Fun with Local Image Features
Multi Kernel Descriptors, a different take on a DoG blob detector, and trying to make it all fast using Vulkan compute.
Big Post
Bite Sized
Machine Learning Inference on STM32/Cortex M7
tl;dr: Tensorflow is currently the way to go to run a QAT quantized model on Cortex Mx using optimized CMSIS-NN kernels.