 0.004, memory: 16118, loss_visual: 0.3229, loss: 0.3229, grad_norm: 1.3600 2021-12-03 05:23:38,128 - mmocr - INFO - Epoch [12][6000/10520] lr: 1.000e-04, eta: 21:59:10, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.3219, loss: 0.3219, grad_norm: 1.3550 2021-12-03 05:38:10,010 - mmocr - INFO - Epoch [12][7000/10520] lr: 1.000e-04, eta: 21:44:02, time: 0.872, data_time: 0.004, memory: 16118, loss_visual: 0.3220, loss: 0.3220, grad_norm: 1.3474 2021-12-03 05:52:44,803 - mmocr - INFO - Epoch [12][8000/10520] lr: 1.000e-04, eta: 21:28:58, time: 0.875, data_time: 0.004, memory: 16118, loss_visual: 0.3204, loss: 0.3204, grad_norm: 1.3186 2021-12-03 06:07:20,311 - mmocr - INFO - Epoch [12][9000/10520] lr: 1.000e-04, eta: 21:13:54, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3201, loss: 0.3201, grad_norm: 1.3159 2021-12-03 06:21:54,414 - mmocr - INFO - Epoch [12][10000/10520] lr: 1.000e-04, eta: 20:58:50, time: 0.874, data_time: 0.004, memory: 16118, loss_visual: 0.3193, loss: 0.3193, grad_norm: 1.3450 2021-12-03 06:29:37,351 - mmocr - INFO - Saving checkpoint at 12 epochs 2021-12-03 06:39:52,375 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-03 06:39:52,443 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-03 06:39:52,453 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-03 06:39:52,467 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-03 06:39:52,502 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-03 06:39:52,512 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-03 06:39:52,517 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-03 06:39:52,518 - mmocr - INFO - Epoch(val) [12][959] 0_word_acc: 0.0757, 0_word_acc_ignore_case: 0.9283, 0_word_acc_ignore_case_symbol: 0.9283, 0_char_recall: 0.9805, 0_char_precision: 0.9775, 0_1-N.E.D: 0.9774, 1_word_acc: 0.9011, 1_word_acc_ignore_case: 0.9011, 1_word_acc_ignore_case_symbol: 0.9011, 1_char_recall: 0.9718, 1_char_precision: 0.9770, 1_1-N.E.D: 0.9693, 2_word_acc: 0.2847, 2_word_acc_ignore_case: 0.9143, 2_word_acc_ignore_case_symbol: 0.9143, 2_char_recall: 0.9811, 2_char_precision: 0.9775, 2_1-N.E.D: 0.9607, 3_word_acc: 0.1271, 3_word_acc_ignore_case: 0.7641, 3_word_acc_ignore_case_symbol: 0.8117, 3_char_recall: 0.9451, 3_char_precision: 0.9361, 3_1-N.E.D: 0.9246, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8248, 4_word_acc_ignore_case_symbol: 0.8248, 4_char_recall: 0.9342, 4_char_precision: 0.9462, 4_1-N.E.D: 0.9264, 5_word_acc: 0.1424, 5_word_acc_ignore_case: 0.8299, 5_word_acc_ignore_case_symbol: 0.8333, 5_char_recall: 0.9361, 5_char_precision: 0.9402, 5_1-N.E.D: 0.9329 2021-12-03 07:04:37,369 - mmocr - INFO - Epoch [13][1000/10520] lr: 1.000e-04, eta: 20:37:38, time: 1.485, data_time: 0.623, memory: 16118, loss_visual: 0.3167, loss: 0.3167, grad_norm: 1.3172 2021-12-03 07:19:08,755 - mmocr - INFO - Epoch [13][2000/10520] lr: 1.000e-04, eta: 20:22:31, time: 0.871, data_time: 0.005, memory: 16118, loss_visual: 0.3170, loss: 0.3170, grad_norm: 1.3336 2021-12-03 07:33:41,802 - mmocr - INFO - Epoch [13][3000/10520] lr: 1.000e-04, eta: 20:07:26, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3161, loss: 0.3161, grad_norm: 1.3282 2021-12-03 07:48:17,389 - mmocr - INFO - Epoch [13][4000/10520] lr: 1.000e-04, eta: 19:52:23, time: 0.876, data_time: 0.004, memory: 16118, loss_visual: 0.3152, loss: 0.3152, grad_norm: 1.3050 2021-12-03 08:02:50,994 - mmocr - INFO - Epoch [13][5000/10520] lr: 1.000e-04, eta: 19:37:19, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.3147, loss: 0.3147, grad_norm: 1.3164 2021-12-03 08:17:26,200 - mmocr - INFO - Epoch [13][6000/10520] lr: 1.000e-04, eta: 19:22:17, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3159, loss: 0.3159, grad_norm: 1.2748 2021-12-03 08:32:00,515 - mmocr - INFO - Epoch [13][7000/10520] lr: 1.000e-04, eta: 