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.

SageMaker edge deployment demonstration

SageMaker edge deployment demonstration - Amazon SageMaker Tutorial

From the course: Machine Learning with SageMaker by Pearson

Start my 1-month free trial Buy for my team

SageMaker edge deployment demonstration

“

In all of the demos I've done thus far, I've used real-time inference on an endpoint that is running within SageMaker. However, in a typical deployment, you're not going to want to do your inference in the cloud. It takes time, it's slow, it costs money, and a whole bunch of other reasons. SageMaker Neo, as we've just learned in the slides for this lesson, is a feature that allows us to compile and run a bunch of different SageMaker deployments. in the slides for this lesson is a feature that allows us to compile our models and then run them on an edge device. So I'm going to give you a demo of doing a compiled model running on Linux. Here in the instructions for this we have prerequisites. I have several links listed here as well that go and talk about Neo and how it works and how you can run these models on on an endpoint over here on the left under edge devices, which is also linked in here, right here. You can see a supported framework, supported devices. For example, under…

Contents