File size: 3,986 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
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
dictionary = dict(
    type='Dictionary',
    dict_file='{{ fileDirname }}/../../../dicts/english_digits_symbols.txt',
    with_start=True,
    with_end=True,
    same_start_end=True,
    with_padding=True,
    with_unknown=True)

model = dict(
    type='RobustScanner',
    data_preprocessor=dict(
        type='TextRecogDataPreprocessor',
        mean=[127, 127, 127],
        std=[127, 127, 127]),
    backbone=dict(type='ResNet31OCR'),
    encoder=dict(
        type='ChannelReductionEncoder', in_channels=512, out_channels=128),
    decoder=dict(
        type='RobustScannerFuser',
        hybrid_decoder=dict(
            type='SequenceAttentionDecoder', dim_input=512, dim_model=128),
        position_decoder=dict(
            type='PositionAttentionDecoder', dim_input=512, dim_model=128),
        in_channels=[512, 512],
        postprocessor=dict(type='AttentionPostprocessor'),
        module_loss=dict(
            type='CEModuleLoss', ignore_first_char=True, reduction='mean'),
        dictionary=dictionary,
        max_seq_len=30))

train_pipeline = [
    dict(type='LoadImageFromFile', ignore_empty=True, min_size=2),
    dict(type='LoadOCRAnnotations', with_text=True),
    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'))
]

test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='RescaleToHeight',
        height=48,
        min_width=48,
        max_width=160,
        width_divisor=4),
    dict(type='PadToWidth', width=160),
    # 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'),
    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=48,
                    min_width=48,
                    max_width=160,
                    width_divisor=4),
            ],
            [dict(type='PadToWidth', width=160)],
            # 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'))
            ]
        ])
]