Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

You have trained an object-detection project by using Custom Vision in Azure AI Vision. The model will be used on production-line cameras inside a factory network that has no reliable Internet connectivity. Inference must execute locally with less than 100 ms latency and without sending images to the cloud. Which deployment approach should you use?

  • Convert the model to ONNX and deploy it to a managed online endpoint in Azure Machine Learning.

  • Export the model and run it in the Azure AI Vision Docker container on an Azure Stack Edge or IoT Edge device within the factory.

  • Publish the model to the Custom Vision cloud prediction endpoint and invoke it from the factory over HTTPS.

  • Import the model into an Azure OpenAI resource and call it with chat completions from the production-line controllers.

Microsoft Azure AI Engineer Associate AI-102
Plan and manage an Azure AI solution
Your Score:
Settings & Objectives
Random Mixed
Questions are selected randomly from all chosen topics, with a preference for those you haven’t seen before. You may see several questions from the same objective or domain in a row.
Rotate by Objective
Questions cycle through each objective or domain in turn, helping you avoid long streaks of questions from the same area. You may see some repeat questions, but the distribution will be more balanced across topics.

Check or uncheck an objective to set which questions you will receive.

Wipe Score
Bash, the Crucial Exams Chat Bot
AI Bot