New Year Sale 2026! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions
Mail Us support@pass4success.com
Location US
Mob_nav_barsMENU

Microsoft DP-100 Exam - Topic 7 Question 47 Discussion

Actual exam question for Microsoft's DP-100 exam
Question #: 47
Topic #: 7
[All DP-100 Questions]

You train and register a machine learning model. You create a batch inference pipeline that uses the model to generate predictions from multiple data files.

You must publish the batch inference pipeline as a service that can be scheduled to run every night.

You need to select an appropriate compute target for the inference service.

Which compute target should you use?

Show Suggested Answer Hide Answer
Suggested Answer: B

Azure Machine Learning compute clusters is used for Batch inference. Run batch scoring on serverless compute. Supports normal and low-priority VMs. No support for real-time inference.


https://docs.microsoft.com/en-us/azure/machine-learning/concept-compute-target

by Terrilyn at May 06, 2022, 09:57 PM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

0/2000 characters
Submit Cancel
Fernanda
4 months ago
Azure ML compute cluster could work too, especially for batch processing.
upvoted 0 times
...
Murray
4 months ago
Surprised that AKS is the go-to, I thought it was overkill for nightly runs.
upvoted 0 times
...
Dyan
4 months ago
But isn't ACI cheaper for smaller jobs?
upvoted 0 times
...
Buddy
5 months ago
Definitely agree, AKS is great for handling large workloads!
upvoted 0 times
...
Shayne
5 months ago
I think Azure Kubernetes Service is the best for scalability.
upvoted 0 times
...
Blossom
5 months ago
I practiced a question like this, and I feel like the compute instance is more for interactive work, not for scheduled jobs.
upvoted 0 times
...
Beth
5 months ago
I remember something about AKS being great for scaling, but for a nightly batch job, wouldn't ACI be more cost-effective?
upvoted 0 times
...
Ranee
5 months ago
I think we might need a compute cluster for batch processing since it can handle multiple files at once, but I'm not entirely sure.
upvoted 0 times
...
Helaine
5 months ago
I’m leaning towards the compute cluster, but I’m a bit confused about the differences between it and AKS for this specific use case.
upvoted 0 times
...
Valda
5 months ago
Okay, I think I've got it. The question is asking about Marie's personality, so I'm going to go with "lighthearted" as the answer. That seems to capture the positive, upbeat vibe the best.
upvoted 0 times
...
Bette
5 months ago
This seems like a straightforward question about risk assessment in an ERP project. I think the key is to focus on the specific requirement that was requested and how the project team evaluated the impact.
upvoted 0 times
...
Brunilda
5 months ago
I'm not completely sure, but I think R4 might prefer to reach R5 through R1 because of the cost differences.
upvoted 0 times
...

Save Cancel