Discover the essential steps for deploying your trained models—deploying inference pipelines, setting up compute clusters, and testing pipelines for seamless functionality in AI projects.
Table of Contents
Question
You trained your model and are ready to deploy.
What steps do you need to execute for a model deployment?
Select all that apply.
A. Test the service
B. Deploy inference pipeline
C. Create compute clusters
D. Create and test inference pipeline
E. Create inference clusters
F. Deploy training pipeline
Answer
A. Test the service
B. Deploy inference pipeline
D. Create and test inference pipeline
E. Create inference clusters
Explanation
After we train the model, we need to create a new production pipeline – inference pipeline. We can do this by selecting the “Real-time inference pipeline” option from the “Create inference pipeline” dropdown in Azure ML Designer with the training pipeline open. After we create and test the inference pipeline, we need to deploy it to the created before inference AKC clusters. And finally, test the new service.
Option C is incorrect. We are creating Compute clusters for the training model.
Option F is incorrect. We need to deploy an inference model, not the training model.
Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.
