We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Why xs_neg = (xs_neg + self.clip).clamp(max=1) instead of xs_neg = (xs_neg - self.clip).clamp(min=0)?
The text was updated successfully, but these errors were encountered:
see #10
Sorry, something went wrong.
OK,I want to use this function in object detection. What are the hyperparameters used in the paper?
we provide full hyperparameters details for each task in the paper appendix
No branches or pull requests
Why xs_neg = (xs_neg + self.clip).clamp(max=1) instead of xs_neg = (xs_neg - self.clip).clamp(min=0)?
The text was updated successfully, but these errors were encountered: