Answer-first summary for fast verification
Answer: Extend your test dataset with images of the newer products when they are introduced to retraining.
The correct answer is B: Extend your test dataset with images of the newer products when they are introduced to retraining. This approach ensures that the test dataset remains representative of the real-world data your model will encounter, including both existing and new products. Keeping the original test set unchanged (option A) would ignore the new products, leading to a less accurate evaluation on how well the model performs with them. Replacing the test set with only new products (option C) would neglect the need to ensure the model still performs well on existing products. Waiting until evaluation metrics drop below a threshold (option D) is a reactive rather than proactive approach and does not leverage the AI Platform's continuous evaluation service effectively from the beginning.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are working as a machine learning engineer for an online retail company that is developing a visual search engine to identify whether an image contains one of the company's products. You have implemented an end-to-end ML pipeline on Google Cloud to handle this task. With new product releases anticipated, you have set up a retraining functionality in the pipeline to incorporate new data into your ML models. Additionally, you aim to utilize AI Platform's continuous evaluation service to maintain high accuracy levels on the test dataset. Considering these requirements, how should you manage your test dataset when integrating images of new products into the retraining process?
A
Keep the original test dataset unchanged even if newer products are incorporated into retraining.
B
Extend your test dataset with images of the newer products when they are introduced to retraining.
C
Replace your test dataset with images of the newer products when they are introduced to retraining.
D
Update your test dataset with images of the newer products when your evaluation metrics drop below a pre-decided threshold.
No comments yet.