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

Questions about table5 in the paper #124

Open
EWE002 opened this issue Dec 21, 2023 · 0 comments
Open

Questions about table5 in the paper #124

EWE002 opened this issue Dec 21, 2023 · 0 comments

Comments

@EWE002
Copy link

EWE002 commented Dec 21, 2023

Thank you for open this great repo.
In section 4.3 of the paper, the effect of attention type, it is mentioned that if you want to change the patch size from 16x16 to 8x8, you have to use the window attention and shift window and pool window in the swin transformer, I tried to modify the original version of vit for training, but I can't achieve the AP&AR of table 5 in the paper. May I know what else needs to be adjusted besides changing the original block in vit to the one in swin?

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