chamgj
/
FT_DSP.gitlink.net
forked from FT_DSP/FT_DSP.gitlink.net
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
FT_DSP.gitlink.net/master/html/functionlib/dsplib/nlllossgrad.html

248 lines
29 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!DOCTYPE html>
<html class="writer-html5" lang="zh-CN" data-content_root="../../">
<head>
<meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>NLLLossGrad &mdash; MindSpore Signal+ 使用手册 alpha 文档</title>
<link rel="stylesheet" type="text/css" href="../../_static/pygments.css?v=03e43079" />
<link rel="stylesheet" type="text/css" href="../../_static/css/theme.css?v=e59714d7" />
<link rel="stylesheet" type="text/css" href="../../_static/table.css?v=72b86d3e" />
<script src="../../_static/jquery.js?v=5d32c60e"></script>
<script src="../../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
<script src="../../_static/documentation_options.js?v=406e4f49"></script>
<script src="../../_static/doctools.js?v=9bcbadda"></script>
<script src="../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../_static/translations.js?v=beaddf03"></script>
<script async="async" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
<script src="../../_static/table.js?v=99ed15ba"></script>
<script src="../../_static/js/theme.js"></script>
<link rel="index" title="索引" href="../../genindex.html" />
<link rel="search" title="搜索" href="../../search.html" />
<link rel="next" title="DeconvGradFilter" href="deconvgradfilter.html" />
<link rel="prev" title="NLLLoss" href="nllloss.html" />
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../index.html" class="icon icon-home">
MindSpore Signal+ 使用手册
</a>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../search.html" method="get">
<input type="text" name="q" placeholder="搜索文档" aria-label="搜索文档" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="导航菜单">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../quickstart/index.html">快速入门</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../appdevelop/index.html">应用开发示例</a></li>
<li class="toctree-l1"><a class="reference internal" href="../index.html">算子库支持</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../refdoc/index.html">参考资料</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="移动版导航菜单" >
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../index.html">MindSpore Signal+ 使用手册</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="页面导航">
<ul class="wy-breadcrumbs">
<li><a href="../../index.html" class="icon icon-home" aria-label="Home"></a></li>
<li class="breadcrumb-item"><a href="../index.html">算子库支持</a></li>
<li class="breadcrumb-item"><a href="dsplib_index.html">DSP Library C API Reference</a></li>
<li class="breadcrumb-item active">NLLLossGrad</li>
<li class="wy-breadcrumbs-aside">
<a href="../../_sources/functionlib/dsplib/nlllossgrad.rst.txt" rel="nofollow"> 查看页面源码</a>
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<section id="nlllossgrad">
<h1>NLLLossGrad<a class="headerlink" href="#nlllossgrad" title="Link to this heading"></a></h1>
<p>对 NLLLoss（Negative Log Likelihood Loss）算子的反向传播过程进行计算，得到输入 logits 的梯度。</p>
<p>该算子根据前向 NLLLoss 的 <code class="docutils literal notranslate"><span class="pre">reduction_type</span></code>，对上游梯度进行对应方式的反向分发，仅在真实类别索引处产生非零梯度，其余位置梯度为 0。</p>
<div class="math notranslate nohighlight">
\[\begin{split}\frac{\partial L}{\partial x_{i,j}} =
\begin{cases}
- g_i \cdot w_{y_i}, &amp; j = y_i,\ \text{reduction = none} \\
- g \cdot w_{y_i}, &amp; j = y_i,\ \text{reduction = sum} \\
- g \cdot \dfrac{w_{y_i}}{\sum w}, &amp; j = y_i,\ \text{reduction = mean} \\
0, &amp; j \neq y_i
\end{cases}\end{split}\]</div>
<p>其中：</p>
<ul class="simple">
<li><p><span class="math notranslate nohighlight">\(g_i\)</span> 表示逐样本损失梯度</p></li>
<li><p><span class="math notranslate nohighlight">\(g\)</span> 表示归约后的标量损失梯度</p></li>
<li><p><span class="math notranslate nohighlight">\(y_i\)</span> 表示第 <span class="math notranslate nohighlight">\(i\)</span> 个样本的真实类别索引</p></li>
<li><p><span class="math notranslate nohighlight">\(w_{y_i}\)</span> 表示对应类别权重</p></li>
</ul>
<dl class="simple">
<dt>输入：</dt><dd><ul class="simple">
<li><p><strong>logits</strong> - 前向输入 logits 地址，形状为 <code class="docutils literal notranslate"><span class="pre">[batch,</span> <span class="pre">class_num]</span></code> （仅用于尺寸信息）。</p></li>
<li><dl class="simple">
<dt><strong>loss_grad</strong> - 上游损失梯度地址：</dt><dd><ul>
<li><p><code class="docutils literal notranslate"><span class="pre">reduction_type</span> <span class="pre">=</span> <span class="pre">0</span> <span class="pre">(none)</span></code> 时，形状为 <code class="docutils literal notranslate"><span class="pre">[batch]</span></code></p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">reduction_type</span> <span class="pre">=</span> <span class="pre">1</span> <span class="pre">/</span> <span class="pre">2</span> <span class="pre">(sum</span> <span class="pre">/</span> <span class="pre">mean)</span></code> 时，仅使用 <code class="docutils literal notranslate"><span class="pre">loss_grad[0]</span></code></p></li>