19:07:14, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.3133, loss: 0.3133, grad_norm: 1.3426 2021-12-03 08:46:34,846 - mmocr - INFO - Epoch [13][8000/10520] lr: 1.000e-04, eta: 18:52:12, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.3132, loss: 0.3132, grad_norm: 1.3180 2021-12-03 09:01:09,509 - mmocr - INFO - Epoch [13][9000/10520] lr: 1.000e-04, eta: 18:37:10, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3129, loss: 0.3129, grad_norm: 1.2882 2021-12-03 09:15:44,407 - mmocr - INFO - Epoch [13][10000/10520] lr: 1.000e-04, eta: 18:22:09, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3123, loss: 0.3123, grad_norm: 1.2876 2021-12-03 09:23:22,482 - mmocr - INFO - Saving checkpoint at 13 epochs 2021-12-03 09:33:33,445 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-03 09:33:33,500 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-03 09:33:33,511 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-03 09:33:33,526 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-03 09:33:33,557 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-03 09:33:33,571 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-03 09:33:33,577 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-03 09:33:33,577 - mmocr - INFO - Epoch(val) [13][959] 0_word_acc: 0.0743, 0_word_acc_ignore_case: 0.9383, 0_word_acc_ignore_case_symbol: 0.9383, 0_char_recall: 0.9833, 0_char_precision: 0.9832, 0_1-N.E.D: 0.9806, 1_word_acc: 0.8964, 1_word_acc_ignore_case: 0.8964, 1_word_acc_ignore_case_symbol: 0.8964, 1_char_recall: 0.9710, 1_char_precision: 0.9764, 1_1-N.E.D: 0.9660, 2_word_acc: 0.2867, 2_word_acc_ignore_case: 0.9232, 2_word_acc_ignore_case_symbol: 0.9232, 2_char_recall: 0.9809, 2_char_precision: 0.9816, 2_1-N.E.D: 0.9610, 3_word_acc: 0.1237, 3_word_acc_ignore_case: 0.7727, 3_word_acc_ignore_case_symbol: 0.8214, 3_char_recall: 0.9468, 3_char_precision: 0.9375, 3_1-N.E.D: 0.9289, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8248, 4_word_acc_ignore_case_symbol: 0.8248, 4_char_recall: 0.9356, 4_char_precision: 0.9486, 4_1-N.E.D: 0.9301, 5_word_acc: 0.1458, 5_word_acc_ignore_case: 0.8611, 5_word_acc_ignore_case_symbol: 0.8646, 5_char_recall: 0.9423, 5_char_precision: 0.9513, 5_1-N.E.D: 0.9425 2021-12-03 09:58:17,662 - mmocr - INFO - Epoch [14][1000/10520] lr: 1.000e-04, eta: 18:00:42, time: 1.484, data_time: 0.621, memory: 16118, loss_visual: 0.3095, loss: 0.3095, grad_norm: 1.3228 2021-12-03 10:12:44,775 - mmocr - INFO - Epoch [14][2000/10520] lr: 1.000e-04, eta: 17:45:36, time: 0.867, data_time: 0.005, memory: 16118, loss_visual: 0.3109, loss: 0.3109, grad_norm: 1.3191 2021-12-03 10:27:19,538 - mmocr - INFO - Epoch [14][3000/10520] lr: 1.000e-04, eta: 17:30:34, time: 0.875, data_time: 0.006, memory: 16118, loss_visual: 0.3099, loss: 0.3099, grad_norm: 1.2949 2021-12-03 10:41:54,098 - mmocr - INFO - Epoch [14][4000/10520] lr: 1.000e-04, eta: 17:15:33, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3097, loss: 0.3097, grad_norm: 1.2976 2021-12-03 10:58:02,919 - mmocr - INFO - Epoch [14][5000/10520] lr: 1.000e-04, eta: 17:01:18, time: 0.969, data_time: 0.004, memory: 16118, loss_visual: 0.3092, loss: 0.3092, grad_norm: 1.3108 2021-12-03 11:12:37,419 - mmocr - INFO - Epoch [14][6000/10520] lr: 1.000e-04, eta: 16:46:17, time: 0.874, data_time: 0.004, memory: 16118, loss_visual: 0.3078, loss: 0.3078, grad_norm: 1.2514 2021-12-03 11:27:11,857 - mmocr - INFO - Epoch [14][7000/10520] lr: 1.000e-04, eta: 16:31:16, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.3081, loss: 0.3081, grad_norm: 1.2855 2021-12-03 11:41:46,142 - mmocr - INFO - Epoch [14][8000/10520] lr: 1.000e-04, eta: 16:16:15, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.3069, loss: 0.3069, grad_norm: 1.2213 2021-12-03 11:56:20,415 - mmocr - INFO - Epoch [14][9000/10520] lr: 1.000e-04, eta: 