Microsoft DP-100 Exam - Topic 1 Question 67 Discussion

Actual exam question for Microsoft's DP-100 exam

Question #: 67
Topic #: 1

You use Azure Machine Learning designer to create a training pipeline for a regression model.

You need to prepare the pipeline for deployment as an endpoint that generates predictions asynchronously for a dataset of input data values.

What should you do?

AClone the training pipeline.

BCreate a batch inference pipeline from the training pipeline.

CCreate a real-time inference pipeline from the training pipeline.

DReplace the dataset in the training pipeline with an Enter Data Manually module.

Show Suggested Answer

Suggested Answer: C

You must first convert the training pipeline into a real-time inference pipeline. This process removes training modules and adds web service inputs and outputs to handle requests.

Incorrect Answers:

A: Use the Enter Data Manually module to create a small dataset by typing values.

https://docs.microsoft.com/en-us/azure/machine-learning/tutorial-designer-automobile-price-deploy

https://docs.microsoft.com/en-us/azure/machine-learning/algorithm-module-reference/enter-data-manually

by Barrett at May 29, 2022, 12:16 AM

Limited Time Offer

25%

Off

Get Premium DP-100 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Shenika

4 months ago

Cloning the pipeline? Seems like a waste of time.

upvoted 0 times

...

Svetlana

4 months ago

Totally agree with B, makes the most sense!

upvoted 0 times

...

Tom

5 months ago

Wait, are we sure D is even a valid option?

upvoted 0 times

...

Johnna

5 months ago

I think C is better for real-time needs.

upvoted 0 times

...

Olive

5 months ago

B is the way to go for batch predictions!

upvoted 0 times

...

Lezlie

5 months ago

Replacing the dataset with an Enter Data Manually module seems off for deployment. I think we should focus on the inference pipelines instead.

upvoted 0 times

...

Trinidad

5 months ago

I’m leaning towards option B, but I vaguely recall something about real-time inference too. I need to double-check the differences.

upvoted 0 times

...

Mireya

5 months ago

I remember practicing a question about deploying models, and I feel like cloning the training pipeline isn’t the right approach for this scenario.

upvoted 0 times

...

Jamal

5 months ago

I think we need to create a batch inference pipeline since it’s for generating predictions asynchronously, but I'm not entirely sure.

upvoted 0 times

...

Jacki

5 months ago

This question seems straightforward. I'll read through the options carefully and choose the one that best matches the information provided.

upvoted 0 times

...

Lashawna

6 months ago

I feel pretty confident about this one. The session logging and archiving policy are going to be the biggest drivers of database growth, in my experience.

upvoted 0 times

...

Avery

6 months ago

Fingerprint signatures sound like a good option too, but did we cover what kind of measures would be necessary for those?

upvoted 0 times

...

Lawana

6 months ago

I thought the pattern needed to start with a digit, so I'm leaning towards option B, but I'm not completely confident.

upvoted 0 times

...