| <!DOCTYPE html> |
| |
| <html lang="en"> |
| <head> |
| <meta charset="utf-8"/> |
| <meta content="IE=edge" http-equiv="X-UA-Compatible"/> |
| <meta content="width=device-width, initial-scale=1" name="viewport"/> |
| <meta content="Gluon Loss API" property="og:title"> |
| <meta content="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/og-logo.png" property="og:image"> |
| <meta content="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/og-logo.png" property="og:image:secure_url"> |
| <meta content="Gluon Loss API" property="og:description"/> |
| <title>Gluon Loss API — mxnet documentation</title> |
| <link crossorigin="anonymous" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css" integrity="sha384-1q8mTJOASx8j1Au+a5WDVnPi2lkFfwwEAa8hDDdjZlpLegxhjVME1fgjWPGmkzs7" rel="stylesheet"/> |
| <link href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css" rel="stylesheet"/> |
| <link href="../../../_static/basic.css" rel="stylesheet" type="text/css"> |
| <link href="../../../_static/pygments.css" rel="stylesheet" type="text/css"> |
| <link href="../../../_static/mxnet.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript"> |
| var DOCUMENTATION_OPTIONS = { |
| URL_ROOT: '../../../', |
| VERSION: '', |
| COLLAPSE_INDEX: false, |
| FILE_SUFFIX: '.html', |
| HAS_SOURCE: true, |
| SOURCELINK_SUFFIX: '.txt' |
| }; |
| </script> |
| <script src="https://code.jquery.com/jquery-1.11.1.min.js" type="text/javascript"></script> |
| <script src="../../../_static/underscore.js" type="text/javascript"></script> |
| <script src="../../../_static/searchtools_custom.js" type="text/javascript"></script> |
| <script src="../../../_static/doctools.js" type="text/javascript"></script> |
| <script src="../../../_static/selectlang.js" type="text/javascript"></script> |
| <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script> |
| <script type="text/javascript"> jQuery(function() { Search.loadIndex("/versions/0.12.1/searchindex.js"); Search.init();}); </script> |
| <script> |
| (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ |
| (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new |
| Date();a=s.createElement(o), |
| m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) |
| })(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); |
| |
| ga('create', 'UA-96378503-1', 'auto'); |
| ga('send', 'pageview'); |
| |
| </script> |
| <!-- --> |
| <!-- <script type="text/javascript" src="../../../_static/jquery.js"></script> --> |
| <!-- --> |
| <!-- <script type="text/javascript" src="../../../_static/underscore.js"></script> --> |
| <!-- --> |
| <!-- <script type="text/javascript" src="../../../_static/doctools.js"></script> --> |
| <!-- --> |
| <!-- <script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script> --> |
| <!-- --> |
| <link href="../../../genindex.html" rel="index" title="Index"> |
| <link href="../../../search.html" rel="search" title="Search"/> |
| <link href="gluon.html" rel="up" title="Gluon Package"/> |
| <link href="data.html" rel="next" title="Gluon Data API"/> |
| <link href="rnn.html" rel="prev" title="Gluon Recurrent Neural Network API"/> |
| <link href="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-icon.png" rel="icon" type="image/png"/> |
| </link></link></link></meta></meta></meta></head> |
| <body background="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-background-compressed.jpeg" role="document"> |
| <div class="content-block"><div class="navbar navbar-fixed-top"> |
| <div class="container" id="navContainer"> |
| <div class="innder" id="header-inner"> |
| <h1 id="logo-wrap"> |
| <a href="../../../" id="logo"><img src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet_logo.png"/></a> |
| </h1> |
| <nav class="nav-bar" id="main-nav"> |
| <a class="main-nav-link" href="/versions/0.12.1/install/index.html">Install</a> |
| <span id="dropdown-menu-position-anchor"> |
| <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Gluon <span class="caret"></span></a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> |
| <li><a class="main-nav-link" href="/versions/0.12.1/tutorials/gluon/gluon.html">About</a></li> |
| <li><a class="main-nav-link" href="https://www.d2l.ai/">Dive into Deep Learning</a></li> |
| <li><a class="main-nav-link" href="https://gluon-cv.mxnet.io">GluonCV Toolkit</a></li> |
| <li><a class="main-nav-link" href="https://gluon-nlp.mxnet.io/">GluonNLP Toolkit</a></li> |
| </ul> |
| </span> |
| <span id="dropdown-menu-position-anchor"> |
| <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">API <span class="caret"></span></a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> |
| <li><a class="main-nav-link" href="/versions/0.12.1/api/python/index.html">Python</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/api/c++/index.html">C++</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/api/julia/index.html">Julia</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/api/perl/index.html">Perl</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/api/r/index.html">R</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/api/scala/index.html">Scala</a></li> |
| </ul> |
| </span> |
| <span id="dropdown-menu-position-anchor-docs"> |
| <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Docs <span class="caret"></span></a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-docs"> |
| <li><a class="main-nav-link" href="/versions/0.12.1/faq/index.html">FAQ</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/tutorials/index.html">Tutorials</a> |