16:01:14, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.3073, loss: 0.3073, grad_norm: 1.2378 2021-12-03 12:10:55,178 - mmocr - INFO - Epoch [14][10000/10520] lr: 1.000e-04, eta: 15:46:15, time: 0.875, data_time: 0.005, memory: 16118, loss_visual: 0.3055, loss: 0.3055, grad_norm: 1.2773 2021-12-03 12:18:34,201 - mmocr - INFO - Saving checkpoint at 14 epochs 2021-12-03 12:28:57,891 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-03 12:28:57,950 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-03 12:28:57,960 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-03 12:28:57,974 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-03 12:28:58,005 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-03 12:28:58,015 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-03 12:28:58,021 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-03 12:28:58,021 - mmocr - INFO - Epoch(val) [14][959] 0_word_acc: 0.0770, 0_word_acc_ignore_case: 0.9443, 0_word_acc_ignore_case_symbol: 0.9443, 0_char_recall: 0.9858, 0_char_precision: 0.9842, 0_1-N.E.D: 0.9837, 1_word_acc: 0.9026, 1_word_acc_ignore_case: 0.9026, 1_word_acc_ignore_case_symbol: 0.9026, 1_char_recall: 0.9723, 1_char_precision: 0.9783, 1_1-N.E.D: 0.9662, 2_word_acc: 0.2877, 2_word_acc_ignore_case: 0.9300, 2_word_acc_ignore_case_symbol: 0.9300, 2_char_recall: 0.9833, 2_char_precision: 0.9800, 2_1-N.E.D: 0.9643, 3_word_acc: 0.1237, 3_word_acc_ignore_case: 0.7723, 3_word_acc_ignore_case_symbol: 0.8195, 3_char_recall: 0.9497, 3_char_precision: 0.9371, 3_1-N.E.D: 0.9309, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8419, 4_word_acc_ignore_case_symbol: 0.8419, 4_char_recall: 0.9374, 4_char_precision: 0.9505, 4_1-N.E.D: 0.9323, 5_word_acc: 0.1528, 5_word_acc_ignore_case: 0.8576, 5_word_acc_ignore_case_symbol: 0.8611, 5_char_recall: 0.9367, 5_char_precision: 0.9462, 5_1-N.E.D: 0.9398 2021-12-03 12:53:40,196 - mmocr - INFO - Epoch [15][1000/10520] lr: 1.000e-04, eta: 15:24:31, time: 1.482, data_time: 0.621, memory: 16118, loss_visual: 0.3040, loss: 0.3040, grad_norm: 1.2574 2021-12-03 13:09:02,549 - mmocr - INFO - Epoch [15][2000/10520] lr: 1.000e-04, eta: 15:09:50, time: 0.922, data_time: 0.004, memory: 16118, loss_visual: 0.3037, loss: 0.3037, grad_norm: 1.2256 2021-12-03 13:23:30,148 - mmocr - INFO - Epoch [15][3000/10520] lr: 1.000e-04, eta: 14:54:47, time: 0.868, data_time: 0.005, memory: 16118, loss_visual: 0.3044, loss: 0.3044, grad_norm: 1.2954 2021-12-03 13:38:00,638 - mmocr - INFO - Epoch [15][4000/10520] lr: 1.000e-04, eta: 14:39:45, time: 0.870, data_time: 0.004, memory: 16118, loss_visual: 0.3034, loss: 0.3034, grad_norm: 1.2695 2021-12-03 13:52:29,438 - mmocr - INFO - Epoch [15][5000/10520] lr: 1.000e-04, eta: 14:24:43, time: 0.869, data_time: 0.004, memory: 16118, loss_visual: 0.3014, loss: 0.3014, grad_norm: 1.2432 2021-12-03 14:07:01,080 - mmocr - INFO - Epoch [15][6000/10520] lr: 1.000e-04, eta: 14:09:43, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.3020, loss: 0.3020, grad_norm: 1.2198 2021-12-03 14:21:33,915 - mmocr - INFO - Epoch [15][7000/10520] lr: 1.000e-04, eta: 13:54:43, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.3021, loss: 0.3021, grad_norm: 1.2670 2021-12-03 14:36:07,230 - mmocr - INFO - Epoch [15][8000/10520] lr: 1.000e-04, eta: 13:39:44, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.3018, loss: 0.3018, grad_norm: 1.2604 2021-12-03 14:50:38,596 - mmocr - INFO - Epoch [15][9000/10520] lr: 1.000e-04, eta: 13:24:44, time: 0.871, data_time: 0.005, memory: 16118, loss_visual: 0.3004, loss: 0.3004, grad_norm: 1.2280 2021-12-03 15:05:11,863 - mmocr - INFO - Epoch [15][10000/10520] lr: 1.000e-04, eta: 13:09:46, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.3010, loss: 0.3010, grad_norm: 1.2184 2021-12-03 15:12:54,699 - mmocr - INFO - Saving checkpoint at 15 epochs 