期刊文献+

激活函数的对比测试与分析 被引量:18

Comparative Test and Analysis of Activation Function Library
下载PDF
导出
摘要 随着人工智能的发展、含有激活函数库开源框架的增加,针对激活函数库的对比与分析越来越重要。在Intel x86架构上进行实验,从函数性能、稳定性、精度3个方面测试并分析了PyTorch和TensorFlow两种主流人工智能框架中的常用激活函数。实验结果表明,PyTorch的整体稳定性要高于TensorFlow,且Sigmoid、Hardsigmoid、SeLU、ReLU、ReLU6、Tanh函数的性能皆优于TensorFlow;在精度方面,TensorFlow中除SeLU函数与LeakyReLU函数稍差些,其余函数与PyTorch表现相当。 With the development of AI,an increasing number of open source framework that includes activation function began to emerge,so the comparison and analysis between different activation libraries become more and more important.The experiment is carried out on the architecture of Intel x86.This paper tests commonly used activation function in two mainstream AI framework,PyTorch and TensorFlow,from three aspects:performance,stability and accuracy.Results show that the stability of PyTorch is higher than that of TensorFlow.The performance of Sigmoid,Hardsigmoid,SeLU,ReLU,ReLU6 and Tanh in PyTorch is better than that in TensorFlow.In terms of accuracy,except SeLU function and leaky ReLU function,the performance of other functions in TensorFlow is similar with that of PyTorch.
作者 王攀杰 郭绍忠 侯明 郝江伟 许瑾晨 WANG Panjie;GUO Shaozhong;HOU Ming;HAO Jiangwei;XU Jinchen(Information Engineering University,Zhengzhou 450001,China;State Key Laboratory of Mathematical Engineering and Advanced Computing,Zhengzhou 450001,China)
出处 《信息工程大学学报》 2021年第5期551-557,共7页 Journal of Information Engineering University
基金 国家自然科学基金资助项目(61802434)。
关键词 激活函数 PyTorch TensorFlow activation function PyTorch TensorFlow
  • 相关文献

参考文献1

二级参考文献9

  • 1Laurent Thevenoux, Matthieu Martel, Philippe Langlois. Accuracy Optimization using Automatic Compensation in Floating-Point Arithmetic [ EB/OL ]. [ 2014-12-10 ]. ht- tp ://perso. univ-perp, fr/mmartel/scan-12-LMT, pdf.
  • 2Takeshi Ogita, Siegfried M, Rump, ShinlchiOishi. Accu- rate Sum and Dot Product[ J]. SIAM Journal on Scientific Computing( SISC ) , 2005, 26 (6) : 1955-1988.
  • 3IEEE. ISBN-13 : 978-0738157535, IEEE 754-2008: IEEE Standard for Floating-Point Arithmetic[ S]. 2008.
  • 4Muller J M. On the definition of ulp (x) [ EB/OL]. [2014-12-10]. http://ljk, imag. fr/membres/Carine. Lu- cas/TPScilab/JMMuller/ulp-toms, pdf.
  • 5Goldberg D. What every computer scientist should know about ? oating-point arithmetic [ J ]. ACM Computing Sur- veys, 199t, 23(1) :5-47.
  • 6Ramon E Moore,R BakerKearfott, Michael J Cloud. Intro- duction to Interval Analysis [ M ]. Society for Industrial and Applied Mathmatics,2009.
  • 7Jean-Michel Muller, Nicolas Brisebarre, Florent de Di- nechin, Claude-Pierre Jeannerod. Handbook of Floating- Point Arithmetic[ M ]. New York : Birkhauser Boston, c/ o Springer Science + Business Media, 2010.
  • 8Laurent Fousse, Guillaume Hanrot, Vincent LeFevre, et al. MPFR: A Multiple-Precision Binary Floating-Point Li- brary With Correct Rounding [ J ]. ACM Transactions on Mathematical Software, 2007,33 ( 2 ) : 1-13.
  • 9Florian Benz, Andreas Hildebrandt, Sebastian Hack. A Dynamic Program Analysis to Find Floating-Point Accura- cy Problems [ C ]//PLDI' 12. 2012 : 11-16.

共引文献3

同被引文献190

引证文献18

二级引证文献9

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部