mirror of https://github.com/open-mmlab/mmocr.git
77 lines
2.2 KiB
Python
77 lines
2.2 KiB
Python
_base_ = [
|
|
'psenet_r50_fpnf.py',
|
|
'../../_base_/default_runtime.py',
|
|
'../../_base_/schedules/schedule_adam_step_600e.py',
|
|
]
|
|
|
|
model = {{_base_.model_quad}}
|
|
|
|
train_pipeline_icdar2015 = [
|
|
dict(type='LoadImageFromFile', 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),
|
|
dict(type='ShortScaleAspectJitter', short_size=736, scale_divisor=32),
|
|
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
|
|
dict(type='RandomRotate', max_angle=10),
|
|
dict(type='TextDetRandomCrop', target_size=(736, 736)),
|
|
dict(type='Pad', size=(736, 736)),
|
|
dict(
|
|
type='PackTextDetInputs',
|
|
meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor'))
|
|
]
|
|
|
|
test_pipeline_icdar2015 = [
|
|
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
|
|
dict(type='Resize', scale=(2240, 2240), keep_ratio=True),
|
|
dict(
|
|
type='PackTextDetInputs',
|
|
meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor',
|
|
'instances'))
|
|
]
|
|
|
|
dataset_type = 'OCRDataset'
|
|
data_root = 'data/icdar2015'
|
|
|
|
train_dataset = dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
ann_file='instances_training.json',
|
|
data_prefix=dict(img_path='imgs/'),
|
|
filter_cfg=dict(filter_empty_gt=True, min_size=32),
|
|
pipeline=train_pipeline_icdar2015)
|
|
|
|
test_dataset = dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
ann_file='instances_test.json',
|
|
data_prefix=dict(img_path='imgs/'),
|
|
test_mode=True,
|
|
pipeline=test_pipeline_icdar2015)
|
|
|
|
train_dataloader = dict(
|
|
batch_size=16,
|
|
num_workers=8,
|
|
persistent_workers=False,
|
|
sampler=dict(type='DefaultSampler', shuffle=True),
|
|
dataset=train_dataset)
|
|
val_dataloader = dict(
|
|
batch_size=1,
|
|
num_workers=4,
|
|
persistent_workers=False,
|
|
sampler=dict(type='DefaultSampler', shuffle=False),
|
|
dataset=test_dataset)
|
|
test_dataloader = val_dataloader
|
|
|
|
val_evaluator = dict(type='HmeanIOUMetric')
|
|
test_evaluator = val_evaluator
|
|
|
|
visualizer = dict(type='TextDetLocalVisualizer', name='visualizer')
|