</ul>
</dd>
</dl>
</li>
<li><p><strong>labels</strong> - 真实标签索引地址，形状为 <code class="docutils literal notranslate"><span class="pre">[batch]</span></code>。</p></li>
<li><p><strong>weight</strong> - 类别权重数组地址，形状为 <code class="docutils literal notranslate"><span class="pre">[class_num]</span></code>。</p></li>
<li><p><strong>total_weight</strong> - 权重和地址（仅 <code class="docutils literal notranslate"><span class="pre">reduction_type</span> <span class="pre">=</span> <span class="pre">mean</span></code> 时使用）。</p></li>
<li><p><strong>batch</strong> - batch 大小。</p></li>
<li><p><strong>class_num</strong> - 类别数量。</p></li>
<li><dl class="simple">
<dt><strong>reduction_type</strong> - 损失归约方式：</dt><dd><ul>
<li><p><code class="docutils literal notranslate"><span class="pre">0</span></code>：Sum</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">1</span></code>：Mean</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">2</span></code>：None</p></li>
</ul>
</dd>
</dl>
</li>
<li><p><strong>core_mask</strong> - 核掩码（仅适用于共享存储版本）。</p></li>
</ul>
</dd>
<dt>输出：</dt><dd><ul class="simple">
<li><p><strong>logits_grad</strong> - logits 的梯度输出地址，形状为 <code class="docutils literal notranslate"><span class="pre">[batch,</span> <span class="pre">class_num]</span></code>。</p></li>
</ul>
</dd>
<dt>支持平台：</dt><dd><p><code class="docutils literal notranslate"><span class="pre">FT78NE</span></code>
<code class="docutils literal notranslate"><span class="pre">MT7004</span></code></p>
</dd>
</dl>
<div class="admonition note">
<p class="admonition-title">备注</p>
<ul class="simple">
<li><p>FT78NE 仅支持 fp 类型</p></li>
<li><p>MT7004 支持 hp, fp 类型</p></li>
<li><p>输出梯度在非真实类别位置恒为 0</p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">labels</span></code> 中索引需满足 <code class="docutils literal notranslate"><span class="pre">0</span> <span class="pre">&lt;=</span> <span class="pre">label</span> <span class="pre">&lt;</span> <span class="pre">class_num</span></code></p></li>
</ul>
</div>
<p><strong>共享存储版本:</strong></p>
<dl class="c function">
<dt class="sig sig-object c" id="c.hp_nlllossgrad_s">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">hp_nlllossgrad_s</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">logits</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">loss_grad</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">labels</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">total_weight</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">logits_grad</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">batch</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">class_num</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">reduction_type</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.hp_nlllossgrad_s" title="Link to this definition"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.fp_nlllossgrad_s">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">fp_nlllossgrad_s</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">logits</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">loss_grad</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">labels</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">total_weight</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">logits_grad</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">batch</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">class_num</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">reduction_type</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.fp_nlllossgrad_s" title="Link to this definition"></a><br /></dt>
<dd></dd></dl>
<p><strong>C调用示例：</strong></p>
<div class="highlight-c notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="c1">//FT78NE示例</span>
<span class="linenos"> 2</span><span class="cp">#include</span><span class="w"> </span><span class="cpf">&lt;stdio.h&gt;</span>
<span class="linenos"> 3</span><span class="cp">#include</span><span class="w"> </span><span class="cpf">&lt;nlllossgrad.h&gt;</span>
<span class="linenos"> 4</span>
<span class="linenos"> 5</span><span class="kt">int</span><span class="w"> </span><span class="nf">main</span><span class="p">(</span><span class="kt">int</span><span class="w"> </span><span class="n">argc</span><span class="p">,</span><span class="w"> </span><span class="kt">char</span><span class="o">*</span><span class="w"> </span><span class="n">argv</span><span class="p">[])</span><span class="w"> </span><span class="p">{</span>
<span class="linenos"> 6</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">logits</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0xA0000000</span><span class="p">;</span><span class="w"> </span><span class="c1">// [batch, class_num]</span>
