AI-102 Implement computer vision solutions Practice Question
You are building a mobile app that allows users to take a photo of a product and get detailed information. The app uses Azure AI Custom Vision to classify products. You need to ensure low latency for inference. What should you do?
⚠ Common exam trap
Test-takers frequently assume cloud-based solutions (like Azure Front Door or Vision API) are always faster, but Microsoft explicitly tests the understanding that on-device inference eliminates network latency and is the optimal choice for low-latency mobile scenarios.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Export the Custom Vision model as a TensorFlow model and run on-device
Exporting the Custom Vision model as a TensorFlow model and running it on-device eliminates network latency entirely. Inference happens locally on the mobile device, which provides the lowest possible latency for real-time classification, especially when network connectivity is poor or inconsistent.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the number of training iterations
Why it's wrong here
Training iterations tune model accuracy, not inference speed; they add training time and can even enlarge the model. Latency depends on where inference runs, so exporting the model to a mobile-friendly format or hosting a real-time endpoint addresses it. More iterations would suit improving classification accuracy on hard-to-distinguish products.
- ✗
Use the Azure AI Vision API directly
Why it's wrong here
The pre-built Azure AI Vision API returns generic labels and captions, not your product taxonomy, so it cannot classify your specific catalogue. Custom Vision exists precisely to train on your labelled product images. Azure AI Vision suits general image description, OCR or face detection where bespoke categories are unnecessary.
- ✗
Use Azure Front Door to cache results
Why it's wrong here
Front Door caches HTTP responses at edge points of presence; Custom Vision inference is a POST with image payloads, which are not cacheable, so latency is unchanged. It is tempting because Front Door genuinely accelerates globally distributed cacheable web content and APIs.
- ✓
Export the Custom Vision model as a TensorFlow model and run on-device
Why this is correct
Exporting the Custom Vision model as TensorFlow and running inference on-device removes the network round trip to the Azure endpoint entirely, which is the dominant latency source for a mobile app. Local execution satisfies the low-latency constraint.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.