Yolov5: Extract features from specific layers

[maxiaotian520]

❔Question

Is there a way to extract features from specific intermediate layers of the model?

Additional context

[github-actions[bot]]

Hello @maxiaotian520, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Jupyter Notebook , Docker Image, and Google Cloud Quickstart Guide for example environments.

If this is a bug report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom model or data training question, please note Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

[Aktcob]

add additional output branch for specific layers

[glenn-jocher]

@maxiaotian520 yes like @Aktcob comment, you can output whatever you want from the model forward function, like any pytorch model.

[maxiaotian520]

@glenn-jocher Got it, it's really helpful, thank you. And I also have one more question that need your help, which is the role of BottleneckCSP layer. I mean, like, which kind of feature was extracted or treated by BottleneckCSP after a image was passing through the architecture?

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.