2022-06-30 02:35 PM
I suspect it's an issue with the stm32ai binary not being compliant with Mac M1, but perhaps someone can guide me towards the solution.
I tried the simplest X-CUBE-AI examples, such as the one with the sine wave and the one with HAR. Even when I take networks pretrained by others, loading them in the STM32CUBE gives me "Analyze fail on the AI model" every time.
I tried running stm32ai directly from the command line and I got "illegal hardware instruction" error.
Anyone running X-CUBE-AI on Mac M1, could you please help?
Thanks!
2022-07-08 10:08 AM
I have the same problem with you.
2022-07-08 10:13 AM
@fauvarque.daniel Looking forward to your solution. Thanks a lot.
2022-07-11 01:18 AM
Hello,
Unfortunately M1 macs are currently not natively supported, but did you try to enable Rosetta 2 compatibility mode ?
You can try the answer used for "nvm" from this thread: https://github.com/nvm-sh/nvm/issues/2350#issuecomment-734132550
Then try starting the stm32ai command line again from the terminal,
Hope it can help,
Romain
2022-07-11 09:57 AM
@Romain LE DONGE
Dear Romain,
Thanks for your answer and possible solution. Unfortunately, I try it but fail. Maybe we need a new build one for M1 specifically or use windows instead.
Hope your team's new build for M1.
Best wishes,
Baichuan