Chapter 4
Leveraging a Deep Learning Framework
IN THIS CHAPTER
Understanding frameworks
Using a basic framework
Working with TensorFlow
This chapter looks at deep learning frameworks because using a deep learning framework can greatly reduce the time, cost, and complexity of developing a deep learning solution. Of course, you must begin by defining the term framework, which is an abstraction that provides generic functionality that your application code modifies. Unlike a library that runs within your application, when you’re using a framework, your application runs within it. You can’t modify basic framework functionality, which means that you have a stable environment in which to work, but most frameworks offer some level of extensibility. Frameworks are generally specific to a particular need, such as the web frameworks used to create online applications. Consequently, even though deep learning frameworks have many characteristics of frameworks in general, they also provide specific functionality that this chapter explores.
Not everyone uses the same ideas and concepts for running deep learning applications. In addition, not every organization wants to invest in a complex deep ...