Overview
Sample & Buy
Solutions
Documentation
Tools & Software
Quality & Reliability
eDesignSuite
Get Started
Partner products
Sales Briefcase
  • X-LINUX-AI is an STM32 MPU OpenSTLinux Expansion Package that targets Artificial Intelligence for STM32MP1 Series microprocessors.

    It contains Linux® AI frameworks, as well as application examples to get started with some basic use cases such as computer vision (CV).
    The examples provided in X-LINUX-AI are based on TensorFlow™ Lite models for image classification based on MobileNet v1, and for object detection based on the COCO SSD MobileNet v1 model.
    These examples use either the TensorFlow™ Lite inference engine supporting Python™ scripting and C/C++ applications, either the Coral Edge TPU™ accelerator supporting Python™ scripting and C/C++application, or the Arm NN inference engine supporting C/C++ application.
    These examples use the TensorFlow™ Lite interpreter supporting Python™ scripting, C/C++ applications or both.
    X-LINUX-AI runs on the STM32MP157C-DK2 with a USB camera, on the STM32MP157A-EV1 and STM32MP157C-EV1 with their built-in camera module.
    It also runs on the STM32MP157A-based Avenger96 board from 96Boards (refer to https://www.96boards.org/product/avenger96/), either with a USB camera or D3 Engineering DesignCore® OV5640 camera mezzanine board (refer to https://www.96boards.org/product/d3camera/).

    Key Features

    • TensorFlow™ Lite 2.2.0
    • Coral Edge TPU™ accelerator native support
    • Arm NN 20.05
    • OpenCV 4.1.x
    • Python™ 3.8.x (enabling Pillow module)
    • Support of the STM32MP157F devices operating at up to 800 MHz
    • Python™ and C++ application samples
      • Image classification example using TensorFlow™ Lite based on MobileNet v1 quantized model
      • Object detection example using TensorFlow™ Lite based on COCO SSD MobileNet v1 quantized model
      • Image classification example using Coral Edge TPU™ based on MobileNet v1 quantized model and compiled for the Edge TPU™
      • Object detection example using Coral Edge TPU™ based on COCO SSD MobileNet v1 quantized model and compiled for the Edge TPU™
      • Image classification example using Arm NN TensorFlow™ Lite parser based on MobileNet v1 float model
      • Object detection example using Arm NN TensorFlow™ Lite parser based on COCO SSD MobileNet v1 quantized model
    • The X-LINUX-AI OpenSTLinux Expansion Package is validated with OpenSTLinux Distributions v2.0.0 and v1.2.0 on STM32MP157C-DK2 with a USB camera, and on STM32MP157A-EV1 and STM32MP157C-EV1 with their built-in camera module
    • Support of the Avenger96 board from Linaro™ 96Boards based on the STM32MP157A microprocessor, either with a USB camera or the DesignCore® OV5640 camera mezzanine board from D3 Engineering only tested with the OpenSTLinux Distribution v1.2.0

Get Software

Latest from ST

STM32MPU WIKI
OpenSTLinux Expansion Package