Learn how to publish a GPU-enabled deep learning model as a web service in Azure Machine Learning using Azure Kubernetes Service (AKS) or Azure Machine Learning compute clusters.
Table of Contents
Question
You have an Azure Machine Learning workspace. You build a deep learning model.
You need to publish a GPU-enabled model as a web service.
Which two compute targets can you use? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.
A. Azure Kubernetes Service (AKS)
B. Azure Container Instances (ACI)
C. Local web service
D. Azure Machine Learning compute clusters
Answer
A. Azure Kubernetes Service (AKS)
D. Azure Machine Learning compute clusters
Explanation
To publish a GPU-enabled model as a web service, you need to use a compute target that supports GPU. Azure Kubernetes Service (AKS) and Azure Machine Learning compute clusters both support GPU-enabled virtual machines.
Azure Container Instances (ACI) does not support GPU-enabled virtual machines. Local web service is not a valid option as it is not a managed compute target in Azure Machine Learning.
Designing and Implementing a Data Science Solution on Azure DP-100 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Designing and Implementing a Data Science Solution on Azure DP-100 exam and earn Designing and Implementing a Data Science Solution on Azure DP-100 certification.