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

How can I use multiple decision tree with the MLC of a LSM6DSOX

Good afternoon everyone,I am currently working on a predictive maintenance projet using vibration classification with the MLC of a LSM6DSOX.I would like to try using several decision tree at the same time (with a maximum of 8 according to the datashe...

Jmong.1 by Associate II
  • 971 Views
  • 2 replies
  • 0 kudos

New ST Community "Idea Zone" is now available

It is now available a section of the Community page dedicated to New Ideas (LINK). This new "zone" is intended for ST products' users to give the Community technical feedback on available product areas.MEMS&Sensors community group has especially a co...

0693W000001rBE9QAM.png

STM32L5 with Cube.AI

Hi,STM32L5 has Cortex-M33 processor. In the official documentation it says that Cube.AI supports Cortex-M CPUs (including M33). Why is it still not possible to choose AI library for Cortex-M33 on STMCubeMX IDE? Is there anything fundamentally differe...

SKuma.14 by Associate
  • 1187 Views
  • 1 replies
  • 0 kudos

Enabling STM32H745ZI-Q AXI SRAM to store Network Activations

I am using the STM32H745ZI-Q Dual Core MCU. My workflow is to generate the AI library using a Single Core processor and then copy the project into my Dual Core. Now I am trying to use External Ram Configuration (STMCube) to map the activations NOT in...

OSala.1 by Associate II
  • 765 Views
  • 0 replies
  • 0 kudos

Resolved! voice recognition application of STM32L1

Hi, everyone have someone know where can find the voice recognition of STM32L1 application?I just need few Japanese vocabulary to identify command, but I didn't find it. AWS didn't match my request. Could you please help me?

I am using X-cube-AI to generate C code for my ML model. But the resulting constant data is larger than my flash, I'm using F7 with 2MB flash.

How do I run larger ML models (greater than 10MB)? Is interfacing external ROM with QSPI and memory mapping it alone sufficient?Can I use an SD card instead? Can the memory card be memory mapped to internal flash? Can I paste the weights on the memor...

GRang.1 by Associate II
  • 1540 Views
  • 2 replies
  • 0 kudos