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

onnxRuntime #1

Open
zw-92 opened this issue Jul 26, 2024 · 4 comments
Open

onnxRuntime #1

zw-92 opened this issue Jul 26, 2024 · 4 comments

Comments

@zw-92
Copy link

zw-92 commented Jul 26, 2024

Thank you very much for your contribution, it is really great.I have two questions for you. Have you used onnxRuntime to accelerate your model?Have you compared how much faster post-processing in C++ is than in python?Looking forward to your reply.

@udaysankar01
Copy link
Owner

Hi,
I have not tried using onnxRuntime as of now, I may try testing it out. As for post processing speed, I am planning to compare both and see if there is any improvement with C++.

@udaysankar01
Copy link
Owner

I just came across this repo, where the author uses onnx runtime to port XFeat into C++.
https://github.com/meyiao/xfeatc

@zw-92
Copy link
Author

zw-92 commented Jul 30, 2024

I just came across this repo, where the author uses onnx runtime to port XFeat into C++. https://github.com/meyiao/xfeatc
I tried running the code but there are many problems. Have you tried it?

@udaysankar01
Copy link
Owner

Oh, I have not been able to test that repo out as I have been working on another project. It probably would be best to wait for the author to post some updates.

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