You need to execute a batch prediction on 100 million records in a BigQuery table with a custom TensorFlow DNN regressor model, and then store the predicted results in a BigQuery table. You want to minimize the effort required to build this inference pipeline. What should you do?
To execute a batch prediction on 100 million records in a BigQuery table with a custom TensorFlow DNN regressor model, the most suitable approach is to utilize a Dataflow pipeline. By loading the TensorFlow SavedModel in the Dataflow pipeline, using the BigQuery I/O connector with a custom function to perform the inference within the pipeline, and writing the results back to BigQuery, you can effectively handle large-scale data and leverage the distributed processing capabilities of Dataflow. This method ensures efficiency and scalability for handling a large volume of data and performing complex model inferences.
A should work with less effort - https://cloud.google.com/bigquery-ml/docs/making-predictions-with-imported-tensorflow-models#api - https://towardsdatascience.com/how-to-do-batch-predictions-of-tensorflow-models-directly-in-bigquery-ffa843ebdba6
for this: https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-inference-overview Predict the label, either a numerical value for regression tasks or a categorical value for classification tasks on DNN regresion
https://cloud.google.com/bigquery-ml/docs/making-predictions-with-imported-tensorflow-models
Went with A
Simplest doesn't mean it is the most effecient/optimal. If I follow the Best practices offered by Google for Serving / Inference Pipeline I would go with Vertex AI predictions. Read More for correct details : https://cloud.google.com/architecture/ml-on-gcp-best-practices#machine-learning-development
Agreed, i'll also go with C.
Answer A as the simplest
ml.predict: https://cloud.google.com/bigquery-ml/docs/making-predictions-with-imported-tensorflow-models#api --> A
Went with C
BigQuery ML might not support custom TensorFlow DNN models directly.