Technical requirements
One of the first things you'll notice is that AutoML is very resource-intensive, so accessing a GPU is a must if you want to replicate and extend the recipes we'll discuss in this chapter. Also, because we'll be using AutoKeras in all the examples provided, install it as follows:
$> pip install git+https://github.com/keras-team/keras-tuner.git@1.0.2rc2 autokeras pydot graphviz
The AutoKeras version we'll be using in this chapter only works with TensorFlow 2.3, so ensure you have it installed as well (if you prefer, you can create a different environment altogether). In the Getting ready section of each recipe, you'll find any preparatory information needed. As usual, the code shown in this chapter is available at https://github.com/PacktPublishing/Tensorflow-2.0-Computer-Vision-Cookbook/tree/master/ch11.
Check out the following link to see the Code in Action video:
