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 understand the linear noise schedule (Eq. 4) in paper? #6

Open
BlueGhostZ opened this issue May 13, 2023 · 1 comment
Open

Comments

@BlueGhostZ
Copy link

Notice that the author uses a new linear noise schedule instead of the Linear or cosine schedules used in DDPM. The selection in the code is noise_ schedule='linear var', which corresponds to lines 303-309 in gaussian_diffusion. py, but I do not understand the correspondence between these codes and Eq. 4 in the paper. I hope the author can help me.
Looking forward to your reply very much.

@YiyanXu
Copy link
Owner

YiyanXu commented Oct 23, 2023

The implementation of the linear noise schedule specified in Eq.(4) is represented by the np.linspace(...) operation found in line 53 of gaussian_diffusion.py. The function betas_from_linear_variance, which can be found in lines 303-309 of the same file, is responsible for deriving $\beta_t$ from the linear $1-\bar{\alpha}_t$.

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