I am following this guide to do continuous inference on my Xiao ESP32-S3 board. When I upload my model, the code compiles quickly and flashes to the board fine… but then I see this error:
Edge Impulse Inferencing Demo
Starting continious inference in 2 seconds…
ERR: Failed to allocate persistent buffer of size 576, does not fit in tensor arena and reached EI_MAX_OVERFLOW_BUFFER_COUNT
Guru Meditation Error: Core 1 panic’ed (StoreProhibited). Exception was unhandled.
Any debugging ideas?
Welcome to the forum!
The error message you’re seeing, “Failed to allocate persistent buffer of size 576, does not fit in tensor arena and reached EI_MAX_OVERFLOW_BUFFER_COUNT,” indicates that the machine learning model you’re trying to run requires more memory than is available in the tensor arena of the ESP32’s microcontroller.
Can you test with a smaller dataset /. model? Was the impulse able to run correctly? Please share more detail on the project configuration, board that was selected, impulse configuration etc. So we can give you some steps to try.