Image Denoising Using AutoEncoders in Keras and Python

Overview

Class Central Tips

In this 1-hour long project-based course, you will be able to: - Understand the theory and intuition behind Autoencoders - Import Key libraries, dataset and visualize images - Perform image normalization, pre-processing, and add random noise to images - Build an Autoencoder using Keras with Tensorflow 2.0 as a backend - Compile and fit Autoencoder model to training data - Assess the performance of trained Autoencoder using various KPIs Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Syllabus

Untitled Module

In this hands-on project, we will train an autoencoder to remove noise from grayscale images. In this practical project we will go through the following tasks: (1) Project Overview, (2) Import libraries and datasets, (3) Perform data visualization, (4) Perform data pre-processing, (5) Understand the theory and intuition behind autoencoders, (6) Build and train autoencoder model, (7) Evaluate trained model performance