wangchunlin
/
cvat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[Datumaro] Fixes (#1953)

Browse Source 
* Add absolute image path in rest api extractor

* Add default split for random split

* Fix image path in datumaro format

* Preserve bboxes in coco format

* update changelog

Co-authored-by: Nikita Manovich <40690625+nmanovic@users.noreply.github.com>
main
zhiltsov-max 6 years ago committed by GitHub
parent e7585b8ce9
commit 0062ecdec3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 74 additions and 71 deletions
Show Stats Download Patch File Download Diff File

1
CHANGELOG.md
Unescape Escape View File

@ -15,6 +15,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Changed
- Smaller object details (<https://github.com/opencv/cvat/pull/1877>)
- `COCO` format does not convert bboxes to polygons on export (<https://github.com/opencv/cvat/pull/1953>)
- It is impossible to submit a DL model in OpenVINO format using UI. Now you can deploy new models on the server using serverless functions (<https://github.com/opencv/cvat/pull/1767>)
- Files and folders under share path are now alphabetically sorted

2
cvat/apps/dataset_manager/formats/datumaro/export_templates/plugins/cvat_rest_api_task_images.py
Unescape Escape View File

@ -100,7 +100,7 @@ class cvat_rest_api_task_images(SourceExtractor):
if entry.get('height') and entry.get('width'):
size = (entry['height'], entry['width'])
image = Image(data=self._make_image_loader(item_id),
path=item_filename, size=size)
path=self._image_local_path(item_id), size=size)
item = DatasetItem(id=item_id, image=image)
items.append((item.id, item))

4
datumaro/datumaro/plugins/coco_format/converter.py
Unescape Escape View File

@ -298,8 +298,8 @@ class _InstancesConverter(_TaskConverter):
rles = mask_utils.merge(rles)
area = mask_utils.area(rles)
else:
x, y, w, h = bbox
segmentation = [[x, y, x + w, y, x + w, y + h, x, y + h]]
_, _, w, h = bbox
segmentation = []
area = w * h
elem = {

3
datumaro/datumaro/plugins/datumaro_format/converter.py
Unescape Escape View File

@ -54,7 +54,8 @@ class _SubsetWriter:
if item.has_image:
path = item.image.path
if self._context._save_images:
path = self._context._save_image(item)
path = self._context._make_image_filename(item)
self._context._save_image(item, path)
item_desc['image'] = {
'size': item.image.size,

1
datumaro/datumaro/plugins/transforms.py
Unescape Escape View File

@ -322,6 +322,7 @@ class RandomSplit(Transform, CliPlugin):
parser = super().build_cmdline_parser(**kwargs)
parser.add_argument('-s', '--subset', action='append',
type=cls._split_arg, dest='splits',
default=[('train', 0.67), ('test', 0.33)],
help="Subsets in the form of: '<subset>:<ratio>' (repeatable)")
parser.add_argument('--seed', type=int, help="Random seed")
return parser

32
datumaro/tests/test_coco_format.py
Unescape Escape View File

@ -4,8 +4,8 @@ import os.path as osp
from unittest import TestCase
from datumaro.components.project import (Project, Dataset)
from datumaro.components.extractor import (Extractor, DatasetItem,
from datumaro.components.project import Project, Dataset
from datumaro.components.extractor import (DatasetItem,
AnnotationType, Label, Mask, Points, Polygon, Bbox, Caption,
LabelCategories, PointsCategories
)
@ -26,7 +26,6 @@ DUMMY_DATASET_DIR = osp.join(osp.dirname(__file__), 'assets', 'coco_dataset')
class CocoImporterTest(TestCase):
def test_can_import(self):
expected_dataset = Dataset.from_iterable([
DatasetItem(id='000000000001', image=np.ones((10, 5, 3)),
subset='val', attributes={'id': 1},
@ -349,7 +348,6 @@ class CocoConverterTest(TestCase):
CocoLabelsConverter.convert, test_dir)
def test_can_save_and_load_keypoints(self):
source_dataset = Dataset.from_iterable([
DatasetItem(id=1, subset='train', image=np.zeros((5, 5, 3)),
annotations=[
@ -373,11 +371,11 @@ class CocoConverterTest(TestCase):
Points([0, 0, 1, 2, 3, 4], [0, 1, 2], id=5),
]),
], categories={
AnnotationType.label: LabelCategories.from_iterable(
str(i) for i in range(10)),
AnnotationType.points: PointsCategories.from_iterable(
(i, None, [[0, 1], [1, 2]]) for i in range(10)
),
AnnotationType.label: LabelCategories.from_iterable(
str(i) for i in range(10)),
AnnotationType.points: PointsCategories.from_iterable(
(i, None, [[0, 1], [1, 2]]) for i in range(10)
),
})
target_dataset = Dataset.from_iterable([
@ -393,30 +391,30 @@ class CocoConverterTest(TestCase):
Points([1, 2, 3, 4, 2, 3],
group=2, id=2,
attributes={'is_crowd': False}),
Polygon([1, 2, 3, 2, 3, 4, 1, 4],
Bbox(1, 2, 2, 2,
group=2, id=2,
attributes={'is_crowd': False}),
Points([1, 2, 0, 2, 4, 1],
label=5, group=3, id=3,
attributes={'is_crowd': False}),
Polygon([0, 1, 4, 1, 4, 2, 0, 2],
Bbox(0, 1, 4, 1,
label=5, group=3, id=3,
attributes={'is_crowd': False}),
Points([0, 0, 1, 2, 3, 4], [0, 1, 2],
group=5, id=5,
attributes={'is_crowd': False}),
Polygon([1, 2, 3, 2, 3, 4, 1, 4],
Bbox(1, 2, 2, 2,
group=5, id=5,
attributes={'is_crowd': False}),
], attributes={'id': 1}),
], categories={
AnnotationType.label: LabelCategories.from_iterable(
str(i) for i in range(10)),
AnnotationType.points: PointsCategories.from_iterable(
(i, None, [[0, 1], [1, 2]]) for i in range(10)
),
AnnotationType.label: LabelCategories.from_iterable(
str(i) for i in range(10)),
AnnotationType.points: PointsCategories.from_iterable(
(i, None, [[0, 1], [1, 2]]) for i in range(10)
),
})
with TestDir() as test_dir:

