2025-07-06 6:35 AM - last edited on 2025-07-06 12:57 PM by mƎALLEm
Hello! How can I store the model's input data in the flash of the STM32N6570-DK, then deploy the model, read the input data from flash, and perform inference? Are there any relevant tutorials for this? I previously followed the model deployment tutorial in the link below. Can this deployment method support reading input_data directly from flash? If not, are there alternative approaches to achieve this goal? Thanks.
https://stm32ai-cs.st.com/assets/embedded-docs/stneuralart_getting_started.html
2025-07-08 2:26 AM - edited 2025-07-08 2:30 AM
Hello @llcc,
We don't currently have any tutorial for that.
We should deliver in the coming days a tutorial about creating a X Cube AI appli to do an ai inference and a FSBL loading this appli from external flash to internal ram. I will update you once we have it available.
Have a good day,
Julian
2025-07-08 6:35 AM
Hello, I am currently trying to write my input_data_int8.bin file to flash, but I keep getting an error that says 'Error: failed to download the file'. How can I fix this? Thanks!
2025-07-08 7:18 AM - edited 2025-07-08 7:19 AM
Hello @llcc,
did you select the external loader for the DK board?
(Click on the bottom left EL icon)
Have a good day,
Julian
2025-07-08 7:24 AM
Yes, I have. I've now identified the issue. It was caused by an incorrect Start Address setting. Changing it to 0x70000000 resolved the problem.