Image Compression Using Autoencoders in Keras

Introduction

Autoencoders are a deep learning model for transforming data from a high-dimensional space to a lower-dimensional space. They work by encoding the data, whatever its size, to a 1-D vector. This vector can then be decoded to reconstruct the original data (in this case, an image). The more accurate the autoencoder, the closer the generated data is to the original.

In this tutorial we’ll explore the autoencoder architecture and see how we can apply this model to compress images from the MNIST dataset using TensorFlow and Keras. In particular, we’ll consider:

• Discriminative vs. Generative Modeling
• How Autoencoders Work
• Building an Autoencoder in Keras
  • Building the Encoder
  • Building the Decoder
• Training
• Making Predictions
• Complete Code
• Conclusion