产品概述
主要优势
在STM32MPU上运行AI模型
包含Linux® AI框架以及应用示例。
XNNPACK支持TensorFlow™ Lite和ONNX Runtime
可使用此工具转换和优化深度神经网络。
描述
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. The face recognition application provided in X-LINUX-AI as a prebuilt binary is based on models retrained by STMicroelectronics. Contact the local STMicroelectronics support for more information about this application.
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.
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/).
-
所有功能
- TensorFlow™ Lite 2.4.1
- Arm NN 20.11
- OpenCV 4.1.x
- Python™ 3.8.x (enabling Pillow module)
- Support for the STM32MP157F devices operating at up to 800 MHz
- 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 tested with the OpenSTLinux Distribution v2.1.0
- Coral Edge TPU™ accelerator native support
- libedgetpu 2.4.1 (built from source) aligned with TensorFlow™ Lite 2.4.1
- The X-LINUX-AI OpenSTLinux Expansion Package v2.1.0 is compatible with Yocto Project build systems Thud and Dunfell. As a consequence, it is compatible with OpenSTLinux Distributions v1.2.0, v2.0.0 and v2.1.0 on STM32MP157C-DK2 with a USB camera, and on STM32MP157A-EV1 and STM32MP157C-EV1 with their built-in camera module
- Support for the OpenSTLinux AI package repository allowing the installation of prebuilt package using apt-* utilities
- Application samples
- C++ / Python™ image classification example using TensorFlow™ Lite based on MobileNet v1 quantized model
- C++ / Python™ object detection example using TensorFlow™ Lite based on COCO SSD MobileNet v1 quantized model
- C++ / Python™ image classification example using Coral Edge TPU™ based on MobileNet v1 quantized model and compiled for the Edge TPU™
- C++ / Python™ object detection example using Coral Edge TPU™ based on COCO SSD MobileNet v1 quantized model and compiled for the Edge TPU™
- C++ image classification example using Arm NN TensorFlow™ Lite parser based on MobileNet v1 float model
- C++ object detection example using Arm NN TensorFlow™ Lite parser based on COCO SSD MobileNet v1 quantized model
- C++ face recognition application using proprietary model capable of recognizing the face of a known (enrolled) user. Contact the local STMicroelectronics support for more information about this application or send a request to edge.ai@st.com
