-
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 TensorFlowâ„¢ 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 TensorFlowâ„¢ Lite inference engine supporting Pythonâ„¢ scripting and C/C++ applications, either the Coral Edge TPUâ„¢ accelerator supporting Pythonâ„¢ scripting and C/C++application, or the Arm NN inference engine supporting C/C++ application.
These examples use the TensorFlowâ„¢ Lite interpreter supporting Pythonâ„¢ 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
- TensorFlowâ„¢ Lite 2.2.0
- Coral Edge TPU™ accelerator native support
- Arm NN 20.05
- OpenCV 4.1.x
- Pythonâ„¢ 3.8.x (enabling Pillow module)
- Support of the STM32MP157F devices operating at up to 800Â MHz
- Pythonâ„¢ 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-AIÂ 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
| Part Number | General Description | Software Version | Supplier | Download |
|---|---|---|---|---|
| X-LINUX-AI | AI Expansion Package for STM32 MPU OpenSTLinux | 2.0 | ST | Go to site Get from GitHub |
Featured Videos
Follow issues and share solutions on Github for STM32Cube MCU packages. Integrate your own software components in a STM32Cube Expansion for STM32CubeMX and STM32CubeIDE tools, thanks to the new STM32PackCreator utility
STM32CubeMX is part of the STM32Cube initiative designed to simplify and accelerate the development of applications for STM32 microcontrollers. STM32CubeMX offers the possibility to generate C projects using embedded software offers packages like CMSIS-Pack compliant software packs. Starting with the 6.0.0 revision, STM32CubeMX is delivered with STM32PackCreator, an STM32 pack creation graphical companion tool, whose main purpose is the creation of software packs.
MadeForSTM32â„¢ is a new quality label delivered by ST, which is granted after an evaluation process. It helps engineers identify third party solutions with the highest level of integration and quality for the STM32 microcontrollers' ecosystem. MadeForSTM32â„¢ is offered to members of the ST Partner Program who want to go one step further in our collaboration, with the overall objective of contributing to a high-quality STM32 ecosystem.
All resources
Product Specifications (1)
| Resource title | Latest update | |||
|---|---|---|---|---|
| 26 Sep 2020 |
26 Sep 2020
|
Presentations (2)
| Resource title | Latest update | |||
|---|---|---|---|---|
| 14 Apr 2020 |
14 Apr 2020
|
|||
| 11 Aug 2020 |
11 Aug 2020
|
License Agreement (1)
| Resource title | Latest update | |||
|---|---|---|---|---|
| 20 Oct 2020 |
20 Oct 2020
|
