Exam DP-100 topic 4 question 4 discussion

Actual exam question from Microsoft's DP-100

Question #: 4
Topic #: 4

You train and register a model in your Azure Machine Learning workspace.
You must publish a pipeline that enables client applications to use the model for batch inferencing. You must use a pipeline with a single ParallelRunStep step that runs a Python inferencing script to get predictions from the input data.
You need to create the inferencing script for the ParallelRunStep pipeline step.
Which two functions should you include? 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)

Show Suggested Answer

Suggested Answer: AD 🗳️

by chaudha4 at May 4, 2021, 3:47 p.m.

Comments

Submit Cancel

chaudha4

Highly Voted 3 years, 2 months ago

https://docs.microsoft.com/en-us/learn/modules/deploy-batch-inference-pipelines-with-azure-machine-learning/2-batch-inference-pipelines

upvoted 16 times

...

rishi_ram

Highly Voted 3 years, 1 month ago

Question was there in June 2021 Exam

upvoted 11 times

...

james2033

Most Recent 9 months, 1 week ago

Selected Answer: AD

run(mini_batch) init() See https://github.com/Azure/MachineLearningNotebooks/tree/master/how-to-use-azureml/machine-learning-pipelines/parallel-run

upvoted 1 times

...

phdykd

11 months, 3 weeks ago

AD. Batch inferencing service requires a scoring script to load the model and use it to predict new values. It must include two functions: init(): Called when the pipeline is initialized. run(mini_batch): Called for each batch of data to be processed. Typically, you use the init function to load the model from the model registry, and use the run function to generate predictions from each batch of data and return the results. The following example script shows this pattern:

upvoted 1 times

...

snegnik

1 year, 1 month ago

In Azure Machine Learning, the inference script is typically a Python script that defines two functions: init() and run(input_data). The init() function is called once when the model is loaded and can be used to perform any initialization tasks, such as loading additional libraries or setting up global variables. The run(input_data) function is called for each input data item and should apply the model to the input data and produce output data

upvoted 1 times

...

phdykd

1 year, 4 months ago

A and D

upvoted 1 times

...

phdykd

1 year, 4 months ago

A and E.

upvoted 1 times

...

Arend78

1 year, 7 months ago

Here's and example of a py script including init() and run(mini_batch): https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/machine-learning-pipelines/parallel-run/Code/digit_identification.py This Python file is loaded by example notebook https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/machine-learning-pipelines/parallel-run/file-dataset-image-inference-mnist.ipynb

upvoted 2 times

...