Exam DP-100 All Questions

View all questions & answers for the DP-100 exam

Exam DP-100 topic 4 question 6 discussion

Actual exam question from Microsoft's DP-100

Question #: 6
Topic #: 4

HOTSPOT -
You deploy a model in Azure Container Instance.
You must use the Azure Machine Learning SDK to call the model API.
You need to invoke the deployed model using native SDK classes and methods.
How should you complete the command? To answer, select the appropriate options in the answer areas.
NOTE: Each correct selection is worth one point.
Hot Area:

Show Suggested Answer

Suggested Answer:

Box 1: from azureml.core.webservice import Webservice
The following code shows how to use the SDK to update the model, environment, and entry script for a web service to Azure Container Instances: from azureml.core import Environment from azureml.core.webservice import Webservice from azureml.core.model import Model, InferenceConfig
Box 2: predictions = service.run(input_json)
Example: The following code demonstrates sending data to the service: import json test_sample = json.dumps({'data': [
[1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
[10, 9, 8, 7, 6, 5, 4, 3, 2, 1]
]})
test_sample = bytes(test_sample, encoding='utf8')
prediction = service.run(input_data=test_sample)
print(prediction)
Reference:
https://docs.microsoft.com/bs-latn-ba/azure/machine-learning/how-to-deploy-azure-container-instance https://docs.microsoft.com/en-us/azure/machine-learning/how-to-troubleshoot-deployment

by rishi_ram at June 7, 2021, 12:38 p.m.

Comments

Submit Cancel

rishi_ram

Highly Voted 1 year, 6 months ago

Question was there in June 2021 Exam

upvoted 12 times

...

1q2w3e4r5t

Highly Voted 1 year, 3 months ago

given answer is correct

upvoted 9 times

...

punz61

Most Recent 8 months ago

given answer is correct

upvoted 2 times

...

synapse

9 months, 1 week ago

Given answer is correct. https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.webservice(class)?view=azure-ml-py#azureml-core-webservice-run

upvoted 2 times

...

AjoseO

9 months, 2 weeks ago

On Exam: 03 March 2022

upvoted 5 times

...

hargur

1 year, 2 months ago

on 19Oct2021

upvoted 2 times

...

azurecert2021

1 year, 5 months ago

First option is correct for sure but second is wrong You deploy a model in Azure Container Instance so it is already deployed! You must use the Azure Machine Learning SDK to call the model API so here ask is how to call ? You need to invoke the deployed model using native SDK classes and methods ,again we need to invoke remember! so second answer should be prediction = requests.post(service.scoring_uri, input_json)

upvoted 5 times

ning

6 months, 1 week ago

Answer is correct! WebService is not the same as normal web request, class definition here: https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.webservice(class)?view=azure-ml-py#azureml-core-webservice-run

upvoted 1 times

...

SnowCheetah

1 year, 5 months ago

The Answer is already correct with Webservice and run() https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.webservice(class)?view=azure-ml-py in Webservice have method call run() to call webservice with an input. It should do the same functionality as requests.post(service.scoring_uri, input_json). I believe that prediction = requests.post(service.scoring_uri, input_json) should not work because of the upper provided code is not include "import requests" to be able running post method.

upvoted 10 times

Maunik

1 year, 5 months ago

Given answer in correct: https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/deploy-to-cloud/model-register-and-deploy.ipynb

upvoted 3 times

...

dda711

1 year, 1 month ago

requests is not a native SDK class either

upvoted 3 times

...

pancman

8 months, 1 week ago

You are mistaken; requests is a python library, which is not part of zure ML SDK. Webservice is part of SDK. The run method of Webservice calls the Webservice with the provided input. And the input parameter is the data your machine learning model expects as an input to run predictions. Here in the correct answer, we feed the json data as the input.

upvoted 1 times

...