femartip / Deep-Generative-Models

Implementation of various generative models in pytorch.

Deep-Generative-Models

Working with pytorch to build different deep generative models.

DL_CNN

• To introduce myself with pytorch. I started by building models of some Deep Learning models, as a basic fully connected feed-forward netowrk and a CNN.

Autoregressive Models

• In this case, using a GRU and a cropus of Shakespear's text. I builded a model to learn how to replicate it.

VAE

• Here I explore different VAE architectures for digit generation with the MNIST dataset. The models I tried are:

1. VAE with continuous latent spaces, modeling a Gaussian distribution.
2. Beta-VAE, adding beta parameter to the VAE to control the desintanglement of the latent space.
3. VAE with discrete latent spaces, 10 classes, one for each digit.

GAN's