forked from openvinotoolkit/datumaro
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathtest_mnist_csv_format.py
185 lines (157 loc) · 6.86 KB
/
test_mnist_csv_format.py
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
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
import os.path as osp
from unittest import TestCase
import numpy as np
from datumaro.components.dataset import Dataset
from datumaro.components.extractor import (AnnotationType, DatasetItem, Label,
LabelCategories)
from datumaro.plugins.mnist_csv_format import (MnistCsvConverter,
MnistCsvImporter)
from datumaro.util.image import Image
from datumaro.util.test_utils import TestDir, compare_datasets
class MnistCsvFormatTest(TestCase):
def test_can_save_and_load(self):
source_dataset = Dataset.from_iterable([
DatasetItem(id=0, subset='test',
image=np.ones((28, 28)),
annotations=[Label(0)]
),
DatasetItem(id=1, subset='test',
image=np.ones((28, 28))
),
DatasetItem(id=2, subset='test',
image=np.ones((28, 28)),
annotations=[Label(1)]
)
], categories={
AnnotationType.label: LabelCategories.from_iterable(
str(label) for label in range(10)),
})
with TestDir() as test_dir:
MnistCsvConverter.convert(source_dataset, test_dir, save_images=True)
parsed_dataset = Dataset.import_from(test_dir, 'mnist_csv')
compare_datasets(self, source_dataset, parsed_dataset,
require_images=True)
def test_can_save_and_load_without_saving_images(self):
source_dataset = Dataset.from_iterable([
DatasetItem(id=0, subset='train',
annotations=[Label(0)]
),
DatasetItem(id=1, subset='train',
annotations=[Label(1)]
),
], categories={
AnnotationType.label: LabelCategories.from_iterable(
str(label) for label in range(10)),
})
with TestDir() as test_dir:
MnistCsvConverter.convert(source_dataset, test_dir, save_images=False)
parsed_dataset = Dataset.import_from(test_dir, 'mnist_csv')
compare_datasets(self, source_dataset, parsed_dataset,
require_images=True)
def test_can_save_and_load_with_different_image_size(self):
source_dataset = Dataset.from_iterable([
DatasetItem(id=0, image=np.ones((10, 8)),
annotations=[Label(0)]
),
DatasetItem(id=1, image=np.ones((4, 3)),
annotations=[Label(1)]
),
], categories={
AnnotationType.label: LabelCategories.from_iterable(
str(label) for label in range(10)),
})
with TestDir() as test_dir:
MnistCsvConverter.convert(source_dataset, test_dir, save_images=True)
parsed_dataset = Dataset.import_from(test_dir, 'mnist_csv')
compare_datasets(self, source_dataset, parsed_dataset,
require_images=True)
def test_can_save_dataset_with_cyrillic_and_spaces_in_filename(self):
source_dataset = Dataset.from_iterable([
DatasetItem(id="кириллица с пробелом",
image=np.ones((28, 28)),
annotations=[Label(0)]
),
], categories={
AnnotationType.label: LabelCategories.from_iterable(
str(label) for label in range(10)),
})
with TestDir() as test_dir:
MnistCsvConverter.convert(source_dataset, test_dir, save_images=True)
parsed_dataset = Dataset.import_from(test_dir, 'mnist_csv')
compare_datasets(self, source_dataset, parsed_dataset,
require_images=True)
def test_can_save_and_load_image_with_arbitrary_extension(self):
dataset = Dataset.from_iterable([
DatasetItem(id='q/1', image=Image(path='q/1.JPEG',
data=np.zeros((28, 28)))),
DatasetItem(id='a/b/c/2', image=Image(path='a/b/c/2.bmp',
data=np.zeros((28, 28)))),
], categories={
AnnotationType.label: LabelCategories.from_iterable(
str(label) for label in range(10)),
})
with TestDir() as test_dir:
MnistCsvConverter.convert(dataset, test_dir, save_images=True)
parsed_dataset = Dataset.import_from(test_dir, 'mnist_csv')
compare_datasets(self, dataset, parsed_dataset,
require_images=True)
def test_can_save_and_load_empty_image(self):
dataset = Dataset.from_iterable([
DatasetItem(id=0, annotations=[Label(0)]),
DatasetItem(id=1)
], categories={
AnnotationType.label: LabelCategories.from_iterable(
str(label) for label in range(10)),
})
with TestDir() as test_dir:
MnistCsvConverter.convert(dataset, test_dir, save_images=True)
parsed_dataset = Dataset.import_from(test_dir, 'mnist_csv')
compare_datasets(self, dataset, parsed_dataset,
require_images=True)
def test_can_save_and_load_with_other_labels(self):
dataset = Dataset.from_iterable([
DatasetItem(id=0, image=np.ones((28, 28)),
annotations=[Label(0)]),
DatasetItem(id=1, image=np.ones((28, 28)),
annotations=[Label(1)])
], categories={
AnnotationType.label: LabelCategories.from_iterable(
'label_%s' % label for label in range(2)),
})
with TestDir() as test_dir:
MnistCsvConverter.convert(dataset, test_dir, save_images=True)
parsed_dataset = Dataset.import_from(test_dir, 'mnist_csv')
compare_datasets(self, dataset, parsed_dataset,
require_images=True)
DUMMY_DATASET_DIR = osp.join(osp.dirname(__file__), 'assets', 'mnist_csv_dataset')
class MnistCsvImporterTest(TestCase):
def test_can_import(self):
expected_dataset = Dataset.from_iterable([
DatasetItem(id=0, subset='test',
image=np.ones((28, 28)),
annotations=[Label(0)]
),
DatasetItem(id=1, subset='test',
image=np.ones((28, 28)),
annotations=[Label(2)]
),
DatasetItem(id=2, subset='test',
image=np.ones((28, 28)),
annotations=[Label(1)]
),
DatasetItem(id=0, subset='train',
image=np.ones((28, 28)),
annotations=[Label(5)]
),
DatasetItem(id=1, subset='train',
image=np.ones((28, 28)),
annotations=[Label(7)]
)
], categories={
AnnotationType.label: LabelCategories.from_iterable(
str(label) for label in range(10)),
})
dataset = Dataset.import_from(DUMMY_DATASET_DIR, 'mnist_csv')
compare_datasets(self, expected_dataset, dataset)
def test_can_detect(self):
self.assertTrue(MnistCsvImporter.detect(DUMMY_DATASET_DIR))