How to get pred box coordinates in loss.py?

[HongYg]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

Hi!
I want to get pred box coordinates in loss.py (x1,y1,y2,y2)

I'm having trouble analyzing it.
What's the solution?

thanks!

Additional

No response

[glenn-jocher]

@HongYg box coordinates are not constructed in loss.py, only the minimum deltas (pred-truth) in gridspace are used there. The closest is this:

yolov5/utils/loss.py

Lines 137 to 143 in 27911dc

	# Regression
	pxy = pxy.sigmoid() * 2 - 0.5
	pwh = (pwh.sigmoid() * 2) ** 2 * anchors[i]
	pbox = torch.cat((pxy, pwh), 1) # predicted box
	iou = bbox_iou(pbox, tbox[i], CIoU=True).squeeze() # iou(prediction, target)
	lbox += (1.0 - iou).mean() # iou loss

[github-actions]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com/hub
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!

[mullenba]

@HongYg box coordinates are not constructed in loss.py, only the minimum deltas (pred-truth) in gridspace are used there. The closest is this:

yolov5/utils/loss.py

Lines 137 to 143 in 27911dc

	# Regression
	pxy = pxy.sigmoid() * 2 - 0.5
	pwh = (pwh.sigmoid() * 2) ** 2 * anchors[i]
	pbox = torch.cat((pxy, pwh), 1) # predicted box
	iou = bbox_iou(pbox, tbox[i], CIoU=True).squeeze() # iou(prediction, target)
	lbox += (1.0 - iou).mean() # iou loss

To answer the original question, you should be able to pull the values from the regression section shown above, and apply the offsets explained in section 4.3 of https://docs.ultralytics.com/yolov5/tutorials/architecture_description#44