Working with the Azure ML service
The Azure ML service trains and delivers a model as a containerized application. When we have built the model, we can easily deploy it as a MaaS so that it is very simple to deploy to the Azure cloud. The Azure ML service integrates a user-friendly interface, a computational cluster, experiment tracking and serving with MLflow, and pipeline management.
The basic steps to develop our analytical model with the Azure ML service are as follows:
- Preparing the data
- Developing the model with a rich tool, such as Jupyter Notebook, Visual Studio Code, or Azure Notebooks
- Training and testing the model, using the computational capabilities of Azure ML
- Registering the model
- Deploying the model as a microservice
When the model is a web service, we can call from different sources (such as Azure Functions, Azure IoT Hub, or Azure Stream Analytics) and integrate them into our business process. The following diagram demonstrates these...
