I am trying to follow the DM00570145 and validate on target (STM32F746 Discovery Board, XCUBE-AI 6.0.0, toolchain: STM32CUBE IDE), I cannot get the output listed on Figure 61. "Layer by layer results - Validation on target", especially the "ms" runni...
Hello,I am trying to generate the code for a neural network with STCubeMX, and I'm following the manual you have posted here (https://www.st.com/resource/en/user_manual/dm00570145-getting-started-with-xcubeai-expansion-package-for-artificial-intellig...
I use x-cube-ai 6.0 version & stm32h747i-disco board.By clicking on the [Advanced Settings] button, i use external flash memory for the weights and it works well.However, when [Use external RAM] button & copy weight to RAM , there's some problem and ...
Hi,I am wondering does ST Micro provides any example around unsupervisory Machine learning examples to implement on board learning using ST MEMS vibration sensor and STM32.As I can see Cartesiam provides some examples and the tools to does this work ...
Dear STM community,I am trying to deploy a simple tflite model on my STM32, but I can't get through the analyze step. I got the following error:TOOL ERROR: Unknown layer type SHAPE, stopping.If I convert the model to Keras (model and topology), it wo...
Hello dear Engineers,I have a system with 3 inputs and 3 outputs. The system outputs are completely coupled with its input, but the system is supposed to be LTI. This leads me to a simple feed-forward neural network since modeling and controlling fro...
Hello, I have a STM32F746G-DISCO which has a microcontroller with 1 Mbytes of Flash memory and 340 Kbytes of RAM. However, I would need more space for my bigger Keras models. I have seen examples of code in the new function pack FP-AI-VISION1 which ...
I'm using a Nucleo-144 and have not been able to get X-CUBE-AI working in TrustZone. I'm using STM32CubeIDE and trying to add X-CUBE-AI with the software component manager (with the integrated STM32CubeMX).Interestingly, before a recent update (so ST...
I loaded my mobilenetv3 model in STM32CubeAI but when I tried to choose the compression ratio of 4 and 8 to reduce size, the RAM and FLASH requirements are still the same.Also, I optimized my model in tensorflow lite which results in ~2MB, but when I...