<span class="linenos"> 7</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">loss_grad</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0xA0001000</span><span class="p">;</span><span class="w"> </span><span class="c1">// 上游梯度</span>
<span class="linenos"> 8</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="o">*</span><span class="n">labels</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">int</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0xA0002000</span><span class="p">;</span><span class="w"> </span><span class="c1">// [batch]</span>
<span class="linenos"> 9</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">weight</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0xA0003000</span><span class="p">;</span><span class="w"> </span><span class="c1">// [class_num]</span>
<span class="linenos">10</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">total_weight</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0xA0004000</span><span class="p">;</span>
<span class="linenos">11</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">logits_grad</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0xC0000000</span><span class="p">;</span>
<span class="linenos">12</span>
<span class="linenos">13</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">batch</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">32</span><span class="p">;</span>
<span class="linenos">14</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">class_num</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1000</span><span class="p">;</span>
<span class="linenos">15</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">reduction_type</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span><span class="w"> </span><span class="c1">// Mean</span>
<span class="linenos">16</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_mask</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mh">0xff</span><span class="p">;</span>
<span class="linenos">17</span>
<span class="hll"><span class="linenos">18</span><span class="w"> </span><span class="n">fp_nlllossgrad_s</span><span class="p">(</span><span class="n">logits</span><span class="p">,</span><span class="w"> </span><span class="n">loss_grad</span><span class="p">,</span><span class="w"> </span><span class="n">labels</span><span class="p">,</span><span class="w"> </span><span class="n">weight</span><span class="p">,</span><span class="w"> </span><span class="n">total_weight</span><span class="p">,</span>
</span><span class="hll"><span class="linenos">19</span><span class="w"> </span><span class="n">logits_grad</span><span class="p">,</span><span class="w"> </span><span class="n">batch</span><span class="p">,</span><span class="w"> </span><span class="n">class_num</span><span class="p">,</span><span class="w"> </span><span class="n">reduction_type</span><span class="p">,</span><span class="w"> </span><span class="n">core_mask</span><span class="p">);</span>
</span><span class="linenos">20</span><span class="w"> </span><span class="k">return</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span>
<span class="linenos">21</span><span class="p">}</span>
</pre></div>
</div>
<p><strong>私有存储版本:</strong></p>
<dl class="c function">
<dt class="sig sig-object c" id="c.hp_nlllossgrad_p">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">hp_nlllossgrad_p</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">logits</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">loss_grad</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">labels</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">total_weight</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">logits_grad</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">batch</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">class_num</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">reduction_type</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.hp_nlllossgrad_p" title="Link to this definition"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.fp_nlllossgrad_p">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">fp_nlllossgrad_p</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">logits</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">loss_grad</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">labels</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">weight</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">total_weight</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">logits_grad</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">batch</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">class_num</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">reduction_type</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.fp_nlllossgrad_p" title="Link to this definition"></a><br /></dt>
