Hugging Face's logo

Spaces:
sunnychenxiwang
/
EasyDetect
Sleeping

App Files Community
EasyDetect
File size: 5,115 Bytes 
0b4516f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
# This configuration prepares the ICDAR13 857 and 1015
# version, and uses ICDAR13 1015 version by default.
# You may uncomment the lines if you want to you the original version,
# which contains 1095 samples.
# You can check out the generated base config and use the 857
# version by using its corresponding config variables in your model.

data_root = 'data/icdar2013'
cache_path = 'data/cache'

train_preparer = dict(
    obtainer=dict(
        type='NaiveDataObtainer',
        cache_path=cache_path,
        files=[
            dict(
                url='https://rrc.cvc.uab.es/downloads/'
                'Challenge2_Training_Task3_Images_GT.zip',
                save_name='ic13_textrecog_train_img_gt.zip',
                md5='6f0dbc823645968030878df7543f40a4',
                content=['image'],
                mapping=[
                    # ['ic13_textrecog_train_img_gt/gt.txt',
                    # 'annotations/train.txt'],
                    ['ic13_textrecog_train_img_gt', 'textrecog_imgs/train']
                ]),
            dict(
                url='https://download.openmmlab.com/mmocr/data/1.x/recog/'
                'icdar_2013/train_labels.json',
                save_name='ic13_train_labels.json',
                md5='008fcd0056e72c4cf3064fb4d1fce81b',
                content=['annotation'],
                mapping=[['ic13_train_labels.json', 'textrecog_train.json']]),
        ]))

# Note that we offer two versions of test set annotations as follows.Please
# choose one of them to download and comment the other. By default, we use the
# second one.
# 1. The original official annotation, which contains 1095 test
# samples.

# Uncomment the test_preparer if you want to use the original 1095 version.

# test_preparer = dict(
#     obtainer=dict(
#         type='NaiveDataObtainer',
#         cache_path=cache_path,
#         files=[
#             dict(
#                 url='https://rrc.cvc.uab.es/downloads/'
#                 'Challenge2_Test_Task3_Images.zip',
#                 save_name='ic13_textrecog_test_img.zip',
#                 md5='3206778eebb3a5c5cc15c249010bf77f',
#                 split=['test'],
#                 content=['image'],
#                 mapping=[['ic13_textrecog_test_img',
#                           'textrecog_imgs/test']]),
#             dict(
#                 url='https://rrc.cvc.uab.es/downloads/'
#                 'Challenge2_Test_Task3_GT.txt',
#                 save_name='ic13_textrecog_test_gt.txt',
#                 md5='2634060ed8fe6e7a4a9b8d68785835a1',
#                 split=['test'],
#                 content=['annotation'],
#                 mapping=[[
#                     'ic13_textrecog_test_gt.txt', 'annotations/test.txt'
#                 ]]),  # noqa
#             # The 857 version further pruned words shorter than 3 characters.
#             dict(
#                 url='https://download.openmmlab.com/mmocr/data/1.x/recog/'
#                 'icdar_2013/textrecog_test_857.json',
#                 save_name='textrecog_test_857.json',
#                 md5='3bed3985b0c51a989ad4006f6de8352b',
#                 split=['test'],
#                 content=['annotation'],
#             ),
#         ]),
#     gatherer=dict(type='MonoGatherer', ann_name='test.txt'),
#     parser=dict(
#         type='ICDARTxtTextRecogAnnParser', separator=', ',
#         format='img, text'),  # noqa
#     packer=dict(type='TextRecogPacker'),
#     dumper=dict(type='JsonDumper'),
# )

# 2. The widely-used version for academic purpose, which filters
# out words with non-alphanumeric characters. This version contains
# 1015 test samples.
test_preparer = dict(
    obtainer=dict(
        type='NaiveDataObtainer',
        cache_path=cache_path,
        files=[
            dict(
                url='https://rrc.cvc.uab.es/downloads/'
                'Challenge2_Test_Task3_Images.zip',
                save_name='ic13_textrecog_test_img.zip',
                md5='3206778eebb3a5c5cc15c249010bf77f',
                split=['test'],
                content=['image'],
                mapping=[['ic13_textrecog_test_img', 'textrecog_imgs/test']]),
            dict(
                url='https://download.openmmlab.com/mmocr/data/1.x/recog/'
                'icdar_2013/textrecog_test_1015.json',
                save_name='textrecog_test.json',
                md5='68fdd818f63df8b93dc952478952009a',
                split=['test'],
                content=['annotation'],
            ),
            # The 857 version further pruned words shorter than 3 characters.
            dict(
                url='https://download.openmmlab.com/mmocr/data/1.x/recog/'
                'icdar_2013/textrecog_test_857.json',
                save_name='textrecog_test_857.json',
                md5='3bed3985b0c51a989ad4006f6de8352b',
                split=['test'],
                content=['annotation'],
            ),
        ]))

config_generator = dict(
    type='TextRecogConfigGenerator',
    test_anns=[
        dict(ann_file='textrecog_test.json'),
        dict(dataset_postfix='857', ann_file='textrecog_test_857.json')
    ])