Skip to content

I explore a few variations of autoencoders (AE) and variational autoencoders (VAE) for tasks such as image generation and denoising.

Notifications You must be signed in to change notification settings

vigkneshvr/Experimenting-with-Autoencoder-Variational-Autoencoder-models

Repository files navigation

Experimenting-with-Autoencoder-Variational-Autoencoder-models

I explore a few variations of autoencoders (AE) and variational autoencoders (VAE) for tasks such as image generation and denoising.

Environment setup- I use few basic python libraries such as numpy, torch, torchvision, scipy, PIL, matplotlib, torchsummary and other builtin packages such as math for this work. These can installed individually using pip/conda in your local system.

Details of experiments:

  1. Vanilla autoencoder that can generate new images of handwritten digits that are similar to the images in the MNIST dataset. image

  2. Denoising Convolutional Autoencoder that is capable of generating clear images from noisy inputs. image

  3. Fully Connected Variational Autoencoder (FC-VAE) for generating new images of handwritten digits. image

References: [1] https://avandekleut.github.io/vae/ [2] https://github.com/seloufian/Deep-Learning-Computer-Vision/blob/master/eecs498-007/A6/variational_autoencoders.ipynb

About

I explore a few variations of autoencoders (AE) and variational autoencoders (VAE) for tasks such as image generation and denoising.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published