/denoising-autoencoder

Denoising Autoencoder on MNIST implemented in Tensorflow

Primary LanguageJupyter Notebook

Denoising Autoencoder

This project implements an autoencoder in Tensorflow and investigates its ability to reconstruct images, from the MNIST dataset, after they are corrupted by artificial noise.

Sample:

Setup

Installation: sudo pip install -r requirements.txt
Run: jupyter notebook Denoise_Autoencoder.ipynb