https://github.com/soumik12345/autoencoders

Implementations of various Autoencoder architectures and applications in Tensorflow
https://github.com/soumik12345/autoencoders

autoencoder deep-learning denoising-autoencoders keras-tensorflow python tensorflow

Last synced: 3 months ago
JSON representation

Implementations of various Autoencoder architectures and applications in Tensorflow

• Host: GitHub
• URL: https://github.com/soumik12345/autoencoders
• Owner: soumik12345
• Created: 2019-05-02T09:33:16.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2019-05-02T14:53:40.000Z (about 7 years ago)
• Last Synced: 2025-03-30T14:42:18.472Z (over 1 year ago)
• Topics: autoencoder, deep-learning, denoising-autoencoders, keras-tensorflow, python, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 1.88 MB
• Stars: 3
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# 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](./1_Simple_Autoencoder/simple-autoencoder.ipynb)

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

![Simple Autoencoder Result](./1_Simple_Autoencoder/simple_autoencoder.png)

### [2. Deep Autoencoder](./2_Deep_Autoencoder/deep-autoencoder.ipynb)

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

![Deep Autoencoder Result](./2_Deep_Autoencoder/deep_autoencoder.png)

### [3. Deep Convolutional Autoencoder](./3_Deep_Convolutional_Autoencoder/deep-convolutional-autoencoder.ipynb)

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

![Deep Convolutional Autoencoder Result](./3_Deep_Convolutional_Autoencoder/conv_autoencoder.png)

### [4. Denoising Autoencoder](./4_Denoising_Autoencoder/denoising-documents-attempt-1.ipynb)

A fully convolutional Autoencoder for Denoising images with noisy backgrounds.

![Noisy Image](./4_Denoising_Autoencoder/noisy.png)

![Denoised Image](./4_Denoising_Autoencoder/denoised.png)