| <li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/0.12.1/example">Examples</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/architecture/index.html">Architecture</a></li> |
| <li><a class="main-nav-link" href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home">Developer Wiki</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/model_zoo/index.html">Model Zoo</a></li> |
| <li><a class="main-nav-link" href="https://github.com/onnx/onnx-mxnet">ONNX</a></li> |
| </li></ul> |
| </span> |
| <span id="dropdown-menu-position-anchor-community"> |
| <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Community <span class="caret"></span></a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-community"> |
| <li><a class="main-nav-link" href="http://discuss.mxnet.io">Forum</a></li> |
| <li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/0.12.1">Github</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/community/contribute.html">Contribute</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/community/powered_by.html">Powered By</a></li> |
| </ul> |
| </span> |
| <span id="dropdown-menu-position-anchor-version" style="position: relative"><a href="#" class="main-nav-link dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">0.12.1<span class="caret"></span></a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a href="/">master</a></li><li><a href="/versions/1.7/">1.7</a></li><li><a href=/versions/1.6/index.html>1.6</a></li><li><a href=/versions/1.5.0/index.html>1.5.0</a></li><li><a href=/versions/1.4.1/index.html>1.4.1</a></li><li><a href=/versions/1.3.1/index.html>1.3.1</a></li><li><a href=/versions/1.2.1/index.html>1.2.1</a></li><li><a href=/versions/1.1.0/index.html>1.1.0</a></li><li><a href=/versions/1.0.0/index.html>1.0.0</a></li><li><a href=/versions/0.12.1/index.html>0.12.1</a></li><li><a href=/versions/0.11.0/index.html>0.11.0</a></li></ul></span></nav> |
| <script> function getRootPath(){ return "../../../" } </script> |
| <div class="burgerIcon dropdown"> |
| <a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button">☰</a> |
| <ul class="dropdown-menu" id="burgerMenu"> |
| <li><a href="/versions/0.12.1/install/index.html">Install</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/tutorials/index.html">Tutorials</a></li> |
| <li class="dropdown-submenu dropdown"> |
| <a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">Gluon</a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> |
| <li><a class="main-nav-link" href="/versions/0.12.1/tutorials/gluon/gluon.html">About</a></li> |
| <li><a class="main-nav-link" href="http://gluon.mxnet.io">The Straight Dope (Tutorials)</a></li> |
| <li><a class="main-nav-link" href="https://gluon-cv.mxnet.io">GluonCV Toolkit</a></li> |
| <li><a class="main-nav-link" href="https://gluon-nlp.mxnet.io/">GluonNLP Toolkit</a></li> |
| </ul> |
| </li> |
| <li class="dropdown-submenu"> |
| <a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">API</a> |
| <ul class="dropdown-menu"> |
| <li><a class="main-nav-link" href="/versions/0.12.1/api/python/index.html">Python</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/api/c++/index.html">C++</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/api/julia/index.html">Julia</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/api/perl/index.html">Perl</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/api/r/index.html">R</a></li> |
| <li><a class="main-nav-link" href="/versions/0.12.1/api/scala/index.html">Scala</a></li> |
| </ul> |
| </li> |
| <li class="dropdown-submenu"> |
| <a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">Docs</a> |
| <ul class="dropdown-menu"> |
| <li><a href="/versions/0.12.1/faq/index.html" tabindex="-1">FAQ</a></li> |
| <li><a href="/versions/0.12.1/tutorials/index.html" tabindex="-1">Tutorials</a></li> |
| <li><a href="https://github.com/apache/incubator-mxnet/tree/0.12.1/example" tabindex="-1">Examples</a></li> |
| <li><a href="/versions/0.12.1/architecture/index.html" tabindex="-1">Architecture</a></li> |
| <li><a href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home" tabindex="-1">Developer Wiki</a></li> |
| <li><a href="/versions/0.12.1/model_zoo/index.html" tabindex="-1">Gluon Model Zoo</a></li> |
| <li><a href="https://github.com/onnx/onnx-mxnet" tabindex="-1">ONNX</a></li> |
| </ul> |
| </li> |
| <li class="dropdown-submenu dropdown"> |
| <a aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" role="button" tabindex="-1">Community</a> |
| <ul class="dropdown-menu"> |
| <li><a href="http://discuss.mxnet.io" tabindex="-1">Forum</a></li> |
| <li><a href="https://github.com/apache/incubator-mxnet/tree/0.12.1" tabindex="-1">Github</a></li> |
| <li><a href="/versions/0.12.1/community/contribute.html" tabindex="-1">Contribute</a></li> |
| <li><a href="/versions/0.12.1/community/powered_by.html" tabindex="-1">Powered By</a></li> |
| </ul> |
| </li> |
| <li id="dropdown-menu-position-anchor-version-mobile" class="dropdown-submenu" style="position: relative"><a href="#" tabindex="-1">0.12.1</a><ul class="dropdown-menu"><li><a tabindex="-1" href=/>master</a></li><li><a tabindex="-1" href=/versions/1.6/index.html>1.6</a></li><li><a tabindex="-1" href=/versions/1.5.0/index.html>1.5.0</a></li><li><a tabindex="-1" href=/versions/1.4.1/index.html>1.4.1</a></li><li><a tabindex="-1" href=/versions/1.3.1/index.html>1.3.1</a></li><li><a tabindex="-1" href=/versions/1.2.1/index.html>1.2.1</a></li><li><a tabindex="-1" href=/versions/1.1.0/index.html>1.1.0</a></li><li><a tabindex="-1" href=/versions/1.0.0/index.html>1.0.0</a></li><li><a tabindex="-1" href=/versions/0.12.1/index.html>0.12.1</a></li><li><a tabindex="-1" href=/versions/0.11.0/index.html>0.11.0</a></li></ul></li></ul> |
