Variational Autoencoder and a Disentangled version (beta-VAE).
-
The Variational Autoencoder is a Generative Model. Its goal is to learn the distribution of a Dataset, and then generate new (unseen) data points from the same distribution.
-
Another form of a Variational Autoencoder is the beta-VAE. The difference between the Vanilla VAE and the beta-VAE is in the loss function of the latter: The KL-Divergence term is multiplied with a hyperprameter beta. This introduces a disentanglement to the idea of the VAE, as in many cases it allows a smoother and more "continuous" transition of the output data, for small changes in the latent vector z. More information on this topic can be found in the sources section below.
$ pip install -r requirements.txt$ python3 main.py -c <config_file_path> -v VAE$ python3 main.py -c <config_file_path> -v B-VAEExamples of configuration files can be found in the config directory.