Skip to content

PyTorch implementation of parametric t-SNE

License

Notifications You must be signed in to change notification settings

ginihumer/ptsne-pytorch

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ptsne-pytorch

PyTorch implementation of parametric t-SNE.

While the code was initially based on a TensorFlow implementation by jsilter, everything is now implemented from scratch, including PCA pretraining and different metrics for comparison of probability distributions.

This version of parametric t-SNE makes use of pynndescent to approximate nearest neighbors for an efficient calculation of an approximated distance matrix. This approach as well as the PCA pretraining are borrowed from the openTSNE package.

About

PyTorch implementation of parametric t-SNE

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 98.8%
  • Python 1.2%