mirror of https://github.com/open-mmlab/mmocr.git
115 lines
3.4 KiB
Python
115 lines
3.4 KiB
Python
_base_ = [
|
|
'../_base_/datasets/union14m_train.py',
|
|
'../_base_/datasets/union14m_benchmark.py',
|
|
'../_base_/datasets/cute80.py',
|
|
'../_base_/datasets/iiit5k.py',
|
|
'../_base_/datasets/svt.py',
|
|
'../_base_/datasets/svtp.py',
|
|
'../_base_/datasets/icdar2013.py',
|
|
'../_base_/datasets/icdar2015.py',
|
|
'../_base_/default_runtime.py',
|
|
'../_base_/schedules/schedule_adam_base.py',
|
|
'_base_nrtr_resnet31.py',
|
|
]
|
|
|
|
# optimizer settings
|
|
train_cfg = dict(max_epochs=6)
|
|
# learning policy
|
|
param_scheduler = [
|
|
dict(type='MultiStepLR', milestones=[3, 4], end=6),
|
|
]
|
|
|
|
_base_.pop('model')
|
|
dictionary = dict(
|
|
type='Dictionary',
|
|
dict_file= # noqa
|
|
'{{ fileDirname }}/../../../dicts/english_digits_symbols_space.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,
|
|
),
|
|
data_preprocessor=dict(
|
|
type='TextRecogDataPreprocessor',
|
|
mean=[123.675, 116.28, 103.53],
|
|
std=[58.395, 57.12, 57.375]))
|
|
|
|
# dataset settings
|
|
train_list = [
|
|
_base_.union14m_challenging, _base_.union14m_hard, _base_.union14m_medium,
|
|
_base_.union14m_normal, _base_.union14m_easy
|
|
]
|
|
val_list = [
|
|
_base_.cute80_textrecog_test, _base_.iiit5k_textrecog_test,
|
|
_base_.svt_textrecog_test, _base_.svtp_textrecog_test,
|
|
_base_.icdar2013_textrecog_test, _base_.icdar2015_textrecog_test
|
|
]
|
|
test_list = [
|
|
_base_.union14m_benchmark_artistic,
|
|
_base_.union14m_benchmark_multi_oriented,
|
|
_base_.union14m_benchmark_contextless,
|
|
_base_.union14m_benchmark_curve,
|
|
_base_.union14m_benchmark_incomplete,
|
|
_base_.union14m_benchmark_incomplete_ori,
|
|
_base_.union14m_benchmark_multi_words,
|
|
_base_.union14m_benchmark_salient,
|
|
_base_.union14m_benchmark_general,
|
|
]
|
|
|
|
train_dataset = dict(
|
|
type='ConcatDataset', datasets=train_list, pipeline=_base_.train_pipeline)
|
|
test_dataset = dict(
|
|
type='ConcatDataset', datasets=test_list, pipeline=_base_.test_pipeline)
|
|
val_dataset = dict(
|
|
type='ConcatDataset', datasets=val_list, pipeline=_base_.test_pipeline)
|
|
|
|
train_dataloader = dict(
|
|
batch_size=128,
|
|
num_workers=24,
|
|
persistent_workers=True,
|
|
sampler=dict(type='DefaultSampler', shuffle=True),
|
|
dataset=train_dataset)
|
|
|
|
test_dataloader = dict(
|
|
batch_size=128,
|
|
num_workers=4,
|
|
persistent_workers=True,
|
|
drop_last=False,
|
|
sampler=dict(type='DefaultSampler', shuffle=False),
|
|
dataset=test_dataset)
|
|
|
|
val_dataloader = dict(
|
|
batch_size=128,
|
|
num_workers=4,
|
|
persistent_workers=True,
|
|
pin_memory=True,
|
|
drop_last=False,
|
|
sampler=dict(type='DefaultSampler', shuffle=False),
|
|
dataset=val_dataset)
|
|
|
|
val_evaluator = dict(
|
|
dataset_prefixes=['CUTE80', 'IIIT5K', 'SVT', 'SVTP', 'IC13', 'IC15'])
|
|
|
|
test_evaluator = dict(dataset_prefixes=[
|
|
'artistic', 'multi-oriented', 'contextless', 'curve', 'incomplete',
|
|
'incomplete-ori', 'multi-words', 'salient', 'general'
|
|
])
|