mmocr/configs/textrecog/sar/sar_r31_sequential_decoder_academic.py

101 lines
2.8 KiB
Python
Raw Normal View History

_base_ = [
'../../_base_/default_runtime.py',
2022-06-24 04:47:20 +00:00
'../../_base_/recog_models/sar.py',
'../../_base_/schedules/schedule_adam_step_5e.py',
]
2022-06-24 04:47:20 +00:00
dataset_type = 'OCRDataset'
data_root = 'data/recog/'
file_client_args = dict(backend='disk')
2022-06-24 04:47:20 +00:00
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'))
]
2021-04-02 23:54:57 +08:00
2022-06-24 04:47:20 +00:00
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=None),
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=None),
ann_file='test_label.json',
test_mode=True,
pipeline=test_pipeline))
test_dataloader = val_dataloader
2021-04-02 23:54:57 +08:00
2022-06-24 04:47:20 +00:00
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)
2021-04-02 23:54:57 +08:00
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,
2022-06-24 04:47:20 +00:00
pred_concat=True,
postprocessor=dict(type='AttentionPostprocessor'),
module_loss=dict(
type='CEModuleLoss', ignore_first_char=True, reduction='mean')),
2022-06-24 04:47:20 +00:00
dictionary=dictionary,
2021-04-02 23:54:57 +08:00
max_seq_len=30)