7 Working with Keras: a deep dive

This chapter covers:

The different ways to create Keras models: the Sequential class, the Functional API, and Model subclassing
How to use the built-in Keras training & 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 & evaluation metrics over time
How to write your own training & 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 TensorFlow GradientTape 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.

7.1 A spectrum of workflows

7.2 Different ways to build Keras models

7.2.1 The Sequential model

7.2.2 The Functional API

7.2.3 Subclassing the `Model` class

7.2.4 Mixing and matching different components

7.2.5 Remember: use the right tool for the job

7.3 Using built-in training and evaluation loops

7.3.1 Writing your own metrics

7.3.2 Using Callbacks

7.3.3 Writing your own callbacks

7.3.4 Monitoring and visualization with TensorBoard

7.4 Writing your own training and evaluation loops

7.4.1 Training versus inference

7.4.2 Low-level usage of metrics

7.4.3 A complete training and evaluation loop

7.5 Chapter summary