2021-12-03 15:23:14,372 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-03 15:23:14,440 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-03 15:23:14,450 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-03 15:23:14,464 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-03 15:23:14,497 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-03 15:23:14,507 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-03 15:23:14,512 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-03 15:23:14,512 - mmocr - INFO - Epoch(val) [15][959] 0_word_acc: 0.0753, 0_word_acc_ignore_case: 0.9407, 0_word_acc_ignore_case_symbol: 0.9407, 0_char_recall: 0.9842, 0_char_precision: 0.9825, 0_1-N.E.D: 0.9814, 1_word_acc: 0.9119, 1_word_acc_ignore_case: 0.9119, 1_word_acc_ignore_case_symbol: 0.9119, 1_char_recall: 0.9739, 1_char_precision: 0.9786, 1_1-N.E.D: 0.9686, 2_word_acc: 0.2828, 2_word_acc_ignore_case: 0.9212, 2_word_acc_ignore_case_symbol: 0.9212, 2_char_recall: 0.9828, 2_char_precision: 0.9793, 2_1-N.E.D: 0.9633, 3_word_acc: 0.1242, 3_word_acc_ignore_case: 0.7675, 3_word_acc_ignore_case_symbol: 0.8151, 3_char_recall: 0.9467, 3_char_precision: 0.9365, 3_1-N.E.D: 0.9273, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8512, 4_word_acc_ignore_case_symbol: 0.8512, 4_char_recall: 0.9414, 4_char_precision: 0.9509, 4_1-N.E.D: 0.9362, 5_word_acc: 0.1458, 5_word_acc_ignore_case: 0.8299, 5_word_acc_ignore_case_symbol: 0.8333, 5_char_recall: 0.9354, 5_char_precision: 0.9461, 5_1-N.E.D: 0.9331 2021-12-03 15:48:02,265 - mmocr - INFO - Epoch [16][1000/10520] lr: 1.000e-04, eta: 12:47:52, time: 1.488, data_time: 0.620, memory: 16118, loss_visual: 0.2983, loss: 0.2983, grad_norm: 1.2593 2021-12-03 16:02:32,313 - mmocr - INFO - Epoch [16][2000/10520] lr: 1.000e-04, eta: 12:32:52, time: 0.870, data_time: 0.004, memory: 16118, loss_visual: 0.2987, loss: 0.2987, grad_norm: 1.2310 2021-12-03 16:17:05,212 - mmocr - INFO - Epoch [16][3000/10520] lr: 1.000e-04, eta: 12:17:53, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.2994, loss: 0.2994, grad_norm: 1.2267 2021-12-03 16:31:38,721 - mmocr - INFO - Epoch [16][4000/10520] lr: 1.000e-04, eta: 12:02:55, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.2971, loss: 0.2971, grad_norm: 1.2207 2021-12-03 16:46:12,410 - mmocr - INFO - Epoch [16][5000/10520] lr: 1.000e-04, eta: 11:47:57, time: 0.874, data_time: 0.004, memory: 16118, loss_visual: 0.2979, loss: 0.2979, grad_norm: 1.2140 2021-12-03 17:00:46,174 - mmocr - INFO - Epoch [16][6000/10520] lr: 1.000e-04, eta: 11:32:59, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.2967, loss: 0.2967, grad_norm: 1.1978 2021-12-03 17:15:19,587 - mmocr - INFO - Epoch [16][7000/10520] lr: 1.000e-04, eta: 11:18:02, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.2960, loss: 0.2960, grad_norm: 1.2226 2021-12-03 17:29:51,943 - mmocr - INFO - Epoch [16][8000/10520] lr: 1.000e-04, eta: 11:03:04, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.2954, loss: 0.2954, grad_norm: 1.2010 2021-12-03 17:44:25,010 - mmocr - INFO - Epoch [16][9000/10520] lr: 1.000e-04, eta: 10:48:07, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.2945, loss: 0.2945, grad_norm: 1.1968 2021-12-03 17:58:56,601 - mmocr - INFO - Epoch [16][10000/10520] lr: 1.000e-04, eta: 10:33:10, time: 0.872, data_time: 0.004, memory: 16118, loss_visual: 0.2945, loss: 0.2945, grad_norm: 1.2281 2021-12-03 18:06:36,081 - mmocr - INFO - Saving checkpoint at 16 epochs 2021-12-03 18:16:51,945 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-03 18:16:51,999 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-03 18:16:52,010 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-03 18:16:52,024 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-03 18:16:52,055 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-03 18:16:52,065 