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 position embedding #17

Open
zhaozhaoooo opened this issue Sep 13, 2024 · 1 comment
Open

about position embedding #17

zhaozhaoooo opened this issue Sep 13, 2024 · 1 comment

Comments

@zhaozhaoooo
Copy link

why doesn't the architecture need position embedding?
@ZZZHANG-jx
Copy link
Owner

why doesn't the architecture need position embedding?

My understanding is that in Restormer, the self-attention module, Multi-Dconv Head Transposed Attention (MDTA), operates along the channel dimension rather than the spatial dimension, so position embedding is not necessary.

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
@ZZZHANG-jx @zhaozhaoooo