Question 26
Domain 4As the lead ML Engineer for your company, you are responsible for building ML models to digitize scanned customer forms. You have developed a TensorFlow model that converts the scanned images into text and stores them in Cloud Storage. You need to use your ML model on the aggregated data collected at the end of each day with minimal manual intervention. What should you do?
Correct answer: A
Explanation
AI Platform batch prediction is designed for offline inference on stored data, so it fits “the aggregated data collected at the end of each day” with minimal manual intervention. It lets you run your TensorFlow model on files in Cloud Storage and write the predictions back in bulk, instead of invoking the model one record at a time.
Why each option is right or wrong
A. Use the batch prediction functionality of Al Platform.
AI Platform batch prediction is the offline inference path for data already sitting in Cloud Storage, which matches the fact pattern of end-of-day aggregated files rather than live requests. It is specifically intended for TensorFlow models and runs as a managed job with no per-record orchestration, so it minimizes manual intervention compared with deploying an online endpoint for continuous calls.
B. Create a serving pipeline in Compute Engine for prediction.
C. Use Cloud Functions for prediction each time a new data point is ingested.
D. Deploy the model on Vertex AI and create a version of it for online inference.