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-03 18:16:52,071 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-03 18:16:52,071 - mmocr - INFO - Epoch(val) [16][959] 0_word_acc: 0.0753, 0_word_acc_ignore_case: 0.9420, 0_word_acc_ignore_case_symbol: 0.9420, 0_char_recall: 0.9854, 0_char_precision: 0.9841, 0_1-N.E.D: 0.9823, 1_word_acc: 0.9057, 1_word_acc_ignore_case: 0.9057, 1_word_acc_ignore_case_symbol: 0.9057, 1_char_recall: 0.9726, 1_char_precision: 0.9785, 1_1-N.E.D: 0.9694, 2_word_acc: 0.2837, 2_word_acc_ignore_case: 0.9271, 2_word_acc_ignore_case_symbol: 0.9271, 2_char_recall: 0.9839, 2_char_precision: 0.9815, 2_1-N.E.D: 0.9644, 3_word_acc: 0.1218, 3_word_acc_ignore_case: 0.7670, 3_word_acc_ignore_case_symbol: 0.8151, 3_char_recall: 0.9477, 3_char_precision: 0.9359, 3_1-N.E.D: 0.9270, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8434, 4_word_acc_ignore_case_symbol: 0.8434, 4_char_recall: 0.9409, 4_char_precision: 0.9509, 4_1-N.E.D: 0.9343, 5_word_acc: 0.1528, 5_word_acc_ignore_case: 0.8611, 5_word_acc_ignore_case_symbol: 0.8646, 5_char_recall: 0.9404, 5_char_precision: 0.9488, 5_1-N.E.D: 0.9414 2021-12-03 18:43:24,835 - mmocr - INFO - Epoch [17][1000/10520] lr: 1.000e-05, eta: 10:11:32, time: 1.593, data_time: 0.732, memory: 16118, loss_visual: 0.2810, loss: 0.2810, grad_norm: 1.0288 2021-12-03 18:57:56,983 - mmocr - INFO - Epoch [17][2000/10520] lr: 1.000e-05, eta: 9:56:34, time: 0.872, data_time: 0.004, memory: 16118, loss_visual: 0.2757, loss: 0.2757, grad_norm: 1.0425 2021-12-03 19:12:30,003 - mmocr - INFO - Epoch [17][3000/10520] lr: 1.000e-05, eta: 9:41:37, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.2737, loss: 0.2737, grad_norm: 1.0535 2021-12-03 19:27:05,805 - mmocr - INFO - Epoch [17][4000/10520] lr: 1.000e-05, eta: 9:26:40, time: 0.876, data_time: 0.004, memory: 16118, loss_visual: 0.2734, loss: 0.2734, grad_norm: 1.0543 2021-12-03 19:41:39,870 - mmocr - INFO - Epoch [17][5000/10520] lr: 1.000e-05, eta: 9:11:43, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.2726, loss: 0.2726, grad_norm: 1.0583 2021-12-03 19:56:14,412 - mmocr - INFO - Epoch [17][6000/10520] lr: 1.000e-05, eta: 8:56:46, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.2703, loss: 0.2703, grad_norm: 1.0687 2021-12-03 20:10:47,963 - mmocr - INFO - Epoch [17][7000/10520] lr: 1.000e-05, eta: 8:41:50, time: 0.874, data_time: 0.004, memory: 16118, loss_visual: 0.2706, loss: 0.2706, grad_norm: 1.0777 2021-12-03 20:25:22,203 - mmocr - INFO - Epoch [17][8000/10520] lr: 1.000e-05, eta: 8:26:54, time: 0.874, data_time: 0.004, memory: 16118, loss_visual: 0.2696, loss: 0.2696, grad_norm: 1.0851 2021-12-03 20:39:55,487 - mmocr - INFO - Epoch [17][9000/10520] lr: 1.000e-05, eta: 8:11:58, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.2686, loss: 0.2686, grad_norm: 1.1279 2021-12-03 20:54:29,309 - mmocr - INFO - Epoch [17][10000/10520] lr: 1.000e-05, eta: 7:57:02, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.2682, loss: 0.2682, grad_norm: 1.1024 2021-12-03 21:02:08,020 - mmocr - INFO - Saving checkpoint at 17 epochs 2021-12-03 21:12:26,841 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-03 21:12:26,937 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-03 21:12:26,947 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-03 21:12:26,961 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-03 21:12:26,992 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-03 21:12:27,003 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-03 21:12:27,008 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-03 21:12:27,008 - mmocr - INFO - Epoch(val) [17][959] 0_word_acc: 0.0757, 0_word_acc_ignore_case: 0.9457, 0_word_acc_ignore_case_symbol: 0.9457, 0_char_recall: 0.9865, 0_char_precision: 0.9851, 0_1-N.E.D: 0.9835, 1_word_acc: 0.9134, 1_word_acc_ignore_case: 