Edge AI

Ask questions and find answers on how to deploy, debug, and optimize AI models on ST microcontrollers, microprocessors, and smart sensors.

cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

Resolved! Tutorial on STM32cubeai

Hi all,I'm starting on AI and so I'm following the tutorial "Getting Started with STM32Cube.AI".  After the first settings I see the message attached. Why?Any Helps?Thanks

sav gas by Associate II
  • 1255 Views
  • 2 replies
  • 0 kudos

How to generate an .ucf/.h file from decision tree .txt file (j48 format).

The standard way to generate a header file with MLC register settings is to generate from decision-tree .txt file (exportet from WEKA or python).In our project we want to avoid tool interaction.The register settings (ucf or header file) should be gen...

HFenz by Associate II
  • 1547 Views
  • 5 replies
  • 0 kudos

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
  • 468 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
  • 1783 Views
  • 4 replies
  • 0 kudos

Resolved! I can't figure how to use external SDRAM for camera&LCD buffer and AI can someone help me please ? (STM32F769I-EVAL)

Hello,I used the example DCMI_CaptureMode for the STM32F769I-EVAL and the CubeMX generator with CubeAI in order to make an object classifier on board. It worked well with the internal RAM for 28*28*1 pictures but now that I want it to work for 128*12...

Bastien.I by Associate II
  • 1037 Views
  • 1 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
  • 1882 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 ...