Deploying ML models in Azure

In previous chapters, we learned how to experiment, train, and optimize various ML models to perform classification, regression, anomaly detection, image recognition, text understanding, recommendations, and much more. This section continues on from successfully performing those steps and having a successfully trained a model. Hence, given a trained model, we want to now package and deploy these models with tools in Azure.

Broadly speaking, there are two common approaches to deploying ML models, namely deploying them as synchronous real-time web services and as asynchronous batch-scoring services. Please note that the same model could be deployed as two different services, serving different use cases. The deployment type depends heavily on the batch size and response time of the scoring pattern of the model. Small batch sizes with fast responses require a horizontally scalable real-time web service, whereas large batch sizes and slow response times...