MMOCR / configs /_base_ /det_pipelines /drrg_pipeline.py
tomofi's picture
Add application file
2366e36
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadTextAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='RandomScaling', size=800, scale=(0.75, 2.5)),
dict(
type='RandomCropFlip', crop_ratio=0.5, iter_num=1, min_area_ratio=0.2),
dict(
type='RandomCropPolyInstances',
instance_key='gt_masks',
crop_ratio=0.8,
min_side_ratio=0.3),
dict(
type='RandomRotatePolyInstances',
rotate_ratio=0.5,
max_angle=60,
pad_with_fixed_color=False),
dict(type='SquareResizePad', target_size=800, pad_ratio=0.6),
dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
dict(type='DRRGTargets'),
dict(type='Pad', size_divisor=32),
dict(
type='CustomFormatBundle',
keys=[
'gt_text_mask', 'gt_center_region_mask', 'gt_mask',
'gt_top_height_map', 'gt_bot_height_map', 'gt_sin_map',
'gt_cos_map', 'gt_comp_attribs'
],
visualize=dict(flag=False, boundary_key='gt_text_mask')),
dict(
type='Collect',
keys=[
'img', 'gt_text_mask', 'gt_center_region_mask', 'gt_mask',
'gt_top_height_map', 'gt_bot_height_map', 'gt_sin_map',
'gt_cos_map', 'gt_comp_attribs'
])
]
test_pipeline = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=(1024, 640),
flip=False,
transforms=[
dict(type='Resize', img_scale=(1024, 640), keep_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]