Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Is it possible to change detect model? #90

Open
cosao opened this issue Feb 13, 2023 · 5 comments
Open

Is it possible to change detect model? #90

cosao opened this issue Feb 13, 2023 · 5 comments

Comments

@cosao
Copy link

cosao commented Feb 13, 2023

Hi, thank you for your work.

I wanted to change the detection model while using your code.

It's currently in yolov3, but I'd like to use the yolov5 model as a detection model, so can you tell me if there's another way or what I need to modify?

@annyhou
Copy link

annyhou commented May 11, 2023

Model file download link failed, can you provide the model files?

@xiuxiudezheng
Copy link

你好,谢谢你的工作。

我想在使用您的代码时更改检测模型。

目前是yolov3,但是我想使用yolov5模型作为检测模型,所以你能告诉我是否还有其他方法或者我需要修改什么?

你好,请问你修改成功了吗

@cosao
Copy link
Author

cosao commented Dec 21, 2023 via email

@jersonal
Copy link

I have successfully used the YOLOv8 model for human keypoint detection, but I feel that the ST-GCN prediction is not effective. The reason may be that OpenPose predicts all keypoints, even if the keypoints do not exist, it will infer possible keypoint coordinates. However, for non-existent keypoints, YOLOv8 sets x=0, y=0, so the effect is not good. If someone has trained the ST-GCN model themselves, it would be appreciated if they could provide it to me for testing.

@yllberishastudent
Copy link

@jersonal Did you manage to achieve that? Would be appreciated if you could share it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants