# Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference

**Authors:** Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, Andrew Howard, Hartwig Adam, Dmitry Kalenichenko  
**arXiv:** [1712.05877](https://arxiv.org/abs/1712.05877)  
**Date:** 2017-12-15  
**Summary page:** https://www.summarizepaper.com/en/paper/1712.05877v1/

## Abstract

The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. We propose a quantization scheme that allows inference to be carried out using integer-only arithmetic, which can be implemented more efficiently than floating point inference on commonly available integer-only hardware. We also co-design a training procedure to preserve end-to-end model accuracy post quantization. As a result, the proposed quantization scheme improves the tradeoff between accuracy and on-device latency. The improvements are significant even on MobileNets, a model family known for run-time efficiency, and are demonstrated in ImageNet classification and COCO detection on popular CPUs.