def compute_iou_dt_gt(self, dt, gt, is_crowd):
if self.is_rotated(dt) or self.is_rotated(gt):
# TODO: take is_crowd into consideration
assert all(c == 0 for c in is_crowd)
dt = RotatedBoxes(self.boxlist_to_tensor(dt, output_box_dim=5))
gt = RotatedBoxes(self.boxlist_to_tensor(gt, output_box_dim=5))
return pairwise_iou_rotated(dt, gt)
else:
# This is the same as the classical COCO evaluation
return maskUtils.iou(dt, gt, is_crowd)
def _get_ground_truth(self):
"""
Returns:
gt_objectness_logits: list of N tensors. Tensor i is a vector whose length is the
total number of anchors in image i (i.e., len(anchors[i])). Label values are
in {-1, 0, 1}, with meanings: -1 = ignore; 0 = negative class; 1 = positive class.
gt_anchor_deltas: list of N tensors. Tensor i has shape (len(anchors[i]), 5).
"""
gt_objectness_logits = []
gt_anchor_deltas = []
# Concatenate anchors from all feature maps into a single RotatedBoxes per image
anchors = [RotatedBoxes.cat(anchors_i) for anchors_i in self.anchors]
for image_size_i, anchors_i, gt_boxes_i in zip(self.image_sizes,
anchors, self.gt_boxes):
"""
image_size_i: (h, w) for the i-th image
anchors_i: anchors for i-th image
gt_boxes_i: ground-truth boxes for i-th image
"""
match_quality_matrix = pairwise_iou_rotated(gt_boxes_i, anchors_i)
matched_idxs, gt_objectness_logits_i = self.anchor_matcher(
match_quality_matrix)
if self.boundary_threshold >= 0:
# Discard anchors that go out of the boundaries of the image
# NOTE: This is legacy functionality that is turned off by default in cvpods
anchors_inside_image = anchors_i.inside_box(
image_size_i, self.boundary_threshold)
gt_objectness_logits_i[~anchors_inside_image] = -1
if len(gt_boxes_i) == 0:
# These values won't be used anyway since the anchor is labeled as background
gt_anchor_deltas_i = torch.zeros_like(anchors_i.tensor)
else:
# TODO wasted computation for ignored boxes
matched_gt_boxes = gt_boxes_i[matched_idxs]
gt_anchor_deltas_i = self.box2box_transform.get_deltas(
anchors_i.tensor, matched_gt_boxes.tensor)
gt_objectness_logits.append(gt_objectness_logits_i)
gt_anchor_deltas.append(gt_anchor_deltas_i)
return gt_objectness_logits, gt_anchor_deltas
def label_and_sample_proposals(self, proposals, targets):
"""
Prepare some proposals to be used to train the RROI heads.
It performs box matching between `proposals` and `targets`, and assigns
training labels to the proposals.
It returns `self.batch_size_per_image` random samples from proposals and groundtruth boxes,
with a fraction of positives that is no larger than `self.positive_sample_fraction.
Args:
See :meth:`StandardROIHeads.forward`
Returns:
list[Instances]: length `N` list of `Instances`s containing the proposals
sampled for training. Each `Instances` has the following fields:
- proposal_boxes: the rotated proposal boxes
- gt_boxes: the ground-truth rotated boxes that the proposal is assigned to
(this is only meaningful if the proposal has a label > 0; if label = 0
then the ground-truth box is random)
- gt_classes: the ground-truth classification lable for each proposal
"""
gt_boxes = [x.gt_boxes for x in targets]
if self.proposal_append_gt:
proposals = add_ground_truth_to_proposals(gt_boxes, proposals)
proposals_with_gt = []
num_fg_samples = []
num_bg_samples = []
for proposals_per_image, targets_per_image in zip(proposals, targets):
has_gt = len(targets_per_image) > 0
match_quality_matrix = pairwise_iou_rotated(
targets_per_image.gt_boxes, proposals_per_image.proposal_boxes)
matched_idxs, matched_labels = self.proposal_matcher(
match_quality_matrix)
sampled_idxs, gt_classes = self._sample_proposals(
matched_idxs, matched_labels, targets_per_image.gt_classes)
proposals_per_image = proposals_per_image[sampled_idxs]
proposals_per_image.gt_classes = gt_classes
if has_gt:
sampled_targets = matched_idxs[sampled_idxs]
proposals_per_image.gt_boxes = targets_per_image.gt_boxes[
sampled_targets]
else:
gt_boxes = RotatedBoxes(
targets_per_image.gt_boxes.tensor.new_zeros(
(len(sampled_idxs), 5)))
proposals_per_image.gt_boxes = gt_boxes
num_bg_samples.append(
(gt_classes == self.num_classes).sum().item())
num_fg_samples.append(gt_classes.numel() - num_bg_samples[-1])
proposals_with_gt.append(proposals_per_image)
# Log the number of fg/bg samples that are selected for training ROI heads
storage = get_event_storage()
storage.put_scalar("roi_head/num_fg_samples", np.mean(num_fg_samples))
storage.put_scalar("roi_head/num_bg_samples", np.mean(num_bg_samples))
return proposals_with_gt
