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

the class center distance expansion loss of FastMLDNN #5

Open
Patrick-Nick opened this issue Mar 17, 2024 · 2 comments
Open

the class center distance expansion loss of FastMLDNN #5

Patrick-Nick opened this issue Mar 17, 2024 · 2 comments

Comments

@Patrick-Nick
Copy link

I have read your paper about FastMLDNN. This is really excellent work. When I looked up your code, it seemed that I couldn't find the code of the class center distance expansion loss. Perhaps I missed it?

@Singingkettle
Copy link
Owner

Singingkettle commented Apr 7, 2024

Hi, recently, the code about FastMLDNN is rewritten upon new mmengine. Basically, the class center is made up of two parts in python code: class center distance and loss function (cross entropy loss ).
image

The class distance is calculated in code (csrr/models/backbones/fastmldnn.py):

"p = sim_matrix(self.classifier[3].weight, self.classifier[3].weight)"

The loss is cross entropy loss in fast_mldnn_head.py

@asq12138
Copy link

It's really excellent work. But I can't find the file that contains the sim_matrix function, and the fastmldnn.py file in current version.
such as, from ...ops import sim_matrix, but i can't Correct import.

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

3 participants