📄 svm_learn.html
字号:
Content-type: text/html<HTML><HEAD><TITLE>Manpage of SVM_LEARN</TITLE></HEAD><BODY><H1>SVM_LEARN</H1>Section: TinySVM (1)<BR>Updated: August 2002<BR><A HREF="#index">Index</A><A HREF="http://localhost/cgi-bin/man/man2html">Return to Main Contents</A><HR><A NAME="lbAB"> </A><H2>NAME</H2>svm_learn - manual page for svm_learn of 0.09<A NAME="lbAC"> </A><H2>SYNOPSIS</H2><B>svm_learn</B>[<I>options</I>] <I>training-file model-file</I><A NAME="lbAD"> </A><H2>DESCRIPTION</H2>TinySVM - tiny SVM packageCopyright (C) 2000-2002 Taku Kudo, All rights reserved.<A NAME="lbAE"> </A><H3>Solver Type:</H3><DL COMPACT><DT><B>-l</B>, <B>--solver-type</B>=<I>INT</I><DD>select type of solver.TYPE: 0 - C-SVM (default)<DT><DD>1 - C-SVR2 - One-Class-SVM (experimental)</DL><A NAME="lbAF"> </A><H3>Kernel Parameter:</H3><DL COMPACT><DT><B>-t</B>, <B>--kernel-type</B>=<I>INT</I><DD>select type of kernel function.TYPE: 0 - linear (w * x) (default)<DT>1 - polynomial<DD>(s w * x + r)^d<DT>2 - neural<DD>tanh (s w * x + r)<DT>3 - RBF<DD>exp (-s * ||w-x||^2)<DT>4 - ANOVA<DD>(sum_i [exp(-s * ||w_i-x_i||^2)])^d<DT><B>-d</B>, <B>--kernel-degree</B>=<I>INT</I><DD>set INT for parameter d in polynomial kernel. (default 1)<DT><B>-r</B>, <B>--kernel-param-r</B>=<I>FLOAT</I><DD>set FLOAT for parameter r in polynomial kernel. (default 1)<DT><B>-s</B>, <B>--kernel-param-s</B>=<I>FLOAT</I><DD>set FLOAT for parameter s in polynomial kernel. (default 1)</DL><A NAME="lbAG"> </A><H3>Optimization Parameter:</H3><DL COMPACT><DT><B>-m</B>, <B>--cache-size</B>=<I>FLOAT</I><DD>set FLOAT for cache memory size (MB). (default 40.0)<DT><B>-c</B>, <B>--cost</B>=<I>FLOAT</I><DD>set FLOAT for cost C of constraints violation,trade-off between training error and margin. (default 1.0)<DT><B>-e</B>, <B>--termination-criterion</B>=<I>FLOAT</I><DD>set FLOAT for tolerance of termination criterion.(default 0.001)<DT><B>-H</B>, <B>--shrinking-size</B>=<I>INT</I><DD>set INT for number of iterations variable needs tobe optimal before considered for shrinking. (default 100)<DT><B>-p</B>, <B>--shrinking-eps</B>=<I>FLOAT</I><DD>set FLOAT for initial threshold value of shrinking process.(default 2.0)<DT><B>-f</B>, <B>--do-final-check</B>=<I>INT</I><DD>do final optimality check for variables removedby shrinking. (default 1)<DT><B>-i</B>, <B>--insensitive-loss</B>=<I>FLOAT</I><DD>set FLOAT for epsilon in epsilon-insensitive loss functionused in C-SVR cost evaluation. (default 0.1)</DL><A NAME="lbAH"> </A><H3>Miscellaneous:</H3><DL COMPACT><DT><B>-M</B>, <B>--model</B>=<I>FILE</I><DD>set FILE, FILE.idx for initial condition model file.<DT><B>-I</B>, <B>--sv-index</B><DD>write all alpha and gradient to MODEL.idx.<DT><B>-W</B>, <B>--compress</B><DD>calculate vector w (w * x + b), instead of alpha.<DT><B>-V</B>, <B>--verbose</B><DD>set verbose mode.<DT><B>-v</B>, <B>--version</B><DD>show the version of TinySVM and exit.<DT><B>-h</B>, <B>--help</B><DD>show this help and exit.</DL><P>TinySVM - tiny SVM packageCopyright (C) 2000-2002 Taku Kudo, All rights reserved.<P><HR><A NAME="index"> </A><H2>Index</H2><DL><DT><A HREF="#lbAB">NAME</A><DD><DT><A HREF="#lbAC">SYNOPSIS</A><DD><DT><A HREF="#lbAD">DESCRIPTION</A><DD><DL><DT><A HREF="#lbAE">Solver Type:</A><DD><DT><A HREF="#lbAF">Kernel Parameter:</A><DD><DT><A HREF="#lbAG">Optimization Parameter:</A><DD><DT><A HREF="#lbAH">Miscellaneous:</A><DD></DL></DL><HR>This document was created by<A HREF="http://localhost/cgi-bin/man/man2html">man2html</A>,using the manual pages.<BR>Time: 06:05:57 GMT, August 20, 2002</BODY></HTML>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -