Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Fix] Fix SimOTA with no valid bbox. #6733

Merged
merged 1 commit into from
Dec 13, 2021
Merged

[Fix] Fix SimOTA with no valid bbox. #6733

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 7 additions & 8 deletions mmdet/core/bbox/assigners/sim_ota_assigner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,7 +127,13 @@ def _assign(self,
assigned_gt_inds = decoded_bboxes.new_full((num_bboxes, ),
0,
dtype=torch.long)
if num_gt == 0 or num_bboxes == 0:
valid_mask, is_in_boxes_and_center = self.get_in_gt_and_in_center_info(
priors, gt_bboxes)
valid_decoded_bbox = decoded_bboxes[valid_mask]
valid_pred_scores = pred_scores[valid_mask]
num_valid = valid_decoded_bbox.size(0)

if num_gt == 0 or num_bboxes == 0 or num_valid == 0:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You can consider adding unit tests to cover num_valid == 0

# No ground truth or boxes, return empty assignment
max_overlaps = decoded_bboxes.new_zeros((num_bboxes, ))
if num_gt == 0:
Expand All @@ -142,13 +148,6 @@ def _assign(self,
return AssignResult(
num_gt, assigned_gt_inds, max_overlaps, labels=assigned_labels)

valid_mask, is_in_boxes_and_center = self.get_in_gt_and_in_center_info(
priors, gt_bboxes)

valid_decoded_bbox = decoded_bboxes[valid_mask]
valid_pred_scores = pred_scores[valid_mask]
num_valid = valid_decoded_bbox.size(0)

pairwise_ious = bbox_overlaps(valid_decoded_bbox, gt_bboxes)
iou_cost = -torch.log(pairwise_ious + eps)

Expand Down