Answer-first summary for fast verification
Answer: Load the model and use it to predict labels from input data.
The question asks about the required function of the entry script for an Azure ML online endpoint deployment. The scoring script's primary purpose is to load the model and use it to make predictions on incoming data. Option C directly addresses this core function. Option A (registering the model) is typically done during model registration, not in the scoring script. Option B (creating Conda environment) is handled by the environment configuration, not the scoring script. Option D (starting nodes) is managed by Azure ML infrastructure, not the scoring script. Option E (specifying compute resources) is configured in the deployment settings, not the scoring script. The community discussion shows 100% consensus on C, with upvoted comments confirming this is correct.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are a data scientist for a hotel booking website. You have trained a model using Azure Machine Learning to identify fraudulent transactions. You plan to deploy this model as an online endpoint using the Azure Machine Learning Python SDK v2 to return real-time fraud predictions based on transaction data.
You must create the scoring script for the scoring_script parameter of the CodeConfiguration class for the deployment.
What is the required function of the entry script?
A
Register the model with appropriate tags and properties.
B
Create a Conda environment for the online endpoint compute and install the necessary Python packages.
C
Load the model and use it to predict labels from input data.
D
Start a node on the inference cluster where the model is deployed.
E
Specify the number of cores and the amount of memory required for the online endpoint compute.
No comments yet.