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

In my opinion, authors define L_{vlb} = L_0 + ... + L_T, not L_t. #147

Open
unl1002 opened this issue Nov 23, 2024 · 2 comments
Open

In my opinion, authors define L_{vlb} = L_0 + ... + L_T, not L_t. #147

unl1002 opened this issue Nov 23, 2024 · 2 comments

Comments

@unl1002
Copy link

unl1002 commented Nov 23, 2024

          In my opinion, authors define L_{vlb} = L_0 + ... + L_T, not L_t.

Thus, they may calculate the vlb loss with scale factor T (self.num_timestep).

Originally posted by @yhy258 in #114 (comment)

@unl1002 unl1002 closed this as completed Nov 23, 2024
@unl1002
Copy link
Author

unl1002 commented Nov 23, 2024

so, which means we use L_t * T (self. num_timestep) to approximate L_ {vlb}?

@unl1002 unl1002 reopened this Nov 23, 2024
@unl1002
Copy link
Author

unl1002 commented Nov 27, 2024

image

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

1 participant