7 A deep dive on Keras
This chapter covers
- The different ways to create Keras models: the
Sequentialclass, the Functional API, and model subclassing - How to use the built-in Keras training and evaluation loops, including how to use custom metrics and custom losses
- Using Keras callbacks to further customize how training proceeds
- Using TensorBoard for monitoring your training and evaluation metrics over time
- How to write your own training and evaluation loops from scratch
You’re starting to have some amount of experience with Keras. You’re familiar with the Sequential model, Dense layers, and built-in APIs for training, evaluation, and inference—compile(), fit(), evaluate(), and predict(). You’ve even learned in chapter 3 how to inherit from the Layer class to create custom layers, and how to use the gradient APIs in TensorFlow, JAX, and PyTorch to implement a step-by-step training loop.
In the coming chapters, we’ll dig into computer vision, timeseries forecasting, natural language processing, and generative deep learning. These complex applications will require much more than a Sequential architecture and the default fit() loop. So let’s first turn you into a Keras expert! In this chapter, you’ll get a complete overview of the key ways to work with Keras APIs: everything you’re going to need to handle the advanced deep learning use cases you’ll encounter next.