Edge AI

Using "ai_<name>_create(ai_handle* network, const ai_buffer* network_config)"

I want to use my converted model, and the first step as is mentioned in the instructions, is to use this function. But I don't exactly understand what should I pass as the first argument (network) to the function. should I pass "ai_linearmodel_data_w...

Stateful LSTMs

When importing a Keras LSTM model, the stateful=True parameter seems to be ignored by Cube.AI, resulting in a state reset after every prediction. Is it somehow possible to prevent this state reset in Cube.AI, so that the model can actually be used in...

X-Cube-AI 5.1.2 "Internal Error" with ONNX file

I created a sklearn random forest decision tree, which I would like deploy to a STM32H743. I am unable to "Analyse" or "Validate" the model in X-Cube-AI Ver 5.1.2. All I get is an "internal error" message in the log file.The conversion to ONNX was do...

INTERNAL ERROR (Stm32com Exception)

Hello,I am currently using X-CUBE-AI library to run neural networks on a stm32h747. I successfully generated and validated on board single input and output networks, but when I execute the validation through CLI with a multi output network, I get an ...

Is ST better or worse than other MEMS based sensors for Artificial Intelligence offer?

 [webinar - Program decision trees in sensors with a Machine Learning Core]

Hi guys. Has anyone here had any success implementing the FP-AI-VISION1 function pack on the Nucleo-F429ZI or the STM32F429? Is this possible and can it be done without adding external RAM?

Unable to load asc_keras_mod_93_int8.tflite from FP-AI-SENSING-1 using various tensorflow versions in python. Error message: ValueError: quantized_dimension must be in range [0, 1). Was 3.

Hello,I am currently working with the acoustic scene classification (ASC) of the FP-AI-SENSING1 project.I tried to load the tflite model, which is provided at: STM32CubeFunctionPack_SENSING1_V4.0.2\Utilities\AI_Ressources\models\asc_keras_mod_93_int8...

For the MLC, how can the IMU work independently from the microcontroller and wake it up with an interrupt?

[webinar - Program decision trees in sensors with a Machine Learning Core]

Which is the difference between FSM and MLC? And how to integrate the two features?

[webinar - Program decision trees in sensors with a Machine Learning Core]