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

How to convert video classification from pytorch to onnx,on cpu #36

Closed
LeiYiNuist opened this issue Apr 11, 2022 · 4 comments
Closed

Comments

@LeiYiNuist
Copy link

I want to convert the pytorch model to the onnx model on the cpu, but there is no relevant code in the source code. Can you upload pytorch2onnx.py in the video classification?

@Andy1621
Copy link
Collaborator

I'm so sorry that I never try to convert the PyTorch model to the onnx model.
Actually, as I know, there is no relevant code to convert Vision Transformer to the onnx model......

@LeiYiNuist
Copy link
Author

Oh, that's kind of interesting, I just converted it to onnx. However, thank you very much for taking the time to reply to me.

@Andy1621
Copy link
Collaborator

Thanks for your try! When designing models, we adopt the most simple and effective component, thus the speed and memory should be friendly.

As shown in speed_UniFormer and speed_VAN, our UniFormer-S/B runs faster than VAN-B/L with better accuracy.

@Andy1621
Copy link
Collaborator

As there is no more activity, I am closing the issue, don't hesitate to reopen it if necessary.

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

2 participants