mirror of https://github.com/open-mmlab/mmocr.git
108 lines
3.0 KiB
Python
108 lines
3.0 KiB
Python
_base_ = [
|
|
'../../_base_/default_runtime.py',
|
|
'../../_base_/schedules/schedule_adam_step_6e.py'
|
|
]
|
|
|
|
optimizer = dict(type='Adam', lr=3e-4)
|
|
default_hooks = dict(logger=dict(type='LoggerHook', interval=50))
|
|
|
|
dictionary = dict(
|
|
type='Dictionary',
|
|
dict_file='dicts/english_digits_symbols.txt',
|
|
with_padding=True,
|
|
with_unknown=True,
|
|
same_start_end=True,
|
|
with_start=True,
|
|
with_end=True)
|
|
|
|
model = dict(
|
|
type='NRTR',
|
|
backbone=dict(
|
|
type='ResNet31OCR',
|
|
layers=[1, 2, 5, 3],
|
|
channels=[32, 64, 128, 256, 512, 512],
|
|
stage4_pool_cfg=dict(kernel_size=(2, 1), stride=(2, 1)),
|
|
last_stage_pool=False),
|
|
encoder=dict(type='NRTREncoder'),
|
|
decoder=dict(
|
|
type='NRTRDecoder',
|
|
module_loss=dict(
|
|
type='CEModuleLoss', ignore_first_char=True, flatten=True),
|
|
postprocessor=dict(type='AttentionPostprocessor')),
|
|
dictionary=dictionary,
|
|
max_seq_len=30,
|
|
preprocess_cfg=dict(
|
|
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]))
|
|
|
|
# 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='RescaleToHeight',
|
|
height=32,
|
|
min_width=32,
|
|
max_width=160,
|
|
width_divisor=4),
|
|
dict(type='PadToWidth', width=160),
|
|
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=32,
|
|
min_width=32,
|
|
max_width=160,
|
|
width_divisor=16),
|
|
dict(type='PadToWidth', width=160),
|
|
dict(
|
|
type='PackTextRecogInputs',
|
|
meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio',
|
|
'instances'))
|
|
]
|
|
|
|
train_dataloader = dict(
|
|
batch_size=256,
|
|
num_workers=2,
|
|
persistent_workers=True,
|
|
sampler=dict(type='DefaultSampler', shuffle=True),
|
|
dataset=dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
data_prefix=dict(img_path=None),
|
|
ann_file='train_label.json',
|
|
pipeline=train_pipeline))
|
|
|
|
val_dataloader = dict(
|
|
batch_size=128,
|
|
num_workers=2,
|
|
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=None),
|
|
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')
|