Edge AI

cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

STM32N6 has been officially launched

The STM32N6 has been officially launched yesterday at the STM32 Summit!      The STM32N6 is based on the Arm® Cortex®-M55 running at 800 MHz. It is the first STM32 MCU to embed the ST Neural-ART accelerator™, an in-house developed neural processing ...

JulianE_0-1733924431757.png

Hii, how to get the quantized model with 8-bits precision?

I am working on the deployment of the CNN model on an STM32F29 board with 8-bits precision.I am able to generate the validation code, but the problem is that the model data are in u64 format (as illustrated in the image below)please help?thanks,

0693W00000Czld5QAB.png
YMaz.1 by Associate
  • 304 Views
  • 0 replies
  • 0 kudos

Data validation failed

Following is my data , I am trying to validate on option of 'validate on desktop'. I am getting following errorLoading: /home/censdata/workspace/har/har_ai/har_ai.ioc projectInitializing: STM32F429ZITx [AI:network] Analyzing model [AI:Generator] Comm...

YMand.6 by Associate II
  • 1202 Views
  • 4 replies
  • 0 kudos

Resolved! STM32CubeMX Cube AI shows less memory than MCU has.

I'm trying to deploy a machine learning model to an STM32H743ZIT6 through cube-ai extension. The model is in .tflite format. When I try to analyze the model this is the result:The tool states that the MCU has 512KB total available and the model excee...

0693W00000BcwCeQAJ.png
RMais by Associate II
  • 1251 Views
  • 6 replies
  • 0 kudos

Extend FP-AI-VISION1 to other boards

FP-AI-VISION1 has many interesting examples. However, all of them are based on STM32H747I-DISCO. Can anyone provide some instructions and ideas about how to extend the examples in FP-AI-VISION1 to other boards, such as STM32H7B3I or even STM32F7 and ...