Check out the Pytorch version of the Dirichlet Variational Autoencoder, implemented with Recjection Sampling Variational Inference, available at https://github.com/mayanknagda/neural-topic-models.
Another Pytorch version of the DVAE using pathwise gradients is available here: https://github.com/ahoho/topics.
Implementation of different Dirichlet Variational Autoencoders. Accepted in JMLR 2019
Implements the following methods
- Dirichlet-Autoencoder with "implicit gradients"
- Dirichlet-Autoencoder with RSVI
- Dirichlet-Autoencoder with inverse CDF
- Dirichlet-Autoencoder with Weibull distribution
python3 nvdm_dirichlet_rsvi.py 2
python3 nvdm_dirichlet_implicitGradients.py 4
Only with current Tensorflow version. Need to install tensorflow-probability
python3 nvdm_dirichlet_invCDF.py 4
python3 nvdm_dirichlet_weibull.py 4
See example dataset in data folder