The STMicroelectronics X-LINUX-AI software environment provides tools to perform inference on embedded systems using neural network models. Examples of applications that typically use neural network inference include object/pattern recognition, gesture control, voice processing, and sound monitoring.

X-LINUX-AI includes support for two standard inference engines:

Demos on pre-built image

Digi Embedded Yocto image recipe dey-image-webkit already includes the X-LINUX-AI layer and pre-built demos.

To test the demos:

  1. Connect a camera, mouse, and display/monitor to your ConnectCore MP25 Development Kit.

  2. Program dey-image-webkit pre-built images as explained in Program images using Fastboot.

  3. When the webkit demo runs, click on Machine Learning on the left sidebar menu.

  4. Select a demo to launch.

Machine Learning demos

Include X-LINUX-AI packages in Digi Embedded Yocto

Add the meta-st-stm32mpu-ai layer to your conf/bblayers.conf configuration file if it isn’t there already:

conf/bblayers.conf
   /usr/local/dey-4.0/sources/meta-digi/meta-digi-arm \
   /usr/local/dey-4.0/sources/meta-digi/meta-digi-dey \
+  /usr/local/dey-4.0/sources/meta-st-stm32mpu-ai \
"

Edit your conf/local.conf file to include one of the X-LINUX-AI package groups in your Digi Embedded Yocto image:

conf/local.conf
IMAGE_INSTALL:append = " packagegroup-x-linux-ai"

Including AI package groups significantly increases the size of the rootfs image.

More information

See ST’s X-LINUX-AI OpenSTLinux Expansion Package article for more information on X-LINUX-AI.