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

Implementation of prior_expert #5

Open
ankit1089sny opened this issue Mar 8, 2023 · 0 comments
Open

Implementation of prior_expert #5

ankit1089sny opened this issue Mar 8, 2023 · 0 comments

Comments

@ankit1089sny
Copy link

ankit1089sny commented Mar 8, 2023 •
edited
Loading

I was looking at the implementation of prior_expert and found the following line :

logvar = Variable(torch.log(torch.ones(size)))

If it's going to represent N(0,1), logvar should be 0 since variance is 1.
Could you confirm if it's ok to replace this with logvar = Variable(torch.zeros(size)) ?
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
@ankit1089sny