File size: 3,470 Bytes
9bf4bd7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
dictionary = dict(
    type='Dictionary',
    dict_file='{{ fileDirname }}/../../../dicts/lower_english_digits.txt',
    with_padding=True)

model = dict(
    type='CRNN',
    preprocessor=None,
    backbone=dict(type='MiniVGG', leaky_relu=False, input_channels=1),
    encoder=None,
    decoder=dict(
        type='CRNNDecoder',
        in_channels=512,
        rnn_flag=True,
        module_loss=dict(type='CTCModuleLoss', letter_case='lower'),
        postprocessor=dict(type='CTCPostProcessor'),
        dictionary=dictionary),
    data_preprocessor=dict(
        type='TextRecogDataPreprocessor', mean=[127], std=[127]))

train_pipeline = [
    dict(
        type='LoadImageFromFile',
        color_type='grayscale',
        ignore_empty=True,
        min_size=2),
    dict(type='LoadOCRAnnotations', with_text=True),
    dict(type='Resize', scale=(100, 32), keep_ratio=False),
    dict(
        type='PackTextRecogInputs',
        meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio'))
]

test_pipeline = [
    dict(type='LoadImageFromFile', color_type='grayscale'),
    dict(
        type='RescaleToHeight',
        height=32,
        min_width=32,
        max_width=None,
        width_divisor=16),
    # add loading annotation after ``Resize`` because ground truth
    # does not need to do resize data transform
    dict(type='LoadOCRAnnotations', with_text=True),
    dict(
        type='PackTextRecogInputs',
        meta_keys=('img_path', 'ori_shape', 'img_shape', 'valid_ratio'))
]

tta_pipeline = [
    dict(type='LoadImageFromFile', color_type='grayscale'),
    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='RescaleToHeight',
                    height=32,
                    min_width=32,
                    max_width=None,
                    width_divisor=16)
            ],
            # add loading annotation after ``Resize`` because ground truth
            # does not need to do resize data transform
            [dict(type='LoadOCRAnnotations', with_text=True)],
            [
                dict(
                    type='PackTextRecogInputs',
                    meta_keys=('img_path', 'ori_shape', 'img_shape',
                               'valid_ratio'))
            ]
        ])
]