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

Angle Based loss versus cosine inverse loss #8

Open

rohun-tripathi opened this issue Oct 2, 2018 · 0 comments

rohun-tripathi commented Oct 2, 2018 •

edited

Thanks for your great work!

Have you experimented with arccos based normal loss. Does the performance vary when using arccos instead of (1 - normalized inner product)?

The code I am referring to is -

prod = ( grad_fake[:,:,None,:] @ grad_real[:,:,:,None] ).squeeze(-1).squeeze(-1)
fake_norm = torch.sqrt( torch.sum( grad_fake2, dim=-1 ) )
real_norm = torch.sqrt( torch.sum( grad_real2, dim=-1 ) )

rohun-tripathi changed the title ~~Query in using angle based surface normal Loss~~ Possible bug in angle based surface normal Loss

rohun-tripathi changed the title ~~Possible bug in angle based surface normal Loss~~ Angle Based loss versus cosine inverse loss

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment