FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs With Dynamic Fixed-Point Representation

量化(信号处理) 计算机科学 推论 计算机工程 深度学习 人工神经网络 浮点型 深层神经网络 水准点(测量) 计算 人工智能 算法 机器学习 大地测量学 地理
作者
Ahmad Shawahna,Sadiq M. Sait,Aiman H. El‐Maleh,Irfan Ahmad
出处
期刊:IEEE Access [Institute of Electrical and Electronics Engineers]
卷期号:10: 30202-30231 被引量:6
标识
DOI:10.1109/access.2022.3157893
摘要

Deep neural networks (DNNs) have demonstrated their effectiveness in a wide range of computer vision tasks, with the state-of-the-art results obtained through complex and deep structures that require intensive computation and memory. Now-a-days, efficient model inference is crucial for consumer applications on resource-constrained platforms. As a result, there is much interest in the research and development of dedicated deep learning (DL) hardware to improve the throughput and energy efficiency of DNNs. Low-precision representation of DNN data-structures through quantization would bring great benefits to specialized DL hardware. However, the rigorous quantization leads to a severe accuracy drop. As such, quantization opens a large hyper-parameter space at bit-precision levels, the exploration of which is a major challenge. In this paper, we propose a novel framework referred to as the Fixed-Point Quantizer of deep neural Networks (FxP-QNet) that flexibly designs a mixed low-precision DNN for integer-arithmetic-only deployment. Specifically, the FxP-QNet gradually adapts the quantization level for each data-structure of each layer based on the trade-off between the network accuracy and the low-precision requirements. Additionally, it employs post-training self-distillation and network prediction error statistics to optimize the quantization of floating-point values into fixed-point numbers. Examining FxP-QNet on state-of-the-art architectures and the benchmark ImageNet dataset, we empirically demonstrate the effectiveness of FxP-QNet in achieving the accuracy-compression trade-off without the need for training. The results show that FxP-QNet-quantized AlexNet, VGG-16, and ResNet-18 reduce the overall memory requirements of their full-precision counterparts by 7.16x, 10.36x, and 6.44x with less than 0.95%, 0.95%, and 1.99% accuracy drop, respectively.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
手打鱼丸完成签到 ,获得积分10
刚刚
体贴凌柏发布了新的文献求助10
刚刚
开心快乐发大财完成签到,获得积分10
2秒前
萌萌哒完成签到,获得积分10
2秒前
小龅牙吖完成签到,获得积分10
2秒前
Propitious完成签到,获得积分10
3秒前
徐先生1106完成签到,获得积分10
3秒前
Epiphany完成签到,获得积分10
4秒前
舒心的久完成签到 ,获得积分10
4秒前
闻巷雨完成签到 ,获得积分10
6秒前
北风完成签到,获得积分10
7秒前
xliiii完成签到,获得积分10
7秒前
时光倒流的鱼完成签到,获得积分10
8秒前
LL完成签到,获得积分10
8秒前
李李完成签到,获得积分20
8秒前
雨无意完成签到,获得积分10
9秒前
盛宇大天才完成签到,获得积分10
11秒前
游戏人间完成签到 ,获得积分10
12秒前
13秒前
科研通AI5应助淡淡的忆彤采纳,获得10
13秒前
早日毕业完成签到,获得积分10
13秒前
Billie完成签到,获得积分10
14秒前
积极行天完成签到,获得积分10
14秒前
98完成签到,获得积分10
15秒前
nkmenghan完成签到,获得积分20
16秒前
韶邑完成签到,获得积分10
16秒前
penzer完成签到 ,获得积分10
17秒前
suwan完成签到,获得积分10
18秒前
张瀚文完成签到 ,获得积分10
21秒前
不吃香菜完成签到 ,获得积分10
23秒前
何日完成签到,获得积分10
25秒前
明天完成签到,获得积分10
25秒前
rrrick完成签到,获得积分10
25秒前
XF发布了新的文献求助10
26秒前
结实乐曲完成签到,获得积分10
26秒前
26秒前
27秒前
顺利紫山完成签到,获得积分10
28秒前
liaodongjun完成签到,获得积分10
29秒前
30秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038303
求助须知:如何正确求助?哪些是违规求助? 3576013
关于积分的说明 11374210
捐赠科研通 3305780
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029