mirror of https://github.com/open-mmlab/mmocr.git
183 lines
6.1 KiB
Python
183 lines
6.1 KiB
Python
file_client_args = dict(backend='disk')
|
|
|
|
model = dict(
|
|
type='MMDetWrapper',
|
|
text_repr_type='poly',
|
|
cfg=dict(
|
|
type='MaskRCNN',
|
|
data_preprocessor=dict(
|
|
type='DetDataPreprocessor',
|
|
mean=[123.675, 116.28, 103.53],
|
|
std=[58.395, 57.12, 57.375],
|
|
bgr_to_rgb=True,
|
|
pad_size_divisor=32),
|
|
backbone=dict(
|
|
type='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=True,
|
|
style='pytorch',
|
|
init_cfg=dict(
|
|
type='Pretrained', checkpoint='torchvision://resnet50')),
|
|
neck=dict(
|
|
type='FPN',
|
|
in_channels=[256, 512, 1024, 2048],
|
|
out_channels=256,
|
|
num_outs=5),
|
|
rpn_head=dict(
|
|
type='RPNHead',
|
|
in_channels=256,
|
|
feat_channels=256,
|
|
anchor_generator=dict(
|
|
type='AnchorGenerator',
|
|
scales=[4],
|
|
ratios=[0.17, 0.44, 1.13, 2.90, 7.46],
|
|
strides=[4, 8, 16, 32, 64]),
|
|
bbox_coder=dict(
|
|
type='DeltaXYWHBBoxCoder',
|
|
target_means=[.0, .0, .0, .0],
|
|
target_stds=[1.0, 1.0, 1.0, 1.0]),
|
|
loss_cls=dict(
|
|
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
|
|
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
|
|
roi_head=dict(
|
|
type='StandardRoIHead',
|
|
bbox_roi_extractor=dict(
|
|
type='SingleRoIExtractor',
|
|
roi_layer=dict(
|
|
type='RoIAlign', output_size=7, sampling_ratio=0.),
|
|
out_channels=256,
|
|
featmap_strides=[4, 8, 16, 32]),
|
|
bbox_head=dict(
|
|
type='Shared2FCBBoxHead',
|
|
in_channels=256,
|
|
fc_out_channels=1024,
|
|
roi_feat_size=7,
|
|
num_classes=1,
|
|
bbox_coder=dict(
|
|
type='DeltaXYWHBBoxCoder',
|
|
target_means=[0., 0., 0., 0.],
|
|
target_stds=[0.1, 0.1, 0.2, 0.2]),
|
|
reg_class_agnostic=False,
|
|
loss_cls=dict(
|
|
type='CrossEntropyLoss',
|
|
use_sigmoid=False,
|
|
loss_weight=1.0),
|
|
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
|
|
mask_roi_extractor=dict(
|
|
type='SingleRoIExtractor',
|
|
roi_layer=dict(
|
|
type='RoIAlign', output_size=14, sampling_ratio=0.),
|
|
out_channels=256,
|
|
featmap_strides=[4, 8, 16, 32]),
|
|
mask_head=dict(
|
|
type='FCNMaskHead',
|
|
num_convs=4,
|
|
in_channels=256,
|
|
conv_out_channels=256,
|
|
num_classes=1,
|
|
loss_mask=dict(
|
|
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
|
|
# model training and testing settings
|
|
train_cfg=dict(
|
|
rpn=dict(
|
|
assigner=dict(
|
|
type='MaxIoUAssigner',
|
|
pos_iou_thr=0.7,
|
|
neg_iou_thr=0.3,
|
|
min_pos_iou=0.3,
|
|
match_low_quality=True,
|
|
ignore_iof_thr=-1),
|
|
sampler=dict(
|
|
type='RandomSampler',
|
|
num=256,
|
|
pos_fraction=0.5,
|
|
neg_pos_ub=-1,
|
|
add_gt_as_proposals=False),
|
|
allowed_border=-1,
|
|
pos_weight=-1,
|
|
debug=False),
|
|
rpn_proposal=dict(
|
|
nms_pre=2000,
|
|
max_per_img=1000,
|
|
nms=dict(type='nms', iou_threshold=0.7),
|
|
min_bbox_size=0),
|
|
rcnn=dict(
|
|
assigner=dict(
|
|
type='MaxIoUAssigner',
|
|
pos_iou_thr=0.5,
|
|
neg_iou_thr=0.5,
|
|
min_pos_iou=0.5,
|
|
match_low_quality=True,
|
|
ignore_iof_thr=-1),
|
|
sampler=dict(
|
|
type='RandomSampler',
|
|
num=512,
|
|
pos_fraction=0.25,
|
|
neg_pos_ub=-1,
|
|
add_gt_as_proposals=True),
|
|
mask_size=28,
|
|
pos_weight=-1,
|
|
debug=False)),
|
|
test_cfg=dict(
|
|
rpn=dict(
|
|
nms_pre=1000,
|
|
max_per_img=1000,
|
|
nms=dict(type='nms', iou_threshold=0.7),
|
|
min_bbox_size=0),
|
|
rcnn=dict(
|
|
score_thr=0.05,
|
|
nms=dict(type='nms', iou_threshold=0.5),
|
|
max_per_img=100,
|
|
mask_thr_binary=0.5))))
|
|
|
|
train_pipeline = [
|
|
dict(
|
|
type='LoadImageFromFile',
|
|
file_client_args=file_client_args,
|
|
color_type='color_ignore_orientation'),
|
|
dict(
|
|
type='LoadOCRAnnotations',
|
|
with_polygon=True,
|
|
with_bbox=True,
|
|
with_label=True,
|
|
),
|
|
dict(
|
|
type='TorchVisionWrapper',
|
|
op='ColorJitter',
|
|
brightness=32.0 / 255,
|
|
saturation=0.5,
|
|
contrast=0.5),
|
|
dict(
|
|
type='RandomResize',
|
|
scale=(640, 640),
|
|
ratio_range=(1.0, 4.125),
|
|
keep_ratio=True),
|
|
dict(type='RandomFlip', prob=0.5),
|
|
dict(type='TextDetRandomCrop', target_size=(640, 640)),
|
|
dict(type='MMOCR2MMDet', poly2mask=True),
|
|
dict(
|
|
type='mmdet.PackDetInputs',
|
|
meta_keys=('img_path', 'ori_shape', 'img_shape', 'flip',
|
|
'scale_factor', 'flip_direction'))
|
|
]
|
|
|
|
test_pipeline = [
|
|
dict(
|
|
type='LoadImageFromFile',
|
|
file_client_args=file_client_args,
|
|
color_type='color_ignore_orientation'),
|
|
dict(type='Resize', scale=(1920, 1920), 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'))
|
|
]
|