You use the Azure Machine Learning designer to create and run a training pipeline. The pipeline must be run every night to inference predictions from a large volume of files. The folder where the…

Question

Options

• ACreate a batch inference pipeline
• BSet the compute target for the pipeline to an inference cluster
• CCreate a real-time inference pipeline
• DClone the pipeline

• A
  75% (46)
• B
  16% (10)
• C
  3% (2)
• D
  5% (3)

Explanation

The correct answer is A: Create a batch inference pipeline. The scenario describes nightly processing of a large volume of files stored in a folder dataset-a classic batch inferencing workload. In Azure ML Designer, you create a batch inference pipeline (distinct from a real-time inference pipeline) by cloning the training pipeline and adding batch scoring components. This can then be published as a REST endpoint that can be triggered on a schedule. Option B is wrong because inference clusters are for real-time (AKS) deployments. Option C (real-time inference pipeline) is for online, low-latency single-request predictions, not large file volumes. Option D (clone the pipeline) alone is incomplete-cloning is a step within the process, not the solution itself.

No community discussion yet for this question.