X-LINUX-AI Starter package

1. Install from the OpenSTLinux AI package repository

Information

The STMicroelectronics packages repository service is provided for evaluation purposes only, its content may be updated at any time without notice and is therefore not approved for use in production.

All the generated X-LINUX-AI packages are available from the OpenSTLinux AI package repository service hosted at the non-browsable URL http://extra.packages.openstlinux.st.com/AI.

This repository contains AI packages that can be simply installed using apt-* utilities, which the same as those used on a Debian system:

• the main group contains the selection of AI packages whose installation is automatically tested by STMicroelectronics
• the updates group is reserved for future uses such as package revision update.

You can install them individually or by package group.

1.1. Prerequisites

• Flash the Starter Package on your SDCard

For OpenSTLinux ecosystem release v5.1.0  :

STM32MP257x-EV Starter Package procedure

• Your board has an internet connection either through the network cable or through a WiFi connection.

Information

If your internet access depends on a proxy server, you should define the http_proxy environment variable with the following command before any apt-* commands: export http_proxy='http://<proxy url>:<proxy port>/'

1.2. Install the X-LINUX-AI tool

Once the board is booted, execute the following command in the console in order to download X-LINUX-AI tool package from OpenSTLinux package repository:

For ecosystem release v5.1.0  :

• Install X-LINUX-AI tool package:

 apt-get install x-linux-ai-tool 

• Then synchronize the AI OpenSTLinux package repository.

 apt-get update

• Once the X-LINUX-AI tool installed, you will find a binary tool named x-linux-ai in /usr/bin directory of your board.

1.3. Install AI packages

Warning

The software package is provided AS IS, and by downloading it, you agree to be bound to the terms of the software license agreement (SLA0048). The detailed content licenses can be found here.

1.3.1. Install X-LINUX-AI demonstration packages

To get started with X-LINUX-AI, it is recommended to install the X-LINUX-AI demonstration package, which provides all the AI frameworks, applications examples, tools and utilities optimized for the specific target used.

Command	Description
x-linux-ai -i packagegroup-x-linux-ai-demo	Install the X-LINUX-AI demonstration packages which provide AI frameworks, application examples and tools dedicated to the board used.

1.3.2. Install X-LINUX-AI package-group

To go further, it is also possible to install specific package-group dedicated to address the NPU for STM32MP2 series' boards or specific AI frameworks liket TensorFlow Lite, ONNX and Coral. It is also possible to install all the X-LINUX-AI packages available on the target at once.

Command	Description
x-linux-ai -i packagegroup-x-linux-ai-npu	Install X-LINUX-AI packages allowing to use OpenVX stack for the NPU hardware acceleration (including NBG benchmark)
x-linux-ai -i packagegroup-x-linux-ai-tflite	Install X-LINUX-AI packages related to TensorFlow™ Lite framework (including application samples)
x-linux-ai -i packagegroup-x-linux-ai-coral	Install X-LINUX-AI packages related to the Coral Edge TPU™ framework (including application samples)
x-linux-ai -i packagegroup-x-linux-ai-onnxruntime	Install X-LINUX-AI packages related to ONNX Runtime™ (including application samples)
x-linux-ai -i packagegroup-x-linux-ai	Install all X-LINUX-AI packages available for the target

1.3.3. Install X-LINUX-AI individual packages

To be able to list or manage all the X-LINUX-AI individual packages available please refer to the dedicated X-LINUX-AI Tool article

2. How to use the X-LINUX-AI Expansion Package

2.1. Material needed

To use the X-LINUX-AI OpenSTLinux Expansion Package, choose one of the following materials:

• STM32MP257F-EV1 Evaluation board + a Sony™ IMX335 5Mpx sensor
• STM32MP257F-DK Discovery kit + a Sony™ IMX335 5Mpx sensor
• STM32MP157F-DK2 Discovery kit + an UVC USB WebCam
• STM32MP157F-EV1 Evaluation board with the built in camera module : MB1379 (OmniVision OV5640 parallel camera)
• STM32MP135F-DK Discovery kit with the built in camera module : MB1897 (GalaxyCore 2145 parallel camera)

Optional:

• Coral USB Edge TPU™ accelerator

2.2. Boot the OpenSTlinux Starter Package

At the end of the boot sequence, the demo launcher application appears on the screen.

2.3. Install the X-LINUX-AI

Warning

The software package is provided AS IS, and by downloading it, you agree to be bound to the terms of the software license agreement (SLA0048). The detailed content licenses can be found here.

After having installed the x-linux-ai-tool you can install the X-LINUX-AI demonstration packages.

 x-linux-ai -i packagegroup-x-linux-ai-demo

And restart the demo launcher:

 systemctl restart weston-graphical-session.service

Check that X-LINUX-AI is properly installed:

 x-linux-ai -v
X-LINUX-AI version: 5.1.0

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.

2.4. Launch an AI application sample

Once the demo launcher is restarted, notice that it is slightly different because new AI application samples have been installed.
The demo launcher has the following appearance, and you can navigate into the different screens by using the NEXT or BACK buttons.

The demo launcher now contain AI application samples that are described within dedicated article available in the X-LINUX-AI application samples zoo page.

2.5. Enjoy running your own NN models

The above examples provide application samples to demonstrate how to execute models easily on the STM32MPUs.

You are free to update the C/C++ application or Python scripts for your own purposes, using your own NN models.

Source code locations are provided in application sample pages.

Artificial intelligence

Flash memory shortened to gain space in titles, tables and block diagrams

Neural processing unit - NEW

USB vdeo class

Neural network