Spaces:
Sleeping
Sleeping
File size: 5,138 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 |
# Copyright (c) OpenMMLab. All rights reserved.
import os.path as osp
import tempfile
from unittest import TestCase
import mmengine
from mmocr.utils.data_converter_utils import (dump_ocr_data,
recog_anno_to_imginfo)
class TestDataConverterUtils(TestCase):
def _create_dummy_data(self):
img_info = dict(
file_name='test.jpg', height=100, width=200, segm_file='seg.txt')
anno_info = [
dict(
iscrowd=0,
category_id=0,
bbox=[0, 0, 10, 20], # x, y, w, h
text='t1',
segmentation=[0, 0, 0, 10, 10, 20, 20, 0]),
dict(
iscrowd=1,
category_id=0,
bbox=[10, 10, 20, 20], # x, y, w, h
text='t2',
segmentation=[10, 10, 10, 30, 30, 30, 30, 10]),
]
img_info['anno_info'] = anno_info
img_infos = [img_info]
det_target = {
'metainfo': {
'dataset_type': 'TextDetDataset',
'task_name': 'textdet',
'category': [{
'id': 0,
'name': 'text'
}],
},
'data_list': [{
'img_path':
'test.jpg',
'height':
100,
'width':
200,
'seg_map':
'seg.txt',
'instances': [
{
'bbox': [0, 0, 10, 20],
'bbox_label': 0,
'polygon': [0, 0, 0, 10, 10, 20, 20, 0],
'ignore': False
},
{
'bbox': [10, 10, 30, 30], # x1, y1, x2, y2
'bbox_label': 0,
'polygon': [10, 10, 10, 30, 30, 30, 30, 10],
'ignore': True
}
]
}]
}
spotter_target = {
'metainfo': {
'dataset_type': 'TextSpotterDataset',
'task_name': 'textspotter',
'category': [{
'id': 0,
'name': 'text'
}],
},
'data_list': [{
'img_path':
'test.jpg',
'height':
100,
'width':
200,
'seg_map':
'seg.txt',
'instances': [
{
'bbox': [0, 0, 10, 20],
'bbox_label': 0,
'polygon': [0, 0, 0, 10, 10, 20, 20, 0],
'text': 't1',
'ignore': False
},
{
'bbox': [10, 10, 30, 30], # x1, y1, x2, y2
'bbox_label': 0,
'polygon': [10, 10, 10, 30, 30, 30, 30, 10],
'text': 't2',
'ignore': True
}
]
}]
}
recog_target = {
'metainfo': {
'dataset_type': 'TextRecogDataset',
'task_name': 'textrecog',
},
'data_list': [{
'img_path': 'test.jpg',
'instances': [{
'text': 't1',
}, {
'text': 't2',
}]
}]
}
return img_infos, det_target, spotter_target, recog_target
def test_dump_ocr_data(self):
with tempfile.TemporaryDirectory() as tmpdir:
output_path = osp.join(tmpdir, 'ocr.json')
input_data, det_target, spotter_target, recog_target = \
self._create_dummy_data()
dump_ocr_data(input_data, output_path, 'textdet')
result = mmengine.load(output_path)
self.assertDictEqual(result, det_target)
dump_ocr_data(input_data, output_path, 'textspotter')
result = mmengine.load(output_path)
self.assertDictEqual(result, spotter_target)
dump_ocr_data(input_data, output_path, 'textrecog')
result = mmengine.load(output_path)
self.assertDictEqual(result, recog_target)
def test_recog_anno_to_imginfo(self):
file_paths = ['a.jpg', 'b.jpg']
labels = ['aaa']
with self.assertRaises(AssertionError):
recog_anno_to_imginfo(file_paths, labels)
file_paths = ['a.jpg', 'b.jpg']
labels = ['aaa', 'bbb']
target = [
{
'file_name': 'a.jpg',
'anno_info': [{
'text': 'aaa'
}]
},
{
'file_name': 'b.jpg',
'anno_info': [{
'text': 'bbb'
}]
},
]
self.assertListEqual(target, recog_anno_to_imginfo(file_paths, labels))
|