def _compute_is_class_correctly_detected_in_image(self,
detected_boxes,
detected_scores,
groundtruth_boxes,
detected_masks=None,
groundtruth_masks=None):
"""Compute CorLoc score for a single class.
Args:
detected_boxes: A numpy array of shape [N, 4] representing detected box
coordinates
detected_scores: A 1-d numpy array of length N representing classification
score
groundtruth_boxes: A numpy array of shape [M, 4] representing ground truth
box coordinates
detected_masks: (optional) A np.uint8 numpy array of shape
[N, height, width]. If not None, the scores will be computed based
on masks.
groundtruth_masks: (optional) A np.uint8 numpy array of shape
[M, height, width].
Returns:
is_class_correctly_detected_in_image: An integer 1 or 0 denoting whether a
class is correctly detected in the image or not
"""
if detected_boxes.size > 0:
if groundtruth_boxes.size > 0:
max_score_id = np.argmax(detected_scores)
mask_mode = False
if detected_masks is not None and groundtruth_masks is not None:
mask_mode = True
if mask_mode:
detected_boxlist = np_box_mask_list.BoxMaskList(
box_data=np.expand_dims(detected_boxes[max_score_id],
axis=0),
mask_data=np.expand_dims(detected_masks[max_score_id],
axis=0))
gt_boxlist = np_box_mask_list.BoxMaskList(
box_data=groundtruth_boxes,
mask_data=groundtruth_masks)
iou = np_box_mask_list_ops.iou(detected_boxlist,
gt_boxlist)
else:
detected_boxlist = np_box_list.BoxList(
np.expand_dims(detected_boxes[max_score_id, :],
axis=0))
gt_boxlist = np_box_list.BoxList(groundtruth_boxes)
iou = np_box_list_ops.iou(detected_boxlist, gt_boxlist)
if np.max(iou) >= self.matching_iou_threshold:
return 1
return 0
def _get_overlaps_and_scores_mask_mode(self, detected_boxes,
detected_scores, detected_masks,
groundtruth_boxes,
groundtruth_masks,
groundtruth_is_group_of_list):
"""Computes overlaps and scores between detected and groudntruth masks.
Args:
detected_boxes: A numpy array of shape [N, 4] representing detected box
coordinates
detected_scores: A 1-d numpy array of length N representing classification
score
detected_masks: A uint8 numpy array of shape [N, height, width]. If not
None, the scores will be computed based on masks.
groundtruth_boxes: A numpy array of shape [M, 4] representing ground truth
box coordinates
groundtruth_masks: A uint8 numpy array of shape [M, height, width].
groundtruth_is_group_of_list: A boolean numpy array of length M denoting
whether a ground truth box has group-of tag. If a groundtruth box
is group-of box, every detection matching this box is ignored.
Returns:
iou: A float numpy array of size [num_detected_boxes, num_gt_boxes]. If
gt_non_group_of_boxlist.num_boxes() == 0 it will be None.
ioa: A float numpy array of size [num_detected_boxes, num_gt_boxes]. If
gt_group_of_boxlist.num_boxes() == 0 it will be None.
scores: The score of the detected boxlist.
num_boxes: Number of non-maximum suppressed detected boxes.
"""
detected_boxlist = np_box_mask_list.BoxMaskList(
box_data=detected_boxes, mask_data=detected_masks)
detected_boxlist.add_field('scores', detected_scores)
detected_boxlist = np_box_mask_list_ops.non_max_suppression(
detected_boxlist, self.nms_max_output_boxes,
self.nms_iou_threshold)
gt_non_group_of_boxlist = np_box_mask_list.BoxMaskList(
box_data=groundtruth_boxes[~groundtruth_is_group_of_list],
mask_data=groundtruth_masks[~groundtruth_is_group_of_list])
gt_group_of_boxlist = np_box_mask_list.BoxMaskList(
box_data=groundtruth_boxes[groundtruth_is_group_of_list],
mask_data=groundtruth_masks[groundtruth_is_group_of_list])
iou = np_box_mask_list_ops.iou(detected_boxlist,
gt_non_group_of_boxlist)
ioa = np.transpose(
np_box_mask_list_ops.ioa(gt_group_of_boxlist, detected_boxlist))
scores = detected_boxlist.get_field('scores')
num_boxes = detected_boxlist.num_boxes()
return iou, ioa, scores, num_boxes
def box_list_to_box_mask_list(boxlist):
"""Converts a BoxList containing 'masks' into a BoxMaskList.
