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

Issue about Loss function #44

Open
EthanZhangYi opened this issue Aug 18, 2016 · 1 comment
Open

Issue about Loss function #44

EthanZhangYi opened this issue Aug 18, 2016 · 1 comment

Comments

@EthanZhangYi
Copy link

EthanZhangYi commented Aug 18, 2016

Content Loss and Style Loss are two loss functions used here.
_compute_style_grad() -------- line 100
_compute_content_grad() -------- line 114
I do not understand why * (Fl>0) when computing gradient.
Is there any specific reason?
@fzliu

@consciousgaze
Copy link

If you go through the paper at http://arxiv.org/abs/1508.06576. You will find that the gradient will be 0 when Fl is less or equal to 0 in equation (2). That is why *(Fl > 0) is here.

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

2 participants