HomeGuidesAPI ReferenceForum
Search…
Getting Started
Getting Started: Next Steps
API and SDK references
What is embedded ML, anyway?
Frequently asked questions
Edge Impulse Studio
Dashboard
Devices
Data sources
Data acquisition
Data explorer
Impulse design
Processing blocks
Learning blocks
EON Tuner
Retrain model
Live classification
Model testing
Deployment
Organizations
Development Platforms
Overview
Officially supported MCU targets
Officially supported CPU/GPU targets
Community boards
Mobile Phone
Porting Guide
Edge Impulse for Linux
Edge Impulse for Linux
Linux Node.js SDK
Linux Go SDK
Linux C++ SDK
Linux Python SDK
Edge Impulse CLI
Overview
Installation
Serial daemon
Uploader
Data forwarder
Impulse runner
Blocks
Himax flash tool
Deployment
C++ library
Arduino library
Cube.MX CMSIS-PACK
WebAssembly
OpenMV
Edge Impulse firmwares
Tutorials
Continuous motion recognition
Responding to your voice
Recognize sounds from audio
Adding sight to your sensors
Detect objects with bounding boxes
Detect objects with centroids
Sensor fusion
Continuous audio sampling
Running jobs using the API
Hardware specific tutorials
Pre-built datasets
Continuous gestures
Running faucet
Keyword spotting
TensorFlow Lite reference models
Tips & Tricks
Increasing model performance
Data augmentation
Inference performance metrics
Lower compute time
Concepts
What is edge machine learning (edge ML)?
Powered By GitBook
Edge Impulse for Linux
Edge Impulse for Linux is the easiest way to build Machine Learning solutions on real embedded hardware. It contains tools which let you collect data from any microphone or camera, can be used with the Node.js, Python, Go and C++ SDKs to collect new data from any sensor, and can run impulses with full hardware acceleration - with easy integration points to write your own applications.

Development boards

This is a list of development boards that are fully supported by Edge Impulse for Linux. Follow the instructions to get started:
Different development board? Probably no problem! You can use the Linux x86_64 getting started guide to set up the Edge Impulse for Linux CLI tool, and you can run your impulse on any x86_64, ARMv7 or AARCH64 Linux target. For support please head to the forums.

SDKs

To build your own applications, or collect data from new sensors, you can use the high-level language SDKs. These use full hardware acceleration, and let you integrate your Edge Impulse models in a few lines of code:

.eim models?

Edge Impulse for Linux models are delivered in .eim format. This is an executable that contains your signal processing and ML code, compiled with optimizations for your processor or GPU (e.g. NEON instructions on ARM cores) plus a very simple IPC layer (over a Unix socket). We do this because your model file is now completely self-contained, it does not depend on anything (except glibc) and thus you don't need specific TensorFlow versions, avoid Python dependency hell, and will never have to worry about why you're not running at full native speed.
The Node.js / Python / Go SDKs talk to the model through the IPC layer to run inference, so these SDKs are very thin, and just need the ability to spawn a binary. The SDKs are open source if you want to take a look, e.g. here is the Node.js IPC client.
You can download .eim files using the Edge Impulse for Linux CLI or from the Studio (go to Dashboard, then enable 'Show Linux deploy options', and they'll be listed under Deployment). You can also build the .eim files yourself with the Edge Impulse for Linux C++ SDK, see Building .eim files.
Development Platforms - Previous
Porting Guide
Next - Edge Impulse for Linux
Linux Node.js SDK
Last modified 3mo ago
Export as PDF
Copy link
Outline
Development boards
SDKs
.eim models?