Section 4 – Model Optimization and Deployment

This part introduces ways to improve the efficiency and speed of a model and its pipeline. We will start with the concept of model runtime, and then model optimization, followed by using TensorFlow Serving to serve models as a Docker container via a RESTful API.

This section comprises the following chapters:

• Chapter 7, Model Optimization
• Chapter 8, Best Practices for Model Training and Performance
• Chapter 9, Serving a TensorFlow Model