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

Flops computation for swin transformer #340

Open
1 task
ChaojifeixiaDazhuang opened this issue Nov 8, 2023 · 0 comments
Open
1 task

Flops computation for swin transformer #340

ChaojifeixiaDazhuang opened this issue Nov 8, 2023 · 0 comments

Comments

@ChaojifeixiaDazhuang
Copy link

ChaojifeixiaDazhuang commented Nov 8, 2023

Hi all, as title described, in the view of engineering and chip, one MAC(Multiply Accumulate) equals two Ops. So the flops computation for Convolution, MatMul, Linear should multiply to 2,which as changed here. Thus, for the swin-v1-tiny, the whole Flops should be 9GFlops.

Tasks

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