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.