Exam DP-100 topic 4 question 37 discussion

Actual exam question from Microsoft's DP-100

Question #: 37
Topic #: 4

You are developing a machine learning model.

You must inference the machine learning model for testing.

You need to use a minimal cost compute target.

Which two compute targets should you use? Each correct answer presents a complete solution.

NOTE: Each correct selection is worth one point.

A. Azure Machine Learning Kubernetes
B. Azure Databricks
C. Remote VM
D. Local web service
E. Azure Container Instances

Show Suggested Answer

Suggested Answer: DE 🗳️

by sap_dg at April 1, 2023, 4:26 a.m.

Comments

Submit Cancel

sap_dg

Highly Voted 2 years, 2 months ago

The inference is for testing. We do not need a Web Service. Answer should be C and E

upvoted 7 times

...

nposteraro

Most Recent 7 months, 1 week ago

I think it's C and D: https://learn.microsoft.com/en-us/azure/machine-learning/concept-compute-target?view=azureml-api-2#compute-targets-for-inferen

upvoted 1 times

sanctafrax

4 months, 3 weeks ago

Why remote VM? VM's are relatively expensive to run. in principle all answers can support a deployment. VM's are always on and therefore are always paid for. Azure container instance isnt. At least its serverless and therefore you dont pay for overhead. I agree with D but disagree with C.

upvoted 1 times

...

haby

1 year, 6 months ago

C & D. Based on my exp, most expensive is Databricks, AKS/ACI with GPU support are the next one, then AKS/ACI w/o GPU, last one is VM. All of them are available as a compute target for Auto ML/ML pipelines [https://learn.microsoft.com/en-us/azure/machine-learning/concept-compute-target?view=azureml-api-2], so I will choose CD for minimal cost.

upvoted 2 times

...

ZoeJ

2 years, 2 months ago

https://learn.microsoft.com/en-us/azure/machine-learning/concept-compute-target?view=azureml-api-2#compute-targets-for-inference I think the given answer is correct

upvoted 3 times

...