Skip to content

A Tensorflow (Keras) implementation of Peer loss functions for classification with noisy labels.

License

Notifications You must be signed in to change notification settings

kumar10725/PeerLoss-Keras

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 

Repository files navigation

Keras-Determinant-based-Mutual-Information-loss-(DMI-loss)

This is a tensorflow/Keras implementation of two versions of DMI-loss, also known as peer-loss. The existing pytorch implementations can be found at following repositories.

  1. L_DMI: An Information-theoretic Noise-robust Loss Function : https://arxiv.org/abs/1909.03388 github: https://github.com/Newbeeer/L_DMI
  2. Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates : https://arxiv.org/abs/1910.03231 github: https://github.com/gohsyi/PeerLoss

About

A Tensorflow (Keras) implementation of Peer loss functions for classification with noisy labels.

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages