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

About the implementation of normalisation #1

Open
mucunzhuzhu opened this issue Jan 2, 2024 · 0 comments
Open

About the implementation of normalisation #1

mucunzhuzhu opened this issue Jan 2, 2024 · 0 comments

Comments

@mucunzhuzhu
Copy link

Hi author, I found that you performed normalisation operations on the true and predicted joints before calculating the FID and Diversity, but I found that the normalisation you implemented is not the same as the normalisation method that I have seen in the code of other papers.

You are normalising the true and predicted joints separately, but the other papers are calculating the mean and variance of the true joints first, and then the predicted joints are normalised using the mean and variance of the true joints. ( The first figure shows your implementation of normalisation, the second figure shows the implementation of normalisation in other papers. )

GSNP6J4$XSDF}`L($YM K

3H6%MNXX40FMJ$F%$SV1BLN

The results calculated by these two methods are not the same, can I ask you the difference between these two normalisation methods?

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