nerdexam
Amazon

MLS-C01 · Question #226

A company wants to predict the classification of documents that are created from an application. New documents are saved to an Amazon S3 bucket every 3 seconds. The company has developed three…

The correct answer is B. Deploy all the models to a single SageMaker endpoint. Treat each model as a production variant. https://aws.amazon.com/cn/blogs/aws/new-for-amazon-sagemaker-perform-shadow-tests-to- compare-inference-performance-between-ml-model-variants/

Machine Learning Implementation and Operations

Question

A company wants to predict the classification of documents that are created from an application. New documents are saved to an Amazon S3 bucket every 3 seconds. The company has developed three versions of a machine learning (ML) model within Amazon SageMaker to classify document text. The company wants to deploy these three versions to predict the classification of each document. Which approach will meet these requirements with the LEAST operational overhead?

Options

  • AConfigure an S3 event notification that invokes an AWS Lambda function when new documents
  • BDeploy all the models to a single SageMaker endpoint. Treat each model as a production variant.
  • CDeploy each model to its own SageMaker endpoint Configure an S3 event notification that
  • DDeploy each model to its own SageMaker endpoint. Create three AWS Lambda functions.

How the community answered

(53 responses)
  • A
    8% (4)
  • B
    75% (40)
  • C
    13% (7)
  • D
    4% (2)

Explanation

https://aws.amazon.com/cn/blogs/aws/new-for-amazon-sagemaker-perform-shadow-tests-to- compare-inference-performance-between-ml-model-variants/

Topics

#SageMaker Endpoints#Real-time Inference#Multi-Model Deployment#Operational Overhead

Community Discussion

No community discussion yet for this question.

Full MLS-C01 Practice