From the course: Machine Learning with SageMaker by Pearson

Unlock this course with a free trial

Join today to access over 25,200 courses taught by industry experts.

Batch and asynchronous inference demonstration

Batch and asynchronous inference demonstration - Amazon SageMaker Tutorial

From the course: Machine Learning with SageMaker by Pearson

Start my 1-month free trial Buy for my team

Batch and asynchronous inference demonstration

“

Thus far, in all of the demos that we've done where we create a model and then we run some sort of inference against it, we are doing a real-time inference. That means we want results right now, and we're willing to wait for those results to come in. But what if you have a large set of data that you need to infer all of it, or you have something that takes a long time to process? may or may not want to wait or have the time to wait. So I can give it to my endpoint, say, work on this. I'm going to go do this other thing. And when you're done, notify me or put the results in an S3 bucket. However you configure it, there are options for that. So we have batch inference and asynchronous inference. And the way we're going to do this demo, we're going to use a model that we've already trained. It's going to be that loan approval data set model, loan approval model that tries to predict if a loan will be approved based on the loan applier's age, education level, and salary. With that model…

Contents