You work for a logistics company that specializes in the storage, movement, and control of massive amounts of packages.
You are on the machine learning team assigned the task of building a machine learning model to assist in the control of your company's package logistics.
Specifically, your model needs to predict the routes your package movers should take for optimal delivery and resource usage.
The model requires various transformations to be performed on the data.
You also want to get inferences on entire datasets once you have your model in production.
Additionally, you won't need a persistent endpoint for applications to call to get inferences. Which type of production deployment would you use to get predictions from your model in the most expeditious manner?
Click on the arrows to vote for the correct answer
A. B. C. D.Answer: B.
Option A is incorrect.
SageMaker Hosting Services is used for applications to send requests to an HTTPS endpoint to get inferences.
This type of deployment is used when you need a persistent endpoint for applications to call to get inferences.
Option B is correct.
SageMaker Batch Transform is used to get inferences for an entire dataset, and you don't need a persistent endpoint for applications to call to get inferences.
Option C is incorrect.
SageMaker Containers is a service you can use to create your own Docker containers to deploy your models.
This would not be the most expeditious option.
Option D is incorrect.
SageMaker Elastic Interface is used to accelerate deep learning inference workloads.
This service alone would not give you the batch transform capabilities you need.
Reference:
Please see the Amazon SageMaker developer guide titled Deploy a Model on Amazon SageMaker Hosting Services, the Amazon SageMaker developer guide titled Get Inferences for an Entire Dataset with Batch Transform, the Amazon Elastic Inference developer guide titled What Is Amazon Elastic Inference?, and the Amazon SageMaker developer guide titled Amazon SageMaker Containers: a Library to Create Docker Containers.
The most expeditious way to get predictions from a machine learning model for an entire dataset without requiring a persistent endpoint is to use Amazon SageMaker Batch Transform.
Amazon SageMaker is a fully managed service that provides developers and data scientists with the ability to build, train, and deploy machine learning models at scale. It offers several deployment options, including SageMaker Hosting Services, SageMaker Batch Transform, SageMaker Containers, and SageMaker Elastic Inference.
SageMaker Hosting Services provides a persistent endpoint for applications to call to get inferences. It is suitable for real-time inference scenarios where low latency is critical. However, it is not the best option for getting inferences on entire datasets, as it requires making a separate request for each inference.
SageMaker Containers allows you to deploy your machine learning models in a Docker container, giving you complete control over your environment. However, it requires more configuration and management than other deployment options.
SageMaker Elastic Inference is a service that enables you to attach GPU-powered inference acceleration to any Amazon SageMaker instance type. It is useful for reducing the cost of inference by allowing you to scale the GPU resources to match the requirements of your model. However, it is not a deployment option on its own, but rather a way to optimize the performance of the other deployment options.
SageMaker Batch Transform is designed to perform inferences on entire datasets. It allows you to submit a batch of data to a pre-deployed model and receive the inferences in a specified output location. Batch Transform uses Amazon Simple Storage Service (S3) to manage input and output data, making it easy to integrate with other AWS services. It is ideal for scenarios where you need to process large amounts of data without the need for a persistent endpoint.
Therefore, for this use case, the most suitable deployment option for getting predictions from the model in the most expeditious manner is Amazon SageMaker Batch Transform.