| </div> |
| <div class="plusIcon dropdown"> |
| <a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button"><span aria-hidden="true" class="glyphicon glyphicon-plus"></span></a> |
| <ul class="dropdown-menu dropdown-menu-right" id="plusMenu"></ul> |
| </div> |
| <div id="search-input-wrap"> |
| <form action="../../../search.html" autocomplete="off" class="" method="get" role="search"> |
| <div class="form-group inner-addon left-addon"> |
| <i class="glyphicon glyphicon-search"></i> |
| <input class="form-control" name="q" placeholder="Search" type="text"/> |
| </div> |
| <input name="check_keywords" type="hidden" value="yes"> |
| <input name="area" type="hidden" value="default"/> |
| </input></form> |
| <div id="search-preview"></div> |
| </div> |
| <div id="searchIcon"> |
| <span aria-hidden="true" class="glyphicon glyphicon-search"></span> |
| </div> |
| <!-- <div id="lang-select-wrap"> --> |
| <!-- <label id="lang-select-label"> --> |
| <!-- <\!-- <i class="fa fa-globe"></i> -\-> --> |
| <!-- <span></span> --> |
| <!-- </label> --> |
| <!-- <select id="lang-select"> --> |
| <!-- <option value="en">Eng</option> --> |
| <!-- <option value="zh">中文</option> --> |
| <!-- </select> --> |
| <!-- </div> --> |
| <!-- <a id="mobile-nav-toggle"> |
| <span class="mobile-nav-toggle-bar"></span> |
| <span class="mobile-nav-toggle-bar"></span> |
| <span class="mobile-nav-toggle-bar"></span> |
| </a> --> |
| </div> |
| </div> |
| </div> |
| <script type="text/javascript"> |
| $('body').css('background', 'white'); |
| </script> |
| <div class="container"> |
| <div class="row"> |
| <div aria-label="main navigation" class="sphinxsidebar leftsidebar" role="navigation"> |
| <div class="sphinxsidebarwrapper"> |
| <ul class="current"> |
| <li class="toctree-l1 current"><a class="reference internal" href="../index.html">Python Documents</a><ul class="current"> |
| <li class="toctree-l2"><a class="reference internal" href="../index.html#ndarray-api">NDArray API</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../index.html#symbol-api">Symbol API</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../index.html#module-api">Module API</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../index.html#autograd-api">Autograd API</a></li> |
| <li class="toctree-l2 current"><a class="reference internal" href="../index.html#gluon-api">Gluon API</a><ul class="current"> |
| <li class="toctree-l3 current"><a class="reference internal" href="gluon.html">Gluon Package</a><ul class="current"> |
| <li class="toctree-l4 current"><a class="reference internal" href="gluon.html#overview">Overview</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="gluon.html#parameter">Parameter</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="gluon.html#containers">Containers</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="gluon.html#trainer">Trainer</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="gluon.html#utilities">Utilities</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="gluon.html#api-reference">API Reference</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="nn.html">Gluon Neural Network Layers</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="rnn.html">Gluon Recurrent Neural Network API</a></li> |
| <li class="toctree-l3 current"><a class="current reference internal" href="#">Gluon Loss API</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="#overview">Overview</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#api-reference">API Reference</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="data.html">Gluon Data API</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="model_zoo.html">Gluon Model Zoo</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="contrib.html">Gluon Contrib API</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../index.html#kvstore-api">KVStore API</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../index.html#io-api">IO API</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../index.html#image-api">Image API</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../index.html#optimization-api">Optimization API</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../index.html#callback-api">Callback API</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../index.html#metric-api">Metric API</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../index.html#run-time-compilation-api">Run-Time Compilation API</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><a class="reference internal" href="../../r/index.html">R Documents</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../julia/index.html">Julia Documents</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../c++/index.html">C++ Documents</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../scala/index.html">Scala Documents</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../perl/index.html">Perl Documents</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../faq/index.html">HowTo Documents</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../architecture/index.html">System Documents</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index.html">Tutorials</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../community/index.html">Community</a></li> |
| </ul> |
| </div> |
| </div> |
| <div class="content"> |
| <div class="page-tracker"></div> |
| <div class="section" id="gluon-loss-api"> |
