Skip to content

code for "Isolating Sources of Disentanglement in Variational Autoencoders".

License

Notifications You must be signed in to change notification settings

chingyaoc/beta-tcvae

 
 

Repository files navigation

beta-TCVAE

This repository contains cleaned-up code for reproducing the quantitative experiments in Isolating Sources of Disentanglement in Variational Autoencoders [arxiv].

Usage

To train a model:

python vae_quant.py --dataset [shapes/faces] --beta 6 --tcvae

Specify --conv to use the convolutional VAE. We used a mlp for dSprites and conv for 3d faces. To see all options, use the -h flag.

The main computational difference between beta-VAE and beta-TCVAE is summarized in these lines.

To evaluate the MIG of a model:

python disentanglement_metrics.py --checkpt [checkpt]

To see all options, use the -h flag.

Datasets

dSprites

Download the npz file from here and place it into data/.

3D faces

We cannot publicly distribute this due to the license.

Contact

Email [email protected] if you have questions about the code/data.

Bibtex

@inproceedings{chen2018isolating,
  title={Isolating Sources of Disentanglement in Variational Autoencoders},
  author={Chen, Ricky T. Q. and Li, Xuechen and Grosse, Roger and Duvenaud, David},
  booktitle = {Advances in Neural Information Processing Systems},
  year={2018}
}

About

code for "Isolating Sources of Disentanglement in Variational Autoencoders".

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%