2025-05-14 4:49 PM
I have a tflite model that I want to test on my B-U585I-IOT02A Discovery kit, after some issues with X-Cube.AI expansion for CubeMX I decided to try use ST Edge AI Developer Cloud. Everything goes smoothly until I try to generate the code, All option to generate fail apart from the C code of the nn. As the error gives no explanation I have no clue of what happend and no way to fix it.
2025-05-15 1:26 AM
Hello @YuriM1
It is possible that your model uses larger RAM and/or size than available on the target.
Did you try a benchmark on B-U585I-IOT02A to see it your model fits ?
Is it possible to share your model ?
Best regards,
Yanis
2025-05-15 4:22 AM
The model benchmarks without problems and does not use more RAM or flash than the maximum. I added some pictures of the benchmark session and it uses 1.16 MiB of flash over 2 and 349.87 KiB over 768 so it should fit and runs in 2 seconds approximately.
As .tflite cannot be uploaded here I added the repo where the model is in case it can be useful