Who is this for?

This Learning Path is for embedded and IoT engineers who want to deploy Edge Impulse ML models to Arm-based edge devices at scale using AWS IoT Greengrass.

What will you learn?

Upon completion of this Learning Path, you will be able to:

  • Set up an Arm-based edge device for ML inference with Edge Impulse.
  • Install and configure AWS IoT Greengrass on the edge device.
  • Deploy an Edge Impulse ML model as a Greengrass custom component.
  • Verify model inference results through AWS IoT Core.

Prerequisites

Before starting, you will need the following:

  • An Edge Impulse Studio account
  • An AWS account with administrator access
  • A supported Arm-based edge device such as a Raspberry Pi 5, NVIDIA Jetson, Qualcomm Dragonwing QC6490, or an Arm-based Amazon EC2 instance
  • An SSH client and familiarity with the Linux command line
  • Basic understanding of ML concepts

Summary

AI-assisted

This summary was drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.

Close
?
You’ll deploy an Edge Impulse ML model to an Arm-based Linux edge device with AWS IoT Greengrass. First, you’ll choose and prepare a supported device or Arm-based Amazon EC2 instance. Then, you’ll clone and build an Edge Impulse project, install Greengrass, and store your API key in AWS Secrets Manager. Finally, you’ll deploy the custom component and verify inference results in AWS IoT Core.

Frequently asked questions

AI-assisted

These FAQs were drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.

Close
?
What should I use to complete the steps if I don't have a supported hardware board?
You can use an Arm-based Amazon EC2 instance as a local edge device and complete every step.
What do I need before running the AWS IoT Greengrass installer on the device?
Before installation, provide your AWS access credentials so you can register your device with AWS IoT Core and configure the required resources.
How should I store my Edge Impulse API key for the Greengrass component?
Store your Edge Impulse API key in AWS Secrets Manager with the secret ID EI_API_KEY. Set its key to ei_api_key.
Why does the Greengrass component need an Edge Impulse API key?
The component uses your API key to authenticate with your Edge Impulse project and download the model.
What result should I expect after deploying the custom component?
You can verify that your model runs on your Arm-based device and view its inference results in AWS IoT Core.
Next