Google Cloud Professional Machine Learning Engineer — Question 192

You are implementing a batch inference ML pipeline in Google Cloud. The model was developed using TensorFlow and is stored in SavedModel format in Cloud Storage. You need to apply the model to a historical dataset containing 10 TB of data that is stored in a BigQuery table. How should you perform the inference?

Answer options

• A. Export the historical data to Cloud Storage in Avro format. Configure a Vertex AI batch prediction job to generate predictions for the exported data
• B. Import the TensorFlow model by using the CREATE MODEL statement in BigQuery ML. Apply the historical data to the TensorFlow model
• C. Export the historical data to Cloud Storage in CSV format. Configure a Vertex AI batch prediction job to generate predictions for the exported data
• D. Configure a Vertex AI batch prediction job to apply the model to the historical data in BigQuery

Correct answer: B

Explanation

The correct answer is B because using the CREATE MODEL statement in BigQuery ML allows for direct application of the TensorFlow model on the data stored in BigQuery, which is efficient for large datasets. Options A and C involve exporting data to Cloud Storage, which adds unnecessary steps, while option D does not utilize the TensorFlow model directly as needed.