mirror of https://github.com/open-mmlab/mmocr.git
83 lines
2.6 KiB
Python
83 lines
2.6 KiB
Python
model = dict(
|
|
type='TextSnake',
|
|
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),
|
|
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
|
|
norm_eval=True,
|
|
style='caffe'),
|
|
neck=dict(
|
|
type='FPN_UNet', in_channels=[256, 512, 1024, 2048], out_channels=32),
|
|
det_head=dict(
|
|
type='TextSnakeHead',
|
|
in_channels=32,
|
|
module_loss=dict(type='TextSnakeModuleLoss'),
|
|
postprocessor=dict(
|
|
type='TextSnakePostprocessor', text_repr_type='poly')),
|
|
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_bbox=True,
|
|
with_polygon=True,
|
|
with_label=True),
|
|
dict(
|
|
type='TorchVisionWrapper',
|
|
op='ColorJitter',
|
|
brightness=32.0 / 255,
|
|
saturation=0.5),
|
|
dict(
|
|
type='RandomApply',
|
|
transforms=[dict(type='RandomCrop', min_side_ratio=0.3)],
|
|
prob=0.65),
|
|
dict(
|
|
type='RandomRotate',
|
|
max_angle=20,
|
|
pad_with_fixed_color=False,
|
|
use_canvas=True),
|
|
dict(
|
|
type='BoundedScaleAspectJitter',
|
|
long_size_bound=800,
|
|
short_size_bound=480,
|
|
ratio_range=(0.7, 1.3),
|
|
aspect_ratio_range=(0.9, 1.1)),
|
|
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=[0.4, 0.6]),
|
|
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
|
|
dict(
|
|
type='PackTextDetInputs',
|
|
meta_keys=('img_path', 'ori_shape', 'img_shape'))
|
|
]
|
|
|
|
test_pipeline = [
|
|
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
|
|
dict(type='Resize', scale=(1333, 736), 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'))
|
|
]
|