| img_norm_cfg = dict(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) | |
| train_pipeline = [ | |
| dict(type='LoadImageFromFile'), | |
| dict( | |
| type='ResizeOCR', | |
| height=32, | |
| min_width=100, | |
| max_width=100, | |
| keep_aspect_ratio=False, | |
| width_downsample_ratio=0.25), | |
| dict(type='ToTensorOCR'), | |
| dict(type='NormalizeOCR', **img_norm_cfg), | |
| dict( | |
| type='Collect', | |
| keys=['img'], | |
| meta_keys=[ | |
| 'filename', 'ori_shape', 'img_shape', 'text', 'valid_ratio', | |
| 'resize_shape' | |
| ]), | |
| ] | |
| test_pipeline = [ | |
| dict(type='LoadImageFromFile'), | |
| dict( | |
| type='MultiRotateAugOCR', | |
| rotate_degrees=[0, 90, 270], | |
| transforms=[ | |
| dict( | |
| type='ResizeOCR', | |
| height=32, | |
| min_width=100, | |
| max_width=100, | |
| keep_aspect_ratio=False, | |
| width_downsample_ratio=0.25), | |
| dict(type='ToTensorOCR'), | |
| dict(type='NormalizeOCR', **img_norm_cfg), | |
| dict( | |
| type='Collect', | |
| keys=['img'], | |
| meta_keys=[ | |
| 'filename', 'ori_shape', 'img_shape', 'valid_ratio', | |
| 'resize_shape', 'img_norm_cfg', 'ori_filename' | |
| ]), | |
| ]) | |
| ] | |