Skip to content

A question regarding the sigmoid_focal_loss function used for computing loss_ce. #28

Description

@hanminpay

When training on my custom dataset, I noticed that at the beginning of training, loss_ce becomes extremely large (around 160), while all other loss components remain below 10. This causes the overall training to be dominated by the classification loss and results in poor final model performance.

I checked the implementation and found that the final loss value in sigmoid_focal_loss is scaled by a factor of 50. Could you please explain the reason for this scaling? Is this multiplier necessary, and how should I adjust it (or other settings) to achieve better training stability and performance on my dataset?

Any guidance would be greatly appreciated. Thanks in advance!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions