soumik12345 / Autoencoders

Implementations of various Autoencoder architectures and applications in Tensorflow

Autoencoders

Autoencoding is a data compression algorithm where the compression and decompression functions are

1. data-specific
2. lossy
3. learned automatically from examples rather than engineered by a human.

In almost all contexts where the term Autoencoder is used, the compression and decompression functions are implemented with neural networks.

1. Simple Autoencoder

The simples possible Autoencoder in which the encoder and decoder consists of a single fully-connected layer each.

2. Deep Autoencoder

A Deep Autoencoder in which both the encoder and decoder consists of multiple fully-connected layer each.

3. Deep Convolutional Autoencoder

A Deep Autoencoder in which both the encoder and decoder consists of multiple fully-convolutional layer each.

4. Denoising Autoencoder

A fully convolutional Autoencoder for Denoising images with noisy backgrounds.