def testSingleImageGroundtruthExport(self):
masks = np.array([[[
1,
1,
], [1, 1]], [[0, 0], [0, 1]], [[0, 0], [0, 0]]],
dtype=np.uint8)
boxes = np.array([[0, 0, 1, 1], [0, 0, .5, .5], [.5, .5, 1, 1]],
dtype=np.float32)
coco_boxes = np.array([[0, 0, 1, 1], [0, 0, .5, .5], [.5, .5, .5, .5]],
dtype=np.float32)
classes = np.array([1, 2, 3], dtype=np.int32)
is_crowd = np.array([0, 1, 0], dtype=np.int32)
next_annotation_id = 1
expected_counts = ['04', '31', '4']
# Tests exporting without passing in is_crowd (for backward compatibility).
coco_annotations = coco_tools.ExportSingleImageGroundtruthToCoco(
image_id='first_image',
category_id_set=set([1, 2, 3]),
next_annotation_id=next_annotation_id,
groundtruth_boxes=boxes,
groundtruth_classes=classes,
groundtruth_masks=masks)
for i, annotation in enumerate(coco_annotations):
self.assertEqual(annotation['segmentation']['counts'],
expected_counts[i])
self.assertTrue(
np.all(
np.equal(mask.decode(annotation['segmentation']),
masks[i])))
self.assertTrue(
np.all(np.isclose(annotation['bbox'], coco_boxes[i])))
self.assertEqual(annotation['image_id'], 'first_image')
self.assertEqual(annotation['category_id'], classes[i])
self.assertEqual(annotation['id'], i + next_annotation_id)
# Tests exporting with is_crowd.
coco_annotations = coco_tools.ExportSingleImageGroundtruthToCoco(
image_id='first_image',
category_id_set=set([1, 2, 3]),
next_annotation_id=next_annotation_id,
groundtruth_boxes=boxes,
groundtruth_classes=classes,
groundtruth_masks=masks,
groundtruth_is_crowd=is_crowd)
for i, annotation in enumerate(coco_annotations):
self.assertEqual(annotation['segmentation']['counts'],
expected_counts[i])
self.assertTrue(
np.all(
np.equal(mask.decode(annotation['segmentation']),
masks[i])))
self.assertTrue(
np.all(np.isclose(annotation['bbox'], coco_boxes[i])))
self.assertEqual(annotation['image_id'], 'first_image')
self.assertEqual(annotation['category_id'], classes[i])
self.assertEqual(annotation['iscrowd'], is_crowd[i])
self.assertEqual(annotation['id'], i + next_annotation_id)
def add_single_ground_truth_image_info(self, image_id, groundtruth_dict):
"""Adds groundtruth for a single image to be used for evaluation.
If the image has already been added, a warning is logged, and groundtruth is
ignored.
Args:
image_id: A unique string/integer identifier for the image.
groundtruth_dict: A dictionary containing -
InputDataFields.groundtruth_boxes: float32 numpy array of shape
[num_boxes, 4] containing `num_boxes` groundtruth boxes of the format
[ymin, xmin, ymax, xmax] in absolute image coordinates.
InputDataFields.groundtruth_classes: integer numpy array of shape
[num_boxes] containing 1-indexed groundtruth classes for the boxes.
"""
if image_id in self._image_ids:
tf.logging.warning(
'Ignoring ground truth with image id %s since it was '
'previously added', image_id)
return
self._groundtruth_list.extend(
coco_tools.ExportSingleImageGroundtruthToCoco(
image_id=image_id,
next_annotation_id=self._annotation_id,
category_id_set=self._category_id_set,
groundtruth_boxes=groundtruth_dict[
standard_fields.InputDataFields.groundtruth_boxes],
groundtruth_classes=groundtruth_dict[
standard_fields.InputDataFields.groundtruth_classes]))
self._annotation_id += groundtruth_dict[
standard_fields.InputDataFields.groundtruth_boxes].shape[0]
self._image_ids[image_id] = False
def add_single_ground_truth_image_info(self, image_id, groundtruth_dict):
"""Adds groundtruth for a single image to be used for evaluation.
If the image has already been added, a warning is logged, and groundtruth is
ignored.
Args:
image_id: A unique string/integer identifier for the image.
groundtruth_dict: A dictionary containing -
InputDataFields.groundtruth_boxes: float32 numpy array of shape
[num_boxes, 4] containing `num_boxes` groundtruth boxes of the format
[ymin, xmin, ymax, xmax] in absolute image coordinates.
InputDataFields.groundtruth_classes: integer numpy array of shape
[num_boxes] containing 1-indexed groundtruth classes for the boxes.
InputDataFields.groundtruth_instance_masks: uint8 numpy array of shape
[num_boxes, image_height, image_width] containing groundtruth masks
corresponding to the boxes. The elements of the array must be in
{0, 1}.
"""
if image_id in self._image_id_to_mask_shape_map:
tf.compat.v1.logging.warning(
'Ignoring ground truth with image id %s since it was '
'previously added', image_id)
return
groundtruth_instance_masks = groundtruth_dict[
standard_fields.InputDataFields.groundtruth_instance_masks]
_check_mask_type_and_value(
standard_fields.InputDataFields.groundtruth_instance_masks,
groundtruth_instance_masks)
self._groundtruth_list.extend(
coco_tools.ExportSingleImageGroundtruthToCoco(
image_id=image_id,
next_annotation_id=self._annotation_id,
category_id_set=self._category_id_set,
groundtruth_boxes=groundtruth_dict[
standard_fields.InputDataFields.groundtruth_boxes],
groundtruth_classes=groundtruth_dict[
standard_fields.InputDataFields.groundtruth_classes],
groundtruth_masks=groundtruth_instance_masks))
self._annotation_id += groundtruth_dict[
standard_fields.InputDataFields.groundtruth_boxes].shape[0]
self._image_id_to_mask_shape_map[image_id] = groundtruth_dict[
standard_fields.InputDataFields.groundtruth_instance_masks].shape
def add_single_ground_truth_image_info(self, image_id, groundtruth_dict):
"""Add groundtruth results of all frames to the eval pipeline.
