Exam AI-100 topic 2 question 17 discussion

Actual exam question from Microsoft's AI-100

Question #: 17
Topic #: 2

Your company has an on-premises datacenter.
You plan to publish an app that will recognize a set of individuals by using the Face API. The model is trained.
You need to ensure that all images are processed in the on-premises datacenter.
What should you deploy to host the Face API?

A. a Docker container
B. Azure File Sync
C. Azure Application Gateway
D. Azure Data Box Edge

Show Suggested Answer

Suggested Answer: A 🗳️
A container is a standard unit of software that packages up code and all its dependencies so the application runs quickly and reliably from one computing environment to another. A Docker container image is a lightweight, standalone, executable package of software that includes everything needed to run an application: code, runtime, system tools, system libraries and settings.
Incorrect Answers:
D: Azure Data Box Edge is an AI-enabled edge computing device with network data transfer capabilities. This article provides you an overview of the Data Box
Edge solution, benefits, key capabilities, and the scenarios where you can deploy this device.
Data Box Edge is a Hardware-as-a-service solution. Microsoft ships you a cloud-managed device with a built-in Field Programmable Gate Array (FPGA) that enables accelerated AI-inferencing and has all the capabilities of a storage gateway.
References:
https://www.docker.com/resources/what-container

by H2HG at Sept. 14, 2020, 11:27 p.m.

Comments

Submit Cancel

rveney

1 year, 12 months ago

to ensure that all images are processed in the on-premises datacenter, the recommended approach is to deploy the Face API within a Docker container (Option A).

upvoted 1 times

...

berserkguts

4 years ago

this was in the AI-100 exam i took today, May 31

upvoted 2 times

...

AlfuryDB

4 years, 2 months ago

There is no question in this case that is a container. The other options seem quite irrelevant in my opinion. For the ones saying databox: https://azure.microsoft.com/en-gb/blog/expanding-the-azure-data-box-family/ it's a product to shop data to the cloud. Does the question we need to send data from on premises to the cloud? in this case you could say azure import/export service which doesn't make a lot of sense.

upvoted 1 times

...

Maunik

4 years, 3 months ago

Azure stack Edge and Azure data box Edge are separate products. Azure stack you can use for model inferencing, data box edge is mainly for moving data. Container is the right answer in my opinion - https://azure.microsoft.com/en-us/services/databox/

upvoted 1 times

...

Cornholioz

4 years, 4 months ago

I think it could be both Data Box Edge and Docker. Since the model is trained, you could deploy it into Docker. However, Data Box Edge can do the preprocessing etc. on the on-premises (edge) data center. Check out 1:06 to 1:42: https://youtu.be/UyJIexkErJw

upvoted 1 times

...

H2HG

4 years, 9 months ago

It should be option D Azure Stack Edge (data box edge) https://docs.microsoft.com/en-us/azure/databox-online/azure-stack-edge-overview

upvoted 1 times

jadepe

4 years, 9 months ago

But a Stack Edge is, (as stated in the link you provide) a hardware-as-a-service solution: "Azure Stack Edge is a Hardware-as-a-service solution. Microsoft ships you a cloud-managed device with a built-in Field Programmable Gate Array (FPGA) that enables accelerated AI-inferencing and has all the capabilities of a network storage gateway." , so I should vote for the Docker container

upvoted 4 times

robn

4 years, 4 months ago

The given answer is correct, Azure Data Box is not a hosting option https://azure.microsoft.com/en-us/services/databox/

upvoted 2 times

...