| <span id="gluon-loss-api"></span><h1>Gluon Loss API<a class="headerlink" href="#gluon-loss-api" title="Permalink to this headline">¶</a></h1> |
| <div class="section" id="overview"> |
| <span id="overview"></span><h2>Overview<a class="headerlink" href="#overview" title="Permalink to this headline">¶</a></h2> |
| <p>This document lists the loss API in Gluon:</p> |
| <p>This package includes several commonly used loss functions in neural networks.</p> |
| <table border="1" class="longtable docutils"> |
| <colgroup> |
| <col width="10%"/> |
| <col width="90%"/> |
| </colgroup> |
| <tbody valign="top"> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.loss.L2Loss" title="mxnet.gluon.loss.L2Loss"><code class="xref py py-obj docutils literal"><span class="pre">L2Loss</span></code></a></td> |
| <td>Calculates the mean squared error between <cite>pred</cite> and <cite>label</cite>.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.loss.L1Loss" title="mxnet.gluon.loss.L1Loss"><code class="xref py py-obj docutils literal"><span class="pre">L1Loss</span></code></a></td> |
| <td>Calculates the mean absolute error between <cite>pred</cite> and <cite>label</cite>.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss"><code class="xref py py-obj docutils literal"><span class="pre">SigmoidBinaryCrossEntropyLoss</span></code></a></td> |
| <td>The cross-entropy loss for binary classification.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss"><code class="xref py py-obj docutils literal"><span class="pre">SoftmaxCrossEntropyLoss</span></code></a></td> |
| <td>Computes the softmax cross entropy loss.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss"><code class="xref py py-obj docutils literal"><span class="pre">SigmoidBinaryCrossEntropyLoss</span></code></a></td> |
| <td>The cross-entropy loss for binary classification.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss" title="mxnet.gluon.loss.KLDivLoss"><code class="xref py py-obj docutils literal"><span class="pre">KLDivLoss</span></code></a></td> |
| <td>The Kullback-Leibler divergence loss.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss" title="mxnet.gluon.loss.HuberLoss"><code class="xref py py-obj docutils literal"><span class="pre">HuberLoss</span></code></a></td> |
| <td>Calculates smoothed L1 loss that is equal to L1 loss if absolute error exceeds rho but is equal to L2 loss otherwise.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss" title="mxnet.gluon.loss.HingeLoss"><code class="xref py py-obj docutils literal"><span class="pre">HingeLoss</span></code></a></td> |
| <td>Calculates the hinge loss function often used in SVMs:</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss" title="mxnet.gluon.loss.SquaredHingeLoss"><code class="xref py py-obj docutils literal"><span class="pre">SquaredHingeLoss</span></code></a></td> |
| <td>Calculates the soft-margin loss function used in SVMs:</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss" title="mxnet.gluon.loss.LogisticLoss"><code class="xref py py-obj docutils literal"><span class="pre">LogisticLoss</span></code></a></td> |
| <td>Calculates the logistic loss (for binary losses only):</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss" title="mxnet.gluon.loss.TripletLoss"><code class="xref py py-obj docutils literal"><span class="pre">TripletLoss</span></code></a></td> |
| <td>Calculates triplet loss given three input tensors and a positive margin.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss" title="mxnet.gluon.loss.CTCLoss"><code class="xref py py-obj docutils literal"><span class="pre">CTCLoss</span></code></a></td> |
| <td>Connectionist Temporal Classification Loss.</td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <div class="section" id="api-reference"> |
| <span id="api-reference"></span><h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to this headline">¶</a></h2> |
| <script src="../../_static/js/auto_module_index.js" type="text/javascript"></script><span class="target" id="module-mxnet.gluon.loss"></span><p>losses for training neural networks</p> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.Loss"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.loss.</code><code class="descname">Loss</code><span class="sig-paren">(</span><em>weight</em>, <em>batch_axis</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#Loss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.Loss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Base class for loss.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</li> |
| <li><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.hybrid_forward"> |
| <code class="descname">hybrid_forward</code><span class="sig-paren">(</span><em>F</em>, <em>x</em>, <em>*args</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#Loss.hybrid_forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.Loss.hybrid_forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>x</strong> (<a class="reference internal" href="../symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</li> |
| <li><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.L2Loss"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.loss.</code><code class="descname">L2Loss</code><span class="sig-paren">(</span><em>weight=1.0</em>, <em>batch_axis=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#L2Loss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.L2Loss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Calculates the mean squared error between <cite>pred</cite> and <cite>label</cite>.</p> |
| <div class="math"> |
