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

Add Functional Interface for MeanAveragePrecision #2877

Open
RoyiAvital opened this issue Dec 23, 2024 · 4 comments
Open

Add Functional Interface for MeanAveragePrecision #2877

RoyiAvital opened this issue Dec 23, 2024 · 4 comments
Assignees
Labels
enhancement New feature or request

Comments

@RoyiAvital
Copy link

🚀 Feature

Currently the MeanAveragePrecision for detection task does not have Functional Interface.

It would be great to have one.

Motivation

Same motivation as given in the Module vs Functional Metrics section from documentation.

It will be great to have such case as optimized as it can get.

@RoyiAvital RoyiAvital added the enhancement New feature or request label Dec 23, 2024
Copy link

Hi! thanks for your contribution!, great first issue!

@Isalia20
Copy link
Contributor

@Borda
I can take this and probably will have something by end of the week~

@Isalia20
Copy link
Contributor

@Borda
Not sure if this is the best place to ask questions, I see that there are 2 MeanAveragePrecision implementations(2 classes), one in src/torchmetrics/detection/mean_ap.py and another src/torchmetrics/detection/_mean_ap.py

What is the difference between these two?

@Borda
Copy link
Member

Borda commented Dec 24, 2024

What is the difference between these two?

We started with the original package and made just a wrapper. Then we wanted to have own implementation which we could optimize for PyTorch, but it was still slower so we preserve the original and default until we improve the own code...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

3 participants