Inferencing libraries
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 Linux models are delivered in an.eim
binary 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). See our Linux EIM executable guide to learn more.
Supported hardware
Development boards
This is a list of development boards that are fully supported by Edge Impulse for Linux. Follow the instructions to get started:- Advantech ICAM-540
- IMDT RZ/V2H
- Mac devices
- Microchip SAMA7G54
- NVIDIA Jetson Orin and Nano
- Linux x86_64 devices
- Qualcomm Dragonwing RB3 Gen 2 Dev Kit
- Raspberry Pi 4
- Renesas RZ/V2L
- Renesas RZ/G2L
- Renesas RZ/V2H
- Texas Instruments SK-TDA4VM
- Texas Instruments SK-AM62A-LP
- Texas Instruments SK-AM668A