1. X-LINUX-AI v6.2.0[edit | edit source]
 Information
|
This version is compatible with Yocto Project® build system Scarthgap (v5.0.15) and has been validated against the OpenSTLinux ecosystem release v6.2.0  and validated on STM32MP1 series' boards  and STM32MP2 series' boards
|
.
1.1. Contents[edit | edit source]
- AI Frameworks :
- STAI_MPU Unified API based on OpenVX™(STM32MP25x and STM32MP23x only), TensorFlow Lite and ONNX Runtime compatible with all STM32MPU series
- TIM-VX [1] 1.2.22 (STM32MP25x and STM32MP23x only)
- TensorFlow™ [2] Lite 2.18.0 with VX-delegate (NPU/GPU for STM32MP25x and STM32MP23x only) and XNNPACK delegate activated (CPU only)
- ONNX Runtime [3] 1.19.2 with VSINPU execution provider (NPU/GPU for STM32MP25 and STM32MP23x only) and XNNPACK provider activated (CPU only)
- On Device Learning features added for ONNX Runtime
- ONNX [4] 1.16.2 python version for On Device Learning
- PyTorch™ [5] 2.3.1 python version for On Device Learning
- Out of the box applications examples:
- Image classification :
- C++ / Python™ example using STAI_MPU Unified API based on the MobileNet v1 and v2 quantized models.
- Object detection :
- C++ / Python™ example using STAI_MPU Unified API based on the SSD MobileNet v1 and v2 quantized models.
- Multi pose estimation :
- Python™ example using STAI_MPU Unified API based on YoloV8n pose quantized model.
- Semantic segmentation :
- Python™ example using STAI_MPU Unified API based on DeepLabV3 quantized model.
- Face Recognition :
- C++ example using STAI_MPU Unified API based on the blazeface and facenet quantized models.
- People Tracking and Heatmap :
- Python™ example using STAI_MPU Unified API based on the yolov8n quantized model.
- On Device Learning for Object detection :
- Python™ example using STAI_MPU Unified API based on SSD MobileNet v2 as student and RT-DETR transformer model as teacher.
- Step by step Jupyterlab™ notebook available for this application.
- Note: applications are based on Gstreamer 1.22.x, GTK® 3.x, OpenCV 4.9.x, Pillow, Python™ 3
- Image classification :
- On-target utilities:
- X-LINUX-AI tool suite: software information, management of AI packages, and benchmarking of neural network models.
- Support for a wide range of image sensors and camera modules for STM32 MPUs including:
- IMX335 (5MP) for STM32MP2 with the use of its internal ISP
- GC2145
- OV5640 for STM32MP13xx
- Host tools:
- ST Edge AI tool for NBG generation
- X-LINUX-AI SDK add-on extending the OpenSTLinux SDK with AI functionality to develop and build an AI application easily. The X-LINUX-AI SDK add-on supports all the above frameworks. It is available from the X-LINUX-AI product page
1.2. Validated hardware[edit | edit source]
X-LINUX-AI v6.2.0 is supported on all STM32MP1 series' boards and STM32MP2 series' boards and it has been validated on the following boards:
- STM32MP257F-EV1 Evaluation board
- STM32MP257F-DK Discovery kit
- STM32MP257F-DK Discovery kit for STM32MP23x lines evaluation
- STM32MP215F-DK Discovery kit
- STM32MP157F-DK2 Discovery kit
- STM32MP135F-DK Discovery kit