2 code implementations • 16 Jul 2020 • Christopher Neff, Aneri Sheth, Steven Furgurson, Hamed Tabkhi
The largest model is able to come within 4. 4% accuracy of the current state-of-the-art, while having 1/3 the model size and 1/6 the computation, achieving 23 FPS on Nvidia Jetson Xavier.