mirror of
https://github.com/open-mmlab/mmocr.git
synced 2025-06-03 21:54:47 +08:00
96 lines
2.7 KiB
Python
96 lines
2.7 KiB
Python
_base_ = [
|
|
'sar.py',
|
|
'../../_base_/recog_datasets/ST_SA_MJ_real_train.py',
|
|
'../../_base_/recog_datasets/academic_test.py',
|
|
'../../_base_/default_runtime.py',
|
|
'../../_base_/schedules/schedule_adam_step_5e.py',
|
|
]
|
|
|
|
# dataset settings
|
|
train_list = {{_base_.train_list}}
|
|
test_list = {{_base_.test_list}}
|
|
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),
|
|
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='ConcatDataset', datasets=train_list, 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='ConcatDataset', datasets=test_list, 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')
|
|
dictionary = dict(
|
|
type='Dictionary',
|
|
dict_file='dicts/english_digits_symbols.txt',
|
|
with_start=True,
|
|
with_end=True,
|
|
same_start_end=True,
|
|
with_padding=True,
|
|
with_unknown=True)
|
|
model = dict(
|
|
type='SARNet',
|
|
backbone=dict(type='ResNet31OCR'),
|
|
encoder=dict(
|
|
type='SAREncoder',
|
|
enc_bi_rnn=False,
|
|
enc_do_rnn=0.1,
|
|
enc_gru=False,
|
|
),
|
|
decoder=dict(
|
|
type='SequentialSARDecoder',
|
|
enc_bi_rnn=False,
|
|
dec_bi_rnn=False,
|
|
dec_do_rnn=0,
|
|
dec_gru=False,
|
|
pred_dropout=0.1,
|
|
d_k=512,
|
|
pred_concat=True,
|
|
postprocessor=dict(type='AttentionPostprocessor'),
|
|
module_loss=dict(
|
|
type='CEModuleLoss', ignore_first_char=True, reduction='mean')),
|
|
dictionary=dictionary,
|
|
max_seq_len=30)
|