102
datumaro/tests/test_datumaro_format.py
Unescape Escape View File

@ -32,56 +32,58 @@ class DatumaroConverterTest(TestCase):
compare_datasets_strict(self,
expected=target_dataset, actual=parsed_dataset)
label_categories = LabelCategories()
for i in range(5):
label_categories.add('cat' + str(i))
mask_categories = MaskCategories(
generate_colormap(len(label_categories.items)))
points_categories = PointsCategories()
for index, _ in enumerate(label_categories.items):
points_categories.add(index, ['cat1', 'cat2'], joints=[[0, 1]])
test_dataset = Dataset.from_iterable([
DatasetItem(id=100, subset='train', image=np.ones((10, 6, 3)),
annotations=[
Caption('hello', id=1),
Caption('world', id=2, group=5),
Label(2, id=3, attributes={
'x': 1,
'y': '2',
}),
Bbox(1, 2, 3, 4, label=4, id=4, z_order=1, attributes={
'score': 1.0,
}),
Bbox(5, 6, 7, 8, id=5, group=5),
Points([1, 2, 2, 0, 1, 1], label=0, id=5, z_order=4),
Mask(label=3, id=5, z_order=2, image=np.ones((2, 3))),
]),
DatasetItem(id=21, subset='train',
annotations=[
Caption('test'),
Label(2),
Bbox(1, 2, 3, 4, 5, id=42, group=42)
]),
DatasetItem(id=2, subset='val',
annotations=[
PolyLine([1, 2, 3, 4, 5, 6, 7, 8], id=11, z_order=1),
Polygon([1, 2, 3, 4, 5, 6, 7, 8], id=12, z_order=4),
]),
DatasetItem(id=42, subset='test',
attributes={'a1': 5, 'a2': '42'}),
DatasetItem(id=42),
DatasetItem(id=43, image=Image(path='1/b/c.qq', size=(2, 4))),
], categories={
AnnotationType.label: label_categories,
AnnotationType.mask: mask_categories,
AnnotationType.points: points_categories,
})
@property
def test_dataset(self):
label_categories = LabelCategories()
for i in range(5):
label_categories.add('cat' + str(i))
mask_categories = MaskCategories(
generate_colormap(len(label_categories.items)))
points_categories = PointsCategories()
for index, _ in enumerate(label_categories.items):
points_categories.add(index, ['cat1', 'cat2'], joints=[[0, 1]])
return Dataset.from_iterable([
DatasetItem(id=100, subset='train', image=np.ones((10, 6, 3)),
annotations=[
Caption('hello', id=1),
Caption('world', id=2, group=5),
Label(2, id=3, attributes={
'x': 1,
'y': '2',
}),
Bbox(1, 2, 3, 4, label=4, id=4, z_order=1, attributes={
'score': 1.0,
}),
Bbox(5, 6, 7, 8, id=5, group=5),
Points([1, 2, 2, 0, 1, 1], label=0, id=5, z_order=4),
Mask(label=3, id=5, z_order=2, image=np.ones((2, 3))),
]),
DatasetItem(id=21, subset='train',
annotations=[
Caption('test'),
Label(2),
Bbox(1, 2, 3, 4, 5, id=42, group=42)
]),
DatasetItem(id=2, subset='val',
annotations=[
PolyLine([1, 2, 3, 4, 5, 6, 7, 8], id=11, z_order=1),
Polygon([1, 2, 3, 4, 5, 6, 7, 8], id=12, z_order=4),
]),
DatasetItem(id=42, subset='test',
attributes={'a1': 5, 'a2': '42'}),
DatasetItem(id=42),
DatasetItem(id=43, image=Image(path='1/b/c.qq', size=(2, 4))),
], categories={
AnnotationType.label: label_categories,
AnnotationType.mask: mask_categories,
AnnotationType.points: points_categories,
})
def test_can_save_and_load(self):
with TestDir() as test_dir:

Write Preview
Loading…
Cancel
Save