| <!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"/> |
| <title>Gluon Model Zoo — 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: '' |
| }; |
| </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("/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://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script> --> |
| <!-- --> |
| <link href="gluon.html" rel="up" title="Gluon Package"> |
| <link href="contrib.html" rel="next" title="Gluon Contrib API"/> |
| <link href="data.html" rel="prev" title="Gluon Data API"/> |
| <link href="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-icon.png" rel="icon" type="image/png"/> |
| </link></link></link></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="../../../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="../../../gluon/index.html">About</a></li> |
| <li><a class="main-nav-link" href="http://gluon.mxnet.io">Tutorials</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="../../../api/python/index.html">Python</a></li> |
| <li><a class="main-nav-link" href="../../../api/scala/index.html">Scala</a></li> |
| <li><a class="main-nav-link" href="../../../api/r/index.html">R</a></li> |
| <li><a class="main-nav-link" href="../../../api/julia/index.html">Julia</a></li> |
| <li><a class="main-nav-link" href="../../../api/c++/index.html">C++</a></li> |
| <li><a class="main-nav-link" href="../../../api/perl/index.html">Perl</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="../../../tutorials/index.html">Tutorials</a> |
| <li><a class="main-nav-link" href="../../../faq/index.html">FAQ</a></li> |
| <li><a class="main-nav-link" href="../../../architecture/index.html">Architecture</a></li> |
| <li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/master/example">Examples</a></li> |
| <li><a class="main-nav-link" href="../../../model_zoo/index.html">Model Zoo</a></li> |
| </li></ul> |
| </span> |
| <a class="main-nav-link" href="https://github.com/dmlc/mxnet">Github</a> |
| <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="../../../community/index.html">Community</a></li> |
| <li><a class="main-nav-link" href="../../../community/contribute.html">Contribute</a></li> |
| <li><a class="main-nav-link" href="../../../community/powered_by.html">Powered By</a></li> |
| <li><a class="main-nav-link" href="http://discuss.mxnet.io">Discuss</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">Versions(master)<span class="caret"></span></a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/>1.0.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.12.1/index.html>0.12.1</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.12.0/index.html>0.12.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.11.0/index.html>0.11.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/master/index.html>master</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="../../../install/index.html">Install</a></li> |
| <li><a class="main-nav-link" href="../../../tutorials/index.html">Tutorials</a></li> |
| <li class="dropdown-submenu"> |
| <a href="#" tabindex="-1">Community</a> |
| <ul class="dropdown-menu"> |
| <li><a href="../../../community/index.html" tabindex="-1">Community</a></li> |
| <li><a href="../../../community/contribute.html" tabindex="-1">Contribute</a></li> |
| <li><a href="../../../community/powered_by.html" tabindex="-1">Powered By</a></li> |
| </ul> |
| </li> |
| <li class="dropdown-submenu"> |
| <a href="#" tabindex="-1">API</a> |
| <ul class="dropdown-menu"> |
| <li><a href="../../../api/python/index.html" tabindex="-1">Python</a> |
| </li> |
| <li><a href="../../../api/scala/index.html" tabindex="-1">Scala</a> |
| </li> |
| <li><a href="../../../api/r/index.html" tabindex="-1">R</a> |
| </li> |
| <li><a href="../../../api/julia/index.html" tabindex="-1">Julia</a> |
| </li> |
| <li><a href="../../../api/c++/index.html" tabindex="-1">C++</a> |
| </li> |
| <li><a href="../../../api/perl/index.html" tabindex="-1">Perl</a> |
| </li> |
| </ul> |
| </li> |
| <li class="dropdown-submenu"> |
| <a href="#" tabindex="-1">Docs</a> |
| <ul class="dropdown-menu"> |
| <li><a href="../../../tutorials/index.html" tabindex="-1">Tutorials</a></li> |
| <li><a href="../../../faq/index.html" tabindex="-1">FAQ</a></li> |
| <li><a href="../../../architecture/index.html" tabindex="-1">Architecture</a></li> |
| <li><a href="https://github.com/apache/incubator-mxnet/tree/master/example" tabindex="-1">Examples</a></li> |
| <li><a href="../../../model_zoo/index.html" tabindex="-1">Model Zoo</a></li> |
| </ul> |
| </li> |
| <li><a href="../../../architecture/index.html">Architecture</a></li> |
| <li><a class="main-nav-link" href="https://github.com/dmlc/mxnet">Github</a></li> |
| <li id="dropdown-menu-position-anchor-version-mobile" class="dropdown-submenu" style="position: relative"><a href="#" tabindex="-1">Versions(master)</a><ul class="dropdown-menu"><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/>1.0.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.12.1/index.html>0.12.1</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.12.0/index.html>0.12.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.11.0/index.html>0.11.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/master/index.html>master</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"><a class="reference internal" href="loss.html">Gluon Loss API</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="data.html">Gluon Data API</a></li> |
| <li class="toctree-l3 current"><a class="current reference internal" href="">Gluon Model Zoo</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="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> |
| <li class="toctree-l2"><a class="reference internal" href="../index.html#contrib-package">Contrib Package</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-model-zoo"> |
| <span id="gluon-model-zoo"></span><h1>Gluon Model Zoo<a class="headerlink" href="#gluon-model-zoo" 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 model APIs in Gluon:</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="#module-mxnet.gluon.model_zoo" title="mxnet.gluon.model_zoo"><code class="xref py py-obj docutils literal"><span class="pre">mxnet.gluon.model_zoo</span></code></a></td> |
| <td>Predefined and pretrained models.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#module-mxnet.gluon.model_zoo.vision" title="mxnet.gluon.model_zoo.vision"><code class="xref py py-obj docutils literal"><span class="pre">mxnet.gluon.model_zoo.vision</span></code></a></td> |
| <td>Module for pre-defined neural network models.</td> |
