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 the possible to speed up the inference speed? #4

Open
ruanjiyang opened this issue Jul 15, 2022 · 1 comment
Open

Is the possible to speed up the inference speed? #4

ruanjiyang opened this issue Jul 15, 2022 · 1 comment

Comments

@ruanjiyang
Copy link

Really cool project! I love it!

Just one question: Is the possible to speed up the inference speed? or any suggestion? thanks!

@qianqianwang68
Copy link
Contributor

qianqianwang68 commented Aug 2, 2022

Yes, I think that would be possible. One way would be to reduce the size of the feature extraction and image synthesis network. In addition, I haven't thoroughly profiled the inference time; it is possible that the code is not efficient and can be improved. Another way to speed up the inference without changing a lot is to remove the whole feature rendering part and directly render the color images only. See here.

direct_rgb = direct_rgb_out[..., :3].permute(0, 3, 1, 2)
But this could also give you a performance drop.

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