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! X-Cube-AI: Can't analyze model

I'm trying to convert the BirdNET-Analyzer (https://github.com/kahst/BirdNET-Analyzer/tree/main) model to run on a STM32U5A5. However, both the TFLite and STM32Cube.AI MCU Runtime fail.The TFLite runtime fails with: Operator REDUCE_MIN not supported ...

JSGraaf by Associate III
  • 429 Views
  • 2 replies
  • 1 kudos

Setting up NanoEdge Library with .a File in Keil v5

I am working on integrating the NanoEdge library into my STM32 Project using Keil IDE V5, I have been provided with the .a fie for NanoEdge library, but i am not entirely sure how to propoerly link it to my project.could anyone provide a step by step...

ACP by Associate II
  • 352 Views
  • 1 replies
  • 0 kudos

Resolved! Issue Running a GRU/LSTM Model on STM32 with Neural-ART

Hello everyone,I’m trying to run a model on an STM32 MCU with Neural-ART using the ST Edge AI Developer Cloud.The final model includes GRU layers, but when I attempt to quantize and then optimize it, I encounter issues. To debug this, I created a min...

Dresult by Associate III
  • 707 Views
  • 2 replies
  • 2 kudos

Flash overflow when using a quantified tflite model

 Hello!I am using CubeAI (version 9.1) to generate code for running an ML model on a microcontroller.When I generate the code with CubeMX using my .keras model, there are no compilation issues, and it runs perfectly.However, when I generate the code ...

Screenshot from 2025-01-21 16-47-47.png Screenshot from 2025-01-21 16-35-31.png
EnzoC by Associate
  • 709 Views
  • 4 replies
  • 1 kudos

Resolved! Inference error running neural network on STM32WB55

I'm trying to make a snoring detector embedded on stm32wb55 dk board but everytime I encounter an inference unsuccessful :\ to be precise, the returned error looks like that input size or dimension is wrong.this is the code that I am running #include...