Spaces:
Sleeping
Sleeping
File size: 1,938 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 |
# Copyright (c) OpenMMLab. All rights reserved.
from unittest import TestCase
from mmocr.datasets import RecogTextDataset
class TestRecogTextDataset(TestCase):
def test_txt_dataset(self):
# test initialization
dataset = RecogTextDataset(
ann_file='tests/data/rec_toy_dataset/old_label.txt',
data_prefix=dict(img_path='imgs'),
parser_cfg=dict(
type='LineStrParser',
keys=['filename', 'text'],
keys_idx=[0, 1]),
pipeline=[])
dataset.full_init()
self.assertEqual(len(dataset), 10)
self.assertEqual(len(dataset.load_data_list()), 10)
# test load_data_list
anno = dataset.load_data_list()
self.assertIn(anno[0]['img_path'],
['imgs/1223731.jpg', 'imgs\\1223731.jpg'])
self.assertEqual(anno[0]['instances'][0]['text'], 'GRAND')
self.assertIn(anno[1]['img_path'],
['imgs/1223733.jpg', 'imgs\\1223733.jpg'])
self.assertEqual(anno[1]['instances'][0]['text'], 'HOTEL')
def test_jsonl_dataset(self):
dataset = RecogTextDataset(
ann_file='tests/data/rec_toy_dataset/old_label.jsonl',
data_prefix=dict(img_path='imgs'),
parser_cfg=dict(type='LineJsonParser', keys=['filename', 'text']),
pipeline=[])
dataset.full_init()
self.assertEqual(len(dataset), 10)
self.assertEqual(len(dataset.load_data_list()), 10)
# test load_data_list
anno = dataset.load_data_list()
self.assertIn(anno[0]['img_path'],
['imgs/1223731.jpg', 'imgs\\1223731.jpg'])
self.assertEqual(anno[0]['instances'][0]['text'], 'GRAND')
self.assertIn(anno[1]['img_path'],
['imgs/1223733.jpg', 'imgs\\1223733.jpg'])
self.assertEqual(anno[1]['instances'][0]['text'], 'HOTEL')
|