| \[L = \frac{1}{2} \sum_i \vert {pred}_i - {label}_i \vert^2.\]</div> |
| <p><cite>pred</cite> and <cite>label</cite> can have arbitrary shape as long as they have the same |
| number of elements.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</li> |
| <li><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="docutils"> |
| <dt>Inputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>pred</strong>: prediction tensor with arbitrary shape</li> |
| <li><strong>label</strong>: target tensor with the same size as pred.</li> |
| <li><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.L1Loss"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.loss.</code><code class="descname">L1Loss</code><span class="sig-paren">(</span><em>weight=None</em>, <em>batch_axis=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#L1Loss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.L1Loss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Calculates the mean absolute error between <cite>pred</cite> and <cite>label</cite>.</p> |
| <div class="math"> |
| \[L = \sum_i \vert {pred}_i - {label}_i \vert.\]</div> |
| <p><cite>pred</cite> and <cite>label</cite> can have arbitrary shape as long as they have the same |
| number of elements.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</li> |
| <li><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="docutils"> |
| <dt>Inputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>pred</strong>: prediction tensor with arbitrary shape</li> |
| <li><strong>label</strong>: target tensor with the same size as pred.</li> |
| <li><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.loss.</code><code class="descname">SigmoidBinaryCrossEntropyLoss</code><span class="sig-paren">(</span><em>from_sigmoid=False</em>, <em>weight=None</em>, <em>batch_axis=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#SigmoidBinaryCrossEntropyLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>The cross-entropy loss for binary classification. (alias: SigmoidBCELoss)</p> |
| <p>BCE loss is useful when training logistic regression. If <cite>from_sigmoid</cite> |
| is False (default), this loss computes:</p> |
| <div class="math"> |
| \[ \begin{align}\begin{aligned}prob = \frac{1}{1 + \exp(-{pred})}\\L = - \sum_i {label}_i * \log({prob}_i) + |
| (1 - {label}_i) * \log(1 - {prob}_i)\end{aligned}\end{align} \]</div> |
| <p>If <cite>from_sigmoid</cite> is True, this loss computes:</p> |
| <div class="math"> |
| \[L = - \sum_i {label}_i * \log({pred}_i) + |
| (1 - {label}_i) * \log(1 - {pred}_i)\]</div> |
| <p><cite>pred</cite> and <cite>label</cite> can have arbitrary shape as long as they have the same |
| number of elements.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>from_sigmoid</strong> (bool, default is <cite>False</cite>) – Whether the input is from the output of sigmoid. Set this to false will make |
| the loss calculate sigmoid and BCE together, which is more numerically |
| stable through log-sum-exp trick.</li> |
| <li><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</li> |
| <li><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="docutils"> |
| <dt>Inputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>pred</strong>: prediction tensor with arbitrary shape</li> |
| <li><strong>label</strong>: target tensor with values in range <cite>[0, 1]</cite>. Must have the |
| same size as <cite>pred</cite>.</li> |
| <li><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| <dl class="attribute"> |
| <dt id="mxnet.gluon.loss.SigmoidBCELoss"> |
| <code class="descclassname">mxnet.gluon.loss.</code><code class="descname">SigmoidBCELoss</code><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBCELoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>alias of <a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss"><code class="xref py py-class docutils literal"><span class="pre">SigmoidBinaryCrossEntropyLoss</span></code></a></p> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.loss.</code><code class="descname">SoftmaxCrossEntropyLoss</code><span class="sig-paren">(</span><em>axis=-1</em>, <em>sparse_label=True</em>, <em>from_logits=False</em>, <em>weight=None</em>, <em>batch_axis=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#SoftmaxCrossEntropyLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Computes the softmax cross entropy loss. (alias: SoftmaxCELoss)</p> |
| <p>If <cite>sparse_label</cite> is <cite>True</cite> (default), label should contain integer |
| category indicators:</p> |
| <div class="math"> |
| \[ \begin{align}\begin{aligned}\DeclareMathOperator{softmax}{softmax}\\p = \softmax({pred})\\L = -\sum_i \log p_{i,{label}_i}\end{aligned}\end{align} \]</div> |
| <p><cite>label</cite>‘s shape should be <cite>pred</cite>‘s shape with the <cite>axis</cite> dimension removed. |
| i.e. for <cite>pred</cite> with shape (1,2,3,4) and <cite>axis = 2</cite>, <cite>label</cite>‘s shape should |
| be (1,2,4).</p> |
| <p>If <cite>sparse_label</cite> is <cite>False</cite>, <cite>label</cite> should contain probability distribution |
| and <cite>label</cite>‘s shape should be the same with <cite>pred</cite>:</p> |
| <div class="math"> |
| \[ \begin{align}\begin{aligned}p = \softmax({pred})\\L = -\sum_i \sum_j {label}_j \log p_{ij}\end{aligned}\end{align} \]</div> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>axis</strong> (<em>int</em><em>, </em><em>default -1</em>) – The axis to sum over when computing softmax and entropy.</li> |
