def _create_pascal_writer(self):
""" Create an instance of pascal writer."""
return PascalWriter(
path=self._image_path,
width=self._image_width,
height=self._image_height,
database=self._project_name)
def write_label( # pylint: disable-msg=too-many-arguments
label_id: str, image_url: str, labels: Dict[str,
Any], label_format: str,
images_output_dir: str, annotations_output_dir: str):
"""Writes a single Pascal VOC formatted image and label pair to disk.
Args:
label_id: ID for the instance to write
image_url: URL to download image file from
labels: Labelbox formatted labels to use for generating annotation
label_format: Format of the labeled data. Valid options are: "WKT" and
"XY", default is "XY".
annotations_output_dir: File path of directory to write Pascal VOC
annotation files.
images_output_dir: File path of directory to write images.
"""
# Download image and save it
response = requests.get(image_url, stream=True, timeout=10.0)
response.raw.decode_content = True
image = Image.open(response.raw)
image_fqn = os.path.join(
images_output_dir, '{img_id}.{ext}'.format(img_id=label_id,
ext=image.format.lower()))
image.save(image_fqn, format=image.format)
# generate image annotation in Pascal VOC
width, height = image.size
xml_writer = PascalWriter(image_fqn, width, height)
# remove classification labels (Skip, etc...)
if not callable(getattr(labels, 'keys', None)):
# skip if no categories (e.g. "Skip")
return
# convert label to Pascal VOC format
for category_name, paths in labels.items():
if label_format == 'WKT':
xml_writer = _add_pascal_object_from_wkt(xml_writer,
wkt_data=paths,
label=category_name)
elif label_format == 'XY':
xml_writer = _add_pascal_object_from_xy(xml_writer,
polygons=paths,
label=category_name)
else:
exc = UnknownFormatError(label_format=label_format)
logging.exception(exc.message)
raise exc
# write Pascal VOC xml annotation for image
xml_writer.save(
os.path.join(annotations_output_dir, '{}.xml'.format(label_id)))
def from_json(labeled_data,
ann_output_dir,
images_output_dir,
label_format='WKT'):
"""Convert Labelbox JSON export to Pascal VOC format.
Args:
labeled_data (str): File path to Labelbox JSON export of label data.
ann_output_dir (str): File path of directory to write Pascal VOC
annotation files.
images_output_dir (str): File path of directory to write images.
label_format (str): Format of the labeled data.
Valid options are: "WKT" and "XY", default is "WKT".
Todo:
* Add functionality to allow use of local copy of an image instead of
downloading it each time.
"""
# make sure annotation output directory is valid
try:
ann_output_dir = os.path.abspath(ann_output_dir)
assert os.path.isdir(ann_output_dir)
except AssertionError as e:
logging.exception('Annotation output directory does not exist')
return None
# read labelbox JSON output
with open(labeled_data, 'r') as f:
lines = f.readlines()
label_data = json.loads(lines[0])
for data in label_data:
# Download image and save it
try:
response = requests.get(data['Labeled Data'], stream=True)
except requests.exceptions.MissingSchema as e:
logging.exception(('"Labeled Data" field must be a URL. '
'Support for local files coming soon'))
continue
except requests.exceptions.ConnectionError as e:
logging.exception('Failed to fetch image from {}'.format(
data['Labeled Data']))
continue
response.raw.decode_content = True
im = Image.open(response.raw)
image_name = ('{img_id}.{ext}'.format(img_id=data['ID'],
ext=im.format.lower()))
image_fqn = os.path.join(images_output_dir, image_name)
im.save(image_fqn, format=im.format)
# generate image annotation in Pascal VOC
width, height = im.size
xml_writer = PascalWriter(image_fqn, width, height)
# convert WKT multipolygon to Pascal VOC format
for cat in data['Label'].keys():
if label_format == 'WKT':
xml_writer = add_pascal_object_from_wkt(
xml_writer,
img_height=height,
wkt_data=data['Label'][cat],
label=cat)
elif label_format == 'XY':
xml_writer = add_pascal_object_from_xy(xml_writer,
img_height=height,
data=data['Label'][cat],
label=cat)
else:
e = UnknownFormatError(label_format=label_format)
print(e.message)
raise e
# write Pascal VOC xml annotation for image
xml_writer.save(
os.path.join(ann_output_dir, '{}.xml'.format(data['ID'])))
def test_1(results_dir):
pascal_writer = PascalWriter('test-image.png', 100, 100)
pascal_writer.addObject(name='triangle', xy_coords=[5, 5, 95, 5, 50, 95])
pascal_writer.save(
os.path.join(results_dir, 'test-annotation-triangle.xml'))
def test_2(results_dir):
pascal_writer = PascalWriter('test-image.png', 100, 100)
pascal_writer.addObject(name='bndbox',
xy_coords=[5, 5, 95, 5, 95, 95, 5, 95])
pascal_writer.save(os.path.join(results_dir, 'test-annotation-bndbox.xml'))
def from_json(labeled_data, ann_output_dir, images_output_dir):
"""Convert Labelbox JSON export to Pascal VOC format.
Args:
labeled_data (str): File path to Labelbox JSON export of label data.
ann_output_dir (str): File path of directory to write Pascal VOC
annotation files.
images_output_dir (str): File path of directory to write images.
Todo:
* Add functionality to allow use of local copy of an image instead of
downloading it each time.
"""
# make sure annotation output directory is valid
try:
ann_output_dir = os.path.abspath(ann_output_dir)
assert os.path.isdir(ann_output_dir)
except AssertionError as e:
logging.exception('Annotation output directory does not exist')
return None
# read labelbox JSON output
with open(labeled_data, 'r') as f:
lines = f.readlines()
label_data = json.loads(lines[0])
for data in label_data:
# Download image and save it
try:
response = requests.get(data['Labeled Data'], stream=True)
except requests.exceptions.MissingSchema as e:
logging.exception(('"Labeled Data" field must be a URL. '
'Support for local files coming soon'))
continue
except requests.exceptions.ConnectionError as e:
logging.exception('Failed to fetch image from {}'
.format(data['Labeled Data']))
continue
response.raw.decode_content = True
im = Image.open(response.raw)
image_name = ('{img_id}.{ext}'
.format(img_id=data['ID'], ext=im.format.lower()))
image_fqn = os.path.join(images_output_dir, image_name)
im.save(image_fqn, format=im.format)
# generate image annotation in Pascal VOC
width, height = im.size
xml_writer = PascalWriter(image_fqn, width, height)
# convert WKT multipolygon to Pascal VOC format
for cat in data['Label'].keys():
multipolygon = wkt.loads(data['Label'][cat])
for m in multipolygon:
xy_coords = []
for x, y in m.exterior.coords:
xy_coords.extend([x, height-y])
# remove last polygon if it is identical to first point
if xy_coords[-2:] == xy_coords[:2]:
xy_coords = xy_coords[:-2]
xml_writer.addObject(name=cat, xy_coords=xy_coords)
# write Pascal VOC xml annotation for image
xml_writer.save(os.path.join(ann_output_dir,
'{}.xml'.format(data['ID'])))