← Back to curriculum

Module 7 — CV production & deployment

Module 7 quiz & review

15 interactive multiple-choice questions on serving, quantization, and production monitoring with review links.

~40 min read + exercises

Before we begin

Aim for at least 12 out of 15 before the deployment project.


Multiple choice quiz

Interactive quiz

Pick one answer per question. Feedback appears immediately — take your time before clicking.

0 / 15 correct·0 answered
  1. Question 1 of 15

    Preprocessing for vision inference should typically:

    Answer options for question 1
  2. Question 2 of 15

    Batching inference requests improves throughput when:

    Answer options for question 2
  3. Question 3 of 15

    Post-training INT8 quantization:

    Answer options for question 3
  4. Question 4 of 15

    TensorRT optimizes models by:

    Answer options for question 4
  5. Question 5 of 15

    Input distribution shift in production means:

    Answer options for question 5
  6. Question 6 of 15

    Shadow deployment for a new vision model:

    Answer options for question 6
  7. Question 7 of 15

    ONNX Runtime as inference backend:

    Answer options for question 7
  8. Question 8 of 15

    Knowledge distillation for edge deployment:

    Answer options for question 8
  9. Question 9 of 15

    Concept drift occurs when:

    Answer options for question 9
  10. Question 10 of 15

    Warm-up requests after deploying a vision API:

    Answer options for question 10
  11. Question 11 of 15

    TFLite delegates on mobile:

    Answer options for question 11
  12. Question 12 of 15

    Human-in-the-loop for vision drift response:

    Answer options for question 12
  13. Question 13 of 15

    gRPC vs REST for vision inference:

    Answer options for question 13
  14. Question 14 of 15

    Pruning neural networks removes:

    Answer options for question 14
  15. Question 15 of 15

    When to fine-tune vs full retrain on drift:

    Answer options for question 15

What's next

Project: deploy a vision inference API