meta-onnxruntime

Yocto layer for ONNX Runtime.

The official website is:

• ONNX Runtime

Available BSP

Please note that it is not official support.

BSP	ONNX Runtime version	Build status
meta-raspberrypi	v1.20.1
meta-riscv	v1.20.1

matrix

BSP	MACHINE	Build status
meta-raspberrypi	raspberrypi raspberrypi0 raspberrypi0-wifi raspberrypi-cm	NG
	raspberrypi2 raspberrypi3 raspberrypi4 raspberrypi-cm3	NG
	raspberrypi0-2w-64 raspberrypi3-64 raspberrypi4-64	OK
	raspberrypi5	OK
meta-riscv	qemueriscv32	NG
	qemuriscv64	OK

Available recipes

• Framework
  • onnxruntime
    ONNX Runtime
• Examples
  • onnxruntime-python-label-image-example
    Python label image

How to

Quick start for the Raspberry Pi AArch64 (core-image-weston)

# Clone repositories and oe-init-build-env
$ git clone git://git.yoctoproject.org/poky.git
$ git clone git://git.yoctoproject.org/meta-raspberrypi
$ git clone git://git.openembedded.org/meta-openembedded
$ git clone https://github.com/NobuoTsukamoto/meta-onnxruntime.git
$ source poky/oe-init-build-env build

# Add layer
$ bitbake-layers add-layer ../meta-openembedded/meta-oe/
$ bitbake-layers add-layer ../meta-openembedded/meta-python/
$ bitbake-layers add-layer ../meta-openembedded/meta-networking/
$ bitbake-layers add-layer ../meta-openembedded/meta-multimedia/
$ bitbake-layers add-layer ../meta-raspberrypi/
$ bitbake-layers add-layer ../meta-onnxruntime/

# Add the package to 'conf/auto.conf' file. 
MACHINE ?= "raspberrypi4-64"
IMAGE_INSTALL:append = " onnxruntime"

# Build
$ bitbake core-image-weston