| <li><strong>sparse_label</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether label is an integer array instead of probability distribution.</li> |
| <li><strong>from_logits</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether input is a log probability (usually from log_softmax) instead |
| of unnormalized numbers.</li> |
| <li><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</li> |
| <li><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="docutils"> |
| <dt>Inputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>pred</strong>: the prediction tensor, where the <cite>batch_axis</cite> dimension |
| ranges over batch size and <cite>axis</cite> dimension ranges over the number |
| of classes.</li> |
| <li><strong>label</strong>: the truth tensor. When <cite>sparse_label</cite> is True, <cite>label</cite>‘s |
| shape should be <cite>pred</cite>‘s shape with the <cite>axis</cite> dimension removed. |
| i.e. for <cite>pred</cite> with shape (1,2,3,4) and <cite>axis = 2</cite>, <cite>label</cite>‘s shape |
| should be (1,2,4) and values should be integers between 0 and 2. If |
| <cite>sparse_label</cite> is False, <cite>label</cite>‘s shape must be the same as <cite>pred</cite> |
| and values should be floats in the range <cite>[0, 1]</cite>.</li> |
| <li><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as label. For example, if label has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| <dl class="attribute"> |
| <dt id="mxnet.gluon.loss.SoftmaxCELoss"> |
| <code class="descclassname">mxnet.gluon.loss.</code><code class="descname">SoftmaxCELoss</code><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCELoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>alias of <a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss"><code class="xref py py-class docutils literal"><span class="pre">SoftmaxCrossEntropyLoss</span></code></a></p> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.KLDivLoss"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.loss.</code><code class="descname">KLDivLoss</code><span class="sig-paren">(</span><em>from_logits=True</em>, <em>axis=-1</em>, <em>weight=None</em>, <em>batch_axis=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#KLDivLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>The Kullback-Leibler divergence loss.</p> |
| <p>KL divergence measures the distance between contiguous distributions. It |
| can be used to minimize information loss when approximating a distribution. |
| If <cite>from_logits</cite> is True (default), loss is defined as:</p> |
| <div class="math"> |
| \[L = \sum_i {label}_i * \big[\log({label}_i) - {pred}_i\big]\]</div> |
| <p>If <cite>from_logits</cite> is False, loss is defined as:</p> |
| <div class="math"> |
| \[ \begin{align}\begin{aligned}\DeclareMathOperator{softmax}{softmax}\\prob = \softmax({pred})\\L = \sum_i {label}_i * \big[\log({label}_i) - log({pred}_i)\big]\end{aligned}\end{align} \]</div> |
| <p><cite>pred</cite> and <cite>label</cite> can have arbitrary shape as long as they have the same |
| number of elements.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>from_logits</strong> (bool, default is <cite>True</cite>) – Whether the input is log probability (usually from log_softmax) instead |
| of unnormalized numbers.</li> |
| <li><strong>axis</strong> (<em>int</em><em>, </em><em>default -1</em>) – The dimension along with to compute softmax. Only used when <cite>from_logits</cite> |
| is False.</li> |
| <li><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</li> |
| <li><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="docutils"> |
| <dt>Inputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>pred</strong>: prediction tensor with arbitrary shape. If <cite>from_logits</cite> is |
| True, <cite>pred</cite> should be log probabilities. Otherwise, it should be |
| unnormalized predictions, i.e. from a dense layer.</li> |
| <li><strong>label</strong>: truth tensor with values in range <cite>(0, 1)</cite>. Must have |
| the same size as <cite>pred</cite>.</li> |
| <li><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://en.wikipedia.org/wiki/Kullback-Leibler_divergence">Kullback-Leibler divergence</a></p> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.CTCLoss"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.loss.</code><code class="descname">CTCLoss</code><span class="sig-paren">(</span><em>layout='NTC'</em>, <em>label_layout='NT'</em>, <em>weight=None</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#CTCLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Connectionist Temporal Classification Loss.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>layout</strong> (<em>str</em><em>, </em><em>default 'NTC'</em>) – Layout of prediction tensor. ‘N’, ‘T’, ‘C’ stands for batch size, |
| sequence length, and alphabet_size respectively.</li> |
| <li><strong>label_layout</strong> (<em>str</em><em>, </em><em>default 'NT'</em>) – Layout of the labels. ‘N’, ‘T’ stands for batch size, and sequence |
| length respectively.</li> |
| <li><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="docutils"> |
| <dt>Inputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>pred</strong>: unnormalized prediction tensor (before softmax). |
| Its shape depends on <cite>layout</cite>. If <cite>layout</cite> is ‘TNC’, pred |
| should have shape <cite>(sequence_length, batch_size, alphabet_size)</cite>. |
| Note that in the last dimension, index <cite>alphabet_size-1</cite> is reserved |
| for internal use as blank label. So <cite>alphabet_size</cite> is one plus the |
| actual alphabet size.</li> |
