def _test_helper(self, exception=None):
with tempfile.NamedTemporaryFile(suffix='.xml') as f:
f.write(ET.tostring(self.root))
f.seek(0)
if exception:
with self.assertRaises(exception):
_ = annotation.read(f.name)
else:
image_filename, boxes = annotation.read(f.name)
return image_filename, boxes
def test_nominal_case(self):
"""Test successfully reading bounding boxes from PASCAL VOC XML file."""
boxes = list(annotation.read(self.filename))
self.assertEqual(len(boxes), 2)
width = 400
height = 300
b = boxes[0]
self.assertEqual(b.xmin, 10 / width)
self.assertEqual(b.ymin, 20 / height)
self.assertEqual(b.xmax, 30 / width)
self.assertEqual(b.ymax, 40 / height)
def gen_csv_from_annotations(
input_dir: str,
output_file=constants.DEFAULT_CSV_FILENAME,
out_path_prefix='',
dataset_type=constants.DEFAULT_DATASET_TYPE):
"""Generates AutoML dataset CSV from annotation files.
Args:
input_dir: Directory of annotation files.
output_file: Output CSV filename.
out_path_prefix: Filepath prefix to prepend to the image files.
e.g.
src_image_filename = '/tmp/path/to/image.jpg'
out_path_prefix = 'gs://bucket/images'
output_image_filename = 'gs://bucket/images/image.jpg'
dataset_type: Dataset type (TRAIN, VAL, TEST, UNSPECIFIED)
to use for all the parsed images.
"""
if not gfile.exists(input_dir):
raise ValueError('Input directory not found.')
with gfile.GFile(os.path.expanduser(output_file), 'w') as outf:
writer = csv.writer(outf, delimiter=',')
for filename in gfile.listdir(os.path.expanduser(input_dir)):
filepath = os.path.join(input_dir, filename)
image_filename, boxes = annotation.read(filepath)
out_image_filename = os.path.join(out_path_prefix, image_filename)
for b in boxes:
row = [
dataset_type,
out_image_filename,
b.label,
b.xmin,
b.ymin,
'',
'',
b.xmax,
b.ymax,
'',
'',
]
writer.writerow(row)