Answer-first summary for fast verification
Answer: Load the model and use it to predict labels from input data.
The entry script for the InferenceConfig class in Azure ML deployment serves as the core logic for model inference. According to the Microsoft documentation and community consensus, the entry script must contain two main functions: init() to load the registered model and run() to process input data and return predictions. Option C directly addresses this core functionality - loading the model and using it to predict labels from input data. Other options are incorrect: A (registering the model) occurs before deployment, B (Conda environment setup) is handled by the environment configuration, D (starting nodes) is managed by the compute infrastructure, and E (specifying compute resources) is part of the deployment configuration rather than the entry script logic.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
You are a data scientist for a hotel booking website. You are using Azure Machine Learning to train a model that identifies fraudulent transactions. You plan to deploy the model as a real-time web service using the Model.deploy method from the Azure Machine Learning SDK. This service will return real-time fraud predictions based on transaction data.
You need to create the script for the entry_script parameter of the InferenceConfig class used in the deployment.
What is the required function of this entry script?
A
Register the model with appropriate tags and properties.
B
Create a Conda environment for the web service 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 web service is deployed.
E
Specify the number of cores and the amount of memory required for the inference compute.