Spaces:
Running
Running
| model = dict( | |
| type='FCENet', | |
| backbone=dict( | |
| type='mmdet.ResNet', | |
| depth=50, | |
| num_stages=4, | |
| out_indices=(1, 2, 3), | |
| frozen_stages=-1, | |
| norm_cfg=dict(type='BN', requires_grad=True), | |
| init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'), | |
| norm_eval=False, | |
| style='pytorch'), | |
| neck=dict( | |
| type='mmdet.FPN', | |
| in_channels=[512, 1024, 2048], | |
| out_channels=256, | |
| add_extra_convs='on_output', | |
| num_outs=3, | |
| relu_before_extra_convs=True, | |
| act_cfg=None), | |
| det_head=dict( | |
| type='FCEHead', | |
| in_channels=256, | |
| fourier_degree=5, | |
| module_loss=dict(type='FCEModuleLoss', num_sample=50), | |
| postprocessor=dict( | |
| type='FCEPostprocessor', | |
| scales=(8, 16, 32), | |
| text_repr_type='quad', | |
| num_reconstr_points=50, | |
| alpha=1.2, | |
| beta=1.0, | |
| score_thr=0.3)), | |
| data_preprocessor=dict( | |
| type='TextDetDataPreprocessor', | |
| mean=[123.675, 116.28, 103.53], | |
| std=[58.395, 57.12, 57.375], | |
| bgr_to_rgb=True, | |
| pad_size_divisor=32)) | |
| train_pipeline = [ | |
| dict(type='LoadImageFromFile', color_type='color_ignore_orientation'), | |
| dict( | |
| type='LoadOCRAnnotations', | |
| with_polygon=True, | |
| with_bbox=True, | |
| with_label=True, | |
| ), | |
| dict( | |
| type='RandomResize', | |
| scale=(800, 800), | |
| ratio_range=(0.75, 2.5), | |
| keep_ratio=True), | |
| dict( | |
| type='TextDetRandomCropFlip', | |
| crop_ratio=0.5, | |
| iter_num=1, | |
| min_area_ratio=0.2), | |
| dict( | |
| type='RandomApply', | |
| transforms=[dict(type='RandomCrop', min_side_ratio=0.3)], | |
| prob=0.8), | |
| dict( | |
| type='RandomApply', | |
| transforms=[ | |
| dict( | |
| type='RandomRotate', | |
| max_angle=30, | |
| pad_with_fixed_color=False, | |
| use_canvas=True) | |
| ], | |
| prob=0.5), | |
| dict( | |
| type='RandomChoice', | |
| transforms=[[ | |
| dict(type='Resize', scale=800, keep_ratio=True), | |
| dict(type='SourceImagePad', target_scale=800) | |
| ], | |
| dict(type='Resize', scale=800, keep_ratio=False)], | |
| prob=[0.6, 0.4]), | |
| dict(type='RandomFlip', prob=0.5, direction='horizontal'), | |
| dict( | |
| type='TorchVisionWrapper', | |
| op='ColorJitter', | |
| brightness=32.0 / 255, | |
| saturation=0.5, | |
| contrast=0.5), | |
| dict( | |
| type='PackTextDetInputs', | |
| meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) | |
| ] | |
| test_pipeline = [ | |
| dict(type='LoadImageFromFile', color_type='color_ignore_orientation'), | |
| dict(type='Resize', scale=(2260, 2260), keep_ratio=True), | |
| # add loading annotation after ``Resize`` because ground truth | |
| # does not need to do resize data transform | |
| dict( | |
| type='LoadOCRAnnotations', | |
| with_polygon=True, | |
| with_bbox=True, | |
| with_label=True), | |
| dict( | |
| type='PackTextDetInputs', | |
| meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor')) | |
| ] | |