def test_can_reiterate_sequence(self):
source = Dataset.from_iterable([
DatasetItem('1', subset='a', annotations=[Label(0),
Label(1)]),
DatasetItem('2', subset='a', annotations=[Label(1)]),
DatasetItem('3', subset='a', annotations=[Label(2)]),
DatasetItem('4', subset='a', annotations=[Label(1),
Label(2)]),
DatasetItem('5', subset='b', annotations=[Label(0)]),
DatasetItem('6', subset='b', annotations=[Label(0),
Label(2)]),
DatasetItem('7', subset='b', annotations=[Label(1),
Label(2)]),
DatasetItem('8', subset='b', annotations=[Label(2)]),
],
categories=['a', 'b', 'c'])
transformed = LabelRandomSampler(source, count=2)
actual1 = Dataset.from_extractors(transformed)
actual1.init_cache()
actual2 = Dataset.from_extractors(transformed)
actual2.init_cache()
compare_datasets_strict(self, actual1, actual2)
def test_inplace_save_writes_only_updated_data_with_direct_changes(self):
expected = Dataset.from_iterable([
DatasetItem(1, subset='a'),
DatasetItem(2, subset='a', image=np.ones((3, 2, 3))),
DatasetItem(2, subset='b'),
])
with TestDir() as path:
# generate initial dataset
dataset = Dataset.from_iterable([
# modified subset
DatasetItem(1, subset='a'),
# unmodified subset
DatasetItem(2, subset='b'),
# removed subset
DatasetItem(3, subset='c', image=np.ones((2, 2, 3))),
])
dataset.save(path, save_images=True)
dataset.put(DatasetItem(2, subset='a', image=np.ones((3, 2, 3))))
dataset.remove(3, 'c')
dataset.save(save_images=True)
self.assertEqual({'a.json', 'b.json'},
set(os.listdir(osp.join(path, 'annotations'))))
self.assertEqual({'2.jpg'},
set(os.listdir(osp.join(path, 'images', 'a'))))
compare_datasets_strict(self, expected, Dataset.load(path))
def test_can_change_sequence(self):
source = self._make_dataset({'a': 7, 'b': 3})
actual1 = RandomSampler(source, 5, seed=1)
actual2 = RandomSampler(source, 5, seed=2)
with self.assertRaises(AssertionError):
compare_datasets_strict(self, actual1, actual2)
def test_can_reproduce_sequence(self):
source = self._make_dataset({'a': 7, 'b': 3})
seed = 42
actual1 = RandomSampler(source, 5, seed=seed)
actual2 = RandomSampler(source, 5, seed=seed)
compare_datasets_strict(self, actual1, actual2)
def test_inplace_save_writes_only_updated_data_with_transforms(self):
with TestDir() as path:
expected = Dataset.from_iterable([
DatasetItem(2, subset='test'),
DatasetItem(3, subset='train', image=np.ones((2, 2, 3))),
DatasetItem(4, subset='train', image=np.ones((2, 3, 3))),
DatasetItem(5,
subset='test',
point_cloud=osp.join(path, 'point_clouds', 'test',
'5.pcd'),
related_images=[
Image(data=np.ones((3, 4, 3)),
path=osp.join(path, 'test', '5',
'image_0.jpg')),
osp.join(path, 'test', '5', 'a', '5.png'),
]),
])
dataset = Dataset.from_iterable([
DatasetItem(1, subset='a'),
DatasetItem(2, subset='b'),
DatasetItem(3, subset='c', image=np.ones((2, 2, 3))),
DatasetItem(4, subset='d', image=np.ones((2, 3, 3))),
DatasetItem(5,
subset='e',
point_cloud='5.pcd',
related_images=[
np.ones((3, 4, 3)),
'a/5.png',
]),
])
dataset.save(path, save_images=True)
dataset.filter('/item[id >= 2]')
dataset.transform('random_split',
splits=(('train', 0.5), ('test', 0.5)),
seed=42)
dataset.save(save_images=True)
self.assertEqual(
{'images', 'annotations', 'point_clouds', 'related_images'},
set(os.listdir(path)))
self.assertEqual({'train.json', 'test.json'},
