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

[Short Survey] Please give us your feedbacks on ST model Zoo Services

Hi everyone,   In order to help our developers understand how their work is used and what to do in order to improve model zoo, we kindly ask you to look at this survey about ST Model Zoo Services.   Link of the survey: https://docs.google.com/forms/d...

Support for autogenerated code by STM32Cube.AI

Good morning,I have created a project with CubeMX.AI based on an .h5 file constructed in keras following the steps shown on ST tutorialhttps://www.youtube.com/watch?v=grgNXdkmzzQ (Getting Started with STM32Cube.AI).Is it possibile to have an example ...

FCata by Associate
  • 1994 Views
  • 2 replies
  • 1 kudos

LSM6DSOX - DRDY Interrupt

I have an LSM6DSOX on a STEVAL-MKI197V1 on a breadboard. I am able to communicate with the device (reading device ID returns the correct value, all driver calls return 0), but I am not getting an interrupt generated on either INT1 or INT2. I'm using ...

IAdam by Associate
  • 1811 Views
  • 2 replies
  • 0 kudos

Will quantized models of TFLite be enabled soon?

I converted a keras model to a quantized TFLite model to load this on my MCU. But i think Cube.ai doesnt yet support fixed Point TFLite models.Will this feature be enabled in the future?

THarn by Associate II
  • 1138 Views
  • 1 replies
  • 0 kudos

Resolved! Data format to run the quantized neural network?

Hello,i used the stm32ai software to quantize my MNIST model. I can load the quantized model on my STM32H743-Nucleo Board and with the Validation Software I can validate my quantized model on target.But I would like to create my own Application, so I...

0690X000009ZfDiQAK.png
THarn by Associate II
  • 1413 Views
  • 1 replies
  • 0 kudos

Unico 9.0.0.0 Machine Learning Core: How to end "Feature" input

Unico 9.0.0.0 / STEVAL-MKI197V1 (LSM6DS0X) / Machine Learning Core (MLC)When entering Features, how do you end? There should be a "End Feature Configuration" selection but I do not see it in version 9.0.0.0. If I just "Next" another feature selection...

RSelt by Associate II
  • 6435 Views
  • 8 replies
  • 0 kudos

Quantization-aware training

Hello,Is there a way to give X-CUBE-AI a model with quantized-weights? Right now the tool is able to do a custom post-training quantization for a given Keras model. However, what if we have a model that already has quantized weights (which is the cas...

AUzpa by Associate II
  • 1971 Views
  • 1 replies
  • 0 kudos

Resolved! Tensorflow Lite support X-CUBE-AI 4.0.0

Hello,I have noticed that the latest version of X-CUBE-AI (4.0.0) has support for Tensorflow Lite. Therefore I tried to analyze a SSD Mobilenet v1 network that I found on this blog post:Link to blog postLink to .tflite modelWhen analyzing the .tflite...

AUzpa by Associate II
  • 1818 Views
  • 2 replies
  • 0 kudos

How to use the generate code with the IA resources ApplicationTemplate

Hello, I have some questions about using the code generator I am currently using an STM32F446 and I want to use a Keras model driven by python to make a prediction on the data retrieved by the micro-controller in order to get better results. I found ...

CSerg by Associate
  • 4357 Views
  • 5 replies
  • 0 kudos
Announcement

We’re moving the ST Community to a new platform to give you a better and more reliable community experience.