Pytorch Multi Class Focal Loss Versions Save

An (unofficial) implementation of Focal Loss, as described in the RetinaNet paper, generalized to the multi-class case.

1.2

4 months ago

Changelog

  • Ensure FocalLoss.forward() always returns a tensor (#7)
  • Put quotes around string values in repr() output (#8, #9)

Full Changelog: https://github.com/AdeelH/pytorch-multi-class-focal-loss/compare/1.1...1.2

1.1

2 years ago

Minor changes.

1.0

3 years ago