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

Objectness mAP Evaluation for Custom Model #5

Open
abdul2706 opened this issue May 27, 2021 · 2 comments
Open

Objectness mAP Evaluation for Custom Model #5

abdul2706 opened this issue May 27, 2021 · 2 comments

Comments

@abdul2706
Copy link

Hi, I wanted to evaluate my custom model using objectness mAP criteria rather than default coco mAP criteria. I tried to figure out the objectness evaluation criteria working, from the code in this repo, but it seems to be divided into multiple files, which is difficult for me to use in my implementation.

I wanted to request that if you could help me with either of the following, then I will be very thankful to you.

  1. Please provide the objectness evaluation criteria as a single function (or file).
  2. or, please guide me to compute it from the default coco evaluator.
  3. or, kindly provide an algorithm to calculate it as an independent evaluation function.

Thanking you in advance.

@kheffah
Copy link
Collaborator

kheffah commented Jun 10, 2021

@abdul2706 Apologies for the delay in getting back to you. Well, this codebase does exactly that. It takes the coco evaluator and makes modifications in places where needed to allow the calculation of objectness AP. The simplest approach would be to simply make sure that both truth and your predictions are remapped so that they only have one class (nucleus), all before instantiating the coco evaluator. I can't remember all the nuances at the moment because did this a while back, but I think that's all you need actually.

@abdul2706
Copy link
Author

@kheffah Thanks for providing helpful guildelines.

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

2 participants