AI-100 · Question #118
You have a Face API solution that updates in real time. A pilot of the solution runs successfully on a small dataset. When you attempt to use the solution on a larger dataset that continually…
The correct answer is B. Separate training into an independent pipeline and schedule the pipeline to run daily. Incorrect Answers: A: The purpose of Computer Vision is to inspects each image associated with an incoming article to (1) scrape out written words from the image and (2) determine what types of objects are present in the image. C: The Bing API provides an experience similar to…
Question
You have a Face API solution that updates in real time. A pilot of the solution runs successfully on a small dataset. When you attempt to use the solution on a larger dataset that continually changes, the performance degrades, slowing how long it takes to recognize existing faces. You need to recommend changes to reduce the time it takes to recognize existing faces without increasing costs. What should you recommend?
Options
- AChange the solution to use the Computer Vision API instead of the Face API.
- BSeparate training into an independent pipeline and schedule the pipeline to run daily.
- CChange the solution to use the Bing Image Search API instead of the Face API.
- DDistribute the face recognition inference process across many Azure Cognitive Services instances.
How the community answered
(21 responses)- A5% (1)
- B81% (17)
- C10% (2)
- D5% (1)
Explanation
Incorrect Answers: A: The purpose of Computer Vision is to inspects each image associated with an incoming article to (1) scrape out written words from the image and (2) determine what types of objects are present in the image. C: The Bing API provides an experience similar to Bing.com/search by returning search results that Bing determines are relevant to a user's query. The results include Web pages and may also include images, videos, and more. D: That would increase cost. https://github.com/Azure/cognitive-services
Topics
Community Discussion
No community discussion yet for this question.