2021-11-30 15:00:37 +08:00

112 lines
2.7 KiB
Python
Executable File

# Copyright (c) OpenMMLab. All rights reserved.
_base_ = []
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=1,
hooks=[
dict(type='TextLoggerHook')
])
# yapf:enable
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
# model
label_convertor = dict(
type='CTCConvertor', dict_type='DICT36', with_unknown=False, lower=True)
model = dict(
type='CRNNNet',
preprocessor=None,
backbone=dict(type='VeryDeepVgg', leaky_relu=False, input_channels=1),
encoder=None,
decoder=dict(type='CRNNDecoder', in_channels=512, rnn_flag=True),
loss=dict(type='CTCLoss'),
label_convertor=label_convertor,
pretrained=None)
train_cfg = None
test_cfg = None
# optimizer
optimizer = dict(type='Adadelta', lr=1.0)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(policy='step', step=[])
total_epochs = 5
# data
img_norm_cfg = dict(mean=[127], std=[127])
train_pipeline = [
dict(type='LoadImageFromFile', color_type='grayscale'),
dict(
type='ResizeOCR',
height=32,
min_width=100,
max_width=100,
keep_aspect_ratio=False),
dict(type='Normalize', **img_norm_cfg),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img'],
meta_keys=['filename', 'resize_shape', 'text', 'valid_ratio']),
]
test_pipeline = [
dict(type='LoadImageFromFile', color_type='grayscale'),
dict(
type='ResizeOCR',
height=32,
min_width=32,
max_width=None,
keep_aspect_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img'],
meta_keys=['filename', 'resize_shape', 'valid_ratio']),
]
dataset_type = 'OCRDataset'
test_prefix = 'tests/test_codebase/test_mmocr/data/'
test_img_prefix1 = test_prefix
test_ann_file1 = test_prefix + 'text_recognition.txt'
test1 = dict(
type=dataset_type,
img_prefix=test_img_prefix1,
ann_file=test_ann_file1,
loader=dict(
type='HardDiskLoader',
repeat=1,
parser=dict(
type='LineStrParser',
keys=['filename', 'text'],
keys_idx=[0, 1],
separator=' ')),
pipeline=None,
test_mode=True)
data = dict(
samples_per_gpu=64,
workers_per_gpu=4,
val_dataloader=dict(samples_per_gpu=1),
test_dataloader=dict(samples_per_gpu=1),
val=dict(
type='UniformConcatDataset', datasets=[test1], pipeline=test_pipeline),
test=dict(
type='UniformConcatDataset', datasets=[test1], pipeline=test_pipeline))
evaluation = dict(interval=1, metric='acc')
cudnn_benchmark = True