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

Is the Model Zoo in the README.md of Autoformer referring to the supernet? #239

Open
dlguswn3659 opened this issue Jul 11, 2024 · 0 comments

Comments

@dlguswn3659
Copy link

dlguswn3659 commented Jul 11, 2024

Hello,

I have a question regarding the autoformer-tiny model mentioned in the README.md of Autoformer.

image

When I downloaded the file, it was named supernet-tiny.pth, leading me to believe that it is a supernet trained with the following configurations: head_num: 4, layer_num: 14, and embed_dim: 240(256). However, after examining the weight matrix of the file, it doesn't seem to match these specifications.

Could you please clarify if the autoformer-tiny is indeed a supernet? If not, can you provide more details about the specific structure options used to train this model?

https://github.com/microsoft/Cream/blob/main/AutoFormer/experiments/subnet/AutoFormer-T.yaml
image
Or, is it a subnet sampled from the supernet with the above configuration?

Thank you for your assistance.

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