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

speed up the process? #7

Open
ruanjiyang opened this issue Aug 23, 2022 · 5 comments
Open

speed up the process? #7

ruanjiyang opened this issue Aug 23, 2022 · 5 comments

Comments

@ruanjiyang
Copy link

What a nice and cool project, but I feel the speed is too slow.

Is that possible to speed up the whole process? Thx.

@rafpyprog
Copy link

Hi @Taeu ! I have been playing with the model and the results are great! As @ruanjiyang 've said, I also had to wait for almost20 minutes for a prediction. Is this the regular average prediction time for this model ? Could you give us any advice on how to speed up ? Thank you very much for the awesome job !

@myoons
Copy link
Collaborator

myoons commented Sep 5, 2022

Could you provide following information for further support on this issue?

  • What kind of CPU/GPU you used
  • Environment

@datased2019
Copy link

Same problem. It really takes too long for prediction. I don't know if we could pre-calculate the latent of target hairstyle to make it faster when using new faces. :)

@mrsaleh
Copy link

mrsaleh commented Feb 19, 2023

Can I replace Stylegan2 with MobileStyleGan? And does it speed up the process?

@ArsalanAli915
Copy link

@myoons I have been using T4 GPU with python=3.7.9 enviroment in anaconda. I am getting around 17 mins on inference time. Could help me know How can I reduce the time?

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

6 participants