Combining a deep-depthwise CNN architecture with variable quantization in BitNetMCU achieves state-of-the-art MNIST accuracy on a low-end 32-bit microcontroller with 4 kB RAM and 16 kB flash.
Is it possible to implement reasonably accurate inference of MNIST, the handwritten numbers dataset, on a “3 cent” Microcontroller with only 64 bytes of RAM and 1K of instruction memory?
BitNetMCU is a project focused on the training and inference of low-bit quantized neural networks, designed to run efficiently on low-end microcontrollers like the CH32V003. Quantization aware training (QAT) and fine-tuning of model structure allowed surpassing 99% Test accuracy on a 16x16 MNIST dataset in only 2kb of RAM and 16kb of Flash.
