Spaces:
Sleeping
Sleeping
File size: 3,554 Bytes
24c4def |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
dictionary = dict(
type='Dictionary',
dict_file='{{ fileDirname }}/../../../dicts/english_digits_symbols.txt',
with_padding=True,
with_unknown=True,
same_start_end=True,
with_start=True,
with_end=True)
model = dict(
type='ASTER',
preprocessor=dict(
type='STN',
in_channels=3,
resized_image_size=(32, 64),
output_image_size=(32, 100),
num_control_points=20),
backbone=dict(
type='ResNet',
in_channels=3,
stem_channels=[32],
block_cfgs=dict(type='BasicBlock', use_conv1x1='True'),
arch_layers=[3, 4, 6, 6, 3],
arch_channels=[32, 64, 128, 256, 512],
strides=[(2, 2), (2, 2), (2, 1), (2, 1), (2, 1)],
init_cfg=[
dict(type='Kaiming', layer='Conv2d'),
dict(type='Constant', val=1, layer='BatchNorm2d'),
]),
encoder=dict(type='ASTEREncoder', in_channels=512),
decoder=dict(
type='ASTERDecoder',
max_seq_len=25,
in_channels=512,
emb_dims=512,
attn_dims=512,
hidden_size=512,
postprocessor=dict(type='AttentionPostprocessor'),
module_loss=dict(
type='CEModuleLoss', flatten=True, ignore_first_char=True),
dictionary=dictionary,
),
data_preprocessor=dict(
type='TextRecogDataPreprocessor',
mean=[127.5, 127.5, 127.5],
std=[127.5, 127.5, 127.5]))
train_pipeline = [
dict(type='LoadImageFromFile', ignore_empty=True, min_size=0),
dict(type='LoadOCRAnnotations', with_text=True),
dict(type='Resize', scale=(256, 64)),
dict(
type='PackTextRecogInputs',
meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio'))
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='Resize', scale=(256, 64)),
dict(type='LoadOCRAnnotations', with_text=True),
dict(
type='PackTextRecogInputs',
meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio',
'instances'))
]
tta_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='TestTimeAug',
transforms=[[
dict(
type='ConditionApply',
true_transforms=[
dict(
type='ImgAugWrapper',
args=[dict(cls='Rot90', k=0, keep_size=False)])
],
condition="results['img_shape'][1]<results['img_shape'][0]"),
dict(
type='ConditionApply',
true_transforms=[
dict(
type='ImgAugWrapper',
args=[dict(cls='Rot90', k=1, keep_size=False)])
],
condition="results['img_shape'][1]<results['img_shape'][0]"),
dict(
type='ConditionApply',
true_transforms=[
dict(
type='ImgAugWrapper',
args=[dict(cls='Rot90', k=3, keep_size=False)])
],
condition="results['img_shape'][1]<results['img_shape'][0]"),
], [dict(type='Resize', scale=(256, 64))],
[dict(type='LoadOCRAnnotations', with_text=True)],
[
dict(
type='PackTextRecogInputs',
meta_keys=('img_path', 'ori_shape', 'img_shape',
'valid_ratio', 'instances'))
]])
]
|