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.

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

Jump to bottom

About the input dimensions of Long-Term Attention #2

Closed
zhouweii234 opened this issue Aug 16, 2021 · 1 comment
Closed

About the input dimensions of Long-Term Attention #2

zhouweii234 opened this issue Aug 16, 2021 · 1 comment

Comments

@zhouweii234
Copy link

1

How do you deal with the changeable input dimensions since the input dimensions of torch.nn.MultiheadAttention should be fixed? Or do I have any misunderstandings about the use of torch.nn.MultiheadAttention ?
@z-x-yang
Copy link
Owner

I realized the module of long-term attention by myself instead of using torch.nn.MultiheadAttention, which can't share the weights for query and key.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@z-x-yang @zhouweii234