Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might…

Question

Options

• AYes
• BNo

• A
  78% (50)
• B
  22% (14)

Explanation

Option A is correct because this is exactly the proper workflow for updating an Azure Custom Vision classifier with new data: upload the new labeled images to the existing project, retrain the model so it learns the new patterns, and then publish the updated iteration so the application can use it via the prediction endpoint.

There are no distractors here - this is a Yes/No question where B ("No") would be wrong because skipping any of these steps (adding labels, retraining, or publishing) would either fail to incorporate the new species or leave the old model in production.

Memory tip: Think of it as "Label → Train → Publish" - the three-step Custom Vision update cycle. If any step is missing (e.g., retraining but not publishing, or adding images without labels), the goal is not fully met. This question includes all three steps, so it's a complete and valid solution.

No community discussion yet for this question.