set(os.listdir(osp.join(path, 'annotations'))))
self.assertEqual({'3.jpg', '4.jpg'},
set(os.listdir(osp.join(path, 'images',
'train'))))
self.assertEqual({'train', 'c', 'd'},
set(os.listdir(osp.join(path, 'images'))))
self.assertEqual(set(),
set(os.listdir(osp.join(path, 'images', 'c'))))
self.assertEqual(set(),
set(os.listdir(osp.join(path, 'images', 'd'))))
self.assertEqual(
{'image_0.jpg'},
set(os.listdir(osp.join(path, 'related_images', 'test', '5'))))
compare_datasets_strict(self, expected, Dataset.load(path))
def test_can_sample_when_subset_selected(self):
source = self._make_dataset({'a': 7, 'b': 3})
s = 'a'
for k in [5, 7, 15]:
with self.subTest(k=k, s=s):
actual = RandomSampler(source, k, subset=s)
self.assertEqual(min(k, len(source.get_subset(s))),
len(actual.get_subset(s)))
compare_datasets_strict(self, source.get_subset('b'),
actual.get_subset('b'))
def test_can_pickle(self):
formats = [
'voc',
'voc_classification',
'voc_detection',
'voc_action',
'voc_layout',
'voc_segmentation'
]
for fmt in formats:
with self.subTest(fmt=fmt):
source = Dataset.import_from(DUMMY_DATASET_DIR, format=fmt)
parsed = pickle.loads(pickle.dumps(source)) # nosec
compare_datasets_strict(self, source, parsed)
def _test_save_and_load(self,
source_dataset,
converter,
test_dir,
target_dataset=None,
importer_args=None):
converter(source_dataset, test_dir)
if importer_args is None:
importer_args = {}
parsed_dataset = Project.import_from(test_dir, 'datumaro',
**importer_args).make_dataset()
if target_dataset is None:
target_dataset = source_dataset
compare_datasets_strict(self,
expected=target_dataset,
actual=parsed_dataset)
def test_can_change_sequence(self):
source = Dataset.from_iterable([
DatasetItem('1', subset='a', annotations=[Label(0),
Label(1)]),
DatasetItem('2', subset='a', annotations=[Label(1)]),
DatasetItem('3', subset='a', annotations=[Label(2)]),
DatasetItem('4', subset='a', annotations=[Label(1),
Label(2)]),
DatasetItem('5', subset='b', annotations=[Label(0)]),
DatasetItem('6', subset='b', annotations=[Label(0),
Label(2)]),
DatasetItem('7', subset='b', annotations=[Label(1),
Label(2)]),
DatasetItem('8', subset='b', annotations=[Label(2)]),
],
categories=['a', 'b', 'c'])
actual1 = LabelRandomSampler(source, count=2, seed=1)
actual2 = LabelRandomSampler(source, count=2, seed=2)
with self.assertRaises(AssertionError):
compare_datasets_strict(self, actual1, actual2)
def test_can_reproduce_sequence(self):
source = Dataset.from_iterable([
DatasetItem('1', subset='a', annotations=[Label(0),
Label(1)]),
DatasetItem('2', subset='a', annotations=[Label(1)]),
DatasetItem('3', subset='a', annotations=[Label(2)]),
DatasetItem('4', subset='a', annotations=[Label(1),
Label(2)]),
DatasetItem('5', subset='b', annotations=[Label(0)]),
DatasetItem('6', subset='b', annotations=[Label(0),
Label(2)]),
DatasetItem('7', subset='b', annotations=[Label(1),
Label(2)]),
DatasetItem('8', subset='b', annotations=[Label(2)]),
],
categories=['a', 'b', 'c'])
seed = 42
actual1 = LabelRandomSampler(source, count=2, seed=seed)
actual2 = LabelRandomSampler(source, count=2, seed=seed)
compare_datasets_strict(self, actual1, actual2)
def test_can_pickle(self):
source = Dataset.import_from(DUMMY_DATASET_DIR, format='imagenet')
parsed = pickle.loads(pickle.dumps(source)) # nosec
compare_datasets_strict(self, source, parsed)
