r494.html
来自「一个功能强大的神经网络分析程序」· HTML 代码 · 共 222 行
HTML
222 行
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN""http://www.w3.org/TR/html4/loose.dtd"><HTML><HEAD><TITLE>fann_save_to_fixed</TITLE><link href="../style.css" rel="stylesheet" type="text/css"><METANAME="GENERATOR"CONTENT="Modular DocBook HTML Stylesheet Version 1.79"><LINKREL="HOME"TITLE="Fast Artificial Neural Network Library"HREF="index.html"><LINKREL="UP"TITLE="Input/Output"HREF="x472.html"><LINKREL="PREVIOUS"TITLE="fann_save"HREF="r474.html"><LINKREL="NEXT"TITLE="fann_create_from_file"HREF="r519.html"></HEAD><BODYCLASS="refentry"BGCOLOR="#FFFFFF"TEXT="#000000"LINK="#0000FF"VLINK="#840084"ALINK="#0000FF"><DIVCLASS="NAVHEADER"><TABLESUMMARY="Header navigation table"WIDTH="100%"BORDER="0"CELLPADDING="0"CELLSPACING="0"><TR><THCOLSPAN="3"ALIGN="center">Fast Artificial Neural Network Library</TH></TR><TR><TDWIDTH="10%"ALIGN="left"VALIGN="bottom"><AHREF="r474.html"ACCESSKEY="P">Prev</A></TD><TDWIDTH="80%"ALIGN="center"VALIGN="bottom"></TD><TDWIDTH="10%"ALIGN="right"VALIGN="bottom"><AHREF="r519.html"ACCESSKEY="N">Next</A></TD></TR></TABLE><HRALIGN="LEFT"WIDTH="100%"></DIV><H1><ANAME="api.fann_save_to_fixed"></A>fann_save_to_fixed</H1><DIVCLASS="refnamediv"><ANAME="AEN495"></A><H2>Name</H2>fann_save_to_fixed -- Save an ANN to a fixed-point file.</DIV><DIVCLASS="refsect1"><ANAME="AEN498"></A><H2>Description</H2><codeclass="methodsynopsis"> <spanclass="type">void </span>fann_save_to_fixed(<spanclass="methodparam"><spanclass="type">struct fann * </span><spanclass="parameter">ann</span></span><spanclass="methodparam">, <spanclass="type">const char * </span><spanclass="parameter">configuration_file</span></span>); </code><P> <CODECLASS="function">fann_save_to_fixed</CODE> will attempt to save <CODECLASS="parameter">ann</CODE> to the file located at <CODECLASS="parameter">configuration_file</CODE> as a fixed-point network. </P><P> This is useful for training a network in floating points, and then later executing it in fixed point. </P><P> The function returns the bit position of the fix point, which can be used to find out how accurate the fixed point network will be. A high value indicates high precision, and a low value indicates low precision. </P><P> A negative value indicates very low precision, and a very strong possibility for overflow. (the actual fix point will be set to 0, since a negative fix point does not make sense). </P><P> Generally, a fix point lower than 6 is bad, and should be avoided. The best way to avoid this, is to have less connections to each neuron, or just less neurons in each layer. </P><P> The fixed point use of this network is only intended for use on machines that have no floating point processor, like an iPAQ. On normal computers the floating point version is actually faster. </P><P>This function appears in FANN >= 1.0.0.</P></DIV><DIVCLASS="NAVFOOTER"><HRALIGN="LEFT"WIDTH="100%"><TABLESUMMARY="Footer navigation table"WIDTH="100%"BORDER="0"CELLPADDING="0"CELLSPACING="0"><TR><TDWIDTH="33%"ALIGN="left"VALIGN="top"><AHREF="r474.html"ACCESSKEY="P">Prev</A></TD><TDWIDTH="34%"ALIGN="center"VALIGN="top"><AHREF="index.html"ACCESSKEY="H">Home</A></TD><TDWIDTH="33%"ALIGN="right"VALIGN="top"><AHREF="r519.html"ACCESSKEY="N">Next</A></TD></TR><TR><TDWIDTH="33%"ALIGN="left"VALIGN="top">fann_save</TD><TDWIDTH="34%"ALIGN="center"VALIGN="top"><AHREF="x472.html"ACCESSKEY="U">Up</A></TD><TDWIDTH="33%"ALIGN="right"VALIGN="top">fann_create_from_file</TD></TR></TABLE></DIV></BODY></HTML>⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?