X-LINUX-AI Developer package

Applicable for

STM32MP13x lines, STM32MP15x lines, STM32MP25x lines

---

1. Developer package : build AI application from the X-LINUX-AI add-on SDK

In order to easily develop and build an AI application without using the Yocto build system, X-LINUX-AI comes with a SDK add-on extending the OpenSTLinux SDK with AI functionality. To install and use the X-LINUX-AI SDK Add-on please refer to the following steps.

2. Prerequisites

2.1. Install the OpenSTLinux SDK

First of all, you must download and install the OpenSTLinux SDK, which contains all the basis needed for the X-LINUX-AI add-on. To do this, follow instructions given in STM32MP2 Developer Package : Installing the SDK chapter. Once this has been done, you should have a directory containing the OpenSTLinux SDK.

Information

Once this is done, if you have follow the exemple of directory structure the path to the OpenSTLinux SDK should be the following  : $HOME/STM32MPU_workspace/STM32MPU-Ecosystem-v5.0.2.BETA/Developer-Package/SDK

3. X-LINUX-AI SDK add-on installation

3.1. Download the X-LINUX-AI SDK add-on

To add the Artificial Intelligence part into the OpenSTLinux SDK, you must download and install the X-LINUX-AI SDK add-on. The add-on is delivered through a tarball file that can be downloaded here:

• For beta:

To download the archive, Follow instructions given in the downloading instructions page, if you didn't retrieve yet the files and download the SDK-x86_64-stm32mp25-openstlinux-6.1-yocto-mickledore-mp2-v23.12.06-addon-x-linux-ai-STM32MP25-beta.tar.gz archive.

Warning

The X-LINUX-AI SDK add-on version must be the same as the OpenSTLinux SDK. If the version are not aligned, it might not work correctly.

3.2. Install the X-LINUX-AI SDK add-on

Once the X-LINUX-AI SDK add-on is downloaded, uncompress the add-on:

Information

The name of the tarball depends on the chosen version. In the example below the last uploaded version is used.

  cd  ~/Downloads/
  tar xzf  SDK-x86_64-stm32mp25-openstlinux-6.1-yocto-mickledore-mp2-v23.12.06-addon-x-linux-ai-STM32MP25-beta.tar.gz

Then, copy the .sh script to your OpenSTLinux SDK directory:

  cp stm32mp25-openstlinux-6.1-yocto-mickledore-mp2-v23.12.06-addon-x-linux-ai-STM32MP25-beta/st-image-ai-openstlinux-weston-stm32mp25-x86_64-toolchain-4.2.2-openstlinux-6.1-yocto-mickledore-mp2-v23.12.06-addon-x-linux-ai-STM32MP25-beta.sh $HOME/STM32MPU_workspace/STM32MPU-Ecosystem-v5.0.2.BETA/Developer-Package/SDK

Warning

It is mandatory run the script inside the OpenSTLinux SDK directory.

Finally, run the script contained in the tarball:

  cd $HOME/STM32MPU_workspace/STM32MPU-Ecosystem-v5.0.2.BETA/Developer-Package/SDK
  ./st-image-ai-openstlinux-weston-stm32mp25-x86_64-toolchain-4.2.2-openstlinux-6.1-yocto-mickledore-mp2-v23.12.06-addon-x-linux-ai-STM32MP25-beta.sh

Optionally, once the script is executed, you can delete it.

  rm *.sh

3.3. Start the SDK

Information

The SDK environment setup script must be run once on each new working terminal on which you cross-compile.

The add-on is now installed into the OpenSTLinux SDK. You can start the SDK. Go to your OpenSTLinux SDK directory and source the environment:

  cd $HOME/STM32MPU_workspace/STM32MPU-Ecosystem-v5.0.2.BETA/Developer-Package/SDK
  source environment-setup-cortexa35-ostl-linux

Check that the SDK is properly installed:

  x-linux-ai -v
 X-LINUX-AI version: STM32MP25-beta

Information

With the x-linux-ai binary it is possible to check the X-LINUX-AI version and the supported frameworks/applications. Use x-linux-ai --help for more information.

4. Use the SDK

4.1. Build an application with the SDK

Information

In this section, the image classification application is used as an example, but all the applications can be built with this method.

Once the SDK is correctly set up, the applications can be built easily. In this example, it is the image classification application that is built.

Download the github repository:

  git clone https://github.com/PRG-MPU-ALPHA/meta-st-x-linux-ai

Warning

The version of the downloaded meta-st-x-linux-ai is be the same as the one of the X-LINUX-AI SDK add-on.

Go to the image classification directory:

  cd meta-st-x-linux-ai/recipes-samples/image-classification/tflite/

Information

To be able to compile AI applications for STM32MP2 series' boards with hardware acceleration it is necessary to export an environment variable named ARCHITECTURE which is used in the makefile provided in X-LINUX-AI repository.

Export ARCHITECTURE variable to build AI applications with NPU acceleration :

 export ARCHITECTURE=stm32mp2_npu

Then, use the make command to build the application:

  make

A new file is displayed, named tflite_image_classification. This is a binary file, which has been generated using the make command. It is compiled for the STM32MP2x architecture. It must now be transferred to the board.

4.2. Use the application

Warning

To use the application, it is mandatory to have an STM32MP2x board with OpenSTLinux and X-LINUX-AI packages installed. If it is not the case, refer to the X-LINUX-AI installation guide.

Once the STM32MP2x board is correctly set up and the X-LINUX-AI packages are installed with the right version, it is possible to send the application to the board.

Information

The X-LINUX-AI packages versions must be the same as the ones in the X-LINUX-AI SDK add-on.

To do it, use the following command using your own IP address:

  scp -r -p tflite_image_classification root@<ip_address>:/usr/local/demo-ai/image-classification/tflite

Then, use the ssh protocol to connect to the board:

  ssh root@<ip_address>

On the board, go to the right directory and use the image classification script to launch the application:

  cd /usr/local/demo-ai/image-classification/tflite
  ./launch_bin_image_classification.sh

This script is using the tflite_image_classification application that has been compiled before.

Artificial intelligence

Software development kit (A programming package that enables a programmer to develop applications for a specific platform.)c

Neural processing unit - NEW