Anyone who has ever tried to write code for neural networks in Python using only NumPy, knows how cumbersome it is. Writing code for a simple one-layer feedforward network requires more than 40 lines, made more difficult as you add the number of layers both in terms of writing code and execution time.

TensorFlow makes it all easier and faster reducing the time between the implementation of an idea and deployment. In this book, you will learn how to unravel the power of TensorFlow to implement deep neural networks.

In this chapter, we will cover the following topics:

• Installing TensorFlow
• Hello world in TensorFlow
• Understanding the TensorFlow program structure
• Working with constants, variables, and placeholders
• Performing matrix manipulations using TensorFlow
• Using a data flow graph
• Migrating from 0.x to 1.x
• Using XLA to enhance computational performance
• Invoking CPU/GPU devices
• TensorFlow for deep learning
• Different Python packages required for DNN-based problems