Evaluating and Publishing Custom Models Quiz

5 questions • Pass: 70% • +25 pts

Quiz covering Custom Vision Models

Evaluating and Publishing Custom Models Quiz

5 questions | Pass: 70% | Earn 25 points

Questions in this quiz

A preview of the 5 questions covered. Start the quiz above to answer them, check your score, and read the explanations.

  1. 1

    Which metric in Custom Vision is used to measure the percentage of actual positive predictions that were correct?

  2. 2

    After training a Custom Vision model, you notice a low Recall score for a specific tag. What is the most effective way to improve this?

  3. 3

    You have published your model to a Prediction Resource. What is required to call the prediction endpoint from an external application?

  4. 4

    Why would you adjust the Probability Threshold on the Custom Vision performance tab?

  5. 5

    When exporting a Custom Vision model for mobile deployment (e.g., TensorFlow Lite or CoreML), what limitation must you consider regarding model domains?