0.9134, 1_word_acc_ignore_case_symbol: 0.9134, 1_char_recall: 0.9752, 1_char_precision: 0.9820, 1_1-N.E.D: 0.9719, 2_word_acc: 0.2847, 2_word_acc_ignore_case: 0.9281, 2_word_acc_ignore_case_symbol: 0.9281, 2_char_recall: 0.9837, 2_char_precision: 0.9822, 2_1-N.E.D: 0.9640, 3_word_acc: 0.1261, 3_word_acc_ignore_case: 0.7795, 3_word_acc_ignore_case_symbol: 0.8291, 3_char_recall: 0.9510, 3_char_precision: 0.9398, 3_1-N.E.D: 0.9326, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8465, 4_word_acc_ignore_case_symbol: 0.8465, 4_char_recall: 0.9438, 4_char_precision: 0.9556, 4_1-N.E.D: 0.9390, 5_word_acc: 0.1528, 5_word_acc_ignore_case: 0.8576, 5_word_acc_ignore_case_symbol: 0.8611, 5_char_recall: 0.9411, 5_char_precision: 0.9494, 5_1-N.E.D: 0.9420 2021-12-03 21:37:09,605 - mmocr - INFO - Epoch [18][1000/10520] lr: 1.000e-05, eta: 7:34:47, time: 1.483, data_time: 0.621, memory: 16118, loss_visual: 0.2679, loss: 0.2679, grad_norm: 1.1069 2021-12-03 21:51:37,421 - mmocr - INFO - Epoch [18][2000/10520] lr: 1.000e-05, eta: 7:19:50, time: 0.868, data_time: 0.004, memory: 16118, loss_visual: 0.2682, loss: 0.2682, grad_norm: 1.0908 2021-12-03 22:06:07,978 - mmocr - INFO - Epoch [18][3000/10520] lr: 1.000e-05, eta: 7:04:54, time: 0.871, data_time: 0.004, memory: 16118, loss_visual: 0.2665, loss: 0.2665, grad_norm: 1.1109 2021-12-03 22:20:41,494 - mmocr - INFO - Epoch [18][4000/10520] lr: 1.000e-05, eta: 6:49:59, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.2681, loss: 0.2681, grad_norm: 1.1114 2021-12-03 22:35:16,206 - mmocr - INFO - Epoch [18][5000/10520] lr: 1.000e-05, eta: 6:35:03, time: 0.875, data_time: 0.004, memory: 16118, loss_visual: 0.2648, loss: 0.2648, grad_norm: 1.1144 2021-12-03 22:49:48,935 - mmocr - INFO - Epoch [18][6000/10520] lr: 1.000e-05, eta: 6:20:08, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.2661, loss: 0.2661, grad_norm: 1.1110 2021-12-03 23:04:22,464 - mmocr - INFO - Epoch [18][7000/10520] lr: 1.000e-05, eta: 6:05:13, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.2652, loss: 0.2652, grad_norm: 1.1324 2021-12-03 23:18:55,336 - mmocr - INFO - Epoch [18][8000/10520] lr: 1.000e-05, eta: 5:50:19, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.2655, loss: 0.2655, grad_norm: 1.1241 2021-12-03 23:33:28,030 - mmocr - INFO - Epoch [18][9000/10520] lr: 1.000e-05, eta: 5:35:24, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.2658, loss: 0.2658, grad_norm: 1.1245 2021-12-03 23:48:01,167 - mmocr - INFO - Epoch [18][10000/10520] lr: 1.000e-05, eta: 5:20:30, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.2648, loss: 0.2648, grad_norm: 1.1121 2021-12-03 23:55:39,834 - mmocr - INFO - Saving checkpoint at 18 epochs 2021-12-04 00:05:58,999 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-04 00:05:59,054 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-04 00:05:59,064 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-04 00:05:59,082 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-04 00:05:59,113 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-04 00:05:59,123 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-04 00:05:59,128 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-04 00:05:59,128 - mmocr - INFO - Epoch(val) [18][959] 0_word_acc: 0.0760, 0_word_acc_ignore_case: 0.9447, 0_word_acc_ignore_case_symbol: 0.9447, 0_char_recall: 0.9865, 0_char_precision: 0.9854, 0_1-N.E.D: 0.9833, 1_word_acc: 0.9212, 1_word_acc_ignore_case: 0.9212, 1_word_acc_ignore_case_symbol: 0.9212, 1_char_recall: 0.9773, 1_char_precision: 0.9830, 1_1-N.E.D: 0.9732, 2_word_acc: 0.2877, 2_word_acc_ignore_case: 0.9369, 2_word_acc_ignore_case_symbol: 0.9369, 2_char_recall: 0.9850, 2_char_precision: 0.9855, 2_1-N.E.D: 0.9667, 3_word_acc: 0.1257, 3_word_acc_ignore_case: 0.7795, 3_word_acc_ignore_case_symbol: 0.8296, 3_char_recall: 