| </tr> |
| </tbody> |
| </table> |
| <p>The <code class="docutils literal"><span class="pre">Gluon</span> <span class="pre">Model</span> <span class="pre">Zoo</span></code> API, defined in the <code class="docutils literal"><span class="pre">gluon.model_zoo</span></code> package, provides pre-defined |
| and pre-trained models to help bootstrap machine learning applications.</p> |
| <p>In the rest of this document, we list routines provided by the <code class="docutils literal"><span class="pre">gluon.model_zoo</span></code> package.</p> |
| <div class="section" id="module-mxnet.gluon.model_zoo.vision"> |
| <span id="vision"></span><span id="vision"></span><h3>Vision<a class="headerlink" href="#module-mxnet.gluon.model_zoo.vision" title="Permalink to this headline">¶</a></h3> |
| <p>Module for pre-defined neural network models.</p> |
| <p>This module contains definitions for the following model architectures: |
| - <a class="reference external" href="https://arxiv.org/abs/1404.5997">AlexNet</a> |
| - <a class="reference external" href="https://arxiv.org/abs/1608.06993">DenseNet</a> |
| - <a class="reference external" href="http://arxiv.org/abs/1512.00567">Inception V3</a> |
| - <a class="reference external" href="https://arxiv.org/abs/1512.03385">ResNet V1</a> |
| - <a class="reference external" href="https://arxiv.org/abs/1512.03385">ResNet V2</a> |
| - <a class="reference external" href="https://arxiv.org/abs/1602.07360">SqueezeNet</a> |
| - <a class="reference external" href="https://arxiv.org/abs/1409.1556">VGG</a> |
| - <a class="reference external" href="https://arxiv.org/abs/1704.04861">MobileNet</a></p> |
| <p>You can construct a model with random weights by calling its constructor:</p> |
| <div class="code highlight-python"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">mxnet.gluon.model_zoo</span> <span class="kn">import</span> <span class="n">vision</span> |
| <span class="n">resnet18</span> <span class="o">=</span> <span class="n">vision</span><span class="o">.</span><span class="n">resnet18_v1</span><span class="p">()</span> |
| <span class="n">alexnet</span> <span class="o">=</span> <span class="n">vision</span><span class="o">.</span><span class="n">alexnet</span><span class="p">()</span> |
| <span class="n">squeezenet</span> <span class="o">=</span> <span class="n">vision</span><span class="o">.</span><span class="n">squeezenet1_0</span><span class="p">()</span> |
| <span class="n">densenet</span> <span class="o">=</span> <span class="n">vision</span><span class="o">.</span><span class="n">densenet_161</span><span class="p">()</span> |
| </pre></div> |
| </div> |
| <p>We provide pre-trained models for all the listed models. |
| These models can constructed by passing <code class="docutils literal"><span class="pre">pretrained=True</span></code>:</p> |
| <div class="code highlight-python"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">mxnet.gluon.model_zoo</span> <span class="kn">import</span> <span class="n">vision</span> |
| <span class="n">resnet18</span> <span class="o">=</span> <span class="n">vision</span><span class="o">.</span><span class="n">resnet18_v1</span><span class="p">(</span><span class="n">pretrained</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span> |
| <span class="n">alexnet</span> <span class="o">=</span> <span class="n">vision</span><span class="o">.</span><span class="n">alexnet</span><span class="p">(</span><span class="n">pretrained</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>All pre-trained models expect input images normalized in the same way, |
| i.e. mini-batches of 3-channel RGB images of shape (N x 3 x H x W), |
| where N is the batch size, and H and W are expected to be at least 224. |
| The images have to be loaded in to a range of [0, 1] and then normalized |
| using <code class="docutils literal"><span class="pre">mean</span> <span class="pre">=</span> <span class="pre">[0.485,</span> <span class="pre">0.456,</span> <span class="pre">0.406]</span></code> and <code class="docutils literal"><span class="pre">std</span> <span class="pre">=</span> <span class="pre">[0.229,</span> <span class="pre">0.224,</span> <span class="pre">0.225]</span></code>. |
| The transformation should preferrably happen at preprocessing. You can use |
| <code class="docutils literal"><span class="pre">mx.image.color_normalize</span></code> for such transformation:</p> |
| <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="o">/</span><span class="mi">255</span> |
| <span class="n">normalized</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">image</span><span class="o">.</span><span class="n">color_normalize</span><span class="p">(</span><span class="n">image</span><span class="p">,</span> |
| <span class="n">mean</span><span class="o">=</span><span class="n">mx</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">0.485</span><span class="p">,</span> <span class="mf">0.456</span><span class="p">,</span> <span class="mf">0.406</span><span class="p">]),</span> |
| <span class="n">std</span><span class="o">=</span><span class="n">mx</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">0.229</span><span class="p">,</span> <span class="mf">0.224</span><span class="p">,</span> <span class="mf">0.225</span><span class="p">]))</span> |
| </pre></div> |
| </div> |
| <p>The following table summarizes the available models.</p> |
| <table border="1" class="docutils"> |
| <colgroup> |
| <col width="17%"/> |
| <col width="17%"/> |
| <col width="17%"/> |
| <col width="17%"/> |
| <col width="17%"/> |
| <col width="17%"/> |
| </colgroup> |
| <thead valign="bottom"> |
| <tr class="row-odd"><th class="head">Alias</th> |
| <th class="head">Network</th> |
| <th class="head"># Parameters</th> |
| <th class="head">Top-1 Accuracy</th> |
| <th class="head">Top-5 Accuracy</th> |
| <th class="head">Origin</th> |
| </tr> |
| </thead> |
| <tbody valign="top"> |
| <tr class="row-even"><td>alexnet</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1404.5997">AlexNet</a></td> |
| <td>61,100,840</td> |
| <td>0.5492</td> |
| <td>0.7803</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-odd"><td>densenet121</td> |
| <td><a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">DenseNet-121</a></td> |
| <td>8,062,504</td> |
| <td>0.7497</td> |
| <td>0.9225</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-even"><td>densenet161</td> |
| <td><a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">DenseNet-161</a></td> |
| <td>28,900,936</td> |
| <td>0.7770</td> |
