This repository contains implementation of Variational Autoencoder and Conditional Variational Autoencoder using Residual and Inverse residual networks
The interesting thing about variational autoencoder which differs it from normal autoencoders is, Variational autoencoder provides a probabilistic manner for describing an observation in latent space.
Thus, rather than building an encoder which outputs a single value to describe each latent state attribute, we'll formulate our encoder to describe a probability distribution for each latent attribute.
This help us to generate new data using the trained Decoder
The further explanation about VAE and CVAE is given in the respective project folders along with links of original paper.
Happy learning :)