xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ultralytics 8.0.92 updates and fixes (#2361)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Yonghye Kwon <developer.0hye@gmail.com>
Co-authored-by: introvin <vinod.4166@gmail.com>
Co-authored-by: marinmarcillat <58145636+marinmarcillat@users.noreply.github.com>
Co-authored-by: BIGBOSS-FOX <47949596+BIGBOSS-FOX@users.noreply.github.com>
This commit is contained in:
Glenn Jocher
2023-05-04 01:27:00 +02:00
committed by GitHub
parent 3fd317edfd
commit 0ebd3f2959
15 changed files with 82 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ultralytics/yolo/v8/detect/train.py
View File

@ -212,7 +212,6 @@ class Loss:
pred_scores.detach().sigmoid(), (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype),
anchor_points * stride_tensor, gt_labels, gt_bboxes, mask_gt)
target_bboxes /= stride_tensor
target_scores_sum = max(target_scores.sum(), 1)
# cls loss
@ -221,6 +220,7 @@ class Loss:
# bbox loss
if fg_mask.sum():
target_bboxes /= stride_tensor
loss[0], loss[2] = self.bbox_loss(pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores,
target_scores_sum, fg_mask)