| <td>0.9380</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-odd"><td>densenet169</td> |
| <td><a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">DenseNet-169</a></td> |
| <td>14,307,880</td> |
| <td>0.7617</td> |
| <td>0.9317</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-even"><td>densenet201</td> |
| <td><a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">DenseNet-201</a></td> |
| <td>20,242,984</td> |
| <td>0.7732</td> |
| <td>0.9362</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-odd"><td>inceptionv3</td> |
| <td><a class="reference external" href="http://arxiv.org/abs/1512.00567">Inception V3 299x299</a></td> |
| <td>23,869,000</td> |
| <td>0.7755</td> |
| <td>0.9364</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-even"><td>mobilenet0.25</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1704.04861">MobileNet 0.25</a></td> |
| <td>475,544</td> |
| <td>0.5185</td> |
| <td>0.7608</td> |
| <td>Trained with <a class="reference external" href="https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py">script</a></td> |
| </tr> |
| <tr class="row-odd"><td>mobilenet0.5</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1704.04861">MobileNet 0.5</a></td> |
| <td>1,342,536</td> |
| <td>0.6307</td> |
| <td>0.8475</td> |
| <td>Trained with <a class="reference external" href="https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py">script</a></td> |
| </tr> |
| <tr class="row-even"><td>mobilenet0.75</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1704.04861">MobileNet 0.75</a></td> |
| <td>2,601,976</td> |
| <td>0.6738</td> |
| <td>0.8782</td> |
| <td>Trained with <a class="reference external" href="https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py">script</a></td> |
| </tr> |
| <tr class="row-odd"><td>mobilenet1.0</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1704.04861">MobileNet 1.0</a></td> |
| <td>4,253,864</td> |
| <td>0.7105</td> |
| <td>0.9006</td> |
| <td>Trained with <a class="reference external" href="https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py">script</a></td> |
| </tr> |
| <tr class="row-even"><td>resnet18_v1</td> |
| <td><a class="reference external" href="http://arxiv.org/abs/1512.03385">ResNet-18 V1</a></td> |
| <td>11,699,112</td> |
| <td>0.6803</td> |
| <td>0.8818</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-odd"><td>resnet34_v1</td> |
| <td><a class="reference external" href="http://arxiv.org/abs/1512.03385">ResNet-34 V1</a></td> |
| <td>21,814,696</td> |
| <td>0.7202</td> |
| <td>0.9066</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-even"><td>resnet50_v1</td> |
| <td><a class="reference external" href="http://arxiv.org/abs/1512.03385">ResNet-50 V1</a></td> |
| <td>25,629,032</td> |
| <td>0.7540</td> |
| <td>0.9266</td> |
| <td>Trained with <a class="reference external" href="https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py">script</a></td> |
| </tr> |
| <tr class="row-odd"><td>resnet101_v1</td> |
| <td><a class="reference external" href="http://arxiv.org/abs/1512.03385">ResNet-101 V1</a></td> |
| <td>44,695,144</td> |
| <td>0.7693</td> |
| <td>0.9334</td> |
| <td>Trained with <a class="reference external" href="https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py">script</a></td> |
| </tr> |
| <tr class="row-even"><td>resnet152_v1</td> |
| <td><a class="reference external" href="http://arxiv.org/abs/1512.03385">ResNet-152 V1</a></td> |
| <td>60,404,072</td> |
| <td>0.7727</td> |
| <td>0.9353</td> |
| <td>Trained with <a class="reference external" href="https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py">script</a></td> |
| </tr> |
| <tr class="row-odd"><td>resnet18_v2</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1603.05027">ResNet-18 V2</a></td> |
| <td>11,695,796</td> |
| <td>0.6961</td> |
| <td>0.8901</td> |
| <td>Trained with <a class="reference external" href="https://github.com/apache/incubator-mxnet/blob/4dcd96ae2f6820e01455079d00f49db1cd21eda9/example/gluon/image_classification.py">script</a></td> |
| </tr> |
| <tr class="row-even"><td>resnet34_v2</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1603.05027">ResNet-34 V2</a></td> |
| <td>21,811,380</td> |
| <td>0.7324</td> |
| <td>0.9125</td> |
| <td>Trained with <a class="reference external" href="https://github.com/apache/incubator-mxnet/blob/4dcd96ae2f6820e01455079d00f49db1cd21eda9/example/gluon/image_classification.py">script</a></td> |
| </tr> |
| <tr class="row-odd"><td>resnet50_v2</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1603.05027">ResNet-50 V2</a></td> |
| <td>25,595,060</td> |
| <td>0.7622</td> |
| <td>0.9297</td> |
| <td>Trained with <a class="reference external" href="https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py">script</a></td> |
| </tr> |
| <tr class="row-even"><td>resnet101_v2</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1603.05027">ResNet-101 V2</a></td> |
| <td>44,639,412</td> |
| <td>0.7747</td> |
| <td>0.9375</td> |
| <td>Trained with <a class="reference external" href="https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py">script</a></td> |
| </tr> |
| <tr class="row-odd"><td>resnet152_v2</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1603.05027">ResNet-152 V2</a></td> |
| <td>60,329,140</td> |
| <td>0.7833</td> |
| <td>0.9409</td> |
| <td>Trained with <a class="reference external" href="https://github.com/zhreshold/mxnet/blob/2fbfdbcbacff8b738bd9f44e9c8cefc84d6dfbb5/example/gluon/train_imagenet.py">script</a></td> |
| </tr> |
| <tr class="row-even"><td>squeezenet1.0</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1602.07360">SqueezeNet 1.0</a></td> |
| <td>1,248,424</td> |
| <td>0.5611</td> |
| <td>0.7909</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-odd"><td>squeezenet1.1</td> |
| <td><a class="reference external" href="https://github.com/DeepScale/SqueezeNet/tree/master/SqueezeNet_v1.1">SqueezeNet 1.1</a></td> |
| <td>1,235,496</td> |
| <td>0.5496</td> |
| <td>0.7817</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-even"><td>vgg11</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1409.1556">VGG-11</a></td> |
| <td>132,863,336</td> |
| <td>0.6662</td> |
| <td>0.8734</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-odd"><td>vgg13</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1409.1556">VGG-13</a></td> |
| <td>133,047,848</td> |
| <td>0.6774</td> |
| <td>0.8811</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-even"><td>vgg16</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1409.1556">VGG-16</a></td> |
| <td>138,357,544</td> |
| <td>0.6986</td> |
