Own loss function for multi class classifikation

[KFrank]

Hi roxor!

@roxor

I want to penalize some missclassification stronger than others.

One approach is to use cross-entropy with probabilistic or soft targets.

This post has further discussion and details:

Label smoothing for only a subset of classes

Hi macazinc! Here’s what I think you’re asking: You have a multi-class (30 classes) classification problem. You know that for most of your classes, your ground-truth target labels are correct, but your labels sometimes mix up two of your classes, say 4 and 9, Let’s say that a sample labelled 4 is actually a 9 25% of the time, and that a sample labelled 9 is actually a 4 10% of the time. You will (most likely) want to use cross-entropy loss, but pytorch only provides a version that tak…

Best.

K. Frank