how to reduce GPU memory cost when inference on one camera?

[XiangjiBU]

hi, I run demo using "python detect.py --source 0 --weights weights/yolov5s.pt", the performance is good, but I find GPU memory cost is more than 4G.
I replace line 40 in detect.py by "dataset = LoadWebcam(source, img_size=imgsz)" . But GPU memory cost didn't reduce, Could you give a method to reduce GPU memory cost when only use one camera? thanks!

[github-actions]

Hello @noahbu, 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 that 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.

[glenn-jocher]

@noahbu I transitioned the repo to use FP16 inference by default now when running test.py or detect.py. This might help. git pull to get the latest.

And don't add bug labels to issues that are not bugs in the future.

[github-actions]

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.

[zhou-huan-1]

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.

[glenn-jocher]

Hello! 👋 It looks like this issue has been marked as stale due to inactivity. If there are still concerns or additional details to add, please update the thread to keep it open. Otherwise, it will be automatically closed. Thanks for your understanding and contributions! 😊