Preparations for model deployments
Throughout this book, we have learned how to experiment with, train, and optimize various ML models to perform classification, regression, anomaly detection, image recognition, text understanding, and recommendations. Having successfully trained our ML model, we now want to package and deploy this model to production with tools in Azure.
In this section, we will learn about the most important preparation steps that are required to deploy a trained model to production using Azure Machine Learning. We will discuss the different components involved in a standardized deployment, customizing a deployment, auto-deployments, and how to choose the right deployment target. Let's delve into it.
Understanding the components of an ML model
Independent of the use case, there are similar preparation steps required for putting an ML model to production. First, the trained model needs to be registered in the model registry. This will allow us to track...