Skip to content

This repository represents a basic implementation of the paper "Riemannian Geometry of Deep Generative Models", along with the results on two datasets namely MNIST and CelebA.

License

Notifications You must be signed in to change notification settings

shagunuppal/Riemannian_Geometry_of_Deep_Generative_Models

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

87 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Riemannian Geometry of Deep Generative Models

This work was done by Sarthak Bhagat and Shagun Uppal in their B.Tech Thesis under Prof. Dr. Saket Anand.

This repository provides partial implementation of our paper Geometry of Deep Generative Models for Disentangled Representations. This repository also provides a basic implementation of the paper Riemannian Geometry of Deep Generative Models on MNIST as well as CelebA.

If you find this code useful in your research, don't forget to cite:

@article{Shukla2019GeometryOD,
  title={Geometry of Deep Generative Models for Disentangled Representations},
  author={Ankita Shukla and Suresh Uppal and Sarthak Bhagat and Saket Anand and Pavan K. Turaga},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.06964}
}

Requirements

  1. Python 2/3
  2. Pytorch
  3. Tensorboard
  4. Tensorflow
  5. Cmake
  6. ONNX

Steps to install ONNX

git clone https://github.com/onnx/onnx.git
cd onnx
git submodule update --init
python setup.py install

Results

About

This repository represents a basic implementation of the paper "Riemannian Geometry of Deep Generative Models", along with the results on two datasets namely MNIST and CelebA.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published