This method overrides the function defined in the base class.
Args:
image_id: A unique string/integer identifier for the image.
groundtruth_dict: A list of dictionary containing -
InputDataFields.groundtruth_boxes: float32 numpy array of shape
[num_boxes, 4] containing `num_boxes` groundtruth boxes of the format
[ymin, xmin, ymax, xmax] in absolute image coordinates.
InputDataFields.groundtruth_classes: integer numpy array of shape
[num_boxes] containing 1-indexed groundtruth classes for the boxes.
InputDataFields.groundtruth_is_crowd (optional): integer numpy array of
shape [num_boxes] containing iscrowd flag for groundtruth boxes.
"""
for idx, gt in enumerate(groundtruth_dict):
if not gt:
continue
image_frame_id = '{}_{}'.format(image_id, idx)
if image_frame_id in self._image_ids:
tf.logging.warning(
'Ignoring ground truth with image id %s since it was '
'previously added', image_frame_id)
continue
self._groundtruth_list.extend(
coco_tools.ExportSingleImageGroundtruthToCoco(
image_id=image_frame_id,
next_annotation_id=self._annotation_id,
category_id_set=self._category_id_set,
groundtruth_boxes=gt[
standard_fields.InputDataFields.groundtruth_boxes],
groundtruth_classes=gt[
standard_fields.InputDataFields.groundtruth_classes]))
self._annotation_id += (
gt[standard_fields.InputDataFields.groundtruth_boxes].shape[0])
# Boolean to indicate whether a detection has been added for this image.
self._image_ids[image_frame_id] = False
def testSingleImageGroundtruthExportWithKeypoints(self):
boxes = np.array([[0, 0, 1, 1], [0, 0, .5, .5], [.5, .5, 1, 1]],
dtype=np.float32)
coco_boxes = np.array([[0, 0, 1, 1], [0, 0, .5, .5], [.5, .5, .5, .5]],
dtype=np.float32)
keypoints = np.array([[[0, 0], [0.25, 0.25], [0.75, 0.75]],
[[0, 0], [0.125, 0.125], [0.375, 0.375]],
[[0.5, 0.5], [0.75, 0.75], [1.0, 1.0]]],
dtype=np.float32)
visibilities = np.array([[2, 2, 2], [2, 2, 0], [2, 0, 0]],
dtype=np.int32)
areas = np.array([15., 16., 17.])
classes = np.array([1, 2, 3], dtype=np.int32)
is_crowd = np.array([0, 1, 0], dtype=np.int32)
next_annotation_id = 1
# Tests exporting without passing in is_crowd (for backward compatibility).
coco_annotations = coco_tools.ExportSingleImageGroundtruthToCoco(
image_id='first_image',
category_id_set=set([1, 2, 3]),
next_annotation_id=next_annotation_id,
groundtruth_boxes=boxes,
groundtruth_classes=classes,
groundtruth_keypoints=keypoints,
groundtruth_keypoint_visibilities=visibilities,
groundtruth_area=areas)
for i, annotation in enumerate(coco_annotations):
self.assertTrue(
np.all(np.isclose(annotation['bbox'], coco_boxes[i])))
self.assertEqual(annotation['image_id'], 'first_image')
self.assertEqual(annotation['category_id'], classes[i])
self.assertEqual(annotation['id'], i + next_annotation_id)
self.assertEqual(annotation['num_keypoints'], 3 - i)
self.assertEqual(annotation['area'], 15.0 + i)
self.assertTrue(
np.all(
np.isclose(annotation['keypoints'][0::3], keypoints[i, :,
1])))
self.assertTrue(
np.all(
np.isclose(annotation['keypoints'][1::3], keypoints[i, :,
0])))
self.assertTrue(
np.all(np.equal(annotation['keypoints'][2::3],
visibilities[i])))
# Tests exporting with is_crowd.
coco_annotations = coco_tools.ExportSingleImageGroundtruthToCoco(
image_id='first_image',
category_id_set=set([1, 2, 3]),
next_annotation_id=next_annotation_id,
groundtruth_boxes=boxes,
groundtruth_classes=classes,
groundtruth_keypoints=keypoints,
groundtruth_keypoint_visibilities=visibilities,
groundtruth_is_crowd=is_crowd)
for i, annotation in enumerate(coco_annotations):
self.assertTrue(
np.all(np.isclose(annotation['bbox'], coco_boxes[i])))
self.assertEqual(annotation['image_id'], 'first_image')
self.assertEqual(annotation['category_id'], classes[i])
self.assertEqual(annotation['iscrowd'], is_crowd[i])
self.assertEqual(annotation['id'], i + next_annotation_id)
self.assertEqual(annotation['num_keypoints'], 3 - i)
self.assertTrue(
np.all(
np.isclose(annotation['keypoints'][0::3], keypoints[i, :,
1])))
self.assertTrue(
np.all(
np.isclose(annotation['keypoints'][1::3], keypoints[i, :,
0])))
self.assertTrue(
np.all(np.equal(annotation['keypoints'][2::3],
visibilities[i])))
# Testing the area values are derived from the bounding boxes.
if i == 0:
self.assertAlmostEqual(annotation['area'], 1.0)
else:
self.assertAlmostEqual(annotation['area'], 0.25)
