2024-01-16 09:59 AM
Hello,
I am currently working on a ML project for an STM MCU and am in a state where I have chosen an compatible board based on inference time and Flash/RAM consumption, but I don't yet have a physical board. Is it possible to get an estimate of power consumption for my model per inference without having to physically do it (I don't yet have the board) in either STM Developer Cloud STM Cube IDE or NanoEdgeAI?
The MCU I chose is STM32H735G-DK.
Thank you in advance
2024-01-16 11:16 AM
Hello,
You can refer to the following Wiki article: https://wiki.st.com/stm32mcu/wiki/AI:STM32Cube.AI_model_performances
It will give you power consumption measures on different STM32 for different neural network models.
The STM32H735G-DK is part of the selection.
Best Regards