Crucial Exams

Microsoft Azure AI Engineer Associate AI-102 Practice Question

You are building an object detection model in the Custom Vision portal that detects surface cracks in concrete. During data collection, you photographed 40 images where the concrete is flawless-no cracks appear anywhere in the frame. Before you perform the initial training, you must decide what to do with these "no-crack" photos. According to Custom Vision object-detection requirements, how should you handle these images?

  • Upload the photos and leave them untagged so they serve as negative examples.

  • Move the photos to a separate image-classification project and mark them with the built-in Negative tag.

  • Draw a bounding box around the entire frame and tag it with a label such as Background.

  • Remove the crack-free photos from the object-detection training set, because each training image must include at least one tagged bounding box.

Microsoft Azure AI Engineer Associate AI-102
Implement computer vision solutions
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