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

what does the arguments 'reduce_D' and 'f_dim' mean? #10

Open
advancera opened this issue Dec 27, 2018 · 7 comments
Open

what does the arguments 'reduce_D' and 'f_dim' mean? #10

advancera opened this issue Dec 27, 2018 · 7 comments

Comments

@advancera
Copy link

sorry, i don't understant the meaning of arguments 'reduce_D' and 'f_dim', can you give me any help? thanks a lot!
def _build_extreme_FM(hparams, nn_input, res=True, direct=False, bias=False, reduce_D=True, f_dim=2)

@Leavingseason
Copy link
Owner

reduce_D and f_dim is about decomposing the filter matrix into two low-rank matrices. You can refer to the equation (9) in our paper.
We have a updated version of implementation for this part. In the old version, we only reduce the space complexity, but not time complexity. In the updated version, we reduce both. Let me know if you are interested in the updated version, and I will send you it.

@jaysharp
Copy link

reduce_D and f_dim is about decomposing the filter matrix into two low-rank matrices. You can refer to the equation (9) in our paper.
We have a updated version of implementation for this part. In the old version, we only reduce the space complexity, but not time complexity. In the updated version, we reduce both. Let me know if you are interested in the updated version, and I will send you it.


could you send me one copy? highly appreciated. my email: [email protected]

@Leavingseason
Copy link
Owner

Sent.

@jaysharp
Copy link

Sent.

thank you very much. it really helps.

@y-ksenia
Copy link

y-ksenia commented Jul 9, 2019

reduce_D and f_dim is about decomposing the filter matrix into two low-rank matrices. You can refer to the equation (9) in our paper.
We have a updated version of implementation for this part. In the old version, we only reduce the space complexity, but not time complexity. In the updated version, we reduce both. Let me know if you are interested in the updated version, and I will send you it.

Hi! I'm also interested in updated version. Could you please send me it too? my mail: [email protected]
Thank you in advance!

@chenhaoenen
Copy link

膜拜大佬,代码很棒,麻烦能否发一份同样的给我,万分感谢,同时期待大佬的其他模型的代码, [email protected],谢谢!祝好!

@yang-XH
Copy link

yang-XH commented Jun 17, 2020

Hello! I'm also interested in the new version. Could you please send me the copy? my mail: [email protected]
Thank you!

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

6 participants