| <td>0.8945</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-odd"><td>vgg19</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1409.1556">VGG-19</a></td> |
| <td>143,667,240</td> |
| <td>0.7072</td> |
| <td>0.8988</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-even"><td>vgg11_bn</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1409.1556">VGG-11 with batch normalization</a></td> |
| <td>132,874,344</td> |
| <td>0.6859</td> |
| <td>0.8872</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-odd"><td>vgg13_bn</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1409.1556">VGG-13 with batch normalization</a></td> |
| <td>133,059,624</td> |
| <td>0.6884</td> |
| <td>0.8882</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-even"><td>vgg16_bn</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1409.1556">VGG-16 with batch normalization</a></td> |
| <td>138,374,440</td> |
| <td>0.7142</td> |
| <td>0.9043</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| <tr class="row-odd"><td>vgg19_bn</td> |
| <td><a class="reference external" href="https://arxiv.org/abs/1409.1556">VGG-19 with batch normalization</a></td> |
| <td>143,689,256</td> |
| <td>0.7241</td> |
| <td>0.9093</td> |
| <td>Converted from pytorch vision</td> |
| </tr> |
| </tbody> |
| </table> |
| <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.model_zoo.vision.get_model" title="mxnet.gluon.model_zoo.vision.get_model"><code class="xref py py-obj docutils literal"><span class="pre">get_model</span></code></a></td> |
| <td>Returns a pre-defined model by name</td> |
| </tr> |
| </tbody> |
| </table> |
| <div class="section" id="resnet"> |
| <span id="resnet"></span><h4>ResNet<a class="headerlink" href="#resnet" title="Permalink to this headline">¶</a></h4> |
| <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.model_zoo.vision.resnet18_v1" title="mxnet.gluon.model_zoo.vision.resnet18_v1"><code class="xref py py-obj docutils literal"><span class="pre">resnet18_v1</span></code></a></td> |
| <td>ResNet-18 V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.resnet34_v1" title="mxnet.gluon.model_zoo.vision.resnet34_v1"><code class="xref py py-obj docutils literal"><span class="pre">resnet34_v1</span></code></a></td> |
| <td>ResNet-34 V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.resnet50_v1" title="mxnet.gluon.model_zoo.vision.resnet50_v1"><code class="xref py py-obj docutils literal"><span class="pre">resnet50_v1</span></code></a></td> |
| <td>ResNet-50 V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.resnet101_v1" title="mxnet.gluon.model_zoo.vision.resnet101_v1"><code class="xref py py-obj docutils literal"><span class="pre">resnet101_v1</span></code></a></td> |
| <td>ResNet-101 V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.resnet152_v1" title="mxnet.gluon.model_zoo.vision.resnet152_v1"><code class="xref py py-obj docutils literal"><span class="pre">resnet152_v1</span></code></a></td> |
| <td>ResNet-152 V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.resnet18_v2" title="mxnet.gluon.model_zoo.vision.resnet18_v2"><code class="xref py py-obj docutils literal"><span class="pre">resnet18_v2</span></code></a></td> |
| <td>ResNet-18 V2 model from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.resnet34_v2" title="mxnet.gluon.model_zoo.vision.resnet34_v2"><code class="xref py py-obj docutils literal"><span class="pre">resnet34_v2</span></code></a></td> |
| <td>ResNet-34 V2 model from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.resnet50_v2" title="mxnet.gluon.model_zoo.vision.resnet50_v2"><code class="xref py py-obj docutils literal"><span class="pre">resnet50_v2</span></code></a></td> |
| <td>ResNet-50 V2 model from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.resnet101_v2" title="mxnet.gluon.model_zoo.vision.resnet101_v2"><code class="xref py py-obj docutils literal"><span class="pre">resnet101_v2</span></code></a></td> |
| <td>ResNet-101 V2 model from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.resnet152_v2" title="mxnet.gluon.model_zoo.vision.resnet152_v2"><code class="xref py py-obj docutils literal"><span class="pre">resnet152_v2</span></code></a></td> |
| <td>ResNet-152 V2 model from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</td> |
| </tr> |
| </tbody> |
| </table> |
| <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.model_zoo.vision.ResNetV1" title="mxnet.gluon.model_zoo.vision.ResNetV1"><code class="xref py py-obj docutils literal"><span class="pre">ResNetV1</span></code></a></td> |
| <td>ResNet V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.ResNetV2" title="mxnet.gluon.model_zoo.vision.ResNetV2"><code class="xref py py-obj docutils literal"><span class="pre">ResNetV2</span></code></a></td> |
| <td>ResNet V2 model from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.BasicBlockV1" title="mxnet.gluon.model_zoo.vision.BasicBlockV1"><code class="xref py py-obj docutils literal"><span class="pre">BasicBlockV1</span></code></a></td> |
| <td>BasicBlock V1 from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.BasicBlockV2" title="mxnet.gluon.model_zoo.vision.BasicBlockV2"><code class="xref py py-obj docutils literal"><span class="pre">BasicBlockV2</span></code></a></td> |
| <td>BasicBlock V2 from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.BottleneckV1" title="mxnet.gluon.model_zoo.vision.BottleneckV1"><code class="xref py py-obj docutils literal"><span class="pre">BottleneckV1</span></code></a></td> |
| <td>Bottleneck V1 from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.BottleneckV2" title="mxnet.gluon.model_zoo.vision.BottleneckV2"><code class="xref py py-obj docutils literal"><span class="pre">BottleneckV2</span></code></a></td> |
| <td>Bottleneck V2 from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.get_resnet" title="mxnet.gluon.model_zoo.vision.get_resnet"><code class="xref py py-obj docutils literal"><span class="pre">get_resnet</span></code></a></td> |
| <td>ResNet V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <div class="section" id="vgg"> |
| <span id="vgg"></span><h4>VGG<a class="headerlink" href="#vgg" title="Permalink to this headline">¶</a></h4> |
| <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.model_zoo.vision.vgg11" title="mxnet.gluon.model_zoo.vision.vgg11"><code class="xref py py-obj docutils literal"><span class="pre">vgg11</span></code></a></td> |
| <td>VGG-11 model from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.vgg13" title="mxnet.gluon.model_zoo.vision.vgg13"><code class="xref py py-obj docutils literal"><span class="pre">vgg13</span></code></a></td> |
| <td>VGG-13 model from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.vgg16" title="mxnet.gluon.model_zoo.vision.vgg16"><code class="xref py py-obj docutils literal"><span class="pre">vgg16</span></code></a></td> |
| <td>VGG-16 model from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.vgg19" title="mxnet.gluon.model_zoo.vision.vgg19"><code class="xref py py-obj docutils literal"><span class="pre">vgg19</span></code></a></td> |
| <td>VGG-19 model from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.vgg11_bn" title="mxnet.gluon.model_zoo.vision.vgg11_bn"><code class="xref py py-obj docutils literal"><span class="pre">vgg11_bn</span></code></a></td> |
| <td>VGG-11 model with batch normalization from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.vgg13_bn" title="mxnet.gluon.model_zoo.vision.vgg13_bn"><code class="xref py py-obj docutils literal"><span class="pre">vgg13_bn</span></code></a></td> |
| <td>VGG-13 model with batch normalization from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.vgg16_bn" title="mxnet.gluon.model_zoo.vision.vgg16_bn"><code class="xref py py-obj docutils literal"><span class="pre">vgg16_bn</span></code></a></td> |
| <td>VGG-16 model with batch normalization from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.vgg19_bn" title="mxnet.gluon.model_zoo.vision.vgg19_bn"><code class="xref py py-obj docutils literal"><span class="pre">vgg19_bn</span></code></a></td> |
| <td>VGG-19 model with batch normalization from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</td> |
| </tr> |
| </tbody> |
| </table> |
| <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.model_zoo.vision.VGG" title="mxnet.gluon.model_zoo.vision.VGG"><code class="xref py py-obj docutils literal"><span class="pre">VGG</span></code></a></td> |
| <td>VGG model from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.get_vgg" title="mxnet.gluon.model_zoo.vision.get_vgg"><code class="xref py py-obj docutils literal"><span class="pre">get_vgg</span></code></a></td> |
| <td>VGG model from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <div class="section" id="alexnet"> |
| <span id="alexnet"></span><h4>Alexnet<a class="headerlink" href="#alexnet" title="Permalink to this headline">¶</a></h4> |
| <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.model_zoo.vision.alexnet" title="mxnet.gluon.model_zoo.vision.alexnet"><code class="xref py py-obj docutils literal"><span class="pre">alexnet</span></code></a></td> |
| <td>AlexNet model from the <a class="reference external" href="https://arxiv.org/abs/1404.5997">“One weird trick...”</a> paper.</td> |
| </tr> |
| </tbody> |
| </table> |
| <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.model_zoo.vision.AlexNet" title="mxnet.gluon.model_zoo.vision.AlexNet"><code class="xref py py-obj docutils literal"><span class="pre">AlexNet</span></code></a></td> |
| <td>AlexNet model from the <a class="reference external" href="https://arxiv.org/abs/1404.5997">“One weird trick...”</a> paper.</td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <div class="section" id="densenet"> |
| <span id="densenet"></span><h4>DenseNet<a class="headerlink" href="#densenet" title="Permalink to this headline">¶</a></h4> |
| <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.model_zoo.vision.densenet121" title="mxnet.gluon.model_zoo.vision.densenet121"><code class="xref py py-obj docutils literal"><span class="pre">densenet121</span></code></a></td> |
| <td>Densenet-BC 121-layer model from the <a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">“Densely Connected Convolutional Networks”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.densenet161" title="mxnet.gluon.model_zoo.vision.densenet161"><code class="xref py py-obj docutils literal"><span class="pre">densenet161</span></code></a></td> |
| <td>Densenet-BC 161-layer model from the <a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">“Densely Connected Convolutional Networks”</a> paper.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.densenet169" title="mxnet.gluon.model_zoo.vision.densenet169"><code class="xref py py-obj docutils literal"><span class="pre">densenet169</span></code></a></td> |
| <td>Densenet-BC 169-layer model from the <a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">“Densely Connected Convolutional Networks”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.densenet201" title="mxnet.gluon.model_zoo.vision.densenet201"><code class="xref py py-obj docutils literal"><span class="pre">densenet201</span></code></a></td> |
| <td>Densenet-BC 201-layer model from the <a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">“Densely Connected Convolutional Networks”</a> paper.</td> |
| </tr> |
| </tbody> |
| </table> |
| <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.model_zoo.vision.DenseNet" title="mxnet.gluon.model_zoo.vision.DenseNet"><code class="xref py py-obj docutils literal"><span class="pre">DenseNet</span></code></a></td> |
| <td>Densenet-BC model from the <a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">“Densely Connected Convolutional Networks”</a> paper.</td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <div class="section" id="squeezenet"> |
| <span id="squeezenet"></span><h4>SqueezeNet<a class="headerlink" href="#squeezenet" title="Permalink to this headline">¶</a></h4> |
| <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.model_zoo.vision.squeezenet1_0" title="mxnet.gluon.model_zoo.vision.squeezenet1_0"><code class="xref py py-obj docutils literal"><span class="pre">squeezenet1_0</span></code></a></td> |
| <td>SqueezeNet 1.0 model from the <a class="reference external" href="https://arxiv.org/abs/1602.07360">“SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size”</a> paper.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.squeezenet1_1" title="mxnet.gluon.model_zoo.vision.squeezenet1_1"><code class="xref py py-obj docutils literal"><span class="pre">squeezenet1_1</span></code></a></td> |
| <td>SqueezeNet 1.1 model from the <a class="reference external" href="https://github.com/DeepScale/SqueezeNet/tree/master/SqueezeNet_v1.1">official SqueezeNet repo</a>.</td> |
| </tr> |
| </tbody> |
| </table> |
| <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.model_zoo.vision.SqueezeNet" title="mxnet.gluon.model_zoo.vision.SqueezeNet"><code class="xref py py-obj docutils literal"><span class="pre">SqueezeNet</span></code></a></td> |
