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
(H*W) x (H+W-1)
Can someone explain how the shape of (H*W) x (H+W-1) for attention is derived in the Python code? The energy shape is H*W, H+W.
H*W, H+W
Thank you @speedinghzl and @honghuis for sharing this amazing repo.
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Can someone explain how the shape of
(H*W) x (H+W-1)
for attention is derived in the Python code? The energy shape isH*W, H+W
.Thank you @speedinghzl and @honghuis for sharing this amazing repo.
The text was updated successfully, but these errors were encountered: