Reproduce “TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Julian Moosmann, Marco Giordano, Christian Vogt, Michele Magno
TinyissimoYOLO is a small, 8-bit-quantized object detector designed for low-power microcontrollers. It uses an 88×88 input and a compact YOLO-inspired network, then runs the same quantized model across four devices. MAX78000 measured 5.5 ms per inference, versus 359 ms on STM32H7A3; this cross-device result shows a speed advantage, but does not isolate the accelerator as its sole cause.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.