Encoding 2D data and matching to 3D objects

This recipe will break down how to create the autoencoder, including the encoder and decoder, train it, and save it for later use in this chapter. We'll focus on a simplified representation of an autoencoder for educational purposes.

Getting ready

Let's do a directory check and make sure we have all of the same files in our directory at this point:

├── data
├── docker
│   ├── build.sh
│   ├── clean.sh
│   ├── Dockerfile
│   └── kaggle.json
├── out
├── README.md
├── run_autoencoder.sh
└── src
    ├── encoder.py

Also, make sure that you've built the container from the previous chapter since all future recipes will rely on that container being built.

How to do it...

Autoencoders are simple to construct and train—this chapter is meant to make the process simple and understandable. This recipe is meant to introduce the concepts of autoencoders and how they can be used in the context of going from 2D to 3D.

 

 

Code to run a simple encoder

This portion of this...