Amazon SageMaker Edge capabilities

Easily operate machine learning (ML) models running on edge devices

Benefits of SageMaker Edge

Optimize models trained in TensorFlow, PyTorch, XGBoost, and TensorFlow Lite so they can be deployed on any edge device
Deploy models across a fleet of devices independent of firmware and application updates
Continuously improve models with smart data capture for model retraining
Create automated MLOps pipelines for any device fleet, from edge servers to smart cameras and IoT sensors

Amazon SageMaker Edge features

Amazon SageMaker edge capabilities help you optimize, secure, monitor, and maintain ML models across fleets of edge devices.

Create Models

Build and refine models

The SageMaker Edge Agent allows you to capture data and metadata based on triggers that you set so that you can retrain your existing models with real-world data or build new models. Additionally, this data can be used to conduct your own analysis, such as model drift analysis.

Watch video

Choice of deployment methods

We offer three options for deployment. GGv2 (~ size 100MB) is a fully integrated AWS IoT deployment mechanism. For those customers with a limited device capacity, we have a smaller built-in deployment mechanism within SageMaker edge capabilities. For customers who have a preferred deployment mechanism, we support third party mechanisms that can be plugged into our user flow.

Watch video

Optimize ML models

Amazon SageMaker Edge Compiler automatically optimizes ML models for deployment on a wide variety of edge devices. SageMaker Edge Compiler compiles your trained model into an executable format that applies performance optimizations that can make your model run up to 25x faster on the target hardware.

Watch video

Scale Models

Dashboard to monitor devices

Amazon SageMaker Edge Manager provides a dashboard so you can understand the performance of models running on each device across your fleet. The dashboard helps you visually understand overall fleet health and identify the problematic models through a dashboard in the console. When a problem is identified, you can collect model data, relabel the data, retrain the model, and redeploy the model.

Support Security and Compliance

Amazon SageMaker Edge packages the ML model by signing it with customer-supplied keys or AWS keys. The Edge Agent authenticates the signature and also verifies that the model has not been tampered with before loading the model into the runtime.

Watch video

Customers

Levnovo customer logo

Lenovo™, the #1 global PC maker, recently incorporated Amazon SageMaker into its latest predictive maintenance offering.  

"The new SageMaker Edge Manager will help eliminate the manual effort required to optimize, monitor, and continuously improve the models after deployment. With it, we expect our models will run faster and consume less memory than with other comparable machine-learning platforms. SageMaker Edge Manager allows us to automatically sample data at the edge, send it securely to the cloud, and monitor the quality of each model on each device continuously after deployment. This enables us to remotely monitor, improve, and update the models on our edge devices around the world and at the same time saves us and our customers' time and costs."

Igor Bergman, Lenovo Vice President, Cloud & Software of PCs and Smart Devices.

Basler customer logo

Basler AG is a leading manufacturer of high-quality digital cameras and accessories for industry, medicine, transportation and a variety of other markets.

“Basler AG delivers intelligent computer vision solutions in a variety of industries, including manufacturing, medical, and retail applications. We are excited to extend our software offering with new features made possible by Amazon SageMaker Edge Manager. To ensure our machine learning solutions are performant and reliable, we need a scalable edge to cloud MLOps tool that allows us to continuously monitor, maintain, and improve machine learning models on edge devices. SageMaker Edge Manager allows us to automatically sample data at the edge, send it securely to the cloud, and monitor the quality of each model on each device continuously after deployment. This enables us to remotely monitor, improve, and update the models on our edge devices around the world and at the same time saves us and our customers' time and costs."

Mark Hebbel, Head of Software Solutions at Basler.