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.

Sign up for GitHub

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

Jump to bottom

How the log_abs_det_jacobian for _TTransform is calculated? #6

Open
pengyanhui opened this issue Dec 13, 2024 · 0 comments
Open

How the log_abs_det_jacobian for _TTransform is calculated? #6

pengyanhui opened this issue Dec 13, 2024 · 0 comments

Comments

@pengyanhui
Copy link

Why the log_abs_det_jacobian for _TTransform is ((x.shape[-1] - 3) / 2) * torch.log(torch.clamp(1 - t ** 2, _EPS))?
I derived the log_abs_det_jacobian, and found that is ((x.shape[-1] - 1) / 2) * torch.log(torch.clamp(1 - t ** 2, _EPS)).
I don't know what the problem is.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@pengyanhui