MMOCR / configs /_base_ /det_pipelines /psenet_pipeline.py
tomofi's picture
Add application file
2366e36
raw
history blame
2.38 kB
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='ScaleAspectJitter',
img_scale=[(3000, 736)],
ratio_range=(0.5, 3),
aspect_ratio_range=(1, 1),
multiscale_mode='value',
long_size_bound=1280,
short_size_bound=640,
resize_type='long_short_bound',
keep_ratio=False),
dict(type='PSENetTargets'),
dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
dict(type='RandomRotateTextDet'),
dict(
type='RandomCropInstances',
target_size=(640, 640),
instance_key='gt_kernels'),
dict(type='Pad', size_divisor=32),
dict(
type='CustomFormatBundle',
keys=['gt_kernels', 'gt_mask'],
visualize=dict(flag=False, boundary_key='gt_kernels')),
dict(type='Collect', keys=['img', 'gt_kernels', 'gt_mask'])
]
# for ctw1500
img_scale_test_ctw1500 = (1280, 1280)
test_pipeline_ctw1500 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale_test_ctw1500,
flip=False,
transforms=[
dict(type='Resize', img_scale=(1280, 1280), 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']),
])
]
# for icdar2015
img_scale_test_icdar2015 = (2240, 2240)
test_pipeline_icdar2015 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale_test_icdar2015,
flip=False,
transforms=[
dict(type='Resize', img_scale=(1280, 1280), 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']),
])
]