
Explanation

Box 1: Azure Container Registry
Azure Container Registry enables storage of images for all types of Docker container deployments including DC/OS, Docker Swarm and Kubernetes. The scoring images are deployed as containers on Azure Kubernetes Service and used to run the scoring script. The image used here is created by Machine Learning from the trained model and scoring script, and then is pushed to the Azure Container Registry.
Box 2: Azure Kubernetes Services
Azure Kubernetes Service (AKS) is used to deploy the application on a Kubernetes cluster. AKS simplifies the deployment and operations of Kubernetes. The cluster can be configured using CPU-only VMs for regular Python models or GPU-enabled VMs for deep learning models.
This reference architecture shows how to deploy Python models as web services to make real-time predictions using the Azure Machine Learning.

References:
https://docs.microsoft.com/sv-se/azure/architecture/reference-architectures/ai/realtime-scoring-python