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

Timing in VAE+INN #4

Open
fa7sa opened this issue May 21, 2024 · 1 comment
Open

Timing in VAE+INN #4

fa7sa opened this issue May 21, 2024 · 1 comment

Comments

@fa7sa
Copy link

fa7sa commented May 21, 2024

While trying to generate samples, I noticed that it does not compute timing information. I am assuming that is same as previous CaloINN repo. However, I just want to make sure that I am calculating time properly as you did in the CaloINN paper. So, I am considering both latent sample creation and final sample creation time from VAE for total time for sampling one event. Is this correct? I am looking at the 'generate' function in trainer.py.

@floern1
Copy link
Collaborator

floern1 commented Dec 18, 2024

Yes, for the 2 stage approach witht the VAE, you should sum up both generation times. It should be safe to just time the trainer.generate function. For the VAE approach the postprocessing is not part of the generate function. So, you could just take the time and divide it by the number of created samples.

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