mirror of
https://github.com/open-mmlab/mmocr.git
synced 2025-06-03 21:54:47 +08:00
7571763376
* [Refactor] Use MMOCR's registry 1. Define MMOCR's registries as a child of MMDet's 2. Register all models to MMOCR's own registries 3. Modify some model configs so that some models in MMDet can be correctly located 4. Remove some outdated demo scripts * add detectors
137 lines
4.0 KiB
Python
137 lines
4.0 KiB
Python
fourier_degree = 5
|
|
model = dict(
|
|
type='FCENet',
|
|
backbone=dict(
|
|
type='mmdet.ResNet',
|
|
depth=50,
|
|
num_stages=4,
|
|
out_indices=(1, 2, 3),
|
|
frozen_stages=-1,
|
|
norm_cfg=dict(type='BN', requires_grad=True),
|
|
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
|
|
norm_eval=False,
|
|
style='pytorch'),
|
|
neck=dict(
|
|
type='mmdet.FPN',
|
|
in_channels=[512, 1024, 2048],
|
|
out_channels=256,
|
|
add_extra_convs='on_output',
|
|
num_outs=3,
|
|
relu_before_extra_convs=True,
|
|
act_cfg=None),
|
|
bbox_head=dict(
|
|
type='FCEHead',
|
|
in_channels=256,
|
|
scales=(8, 16, 32),
|
|
loss=dict(type='FCELoss'),
|
|
alpha=1.2,
|
|
beta=1.0,
|
|
text_repr_type='quad',
|
|
fourier_degree=fourier_degree,
|
|
))
|
|
|
|
train_cfg = None
|
|
test_cfg = None
|
|
|
|
dataset_type = 'IcdarDataset'
|
|
data_root = 'data/icdar2015/'
|
|
|
|
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,
|
|
contrast=0.5),
|
|
dict(type='Normalize', **img_norm_cfg),
|
|
dict(type='RandomScaling', size=800, scale=(3. / 4, 5. / 2)),
|
|
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=30,
|
|
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='Pad', size_divisor=32),
|
|
dict(
|
|
type='FCENetTargets',
|
|
fourier_degree=fourier_degree,
|
|
level_proportion_range=((0, 0.4), (0.3, 0.7), (0.6, 1.0))),
|
|
dict(
|
|
type='CustomFormatBundle',
|
|
keys=['p3_maps', 'p4_maps', 'p5_maps'],
|
|
visualize=dict(flag=False, boundary_key=None)),
|
|
dict(type='Collect', keys=['img', 'p3_maps', 'p4_maps', 'p5_maps'])
|
|
]
|
|
test_pipeline = [
|
|
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
|
|
dict(
|
|
type='MultiScaleFlipAug',
|
|
img_scale=(2260, 2260),
|
|
flip=False,
|
|
transforms=[
|
|
dict(type='Resize', img_scale=(1280, 800), 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']),
|
|
])
|
|
]
|
|
data = dict(
|
|
samples_per_gpu=8,
|
|
workers_per_gpu=2,
|
|
val_dataloader=dict(samples_per_gpu=1),
|
|
test_dataloader=dict(samples_per_gpu=1),
|
|
train=dict(
|
|
type=dataset_type,
|
|
ann_file=data_root + '/instances_training.json',
|
|
img_prefix=data_root + '/imgs',
|
|
pipeline=train_pipeline),
|
|
val=dict(
|
|
type=dataset_type,
|
|
ann_file=data_root + '/instances_test.json',
|
|
img_prefix=data_root + '/imgs',
|
|
pipeline=test_pipeline),
|
|
test=dict(
|
|
type=dataset_type,
|
|
ann_file=data_root + '/instances_test.json',
|
|
img_prefix=data_root + '/imgs',
|
|
pipeline=test_pipeline))
|
|
evaluation = dict(interval=5, metric='hmean-iou')
|
|
|
|
# optimizer
|
|
optimizer = dict(type='SGD', lr=1e-3, momentum=0.90, weight_decay=5e-4)
|
|
optimizer_config = dict(grad_clip=None)
|
|
lr_config = dict(policy='poly', power=0.9, min_lr=1e-7, by_epoch=True)
|
|
total_epochs = 1500
|
|
|
|
checkpoint_config = dict(interval=5)
|
|
# yapf:disable
|
|
log_config = dict(
|
|
interval=20,
|
|
hooks=[
|
|
dict(type='TextLoggerHook')
|
|
|
|
])
|
|
# yapf:enable
|
|
dist_params = dict(backend='nccl')
|
|
log_level = 'INFO'
|
|
load_from = None
|
|
resume_from = None
|
|
workflow = [('train', 1)]
|