| <td>SqueezeNet model from the <a class="reference external" href="https://arxiv.org/abs/1602.07360">“SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size”</a> paper.</td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <div class="section" id="inception"> |
| <span id="inception"></span><h4>Inception<a class="headerlink" href="#inception" title="Permalink to this headline">¶</a></h4> |
| <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.model_zoo.vision.inception_v3" title="mxnet.gluon.model_zoo.vision.inception_v3"><code class="xref py py-obj docutils literal"><span class="pre">inception_v3</span></code></a></td> |
| <td>Inception v3 model from <a class="reference external" href="http://arxiv.org/abs/1512.00567">“Rethinking the Inception Architecture for Computer Vision”</a> paper.</td> |
| </tr> |
| </tbody> |
| </table> |
| <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.model_zoo.vision.Inception3" title="mxnet.gluon.model_zoo.vision.Inception3"><code class="xref py py-obj docutils literal"><span class="pre">Inception3</span></code></a></td> |
| <td>Inception v3 model from <a class="reference external" href="http://arxiv.org/abs/1512.00567">“Rethinking the Inception Architecture for Computer Vision”</a> paper.</td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <div class="section" id="mobilenet"> |
| <span id="mobilenet"></span><h4>MobileNet<a class="headerlink" href="#mobilenet" title="Permalink to this headline">¶</a></h4> |
| <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.model_zoo.vision.mobilenet1_0" title="mxnet.gluon.model_zoo.vision.mobilenet1_0"><code class="xref py py-obj docutils literal"><span class="pre">mobilenet1_0</span></code></a></td> |
| <td>MobileNet model from the <a class="reference external" href="https://arxiv.org/abs/1704.04861">“MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”</a> paper, with width multiplier 1.0.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.mobilenet0_75" title="mxnet.gluon.model_zoo.vision.mobilenet0_75"><code class="xref py py-obj docutils literal"><span class="pre">mobilenet0_75</span></code></a></td> |
| <td>MobileNet model from the <a class="reference external" href="https://arxiv.org/abs/1704.04861">“MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”</a> paper, with width multiplier 0.75.</td> |
| </tr> |
| <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.mobilenet0_5" title="mxnet.gluon.model_zoo.vision.mobilenet0_5"><code class="xref py py-obj docutils literal"><span class="pre">mobilenet0_5</span></code></a></td> |
| <td>MobileNet model from the <a class="reference external" href="https://arxiv.org/abs/1704.04861">“MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”</a> paper, with width multiplier 0.5.</td> |
| </tr> |
| <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.model_zoo.vision.mobilenet0_25" title="mxnet.gluon.model_zoo.vision.mobilenet0_25"><code class="xref py py-obj docutils literal"><span class="pre">mobilenet0_25</span></code></a></td> |
| <td>MobileNet model from the <a class="reference external" href="https://arxiv.org/abs/1704.04861">“MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”</a> paper, with width multiplier 0.25.</td> |
| </tr> |
| </tbody> |
| </table> |
| <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.model_zoo.vision.MobileNet" title="mxnet.gluon.model_zoo.vision.MobileNet"><code class="xref py py-obj docutils literal"><span class="pre">MobileNet</span></code></a></td> |
| <td>MobileNet model from the <a class="reference external" href="https://arxiv.org/abs/1704.04861">“MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”</a> paper.</td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| </div> |
| </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.model_zoo"></span><p>Predefined and pretrained models.</p> |
| <span class="target" id="module-mxnet.gluon.model_zoo.vision"></span><p>Module for pre-defined neural network models.</p> |
| <p>This module contains definitions for the following model architectures: |
| - <a class="reference external" href="https://arxiv.org/abs/1404.5997">AlexNet</a> |
| - <a class="reference external" href="https://arxiv.org/abs/1608.06993">DenseNet</a> |
| - <a class="reference external" href="http://arxiv.org/abs/1512.00567">Inception V3</a> |
| - <a class="reference external" href="https://arxiv.org/abs/1512.03385">ResNet V1</a> |
| - <a class="reference external" href="https://arxiv.org/abs/1512.03385">ResNet V2</a> |
| - <a class="reference external" href="https://arxiv.org/abs/1602.07360">SqueezeNet</a> |
| - <a class="reference external" href="https://arxiv.org/abs/1409.1556">VGG</a> |
| - <a class="reference external" href="https://arxiv.org/abs/1704.04861">MobileNet</a></p> |
| <p>You can construct a model with random weights by calling its constructor:</p> |
| <div class="code highlight-python"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">mxnet.gluon.model_zoo</span> <span class="kn">import</span> <span class="n">vision</span> |
| <span class="n">resnet18</span> <span class="o">=</span> <span class="n">vision</span><span class="o">.</span><span class="n">resnet18_v1</span><span class="p">()</span> |
| <span class="n">alexnet</span> <span class="o">=</span> <span class="n">vision</span><span class="o">.</span><span class="n">alexnet</span><span class="p">()</span> |
| <span class="n">squeezenet</span> <span class="o">=</span> <span class="n">vision</span><span class="o">.</span><span class="n">squeezenet1_0</span><span class="p">()</span> |
| <span class="n">densenet</span> <span class="o">=</span> <span class="n">vision</span><span class="o">.</span><span class="n">densenet_161</span><span class="p">()</span> |
| </pre></div> |
| </div> |
| <p>We provide pre-trained models for all the listed models. |
| These models can constructed by passing <code class="docutils literal"><span class="pre">pretrained=True</span></code>:</p> |
| <div class="code highlight-python"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">mxnet.gluon.model_zoo</span> <span class="kn">import</span> <span class="n">vision</span> |
| <span class="n">resnet18</span> <span class="o">=</span> <span class="n">vision</span><span class="o">.</span><span class="n">resnet18_v1</span><span class="p">(</span><span class="n">pretrained</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span> |
| <span class="n">alexnet</span> <span class="o">=</span> <span class="n">vision</span><span class="o">.</span><span class="n">alexnet</span><span class="p">(</span><span class="n">pretrained</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>All pre-trained models expect input images normalized in the same way, |
