Skip to content

label-smooth, amsoftmax, focal-loss, triplet-loss. Maybe useful

License

Notifications You must be signed in to change notification settings

xy524679663/pytorch-loss

 
 

Repository files navigation

pytorch-loss

My implementation of label-smooth, amsoftmax, focal-loss, dual-focal-loss, triplet-loss, giou-loss, affinity-loss, pc_softmax_cross_entropy, and dice-loss(both generalized soft dice loss and batch soft dice loss). Maybe this is useful in my future work.

Also tried to implement swish and mish activation functions.

Additionally, one-hot function is added.

Newly add an "Exponential Moving Average(EMA)" operator.

For those who happen to find this repo, if you see errors in my code, feel free to open an issue to correct me.

About

label-smooth, amsoftmax, focal-loss, triplet-loss. Maybe useful

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%