Hugging Face's logo

Spaces:
tomofi
/
MMOCR
Runtime error

App Files Community
2
MMOCR
File size: 5,610 Bytes 
2366e36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
 
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)

# for ctw1500
img_scale_train_ctw1500 = [(3000, 640)]
shrink_ratio_train_ctw1500 = (1.0, 0.7)
target_size_train_ctw1500 = (640, 640)
train_pipeline_ctw1500 = [
    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
    dict(
        type='LoadTextAnnotations',
        with_bbox=True,
        with_mask=True,
        poly2mask=False),
    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
    dict(type='Normalize', **img_norm_cfg),
    dict(
        type='ScaleAspectJitter',
        img_scale=img_scale_train_ctw1500,
        ratio_range=(0.7, 1.3),
        aspect_ratio_range=(0.9, 1.1),
        multiscale_mode='value',
        keep_ratio=False),
    # shrink_ratio is from big to small. The 1st must be 1.0
    dict(type='PANetTargets', shrink_ratio=shrink_ratio_train_ctw1500),
    dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
    dict(type='RandomRotateTextDet'),
    dict(
        type='RandomCropInstances',
        target_size=target_size_train_ctw1500,
        instance_key='gt_kernels'),
    dict(type='Pad', size_divisor=32),
    dict(
        type='CustomFormatBundle',
        keys=['gt_kernels', 'gt_mask'],
        visualize=dict(flag=False, boundary_key='gt_kernels')),
    dict(type='Collect', keys=['img', 'gt_kernels', 'gt_mask'])
]

img_scale_test_ctw1500 = (3000, 640)
test_pipeline_ctw1500 = [
    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=img_scale_test_ctw1500,
        flip=False,
        transforms=[
            dict(type='Resize', img_scale=(3000, 640), keep_ratio=True),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]

# for icdar2015
img_scale_train_icdar2015 = [(3000, 736)]
shrink_ratio_train_icdar2015 = (1.0, 0.5)
target_size_train_icdar2015 = (736, 736)
train_pipeline_icdar2015 = [
    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
    dict(
        type='LoadTextAnnotations',
        with_bbox=True,
        with_mask=True,
        poly2mask=False),
    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
    dict(type='Normalize', **img_norm_cfg),
    dict(
        type='ScaleAspectJitter',
        img_scale=img_scale_train_icdar2015,
        ratio_range=(0.7, 1.3),
        aspect_ratio_range=(0.9, 1.1),
        multiscale_mode='value',
        keep_ratio=False),
    dict(type='PANetTargets', shrink_ratio=shrink_ratio_train_icdar2015),
    dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
    dict(type='RandomRotateTextDet'),
    dict(
        type='RandomCropInstances',
        target_size=target_size_train_icdar2015,
        instance_key='gt_kernels'),
    dict(type='Pad', size_divisor=32),
    dict(
        type='CustomFormatBundle',
        keys=['gt_kernels', 'gt_mask'],
        visualize=dict(flag=False, boundary_key='gt_kernels')),
    dict(type='Collect', keys=['img', 'gt_kernels', 'gt_mask'])
]

img_scale_test_icdar2015 = (1333, 736)
test_pipeline_icdar2015 = [
    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=img_scale_test_icdar2015,
        flip=False,
        transforms=[
            dict(type='Resize', img_scale=(3000, 640), keep_ratio=True),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]

# for icdar2017
img_scale_train_icdar2017 = [(3000, 800)]
shrink_ratio_train_icdar2017 = (1.0, 0.5)
target_size_train_icdar2017 = (800, 800)
train_pipeline_icdar2017 = [
    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
    dict(
        type='LoadTextAnnotations',
        with_bbox=True,
        with_mask=True,
        poly2mask=False),
    dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
    dict(type='Normalize', **img_norm_cfg),
    dict(
        type='ScaleAspectJitter',
        img_scale=img_scale_train_icdar2017,
        ratio_range=(0.7, 1.3),
        aspect_ratio_range=(0.9, 1.1),
        multiscale_mode='value',
        keep_ratio=False),
    dict(type='PANetTargets', shrink_ratio=shrink_ratio_train_icdar2017),
    dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
    dict(type='RandomRotateTextDet'),
    dict(
        type='RandomCropInstances',
        target_size=target_size_train_icdar2017,
        instance_key='gt_kernels'),
    dict(type='Pad', size_divisor=32),
    dict(
        type='CustomFormatBundle',
        keys=['gt_kernels', 'gt_mask'],
        visualize=dict(flag=False, boundary_key='gt_kernels')),
    dict(type='Collect', keys=['img', 'gt_kernels', 'gt_mask'])
]

img_scale_test_icdar2017 = (1333, 800)
test_pipeline_icdar2017 = [
    dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=img_scale_test_icdar2017,
        flip=False,
        transforms=[
            dict(type='Resize', img_scale=(3000, 640), keep_ratio=True),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]