Answer-first summary for fast verification
Answer: run(mini_batch), init()
The correct functions for a ParallelRunStep inference script are init() and run(mini_batch). The init() function is called once during pipeline initialization to load the model and perform setup tasks, while run(mini_batch) is called for each batch of data to generate predictions. This is confirmed by the community consensus (100% AD), official Microsoft documentation links provided in the discussion, and Azure Machine Learning Notebook examples. Other options like main(), batch(), and score(mini_batch) are not required or standard for ParallelRunStep scripts.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are creating an inference script for a ParallelRunStep in an Azure Machine Learning pipeline. The script is for batch inferencing using a registered model.
Which two functions must be included in the script? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.
A
run(mini_batch)
B
main()
C
batch()
D
init()
E
score(mini_batch)
No comments yet.