Hello everyone,
I am a research intern working on edge AI for anomaly detection.
I am trying to deploy the NEAI (libneai.a) model on Cortex A7 of my STM32MP1 target based on Yocto cortexa7t2hf-neon-vfpv4-oe-linux-gnueabi architecture but I am getting error as seen below (highlighted in yellow)
- "conflicting architecture profiles M/A " and
- warning " (NanoEdgeAI.o) uses variable-size enums yet the output is to use 32-bit enums; use of enum values across objects may fail"
I assume the error is because my NEAI project was created for cortex - M4 as Cortex -A7/ STM32MP1 targets were not available.
I can't deploy on Cortex M4 and intend to deploy it on Cortex A7 because -
- AI model input data are available on Cortex A7 so running AI model on Cortex M4 requires inter processor communication between CA7 and CM4 via RPMsgs and OpenAMP which is complicated.
A solution could be to create NEAI project for Cortex A7 as a target but unfortunately NanoEdge AI doesn't have support for Cortex A7 in target selection.
Can you please advise on how I can create NEAI static library for Yocto based Cortex A7 Core on STM32MP1?
Thanks in advance!
