mirror of
https://github.com/fofolee/uTools-Manuals.git
synced 2025-06-18 22:06:57 +08:00
91 lines
4.3 KiB
HTML
91 lines
4.3 KiB
HTML
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
|
|
<html>
|
|
<head>
|
|
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
|
|
<title>设置训练期间使用的回调函数。</title>
|
|
</head>
|
|
<body class="docs"><div id="layout">
|
|
<div id="layout-content"><div id="function.fann-set-callback" class="refentry">
|
|
<div class="refnamediv">
|
|
<h1 class="refname">fann_set_callback</h1>
|
|
<p class="verinfo">(PECL fann >= 1.0.0)</p><p class="refpurpose"><span class="refname">fann_set_callback</span> — <span class="dc-title">设置训练期间使用的回调函数。</span></p>
|
|
|
|
</div>
|
|
|
|
<div class="refsect1 description" id="refsect1-function.fann-set-callback-description">
|
|
<h3 class="title">说明</h3>
|
|
<div class="methodsynopsis dc-description">
|
|
<span class="methodname"><strong>fann_set_callback</strong></span>
|
|
( <span class="methodparam"><span class="type">resource</span> <code class="parameter">$ann</code></span>
|
|
, <span class="methodparam"><span class="type"><span class="type collable">collable</span></span> <code class="parameter">$callback</code></span>
|
|
) : <span class="type">bool</span></div>
|
|
|
|
<p class="para rdfs-comment">
|
|
设置训练期间使用的回调函数。 这意味着它被<span class="function"><a href="fann_train_on_data.html" class="function">fann_train_on_data()</a></span> 或 <span class="function"><a href="fann_train_on_file.html" class="function">fann_train_on_file()</a></span>调用。
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<div class="refsect1 parameters" id="refsect1-function.fann-set-callback-parameters">
|
|
<h3 class="title">参数</h3>
|
|
<dl>
|
|
|
|
|
|
<dt>
|
|
<code class="parameter">ann</code></dt>
|
|
|
|
<dd>
|
|
|
|
<p class="para">Neural network <span class="type"><a href="language.types.resource.html" class="type resource">resource</a></span>.</p>
|
|
</dd>
|
|
|
|
|
|
|
|
<dt>
|
|
<code class="parameter">callback</code></dt>
|
|
|
|
<dd>
|
|
|
|
<p class="para">
|
|
提供的回调函数接受以下参数：
|
|
<ul class="simplelist">
|
|
<li class="member"><em>ann</em> - 神经网络 <span class="type"><a href="language.types.resource.html" class="type resource">resource</a></span></li>
|
|
<li class="member"><em>train</em> - 训练数据 <span class="type"><a href="language.types.resource.html" class="type resource">resource</a></span>
|
|
或者 当被 <span class="function"><a href="fann_train_on_file.html" class="function">fann_train_on_file()</a></span> 为 <strong><code>NULL</code></strong></li>
|
|
<li class="member"><em>max_epochs</em> - 训练将进行的最大周期数。</li>
|
|
<li class="member"><em>epochs_between_reports</em> - 在调用该函数之前训练进行的最大周期数。</li>
|
|
<li class="member"><em>desired_error</em> - 期望的 <span class="function"><a href="fann_get_mse.html" class="function">fann_get_MSE()</a></span> 或者
|
|
<span class="function"><a href="fann_get_bit_fail.html" class="function">fann_get_bit_fail()</a></span>, 取决于<span class="function"><a href="fann_set_train_stop_function.html" class="function">fann_set_train_stop_function()</a></span>函数选择的停止函数。</li>
|
|
<li class="member"><em>epochs</em> - The current epoch</li>
|
|
</ul>
|
|
</p>
|
|
<p class="para">
|
|
回调将会返回 <strong><code>TRUE</code></strong>. 如果返回 <strong><code>FALSE</code></strong>, 表明训练将会终止。
|
|
</p>
|
|
</dd>
|
|
|
|
|
|
</dl>
|
|
|
|
</div>
|
|
|
|
|
|
<div class="refsect1 returnvalues" id="refsect1-function.fann-set-callback-returnvalues">
|
|
<h3 class="title">返回值</h3>
|
|
<p class="para">Returns <strong><code>TRUE</code></strong> on success, or <strong><code>FALSE</code></strong> otherwise.</p>
|
|
</div>
|
|
|
|
|
|
<div class="refsect1 seealso" id="refsect1-function.fann-set-callback-seealso">
|
|
<h3 class="title">参见</h3>
|
|
<p class="para">
|
|
<ul class="simplelist">
|
|
<li class="member"><span class="function"><a href="fann_train_on_data.html" class="function" rel="rdfs-seeAlso">fann_train_on_data()</a> - 在整个数据集上训练一段时间。</span></li>
|
|
<li class="member"><span class="function"><a href="fann_train_on_file.html" class="function" rel="rdfs-seeAlso">fann_train_on_file()</a> - 在从某个文件读取的整个数据集上训练一段时间。</span></li>
|
|
</ul>
|
|
</p>
|
|
</div>
|
|
|
|
|
|
|
|
</div></div></div></body></html> |