questions about the feature map visualize

[mcjqwer]

Search before asking

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

Question

Firstly, after doing the visualisation of the feature maps, I see that a feature map for each layer is generated and that each image has several rows and columns of sub-maps, what does this mean for each sub-map? Secondly, I encountered the error that there was no gradient backpropagation when I used Grad-Cam for visualisation and used the visualisation provided by the author, which is very convenient, so what is the difference between this and grad-cam and how did you do your visualisation?

Additional

No response

[glenn-jocher]

@mcjqwer first 32 channels of any grid. YOLOv5 layers each output hundreds or thousands of channels. There is no gradient here, these are features.

[github-actions[bot]]

👋 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 ⭐!