STM32 MCUs Machine learning & AI

Showing results for 
Search instead for 
Did you mean: 

Forum Posts

Edge AI for all. NanoEdge AI Studio autoML tool, now free for STM32 and open to all ARM Cortex-M bas

NanoEdge AI Studio v4.3 is now offered for free to all engineers, giving them the opportunity to create highly efficient TinyML libraries that can be deployed on Cortex-M based microcontrollers. In addition, other enhancements have been integrated to...

ST30449_nanoedge-ai-studio-motor (2).jpg ST30449_nanoedge-ai-studio-motor (2).jpg

Nucleo F746 SPI

HelloI am using NUCLEO-F746ZG. SPI1 and ETH are set with CubeMX and programmed with EWARM.SPI1 will not work if there is an ETH setting ”MX_ETH_Init();”. Do you know the reason?

shank by Associate
  • 1 replies
  • 0 kudos

X-CUBE-AI 8.1 is out!

We are pleased to announce that the latest version of STM32Cube.AI is now available.You can download it here. What is new in X-CUBE-AI 8.1.0? TensorFlow 2.12 and 2.12ONNX Runtime 1.15.0Host PC system: adding support for MacOS ARM systemInclu...

Resolved! Updated CubeAI can't find Runtime

I've updated my code to CubeAI 8.1. The middleware is still deleted... but I can add it manually. However when I build the code I gett the error:Description Resource Path Location Typecannot find -l:NetworkRuntime730_CM7_GCC.a AI_FILES_GENERATOR C/C+...

KSOdin2_0-1689857782573.png KSOdin2_1-1689857823405.png KSOdin2_2-1689857862226.png
KSOdin2 by Associate III
  • 1 replies
  • 0 kudos

About Yolov5 being unable to be deployed on CubeAI when transitioning to Onnx

我真的不知道为什么..将出现此问题。将 YOLOv5 转换为 ONNX 后,我无法在其上部署它,因为我的显卡是 1660ti 并将半精度转换为单精度。如果我使用半精度,它可能不支持 16 位半精度(所以要减小我的权重文件的大小并不容易),但如果我切换到单精度,则意味着列表溢出,并且没有指示溢出发生的位置。我真的很相信,事实上,我还没有看到一些 Yolov5 部署在 cubeAI 上......一些大人物知道为什么在这里

微信图片_20230714085808.png 微信图片_20230714085752.png