Skip to content

Update the description of TverskyLoss #626

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

Merged
merged 1 commit into from
Aug 7, 2022

Conversation

gracikk-ds
Copy link
Contributor

I think you should rethink the description of the Tversky loss function.
You can check the article and see that FN and FP are alpha and beta weighted, while your description says that the loss function weights TP and FP. But the function itself is implemented correctly.

I think you should rethink the description of the [Tversky loss function](https://smp.readthedocs.io/en/latest/losses.html#:~:text=Tversky%20loss%20for%20image%20segmentation%20task.%20Where%20TP%20and%20FP%20is%20weighted%20by%20alpha%20and%20beta%20params.%20With%20alpha%20%3D%3D%20beta%20%3D%3D%200.5%2C%20this%20loss%20becomes%20equal%20DiceLoss.%20It%20supports%20binary%2C%20multiclass%20and%20multilabel%20cases).
You can check the article and see that FN and FP are alpha and beta weighted, while your description says that the loss function weights TP and FP. But the function itself is implemented correctly.
@qubvel
Copy link
Collaborator

qubvel commented Aug 7, 2022

Thanks!

@qubvel qubvel closed this Aug 7, 2022
@qubvel qubvel reopened this Aug 7, 2022
@qubvel qubvel merged commit f58fd6d into qubvel-org:master Aug 7, 2022
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

Successfully merging this pull request may close these issues.

2 participants