What this book covers

Chapter 1, Introducing TensorFlow 2, introduces TensorFlow by looking at a number of snippets of code, illustrating some basic operations. We will have an overview of the modern TensorFlow ecosystem and will see how to install TensorFlow.

Chapter 2, Keras, a High-Level API for TensorFlow 2, takes a look at the Keras API, including some general comments and insights, followed by a basic architecture expressed in four different ways, for training with the MNIST dataset.

Chapter 3, ANN Technologies Using TensorFlow 2, examines a number of technologies that support the creation and use of neural networks. This chapter will cover data presentation to an ANN, layers of an ANN, creating the model, gradient calculations for gradient descent algorithms, loss functions, and saving and restoring models.

Chapter 4, Supervised Machine Learning Using TensorFlow 2, describes examples of the use of TensorFlow for two situations involving linear regression where features are mapped to known labels that have continuous values, allowing predictions on unseen features to be made.

Chapter 5, Unsupervised Learning Using TensorFlow 2, looks at two applications of autoencoders in unsupervised learning: firstly for compressing data; and secondly, for denoising, in other words, removing noise from images.

Chapter 6, Recognizing Images with TensorFlow 2, firstly looks at the Google Quick Draw 1 image dataset, and secondly, at the CIFAR 10 image dataset.

Chapter 7, Neural Style Transfer Using TensorFlow 2, explains how to take a content image and a style image and then produce a hybrid image. We will use layers from the trained VGG19 model to accomplish this.

Chapter 8, Recurrent Neural Networks Using TensorFlow 2, initially discusses the general principles of RNNs and then looks at how to acquire and prepare some text for use by a model.

Chapter 9, TensorFlow Estimators and TensorFlow Hub, firstly looks at an estimator for training the fashion dataset. We will see how estimators provide a simple, intuitive API for TensorFlow. We will also look at a neural network for analyzing the film feedback database, IMDb.

Appendix, Converting from tf1.12 to tf2, contains some tips for converting your tf1.12 files to tf2.