Edge AI

cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

Failed Implementing Tensorflow Lite model with X-CUBE-AI

Hi all,I am trying to build a tensorflow model on STM32G474RE chip,I've got my model.tflite and analyze through the X-CUBE-AI package,but I will always get "Internal Error: 'int' object is not iterable" with the analyzing tool,how should I debug this...

KChen.6 by Associate
  • 572 Views
  • 0 replies
  • 0 kudos

Accuracy metric on new X-Cube-AI Version 5.2.0

With the new X-Cube-AI Version 5.2.0, when I try to validate on desktop/validate on target, the metric for accuracy says "n/a" in the output report, with a note "ACC metric is not computed ("--classifier" option can be used to force it)". Does anyone...

TGan.2 by Associate
  • 853 Views
  • 3 replies
  • 0 kudos

Resolved! X-CUBE-AI not available in CubeMX for the STM32H747I-DISCO?

Hello,When I create a new project in CubeMX for the STM32H747I-DISCO board, I cannot see the X-CUBE-AI package when I click on "Additional Software". Is it because this board has 2 cores Cortex-M7 and M4? Somehow we need to specify on which core the ...

AUzpa by Associate II
  • 1000 Views
  • 3 replies
  • 0 kudos

Validating custom dataset on STM32 X AI.

HiI am following this material to start using STM32 for AI. I have got to the data validation step on page 29 of the document. It works fine while validating using random numbers.But while trying to validate using the dataset, I get the error: TOOL E...

AS.4 by Associate
  • 1018 Views
  • 3 replies
  • 1 kudos

STM32CubeMX, X-CUBE-AI error occurring from analysis of prebuilt .tflite network [AI:network] NOT IMPLEMENTED: Unsupported code generation for layer 'Detection' [AI:network] Analyze fail on the AI model

Hi all,Currently using the STM32H747I-DISCO with camera to explore using computer vision for people detection. I have already successfully used one of the example NN (found in the FP-VISION-AI1) and now look to use the X-Cube-AI to integrate further ...

0693W000006ElCkQAK.png
GWall.2 by Associate II
  • 1126 Views
  • 1 replies
  • 0 kudos

Resolved! Configuration of MLC sensors

I am playing with my STWIN evaluation kit and I am trying to understand the final step of configuration of the Machine Learning Core in the sensor. Are the configuration registers on the sensor flashed like that of an MCU when you load the ucf file? ...

SYama.3 by Associate II
  • 1414 Views
  • 4 replies
  • 0 kudos

installation issue of x-cube.ai on linux system

I have downloaded x-cube.ai software for converting PyTorch model for MCU. I am unable to install x-cube. After extracting zip file, i don't see any option to install. I see a file after extraction "stm32ai. But unable to run it.Please help me regard...

Hpott.2 by Associate
  • 581 Views
  • 1 replies
  • 1 kudos

Hello. I am developing a device to get optical sensor data(about 10KB) and predict. And this device is portable, so power consumption should be considered. STLinux can be a solution? and which board is suggestable? Thanks. GB

I am a SW engineer, so I ordered HW devp. to others.They are using STM32F4 board to gather optical sensor data and display prediction(sensor requires over 200 KHz reliable clock freq. at minimum).For prediction data will be transfered to phone via bl...

GYoon.1 by Associate II
  • 982 Views
  • 5 replies
  • 0 kudos

trying to run an AI validation project.

Hello,I am using stm32l476, i am trying to run an AI validation project.i replaced the UART with USB (CDC profile)but, when trying to run "validation on target" from the CubeMX, i get this message -> LOAD ERROR: STM32 - no connected board(s), invalid...

AA.10 by Associate III
  • 1299 Views
  • 3 replies
  • 0 kudos