mirror of https://github.com/open-mmlab/mmocr.git
75 lines
2.2 KiB
Python
75 lines
2.2 KiB
Python
file_client_args = dict(backend='disk')
|
|
|
|
model = dict(
|
|
type='DBNet',
|
|
backbone=dict(
|
|
type='mmdet.ResNet',
|
|
depth=50,
|
|
num_stages=4,
|
|
out_indices=(0, 1, 2, 3),
|
|
frozen_stages=-1,
|
|
norm_cfg=dict(type='BN', requires_grad=True),
|
|
norm_eval=False,
|
|
style='pytorch',
|
|
dcn=dict(type='DCNv2', deform_groups=1, fallback_on_stride=False),
|
|
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
|
|
stage_with_dcn=(False, True, True, True)),
|
|
neck=dict(
|
|
type='FPNC', in_channels=[256, 512, 1024, 2048], lateral_channels=256),
|
|
det_head=dict(
|
|
type='DBHead',
|
|
in_channels=256,
|
|
module_loss=dict(type='DBModuleLoss'),
|
|
postprocessor=dict(type='DBPostprocessor', text_repr_type='quad')),
|
|
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',
|
|
file_client_args=file_client_args,
|
|
color_type='color_ignore_orientation'),
|
|
dict(
|
|
type='LoadOCRAnnotations',
|
|
with_bbox=True,
|
|
with_polygon=True,
|
|
with_label=True,
|
|
),
|
|
dict(
|
|
type='TorchVisionWrapper',
|
|
op='ColorJitter',
|
|
brightness=32.0 / 255,
|
|
saturation=0.5),
|
|
dict(
|
|
type='ImgAugWrapper',
|
|
args=[['Fliplr', 0.5],
|
|
dict(cls='Affine', rotate=[-10, 10]), ['Resize', [0.5, 3.0]]]),
|
|
dict(type='RandomCrop', min_side_ratio=0.1),
|
|
dict(type='Resize', scale=(640, 640), keep_ratio=True),
|
|
dict(type='Pad', size=(640, 640)),
|
|
dict(
|
|
type='PackTextDetInputs',
|
|
meta_keys=('img_path', 'ori_shape', 'img_shape'))
|
|
]
|
|
|
|
test_pipeline = [
|
|
dict(
|
|
type='LoadImageFromFile',
|
|
file_client_args=file_client_args,
|
|
color_type='color_ignore_orientation'),
|
|
dict(type='Resize', scale=(4068, 1024), keep_ratio=True),
|
|
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'))
|
|
]
|