DNQ: Dynamic Network Quantization
data compression conference, 2019.
Network quantization is an effective method for the deployment of neural networks on memory and energy constrained mobile devices. In this paper, we propose a Dynamic Network Quantization (DNQ) framework which is composed of two modules: a bit-width controller and a quantizer. Unlike most existing quantization methods that use a universal...More
Full Text (Upload PDF)
PPT (Upload PPT)