DNQ: Dynamic Network Quantization

data compression conference, 2019.

Cited by: 1|Bibtex|Views41|Links
EI

Abstract:

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

Code:

Data:

Your rating :
0

 

Tags
Comments