| img_norm_cfg = dict(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]) | |
| train_pipeline = [ | |
| dict(type='LoadImageFromFile'), | |
| dict( | |
| type='ResizeOCR', | |
| height=48, | |
| min_width=48, | |
| max_width=160, | |
| keep_aspect_ratio=True, | |
| width_downsample_ratio=0.25), | |
| dict(type='ToTensorOCR'), | |
| dict(type='NormalizeOCR', **img_norm_cfg), | |
| dict( | |
| type='Collect', | |
| keys=['img'], | |
| meta_keys=[ | |
| 'filename', 'ori_shape', 'resize_shape', 'text', 'valid_ratio' | |
| ]), | |
| ] | |
| test_pipeline = [ | |
| dict(type='LoadImageFromFile'), | |
| dict( | |
| type='MultiRotateAugOCR', | |
| rotate_degrees=[0, 90, 270], | |
| transforms=[ | |
| dict( | |
| type='ResizeOCR', | |
| height=48, | |
| min_width=48, | |
| max_width=160, | |
| keep_aspect_ratio=True, | |
| width_downsample_ratio=0.25), | |
| dict(type='ToTensorOCR'), | |
| dict(type='NormalizeOCR', **img_norm_cfg), | |
| dict( | |
| type='Collect', | |
| keys=['img'], | |
| meta_keys=[ | |
| 'filename', 'ori_shape', 'resize_shape', 'valid_ratio', | |
| 'img_norm_cfg', 'ori_filename', 'img_shape' | |
| ]), | |
| ]) | |
| ] | |