| i.e. mini-batches of 3-channel RGB images of shape (N x 3 x H x W), |
| where N is the batch size, and H and W are expected to be at least 224. |
| The images have to be loaded in to a range of [0, 1] and then normalized |
| using <code class="docutils literal"><span class="pre">mean</span> <span class="pre">=</span> <span class="pre">[0.485,</span> <span class="pre">0.456,</span> <span class="pre">0.406]</span></code> and <code class="docutils literal"><span class="pre">std</span> <span class="pre">=</span> <span class="pre">[0.229,</span> <span class="pre">0.224,</span> <span class="pre">0.225]</span></code>. |
| The transformation should preferrably happen at preprocessing. You can use |
| <code class="docutils literal"><span class="pre">mx.image.color_normalize</span></code> for such transformation:</p> |
| <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="o">/</span><span class="mi">255</span> |
| <span class="n">normalized</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">image</span><span class="o">.</span><span class="n">color_normalize</span><span class="p">(</span><span class="n">image</span><span class="p">,</span> |
| <span class="n">mean</span><span class="o">=</span><span class="n">mx</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">0.485</span><span class="p">,</span> <span class="mf">0.456</span><span class="p">,</span> <span class="mf">0.406</span><span class="p">]),</span> |
| <span class="n">std</span><span class="o">=</span><span class="n">mx</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">0.229</span><span class="p">,</span> <span class="mf">0.224</span><span class="p">,</span> <span class="mf">0.225</span><span class="p">]))</span> |
| </pre></div> |
| </div> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.get_model"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">get_model</code><span class="sig-paren">(</span><em>name</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision.html#get_model"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.get_model" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a pre-defined model by name</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 simple"> |
| <li><strong>name</strong> (<em>str</em>) – Name of the model.</li> |
| <li><strong>pretrained</strong> (<em>bool</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>classes</strong> (<em>int</em>) – Number of classes for the output layer.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| <tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">The model.</p> |
| </td> |
| </tr> |
| <tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><p class="first last"><a class="reference internal" href="gluon.html#mxnet.gluon.HybridBlock" title="mxnet.gluon.HybridBlock">HybridBlock</a></p> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.model_zoo.vision.AlexNet"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">AlexNet</code><span class="sig-paren">(</span><em>classes=1000</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/alexnet.html#AlexNet"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.AlexNet" title="Permalink to this definition">¶</a></dt> |
| <dd><p>AlexNet model from the <a class="reference external" href="https://arxiv.org/abs/1404.5997">“One weird trick...”</a> paper.</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"><strong>classes</strong> (<em>int, default 1000</em>) – Number of classes for the output layer.</td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.model_zoo.vision.BasicBlockV1"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">BasicBlockV1</code><span class="sig-paren">(</span><em>channels</em>, <em>stride</em>, <em>downsample=False</em>, <em>in_channels=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#BasicBlockV1"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.BasicBlockV1" title="Permalink to this definition">¶</a></dt> |
| <dd><p>BasicBlock V1 from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper. |
| This is used for ResNet V1 for 18, 34 layers.</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>channels</strong> (<em>int</em>) – Number of output channels.</li> |
| <li><strong>stride</strong> (<em>int</em>) – Stride size.</li> |
| <li><strong>downsample</strong> (<em>bool, default False</em>) – Whether to downsample the input.</li> |
| <li><strong>in_channels</strong> (<em>int, default 0</em>) – Number of input channels. Default is 0, to infer from the graph.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.model_zoo.vision.BasicBlockV2"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">BasicBlockV2</code><span class="sig-paren">(</span><em>channels</em>, <em>stride</em>, <em>downsample=False</em>, <em>in_channels=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#BasicBlockV2"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.BasicBlockV2" title="Permalink to this definition">¶</a></dt> |
| <dd><p>BasicBlock V2 from |
| <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper. |
| This is used for ResNet V2 for 18, 34 layers.</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>channels</strong> (<em>int</em>) – Number of output channels.</li> |
| <li><strong>stride</strong> (<em>int</em>) – Stride size.</li> |
| <li><strong>downsample</strong> (<em>bool, default False</em>) – Whether to downsample the input.</li> |
| <li><strong>in_channels</strong> (<em>int, default 0</em>) – Number of input channels. Default is 0, to infer from the graph.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.model_zoo.vision.BottleneckV1"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">BottleneckV1</code><span class="sig-paren">(</span><em>channels</em>, <em>stride</em>, <em>downsample=False</em>, <em>in_channels=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#BottleneckV1"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.BottleneckV1" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bottleneck V1 from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper. |
| This is used for ResNet V1 for 50, 101, 152 layers.</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>channels</strong> (<em>int</em>) – Number of output channels.</li> |
| <li><strong>stride</strong> (<em>int</em>) – Stride size.</li> |
| <li><strong>downsample</strong> (<em>bool, default False</em>) – Whether to downsample the input.</li> |
