Chapter 6: Key Principles for Deploying Your ML System
In this chapter, you will learn the fundamental principles for deploying machine learning (ML) models in production and implement the hands-on deployment of ML models for the business problem we have been working on. To get a comprehensive understanding and first-hand experience, we will deploy ML models that were trained and packaged previously (in Chapter 4, Machine Learning Pipelines, and Chapter 5, Model Evaluation and Packaging) using the Azure ML service on two different deployment targets: an Azure container instance and a Kubernetes cluster.
We will also learn how to deploy ML models using an open source framework called MLflow that we have already worked with. This will enable you to get an understanding of deploying ML models as REST API endpoints on diverse deployment targets using two different tools (the Azure ML service and MLflow). This will equip you with the skills required to deploy ML models for any given...
