Answer-first summary for fast verification
Answer: Import the model into BigQuery, and use SQL for inference.
The question asks for the simplest and most efficient approach for a SQL analyst to use a TensorFlow model stored in Cloud Storage. Option D is correct because BigQuery ML directly supports importing TensorFlow models in SavedModel format from Cloud Storage, allowing SQL-based inference without additional deployment steps. This aligns with the user's SQL analyst role and minimizes complexity. Option A involves unnecessary Vertex AI deployment steps. Option B requires TensorFlow Serving setup and external calls. Option C suggests converting the model, which adds complexity and may not preserve all TensorFlow features. The community discussion confirms D as the consensus, with upvoted comments emphasizing BigQuery ML's native support for TensorFlow models.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
You are a SQL analyst and need to use a TensorFlow customer segmentation model stored in Cloud Storage. You want to use the simplest and most efficient approach. What should you do?
A
Import the model into Vertex AI Model Registry. Deploy the model to a Vertex AI endpoint, and use SQL for inference in BigQuery.
B
Deploy the model by using TensorFlow Serving, and call for inference from BigQuery.
C
Convert the model into a BigQuery ML model, and use SQL for inference.
D
Import the model into BigQuery, and use SQL for inference.