| <li><strong>label</strong>: zero-based label tensor. Its shape depends on <cite>label_layout</cite>. |
| If <cite>label_layout</cite> is ‘TN’, <cite>label</cite> should have shape |
| <cite>(label_sequence_length, batch_size)</cite>.</li> |
| <li><strong>pred_lengths</strong>: optional (default None), used for specifying the |
| length of each entry when different <cite>pred</cite> entries in the same batch |
| have different lengths. <cite>pred_lengths</cite> should have shape <cite>(batch_size,)</cite>.</li> |
| <li><strong>label_lengths</strong>: optional (default None), used for specifying the |
| length of each entry when different <cite>label</cite> entries in the same batch |
| have different lengths. <cite>label_lengths</cite> should have shape <cite>(batch_size,)</cite>.</li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>loss</strong>: output loss has shape <cite>(batch_size,)</cite>.</li> |
| </ul> |
| </dd> |
| </dl> |
| <p><strong>Example</strong>: suppose the vocabulary is <cite>[a, b, c]</cite>, and in one batch we |
| have three sequences ‘ba’, ‘cbb’, and ‘abac’. We can index the labels as |
| <cite>{‘a’: 0, ‘b’: 1, ‘c’: 2, blank: 3}</cite>. Then <cite>alphabet_size</cite> should be 4, |
| where label 3 is reserved for internal use by <cite>CTCLoss</cite>. We then need to |
| pad each sequence with <cite>-1</cite> to make a rectangular <cite>label</cite> tensor:</p> |
| <div class="highlight-default"><div class="highlight"><pre><span></span><span class="p">[[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">],</span> |
| <span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">],</span> |
| <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">]]</span> |
| </pre></div> |
| </div> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="http://www.cs.toronto.edu/~graves/icml_2006.pdf">Connectionist Temporal Classification: Labelling Unsegmented |
| Sequence Data with Recurrent Neural Networks</a></p> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.HuberLoss"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.loss.</code><code class="descname">HuberLoss</code><span class="sig-paren">(</span><em>rho=1</em>, <em>weight=None</em>, <em>batch_axis=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#HuberLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Calculates smoothed L1 loss that is equal to L1 loss if absolute error |
| exceeds rho but is equal to L2 loss otherwise. Also called SmoothedL1 loss.</p> |
| <div class="math"> |
| \[\begin{split}L = \sum_i \begin{cases} \frac{1}{2 {rho}} ({pred}_i - {label}_i)^2 & |
| \text{ if } |{pred}_i - {label}_i| < {rho} \\ |
| |{pred}_i - {label}_i| - \frac{{rho}}{2} & |
| \text{ otherwise } |
| \end{cases}\end{split}\]</div> |
| <p><cite>pred</cite> and <cite>label</cite> can have arbitrary shape as long as they have the same |
| number of elements.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>rho</strong> (<em>float</em><em>, </em><em>default 1</em>) – Threshold for trimmed mean estimator.</li> |
| <li><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</li> |
| <li><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="docutils"> |
| <dt>Inputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>pred</strong>: prediction tensor with arbitrary shape</li> |
| <li><strong>label</strong>: target tensor with the same size as pred.</li> |
| <li><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.HingeLoss"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.loss.</code><code class="descname">HingeLoss</code><span class="sig-paren">(</span><em>margin=1</em>, <em>weight=None</em>, <em>batch_axis=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#HingeLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Calculates the hinge loss function often used in SVMs:</p> |
| <div class="math"> |
| \[L = \sum_i max(0, {margin} - {pred}_i \cdot {label}_i)\]</div> |
| <p>where <cite>pred</cite> is the classifier prediction and <cite>label</cite> is the target tensor |
| containing values -1 or 1. <cite>pred</cite> and <cite>label</cite> must have the same number of |
| elements.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>margin</strong> (<em>float</em>) – The margin in hinge loss. Defaults to 1.0</li> |
| <li><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</li> |
| <li><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="docutils"> |
| <dt>Inputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>pred</strong>: prediction tensor with arbitrary shape.</li> |
| <li><strong>label</strong>: truth tensor with values -1 or 1. Must have the same size |
| as pred.</li> |
| <li><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.loss.</code><code class="descname">SquaredHingeLoss</code><span class="sig-paren">(</span><em>margin=1</em>, <em>weight=None</em>, <em>batch_axis=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#SquaredHingeLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Calculates the soft-margin loss function used in SVMs:</p> |
| <div class="math"> |
| \[L = \sum_i max(0, {margin} - {pred}_i \cdot {label}_i)^2\]</div> |
| <p>where <cite>pred</cite> is the classifier prediction and <cite>label</cite> is the target tensor |
| containing values -1 or 1. <cite>pred</cite> and <cite>label</cite> can have arbitrary shape as |
| long as they have the same number of elements.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>margin</strong> (<em>float</em>) – The margin in hinge loss. Defaults to 1.0</li> |
| <li><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</li> |