Args:
boxlist: An np_box_list.BoxList object.
Returns:
An np_box_mask_list.BoxMaskList object.
Raises:
ValueError: If boxlist does not contain `masks` as a field.
"""
if not boxlist.has_field('masks'):
raise ValueError('boxlist does not contain mask field.')
box_mask_list = np_box_mask_list.BoxMaskList(
box_data=boxlist.get(),
mask_data=boxlist.get_field('masks'))
extra_fields = boxlist.get_extra_fields()
for key in extra_fields:
if key != 'masks':
box_mask_list.data[key] = boxlist.get_field(key)
return box_mask_list
def multi_class_non_max_suppression(box_mask_list, score_thresh, iou_thresh,
max_output_size):
"""Multi-class version of non maximum suppression.
This op greedily selects a subset of detection bounding boxes, pruning
away boxes that have high IOU (intersection over union) overlap (> thresh)
with already selected boxes. It operates independently for each class for
which scores are provided (via the scores field of the input box_list),
pruning boxes with score less than a provided threshold prior to
applying NMS.
Args:
box_mask_list: np_box_mask_list.BoxMaskList holding N boxes. Must contain a
'scores' field representing detection scores. This scores field is a
tensor that can be 1 dimensional (in the case of a single class) or
2-dimensional, in which case we assume that it takes the
shape [num_boxes, num_classes]. We further assume that this rank is known
statically and that scores.shape[1] is also known (i.e., the number of
classes is fixed and known at graph construction time).
score_thresh: scalar threshold for score (low scoring boxes are removed).
iou_thresh: scalar threshold for IOU (boxes that that high IOU overlap
with previously selected boxes are removed).
max_output_size: maximum number of retained boxes per class.
Returns:
a box_mask_list holding M boxes with a rank-1 scores field representing
corresponding scores for each box with scores sorted in decreasing order
and a rank-1 classes field representing a class label for each box.
Raises:
ValueError: if iou_thresh is not in [0, 1] or if input box_mask_list does
not have a valid scores field.
"""
if not 0 <= iou_thresh <= 1.0:
raise ValueError('thresh must be between 0 and 1')
if not isinstance(box_mask_list, np_box_mask_list.BoxMaskList):
raise ValueError('box_mask_list must be a box_mask_list')
if not box_mask_list.has_field('scores'):
raise ValueError('input box_mask_list must have \'scores\' field')
scores = box_mask_list.get_field('scores')
if len(scores.shape) == 1:
scores = np.reshape(scores, [-1, 1])
elif len(scores.shape) == 2:
if scores.shape[1] is None:
raise ValueError('scores field must have statically defined second '
'dimension')
else:
raise ValueError('scores field must be of rank 1 or 2')
num_boxes = box_mask_list.num_boxes()
num_scores = scores.shape[0]
num_classes = scores.shape[1]
if num_boxes != num_scores:
raise ValueError('Incorrect scores field length: actual vs expected.')
selected_boxes_list = []
for class_idx in range(num_classes):
box_mask_list_and_class_scores = np_box_mask_list.BoxMaskList(
box_data=box_mask_list.get(),
mask_data=box_mask_list.get_masks())
class_scores = np.reshape(scores[0:num_scores, class_idx], [-1])
box_mask_list_and_class_scores.add_field('scores', class_scores)
box_mask_list_filt = filter_scores_greater_than(
box_mask_list_and_class_scores, score_thresh)
nms_result = non_max_suppression(
box_mask_list_filt,
max_output_size=max_output_size,
iou_threshold=iou_thresh,
score_threshold=score_thresh)
nms_result.add_field(
'classes',
np.zeros_like(nms_result.get_field('scores')) + class_idx)
selected_boxes_list.append(nms_result)
selected_boxes = np_box_list_ops.concatenate(selected_boxes_list)
sorted_boxes = np_box_list_ops.sort_by_field(selected_boxes, 'scores')
return box_list_to_box_mask_list(boxlist=sorted_boxes)