Skip to content
This repository has been archived by the owner on Aug 1, 2024. It is now read-only.

A question about focal loss #3

Open
PengxinWang opened this issue Feb 19, 2024 · 1 comment
Open

A question about focal loss #3

PengxinWang opened this issue Feb 19, 2024 · 1 comment

Comments

@PengxinWang
Copy link

PengxinWang commented Feb 19, 2024

In losses.py, we're required to finish the part of Focal Loss from 107th line to 117th line.

focal_weight = "?"

bce = "?"

cls_loss = focal_weight * bce

However, I'm a little bit confused about bce since we are handling multiclasses. Are we supposed to use cce(categorical cross entropy) instead?

Another question is about evaluation, since the evaluation metric (the AP score) is wrapped in COCOeval, I can't see very clearly. I want to ask, does the model's performance on categorical classification is taken into consideration in evaluation? Also, does model's ability of correctly classify the category will influence the performance of correctly positioning the object?

Really thanks!!

@PengxinWang PengxinWang closed this as not planned Won't fix, can't repro, duplicate, stale Feb 19, 2024
@PengxinWang PengxinWang reopened this Mar 2, 2024
@PengxinWang
Copy link
Author

It confused me a lot about the intepretation of classification loss because I formerlly thought the output layer head of classification head is a softmax layer... Until I find similar question on the stackoverflow. In case others get similar confusion. I post this issue.

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant