Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Readable COCO and datumaro format for CJK #307

Merged
merged 4 commits into from
Jun 23, 2021
Merged

Readable COCO and datumaro format for CJK #307

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
01c5ac2
Readable COCO and datumaro format for CJK
jaesuny Jun 22, 2021
dfd62e5
Add mark in tests
jaesuny Jun 23, 2021
448a541
Use utf-8 encoding for writing
Jun 23, 2021
48c8141
Update datumaro/plugins/coco_format/converter.py
Jun 23, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions datumaro/plugins/coco_format/converter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,7 +101,7 @@ def write(self, path):
next_id += 1

with open(path, 'w') as outfile:
zhiltsov-max marked this conversation as resolved.
Show resolved Hide resolved
json.dump(self._data, outfile)
json.dump(self._data, outfile, ensure_ascii=False)

@property
def annotations(self):
Expand Down Expand Up @@ -462,7 +462,7 @@ class _StuffConverter(_InstancesConverter):
class _PanopticConverter(_TaskConverter):
def write(self, path):
with open(path, 'w') as outfile:
zhiltsov-max marked this conversation as resolved.
Show resolved Hide resolved
json.dump(self._data, outfile)
json.dump(self._data, outfile, ensure_ascii=False)

def save_categories(self, dataset):
label_categories = dataset.categories().get(AnnotationType.label)
Expand Down
2 changes: 1 addition & 1 deletion datumaro/plugins/datumaro_format/converter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,7 +101,7 @@ def write_categories(self, categories):

def write(self, save_dir):
with open(osp.join(save_dir, '%s.json' % self._name), 'w') as f:
zhiltsov-max marked this conversation as resolved.
Show resolved Hide resolved
json.dump(self._data, f)
json.dump(self._data, f, ensure_ascii=False)

def _convert_annotation(self, obj):
assert isinstance(obj, Annotation)
Expand Down
1 change: 1 addition & 0 deletions tests/requirements.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@ class Requirements:

# GitHub issues (not bugs)
# https://github.com/openvinotoolkit/datumaro/issues
DATUM_231 = "Readable formats for CJK"
DATUM_244 = "Add Snyk integration"
DATUM_267 = "Add Image zip format"
DATUM_280 = "Support KITTI dataset formats"
Expand Down
30 changes: 30 additions & 0 deletions tests/test_coco_format.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -718,6 +718,36 @@ def test_can_save_and_load_images(self):
self._test_save_and_load(expected_dataset,
CocoImageInfoConverter.convert, test_dir)

@mark_requirement(Requirements.DATUM_231)
def test_can_save_dataset_with_cjk_categories(self):
expected_dataset = Dataset.from_iterable([
DatasetItem(id=1, subset='train', image=np.ones((4, 4, 3)),
annotations=[
Bbox(0, 1, 2, 2,
label=0, group=1, id=1,
attributes={ 'is_crowd': False }),
], attributes={'id': 1}),
DatasetItem(id=2, subset='train', image=np.ones((4, 4, 3)),
annotations=[
Bbox(1, 0, 2, 2, label=1, group=2, id=2,
attributes={ 'is_crowd': False }),
], attributes={'id': 2}),

DatasetItem(id=3, subset='train', image=np.ones((4, 4, 3)),
annotations=[
Bbox(0, 1, 2, 2, label=2, group=3, id=3,
attributes={ 'is_crowd': False }),
], attributes={'id': 3}),
],
categories=[
"고양이", "ネコ", "猫"
]
)

with TestDir() as test_dir:
self._test_save_and_load(expected_dataset,
CocoInstancesConverter.convert, test_dir)

@mark_requirement(Requirements.DATUM_GENERAL_REQ)
def test_can_save_dataset_with_cyrillic_and_spaces_in_filename(self):
expected_dataset = Dataset.from_iterable([
Expand Down
31 changes: 31 additions & 0 deletions tests/test_datumaro_format.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,6 +111,37 @@ def test_relative_paths(self):
self._test_save_and_load(test_dataset,
partial(DatumaroConverter.convert, save_images=True), test_dir)


@mark_requirement(Requirements.DATUM_231)
def test_can_save_dataset_with_cjk_categories(self):
expected = Dataset.from_iterable([
DatasetItem(id=1, subset='train', image=np.ones((4, 4, 3)),
annotations=[
Bbox(0, 1, 2, 2,
label=0, group=1, id=1,
attributes={ 'is_crowd': False }),
], attributes={'id': 1}),
DatasetItem(id=2, subset='train', image=np.ones((4, 4, 3)),
annotations=[
Bbox(1, 0, 2, 2, label=1, group=2, id=2,
attributes={ 'is_crowd': False }),
], attributes={'id': 2}),

DatasetItem(id=3, subset='train', image=np.ones((4, 4, 3)),
annotations=[
Bbox(0, 1, 2, 2, label=2, group=3, id=3,
attributes={ 'is_crowd': False }),
], attributes={'id': 3}),
],
categories=[
"고양이", "ネコ", "猫"
]
)

with TestDir() as test_dir:
self._test_save_and_load(expected,
partial(DatumaroConverter.convert, save_images=True), test_dir)

@mark_requirement(Requirements.DATUM_GENERAL_REQ)
def test_can_save_dataset_with_cyrillic_and_spaces_in_filename(self):
test_dataset = Dataset.from_iterable([
Expand Down