Book Image

What's New in TensorFlow 2.0

By : Ajay Baranwal, Alizishaan Khatri, Tanish Baranwal
Book Image

What's New in TensorFlow 2.0

By: Ajay Baranwal, Alizishaan Khatri, Tanish Baranwal

Overview of this book

TensorFlow is an end-to-end machine learning platform for experts as well as beginners, and its new version, TensorFlow 2.0 (TF 2.0), improves its simplicity and ease of use. This book will help you understand and utilize the latest TensorFlow features. What's New in TensorFlow 2.0 starts by focusing on advanced concepts such as the new TensorFlow Keras APIs, eager execution, and efficient distribution strategies that help you to run your machine learning models on multiple GPUs and TPUs. The book then takes you through the process of building data ingestion and training pipelines, and it provides recommendations and best practices for feeding data to models created using the new tf.keras API. You'll explore the process of building an inference pipeline using TF Serving and other multi-platform deployments before moving on to explore the newly released AIY, which is essentially do-it-yourself AI. This book delves into the core APIs to help you build unified convolutional and recurrent layers and use TensorBoard to visualize deep learning models using what-if analysis. By the end of the book, you'll have learned about compatibility between TF 2.0 and TF 1.x and be able to migrate to TF 2.0 smoothly.
Table of Contents (13 chapters)
Title Page

Creating models using tf.keras 2.0

In this section, we will learn three major types of tf.keras APIs to define neural network layers, namely the following:

  • Sequential APIs: These are based on stacking NN layers, which could be either dense (feedforward), convolutional, or recurrent layers)
  • Functional APIs: These help to build complex models
  • Model subclassing APIs: These are fully customizable models; these APIs are flexible and require care to write

The following diagram shows a Python class hierarchy for these three APIs to build tf.keras.Model:

Let's create a relatively simple neural network to build a handwriting recognition classifier using MNIST data. We will use this example to demonstrate all three sets of APIs.

MNIST data contains 50,000 training datasets and 10,000 test datasets. These datasets have images of numerical digits and they are labeled to 10 classes...