What happened?
Amazon SageMaker Edge Manager was announced during the re:Invent Machine Learning Keynote. This new feature gives developers model management tools for to optimize, secure, monitor, and maintain machine learning models on fleets of edge devices such as smart cameras, robots, personal computers, and mobile devices.
Why is it important?
- Device Compatibility: It enables developers to train ML models once in the cloud and across fleets of devices at the edge.
- Optimize ML Models: Amazon SageMaker Edge Manager provides a software agent that comes with an ML model optimized with SageMaker Neo automatically. This eliminates the need to have Neo runtime installed on devices to leverage model optimizations.
- Reduce Downtime and Service Disruption Costs: SageMaker Edge Manager manages models separately from the rest of the application so update the model and the application independently reducing downtime and service disruptions.
Why are we excited?
The new SageMaker Edge Manager helps data scientists remotely optimize, monitor, and improve the ML models on edge devices across the world, saving developer time and customer costs. It reduces the time and effort required to get models to production, while continuously monitoring and improving model quality.
Availability
It’s available today in the US East (N. Virginia), US West (Oregon), US East (Ohio), Europe (Ireland), Europe (Frankfurt), and Asia Pacific (Tokyo) regions.
If you’re looking to explore these services further and need some guidance, let us know and we’ll connect you to an Idexcel expert!