mirror of
https://github.com/open-mmlab/mmocr.git
synced 2025-06-03 21:54:47 +08:00
128 lines
4.0 KiB
Python
128 lines
4.0 KiB
Python
_base_ = [
|
|
'../../_base_/recog_datasets/mjsynth.py',
|
|
'../../_base_/recog_datasets/synthtext.py',
|
|
'../../_base_/recog_datasets/cute80.py',
|
|
'../../_base_/recog_datasets/iiit5k.py',
|
|
'../../_base_/recog_datasets/svt.py',
|
|
'../../_base_/recog_datasets/svtp.py',
|
|
'../../_base_/recog_datasets/icdar2013.py',
|
|
'../../_base_/recog_datasets/icdar2015.py',
|
|
'../../_base_/default_runtime.py',
|
|
'../../_base_/schedules/schedule_adam_step_20e.py',
|
|
]
|
|
|
|
# dataset settings
|
|
train_list = [_base_.mj_rec_train, _base_.st_an_rec_train]
|
|
test_list = [
|
|
_base_.cute80_rec_test, _base_.iiit5k_rec_test, _base_.svt_rec_test,
|
|
_base_.svtp_rec_test, _base_.ic13_rec_test, _base_.ic15_rec_test
|
|
]
|
|
file_client_args = dict(backend='disk')
|
|
default_hooks = dict(logger=dict(type='LoggerHook', interval=100))
|
|
|
|
train_pipeline = [
|
|
dict(
|
|
type='LoadImageFromFile',
|
|
file_client_args=file_client_args,
|
|
ignore_empty=True,
|
|
min_size=5),
|
|
dict(type='LoadOCRAnnotations', with_text=True),
|
|
dict(type='Resize', scale=(128, 32)),
|
|
dict(
|
|
type='RandomApply',
|
|
prob=0.5,
|
|
transforms=[
|
|
dict(
|
|
type='RandomChoice',
|
|
transforms=[
|
|
dict(
|
|
type='RandomRotate',
|
|
max_angle=15,
|
|
),
|
|
dict(
|
|
type='TorchVisionWrapper',
|
|
op='RandomAffine',
|
|
degrees=15,
|
|
translate=(0.3, 0.3),
|
|
scale=(0.5, 2.),
|
|
shear=(-45, 45),
|
|
),
|
|
dict(
|
|
type='TorchVisionWrapper',
|
|
op='RandomPerspective',
|
|
distortion_scale=0.5,
|
|
p=1,
|
|
),
|
|
])
|
|
],
|
|
),
|
|
dict(
|
|
type='RandomApply',
|
|
prob=0.25,
|
|
transforms=[
|
|
dict(type='PyramidRescale'),
|
|
dict(
|
|
type='mmdet.Albu',
|
|
transforms=[
|
|
dict(type='GaussNoise', var_limit=(20, 20), p=0.5),
|
|
dict(type='MotionBlur', blur_limit=6, p=0.5),
|
|
]),
|
|
]),
|
|
dict(
|
|
type='RandomApply',
|
|
prob=0.25,
|
|
transforms=[
|
|
dict(
|
|
type='TorchVisionWrapper',
|
|
op='ColorJitter',
|
|
brightness=0.5,
|
|
saturation=0.5,
|
|
contrast=0.5,
|
|
hue=0.1),
|
|
]),
|
|
dict(
|
|
type='PackTextRecogInputs',
|
|
meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio'))
|
|
]
|
|
test_pipeline = [
|
|
dict(type='LoadImageFromFile', file_client_args=file_client_args),
|
|
dict(type='Resize', scale=(128, 32)),
|
|
# add loading annotation after ``Resize`` because ground truth
|
|
# does not need to do resize data transform
|
|
dict(type='LoadOCRAnnotations', with_text=True),
|
|
dict(
|
|
type='PackTextRecogInputs',
|
|
meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio'))
|
|
]
|
|
|
|
train_dataloader = dict(
|
|
batch_size=192 * 4,
|
|
num_workers=32,
|
|
persistent_workers=True,
|
|
sampler=dict(type='DefaultSampler', shuffle=True),
|
|
dataset=dict(
|
|
type='ConcatDataset', datasets=train_list, pipeline=train_pipeline))
|
|
|
|
test_dataloader = dict(
|
|
batch_size=1,
|
|
num_workers=4,
|
|
persistent_workers=True,
|
|
drop_last=False,
|
|
sampler=dict(type='DefaultSampler', shuffle=False),
|
|
dataset=dict(
|
|
type='ConcatDataset', datasets=test_list, pipeline=test_pipeline))
|
|
val_dataloader = test_dataloader
|
|
|
|
val_evaluator = dict(
|
|
type='MultiDatasetsEvaluator',
|
|
metrics=[
|
|
dict(
|
|
type='WordMetric',
|
|
mode=['exact', 'ignore_case', 'ignore_case_symbol']),
|
|
dict(type='CharMetric')
|
|
],
|
|
datasets_prefix=['CUTE80', 'IIIT5K', 'SVT', 'SVTP', 'IC13', 'IC15'])
|
|
test_evaluator = val_evaluator
|
|
|
|
visualizer = dict(type='TextRecogLocalVisualizer', name='visualizer')
|