Book Image

Mastering TensorFlow 1.x

Book Image

Mastering TensorFlow 1.x

Overview of this book

TensorFlow is the most popular numerical computation library built from the ground up for distributed, cloud, and mobile environments. TensorFlow represents the data as tensors and the computation as graphs. This book is a comprehensive guide that lets you explore the advanced features of TensorFlow 1.x. Gain insight into TensorFlow Core, Keras, TF Estimators, TFLearn, TF Slim, Pretty Tensor, and Sonnet. Leverage the power of TensorFlow and Keras to build deep learning models, using concepts such as transfer learning, generative adversarial networks, and deep reinforcement learning. Throughout the book, you will obtain hands-on experience with varied datasets, such as MNIST, CIFAR-10, PTB, text8, and COCO-Images. You will learn the advanced features of TensorFlow1.x, such as distributed TensorFlow with TF Clusters, deploy production models with TensorFlow Serving, and build and deploy TensorFlow models for mobile and embedded devices on Android and iOS platforms. You will see how to call TensorFlow and Keras API within the R statistical software, and learn the required techniques for debugging when the TensorFlow API-based code does not work as expected. The book helps you obtain in-depth knowledge of TensorFlow, making you the go-to person for solving artificial intelligence problems. By the end of this guide, you will have mastered the offerings of TensorFlow and Keras, and gained the skills you need to build smarter, faster, and efficient machine learning and deep learning systems.
Table of Contents (21 chapters)
19
Tensor Processing Units

TensorFlow 101

TensorFlow is one of the popular libraries for solving problems with machine learning and deep learning. After being developed for internal use by Google, it was released for public use and development as open source. Let us understand the three models of the TensorFlow: data model, programming model, and execution model.

TensorFlow data model consists of tensors, and the programming model consists of data flow graphs or computation graphs. TensorFlow execution model consists of firing the nodes in a sequence based on the dependence conditions, starting from the initial nodes that depend on inputs.

In this chapter, we will review the elements of TensorFlow that make up these three models, also known as the core TensorFlow.

We will cover the following topics in this chapter:

  • TensorFlow core
    • Tensors
    • Constants
    • Placeholders
    • Operations
    • Creating tensors from Python objects
    • Variables
    • Tensors generated from library functions
  • Data flow graph or computation graph
    • Order of execution and lazy loading
    • Executing graphs across compute devices - CPU and GPGPU
    • Multiple graphs
  • TensorBoard overview
This book is written with a practical focus in mind, hence you can clone the code from the book's GitHub repository or download it from Packt Publishing. You can follow the code examples in this chapter with the Jupyter Notebook ch-01_TensorFlow_101 included in the code bundle.