mmocr/configs/textrecog/robust_scanner/robustscanner_r31_academic.py

70 lines
1.9 KiB
Python

_base_ = [
'robust_scanner.py', '../../_base_/default_runtime.py',
'../../_base_/schedules/schedule_adam_step_5e.py'
]
# dataset settings
dataset_type = 'OCRDataset'
data_root = 'data/recog'
file_client_args = dict(backend='disk')
train_pipeline = [
dict(type='LoadImageFromFile', file_client_args=file_client_args),
dict(type='LoadOCRAnnotations', with_text=True),
dict(type='Resize', scale=(160, 48), keep_ratio=False),
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='RescaleToHeight',
height=48,
min_width=48,
max_width=160,
width_divisor=4),
dict(type='PadToWidth', width=160),
dict(
type='PackTextRecogInputs',
meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio',
'instances'))
]
train_dataloader = dict(
batch_size=64,
num_workers=8,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=dict(
type=dataset_type,
data_root=data_root,
data_prefix=dict(img_path=''),
ann_file='train_label.json',
pipeline=train_pipeline))
val_dataloader = dict(
batch_size=1,
num_workers=4,
persistent_workers=True,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type=dataset_type,
data_root=data_root,
data_prefix=dict(img_path=''),
ann_file='test_label.json',
test_mode=True,
pipeline=test_pipeline))
test_dataloader = val_dataloader
val_evaluator = [
dict(
type='WordMetric', mode=['exact', 'ignore_case',
'ignore_case_symbol']),
dict(type='CharMetric')
]
test_evaluator = val_evaluator
visualizer = dict(type='TextRecogLocalVisualizer', name='visualizer')