| <li><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="docutils"> |
| <dt>Inputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>pred</strong>: prediction tensor with arbitrary shape</li> |
| <li><strong>label</strong>: truth tensor with values -1 or 1. Must have the same size |
| as pred.</li> |
| <li><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.LogisticLoss"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.loss.</code><code class="descname">LogisticLoss</code><span class="sig-paren">(</span><em>weight=None</em>, <em>batch_axis=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#LogisticLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Calculates the logistic loss (for binary losses only):</p> |
| <div class="math"> |
| \[L = \sum_i \log(1 + \exp(- {pred}_i \cdot {label}_i))\]</div> |
| <p>where <cite>pred</cite> is the classifier prediction and <cite>label</cite> is the target tensor |
| containing values -1 or 1. <cite>pred</cite> and <cite>label</cite> can have arbitrary shape as |
| long as they have the same number of elements.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</li> |
| <li><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="docutils"> |
| <dt>Inputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>pred</strong>: prediction tensor with arbitrary shape.</li> |
| <li><strong>label</strong>: truth tensor with values -1 or 1. Must have the same size |
| as pred.</li> |
| <li><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.TripletLoss"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.loss.</code><code class="descname">TripletLoss</code><span class="sig-paren">(</span><em>margin=1</em>, <em>weight=None</em>, <em>batch_axis=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#TripletLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Calculates triplet loss given three input tensors and a positive margin. |
| Triplet loss measures the relative similarity between prediction, a positive |
| example and a negative example:</p> |
| <div class="math"> |
| \[L = \sum_i \max(\Vert {pred}_i - {pos_i} \Vert_2^2 - |
| \Vert {pred}_i - {neg_i} \Vert_2^2 + {margin}, 0)\]</div> |
| <p><cite>pred</cite>, <cite>positive</cite> and <cite>negative</cite> can have arbitrary shape as long as they |
| have the same number of elements.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name"/> |
| <col class="field-body"/> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>margin</strong> (<em>float</em>) – Margin of separation between correct and incorrect pair.</li> |
| <li><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</li> |
| <li><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="docutils"> |
| <dt>Inputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>pred</strong>: prediction tensor with arbitrary shape</li> |
| <li><strong>positive</strong>: positive example tensor with arbitrary shape. Must have |
| the same size as pred.</li> |
| <li><strong>negative</strong>: negative example tensor with arbitrary shape Must have |
| the same size as pred.</li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt> |
| <dd><ul class="first last simple"> |
| <li><strong>loss</strong>: loss tensor with shape (batch_size,).</li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| <script>auto_index("api-reference");</script></div> |
| </div> |
| </div> |
| </div> |
| <div aria-label="main navigation" class="sphinxsidebar rightsidebar" role="navigation"> |
| <div class="sphinxsidebarwrapper"> |
| <h3><a href="../../../index.html">Table Of Contents</a></h3> |
| <ul> |
| <li><a class="reference internal" href="#">Gluon Loss API</a><ul> |
| <li><a class="reference internal" href="#overview">Overview</a></li> |
| <li><a class="reference internal" href="#api-reference">API Reference</a></li> |
| </ul> |
| </li> |
| </ul> |
| </div> |
| </div> |
| </div><div class="footer"> |
| <div class="section-disclaimer"> |
| <div class="container"> |
| <div> |
| <img height="60" src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/apache_incubator_logo.png"/> |
| <p> |
| Apache MXNet is an effort undergoing incubation at The Apache Software Foundation (ASF), <strong>sponsored by the <i>Apache Incubator</i></strong>. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF. |
| </p> |
| <p> |
| "Copyright © 2017-2018, The Apache Software Foundation |
| Apache MXNet, MXNet, Apache, the Apache feather, and the Apache MXNet project logo are either registered trademarks or trademarks of the Apache Software Foundation." |
| </p> |
| </div> |
| </div> |
| </div> |
| </div> <!-- pagename != index --> |
| </div> |
| <script crossorigin="anonymous" integrity="sha384-0mSbJDEHialfmuBBQP6A4Qrprq5OVfW37PRR3j5ELqxss1yVqOtnepnHVP9aJ7xS" src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/js/bootstrap.min.js"></script> |
| <script src="../../../_static/js/sidebar.js" type="text/javascript"></script> |
| <script src="../../../_static/js/search.js" type="text/javascript"></script> |
| <script src="../../../_static/js/navbar.js" type="text/javascript"></script> |
| <script src="../../../_static/js/clipboard.min.js" type="text/javascript"></script> |
| <script src="../../../_static/js/copycode.js" type="text/javascript"></script> |
| <script src="../../../_static/js/page.js" type="text/javascript"></script> |
| <script src="../../../_static/js/docversion.js" type="text/javascript"></script> |
| <script type="text/javascript"> |
| $('body').ready(function () { |
| $('body').css('visibility', 'visible'); |
| }); |
| </script> |
| </body> |
| </html> |