0.9514, 3_char_precision: 0.9402, 3_1-N.E.D: 0.9324, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8465, 4_word_acc_ignore_case_symbol: 0.8465, 4_char_recall: 0.9438, 4_char_precision: 0.9569, 4_1-N.E.D: 0.9404, 5_word_acc: 0.1528, 5_word_acc_ignore_case: 0.8611, 5_word_acc_ignore_case_symbol: 0.8646, 5_char_recall: 0.9442, 5_char_precision: 0.9508, 5_1-N.E.D: 0.9439 2021-12-04 00:30:47,839 - mmocr - INFO - Epoch [19][1000/10520] lr: 1.000e-06, eta: 4:58:08, time: 1.489, data_time: 0.625, memory: 16118, loss_visual: 0.2632, loss: 0.2632, grad_norm: 1.1077 2021-12-04 00:45:17,228 - mmocr - INFO - Epoch [19][2000/10520] lr: 1.000e-06, eta: 4:43:13, time: 0.869, data_time: 0.004, memory: 16118, loss_visual: 0.2633, loss: 0.2633, grad_norm: 1.1210 2021-12-04 00:59:47,461 - mmocr - INFO - Epoch [19][3000/10520] lr: 1.000e-06, eta: 4:28:19, time: 0.870, data_time: 0.004, memory: 16118, loss_visual: 0.2634, loss: 0.2634, grad_norm: 1.1175 2021-12-04 01:14:18,739 - mmocr - INFO - Epoch [19][4000/10520] lr: 1.000e-06, eta: 4:13:24, time: 0.871, data_time: 0.005, memory: 16118, loss_visual: 0.2636, loss: 0.2636, grad_norm: 1.1137 2021-12-04 01:28:47,475 - mmocr - INFO - Epoch [19][5000/10520] lr: 1.000e-06, eta: 3:58:30, time: 0.869, data_time: 0.005, memory: 16118, loss_visual: 0.2623, loss: 0.2623, grad_norm: 1.0942 2021-12-04 01:43:19,851 - mmocr - INFO - Epoch [19][6000/10520] lr: 1.000e-06, eta: 3:43:36, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.2623, loss: 0.2623, grad_norm: 1.1142 2021-12-04 01:57:56,041 - mmocr - INFO - Epoch [19][7000/10520] lr: 1.000e-06, eta: 3:28:43, time: 0.876, data_time: 0.004, memory: 16118, loss_visual: 0.2622, loss: 0.2622, grad_norm: 1.1187 2021-12-04 02:12:32,494 - mmocr - INFO - Epoch [19][8000/10520] lr: 1.000e-06, eta: 3:13:50, time: 0.876, data_time: 0.005, memory: 16118, loss_visual: 0.2641, loss: 0.2641, grad_norm: 1.1242 2021-12-04 02:27:05,547 - mmocr - INFO - Epoch [19][9000/10520] lr: 1.000e-06, eta: 2:58:57, time: 0.873, data_time: 0.004, memory: 16118, loss_visual: 0.2630, loss: 0.2630, grad_norm: 1.1390 2021-12-04 02:41:39,244 - mmocr - INFO - Epoch [19][10000/10520] lr: 1.000e-06, eta: 2:44:04, time: 0.874, data_time: 0.004, memory: 16118, loss_visual: 0.2633, loss: 0.2633, grad_norm: 1.1258 2021-12-04 02:49:21,133 - mmocr - INFO - Saving checkpoint at 19 epochs 2021-12-04 02:59:36,823 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-04 02:59:36,877 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-04 02:59:36,887 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-04 02:59:36,901 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-04 02:59:36,932 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-04 02:59:36,942 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-04 02:59:36,947 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-04 02:59:36,947 - mmocr - INFO - Epoch(val) [19][959] 0_word_acc: 0.0760, 0_word_acc_ignore_case: 0.9457, 0_word_acc_ignore_case_symbol: 0.9457, 0_char_recall: 0.9866, 0_char_precision: 0.9849, 0_1-N.E.D: 0.9836, 1_word_acc: 0.9181, 1_word_acc_ignore_case: 0.9181, 1_word_acc_ignore_case_symbol: 0.9181, 1_char_recall: 0.9771, 1_char_precision: 0.9825, 1_1-N.E.D: 0.9727, 2_word_acc: 0.2857, 2_word_acc_ignore_case: 0.9350, 2_word_acc_ignore_case_symbol: 0.9350, 2_char_recall: 0.9854, 2_char_precision: 0.9843, 2_1-N.E.D: 0.9657, 3_word_acc: 0.1271, 3_word_acc_ignore_case: 0.7853, 3_word_acc_ignore_case_symbol: 0.8344, 3_char_recall: 0.9531, 3_char_precision: 0.9410, 3_1-N.E.D: 0.9342, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8481, 4_word_acc_ignore_case_symbol: 0.8481, 4_char_recall: 0.9440, 4_char_precision: 0.9564, 4_1-N.E.D: 0.9402, 5_word_acc: 0.1493, 5_word_acc_ignore_case: 0.8611, 5_word_acc_ignore_case_symbol: 0.8646, 5_char_recall: 0.9429, 5_char_precision: 0.9507, 5_1-N.E.D: 0.9427 2021-12-04 03:24:20,564 - mmocr - INFO - Epoch [20][1000/10520] lr: 1.000e-06, eta: 2:21:35, time: 1.484, data_time: 0.622, memory: 16118, loss_visual: 0.2631, loss: 0.2631, grad_norm: 1.1337 2021-12-04 03:38:47,555 - mmocr - INFO - Epoch [20][2000/10520] lr: 1.000e-06, eta: 2:06:41, time: 0.867, data_time: 0.005, memory: 16118, loss_visual: 0.2629, loss: 0.2629, grad_norm: 1.1289 2021-12-04 03:53:17,364 - mmocr - INFO - Epoch [20][3000/10520] lr: 1.000e-06, eta: 1:51:48, time: 0.870, data_time: 0.005, memory: 16118, loss_visual: 0.2613, loss: 0.2613, grad_norm: 1.1159 2021-12-04 04:07:48,953 - mmocr - INFO - Epoch [20][4000/10520] lr: 1.000e-06, eta: 1:36:56, time: 0.872, data_time: 0.004, memory: 16118, loss_visual: 0.2621, loss: 0.2621, grad_norm: 1.0965 2021-12-04 04:22:19,603 - mmocr - INFO - Epoch [20][5000/10520] lr: 1.000e-06, eta: 1:22:03, time: 0.871, data_time: 0.005, memory: 16118, loss_visual: 0.2612, loss: 0.2612, grad_norm: 1.1314 2021-12-04 04:36:52,654 - mmocr - INFO - Epoch [20][6000/10520] lr: 1.000e-06, eta: 1:07:11, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.2638, loss: 0.2638, grad_norm: 1.1516 2021-12-04 04:51:24,964 - mmocr - INFO - Epoch [20][7000/10520] lr: 1.000e-06, eta: 0:52:18, time: 0.872, data_time: 0.005, memory: 16118, loss_visual: 0.2621, loss: 0.2621, grad_norm: 1.1210 2021-12-04 05:05:57,673 - mmocr - INFO - Epoch [20][8000/10520] lr: 1.000e-06, eta: 0:37:26, time: 0.873, data_time: 0.005, memory: 16118, loss_visual: 0.2619, loss: 0.2619, grad_norm: 1.1308 2021-12-04 05:20:31,926 - mmocr - INFO - Epoch [20][9000/10520] lr: 1.000e-06, eta: 0:22:35, time: 0.874, data_time: 0.005, memory: 16118, loss_visual: 0.2621, loss: 0.2621, grad_norm: 1.1118 2021-12-04 05:35:04,355 - mmocr - INFO - Epoch [20][10000/10520] lr: 1.000e-06, eta: 0:07:43, time: 0.872, data_time: 0.004, memory: 16118, loss_visual: 0.2626, loss: 0.2626, grad_norm: 1.1383 2021-12-04 05:42:43,073 - mmocr - INFO - Saving checkpoint at 20 epochs 2021-12-04 05:53:00,214 - mmocr - INFO - Evaluateing data/mixture/testset/IIIT5K/label.txt with 3000 images now 2021-12-04 05:53:00,268 - mmocr - INFO - Evaluateing data/mixture/testset/svt/test_list.txt with 647 images now 2021-12-04 05:53:00,278 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2013/1015_test_label.txt with 1015 images now 2021-12-04 05:53:00,293 - mmocr - INFO - Evaluateing data/mixture/testset/icdar_2015/test_label.txt with 2077 images now 2021-12-04 05:53:00,323 - mmocr - INFO - Evaluateing data/mixture/testset/svtp/imagelist.txt with 645 images now 2021-12-04 05:53:00,333 - mmocr - INFO - Evaluateing data/mixture/testset/ct80/imagelist.txt with 288 images now 2021-12-04 05:53:00,339 - mmocr - INFO - Exp name: abinet_pretrain_vision_alphanumeric_reimplement_aug.py 2021-12-04 05:53:00,339 - mmocr - INFO - Epoch(val) [20][959] 0_word_acc: 0.0760, 0_word_acc_ignore_case: 0.9470, 0_word_acc_ignore_case_symbol: 0.9470, 0_char_recall: 0.9866, 0_char_precision: 0.9854, 0_1-N.E.D: 0.9841, 1_word_acc: 0.9165, 1_word_acc_ignore_case: 0.9165, 1_word_acc_ignore_case_symbol: 0.9165, 1_char_recall: 0.9760, 1_char_precision: 0.9815, 1_1-N.E.D: 0.9715, 2_word_acc: 0.2857, 2_word_acc_ignore_case: 0.9360, 2_word_acc_ignore_case_symbol: 0.9360, 2_char_recall: 0.9854, 2_char_precision: 0.9835, 2_1-N.E.D: 0.9666, 3_word_acc: 0.1257, 3_word_acc_ignore_case: 0.7800, 3_word_acc_ignore_case_symbol: 0.8296, 3_char_recall: 0.9518, 3_char_precision: 0.9401, 3_1-N.E.D: 0.9329, 4_word_acc: 0.0000, 4_word_acc_ignore_case: 0.8512, 4_word_acc_ignore_case_symbol: 0.8512, 4_char_recall: 0.9430, 4_char_precision: 0.9558, 4_1-N.E.D: 0.9391, 5_word_acc: 0.1493, 5_word_acc_ignore_case: 0.8611, 5_word_acc_ignore_case_symbol: 0.8646, 5_char_recall: 0.9398, 5_char_precision: 0.9481, 5_1-N.E.D: 0.9403