FOMO is a deep learning architecture for running object detection on constrained devices, developed by Edge Impulse.
This is a companion discussion topic for the original entry at https://www.edgeimpulse.com/blog/fomo-self-attention
This is a companion discussion topic for the original entry at https://www.edgeimpulse.com/blog/fomo-self-attention
In the public Impulse referenced in the article on the Impulse Design - Object Detection page, why does it say:
This model won't run on MCUs. Verifying model failed with code -6 and no error message
Does it require a GPU?
Hi @MMarcial
My clone of this project seems to train just fine on the default setting (Cortex-M7 216MHZ).
I can however see in your project that message, and reproduce it when selecting the Arduino Portenta H7 in my cloned project.
It seems to be related to the quantization:
Quantized (int8)
Unptimized (float32)
Let me check with the team, and see what if this is an issue we need to raise.
Best
Eoin