<dd></dd></dl>
<p><strong>C调用示例：</strong></p>
<div class="highlight-c notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="c1">//FT78NE示例</span>
<span class="linenos"> 2</span><span class="cp">#include</span><span class="w"> </span><span class="cpf">&lt;stdio.h&gt;</span>
<span class="linenos"> 3</span><span class="cp">#include</span><span class="w"> </span><span class="cpf">&lt;nlllossgrad.h&gt;</span>
<span class="linenos"> 4</span>
<span class="linenos"> 5</span><span class="kt">int</span><span class="w"> </span><span class="nf">main</span><span class="p">(</span><span class="kt">int</span><span class="w"> </span><span class="n">argc</span><span class="p">,</span><span class="w"> </span><span class="kt">char</span><span class="o">*</span><span class="w"> </span><span class="n">argv</span><span class="p">[])</span><span class="w"> </span><span class="p">{</span>
<span class="linenos"> 6</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">logits</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0x10810000</span><span class="p">;</span><span class="w"> </span><span class="c1">// L2空间</span>
<span class="linenos"> 7</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">loss_grad</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0x10820000</span><span class="p">;</span>
<span class="linenos"> 8</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="o">*</span><span class="n">labels</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">int</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0x10830000</span><span class="p">;</span>
<span class="linenos"> 9</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">weight</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0x10840000</span><span class="p">;</span>
<span class="linenos">10</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">total_weight</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0x10850000</span><span class="p">;</span>
<span class="linenos">11</span><span class="w"> </span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="n">logits_grad</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="w"> </span><span class="o">*</span><span class="p">)</span><span class="mh">0x10860000</span><span class="p">;</span>
<span class="linenos">12</span>
<span class="linenos">13</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">batch</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">32</span><span class="p">;</span>
<span class="linenos">14</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">class_num</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1000</span><span class="p">;</span>
<span class="linenos">15</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">reduction_type</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">2</span><span class="p">;</span><span class="w"> </span><span class="c1">// None</span>
<span class="linenos">16</span>
<span class="hll"><span class="linenos">17</span><span class="w"> </span><span class="n">fp_nlllossgrad_p</span><span class="p">(</span><span class="n">logits</span><span class="p">,</span><span class="w"> </span><span class="n">loss_grad</span><span class="p">,</span><span class="w"> </span><span class="n">labels</span><span class="p">,</span><span class="w"> </span><span class="n">weight</span><span class="p">,</span><span class="w"> </span><span class="n">total_weight</span><span class="p">,</span>
</span><span class="hll"><span class="linenos">18</span><span class="w"> </span><span class="n">logits_grad</span><span class="p">,</span><span class="w"> </span><span class="n">batch</span><span class="p">,</span><span class="w"> </span><span class="n">class_num</span><span class="p">,</span><span class="w"> </span><span class="n">reduction_type</span><span class="p">);</span>
</span><span class="linenos">19</span><span class="w"> </span><span class="k">return</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span>
<span class="linenos">20</span><span class="p">}</span>
</pre></div>
</div>
</section>
</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="页脚">
<a href="nllloss.html" class="btn btn-neutral float-left" title="NLLLoss" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> 上一页</a>
<a href="deconvgradfilter.html" class="btn btn-neutral float-right" title="DeconvGradFilter" accesskey="n" rel="next">下一页 <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div>
<hr/>
<div role="contentinfo">
<p>&#169; 版权所有 2025 - 2026, NUDT-674。</p>
</div>
利用 <a href="https://www.sphinx-doc.org/">Sphinx</a> 构建，使用的
<a href="https://github.com/readthedocs/sphinx_rtd_theme">主题</a>
由 <a href="https://readthedocs.org">Read the Docs</a> 开发.
</footer>
</div>
</div>
</section>
</div>
<script>
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink