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.

Using SageMaker Neo for edge deployment

Using SageMaker Neo for edge deployment - Amazon SageMaker Tutorial

From the course: Machine Learning with SageMaker by Pearson

Start my 1-month free trial Buy for my team

Using SageMaker Neo for edge deployment

“

Everything we've talked about thus far, such as real-time inference or batch or asynchronous is done in the cloud. And we're most likely making the request from some piece of software that might be in AWS, but it might be on-prem as well. Like, what if it's just code running on our laptop and we make the request out to that SageMaker endpoint saying, here's a piece of information, I want you to predict the outcome of that request. And then we're going to send that request out to SageMaker information, I want you to predict the outcome based on this piece of information. That could come from our laptop, just talking to that SageMaker endpoint. But what if we don't have internet access? What if we're doing image processing for quality assurance on a factory line that is processing critical type of national security type things, right? Like it's making defense weaponry, or whatever the case may be, that is most likely isolated from the Internet. You wouldn't want that to be accessible…

Contents