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

Negative self.gamma parameter?? #60

Closed
theelon opened this issue Jul 26, 2021 · 0 comments
Closed

Negative self.gamma parameter?? #60

theelon opened this issue Jul 26, 2021 · 0 comments

Comments

@theelon
Copy link

theelon commented Jul 26, 2021

Hi, What does negative self.gamma = nn.Parameter(torch.tensor([0.0])) value means as training progresses ? if i used it in Self-Attention(SA) module as follow: Y = self.gamma*SA features + Input Do I have to take only the magnitude ? Thanks

@theelon theelon closed this as completed Jul 26, 2021
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