Post training 4-bit quantization of convolutional
networks for rapid-deployment
Ron Banner1 , Yury Nahshan1 , and Daniel Soudry2
Intel – Artificial Intelligence Products Group (AIPG)1
Technion – Israel Institute of Technology2
{ron.banner, yury.nahshan}@intel.com
daniel.soudry@gmail.com
Abstract
Convolutional neural networks require significant memory bandwidth and stor-
age for in ...
附件列表