| <li><strong>in_channels</strong> (<em>int, default 0</em>) – Number of input channels. Default is 0, to infer from the graph.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.model_zoo.vision.BottleneckV2"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">BottleneckV2</code><span class="sig-paren">(</span><em>channels</em>, <em>stride</em>, <em>downsample=False</em>, <em>in_channels=0</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#BottleneckV2"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.BottleneckV2" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bottleneck V2 from |
| <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper. |
| This is used for ResNet V2 for 50, 101, 152 layers.</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>channels</strong> (<em>int</em>) – Number of output channels.</li> |
| <li><strong>stride</strong> (<em>int</em>) – Stride size.</li> |
| <li><strong>downsample</strong> (<em>bool, default False</em>) – Whether to downsample the input.</li> |
| <li><strong>in_channels</strong> (<em>int, default 0</em>) – Number of input channels. Default is 0, to infer from the graph.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.model_zoo.vision.DenseNet"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">DenseNet</code><span class="sig-paren">(</span><em>num_init_features</em>, <em>growth_rate</em>, <em>block_config</em>, <em>bn_size=4</em>, <em>dropout=0</em>, <em>classes=1000</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/densenet.html#DenseNet"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.DenseNet" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Densenet-BC model from the |
| <a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">“Densely Connected Convolutional Networks”</a> paper.</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>num_init_features</strong> (<em>int</em>) – Number of filters to learn in the first convolution layer.</li> |
| <li><strong>growth_rate</strong> (<em>int</em>) – Number of filters to add each layer (<cite>k</cite> in the paper).</li> |
| <li><strong>block_config</strong> (<em>list of int</em>) – List of integers for numbers of layers in each pooling block.</li> |
| <li><strong>bn_size</strong> (<em>int, default 4</em>) – Multiplicative factor for number of bottle neck layers. |
| (i.e. bn_size * k features in the bottleneck layer)</li> |
| <li><strong>dropout</strong> (<em>float, default 0</em>) – Rate of dropout after each dense layer.</li> |
| <li><strong>classes</strong> (<em>int, default 1000</em>) – Number of classification classes.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.model_zoo.vision.Inception3"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">Inception3</code><span class="sig-paren">(</span><em>classes=1000</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/inception.html#Inception3"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.Inception3" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Inception v3 model from |
| <a class="reference external" href="http://arxiv.org/abs/1512.00567">“Rethinking the Inception Architecture for Computer Vision”</a> paper.</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"><strong>classes</strong> (<em>int, default 1000</em>) – Number of classification classes.</td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.model_zoo.vision.MobileNet"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">MobileNet</code><span class="sig-paren">(</span><em>multiplier=1.0</em>, <em>classes=1000</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/mobilenet.html#MobileNet"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.MobileNet" title="Permalink to this definition">¶</a></dt> |
| <dd><p>MobileNet model from the |
| <a class="reference external" href="https://arxiv.org/abs/1704.04861">“MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”</a> paper.</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>multiplier</strong> (<em>float, default 1.0</em>) – The width multiplier for controling the model size. Only multipliers that are no |
| less than 0.25 are supported. The actual number of channels is equal to the original |
| channel size multiplied by this multiplier.</li> |
| <li><strong>classes</strong> (<em>int, default 1000</em>) – Number of classes for the output layer.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.model_zoo.vision.ResNetV1"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">ResNetV1</code><span class="sig-paren">(</span><em>block</em>, <em>layers</em>, <em>channels</em>, <em>classes=1000</em>, <em>thumbnail=False</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#ResNetV1"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.ResNetV1" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet V1 model from |
| <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</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>block</strong> (<a class="reference internal" href="gluon.html#mxnet.gluon.HybridBlock" title="mxnet.gluon.HybridBlock"><em>HybridBlock</em></a>) – Class for the residual block. Options are BasicBlockV1, BottleneckV1.</li> |
| <li><strong>layers</strong> (<em>list of int</em>) – Numbers of layers in each block</li> |
| <li><strong>channels</strong> (<em>list of int</em>) – Numbers of channels in each block. Length should be one larger than layers list.</li> |
| <li><strong>classes</strong> (<em>int, default 1000</em>) – Number of classification classes.</li> |
| <li><strong>thumbnail</strong> (<em>bool, default False</em>) – Enable thumbnail.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.model_zoo.vision.ResNetV2"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">ResNetV2</code><span class="sig-paren">(</span><em>block</em>, <em>layers</em>, <em>channels</em>, <em>classes=1000</em>, <em>thumbnail=False</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#ResNetV2"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.ResNetV2" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet V2 model from |
| <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</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>block</strong> (<a class="reference internal" href="gluon.html#mxnet.gluon.HybridBlock" title="mxnet.gluon.HybridBlock"><em>HybridBlock</em></a>) – Class for the residual block. Options are BasicBlockV1, BottleneckV1.</li> |
| <li><strong>layers</strong> (<em>list of int</em>) – Numbers of layers in each block</li> |
| <li><strong>channels</strong> (<em>list of int</em>) – Numbers of channels in each block. Length should be one larger than layers list.</li> |
| <li><strong>classes</strong> (<em>int, default 1000</em>) – Number of classification classes.</li> |
| <li><strong>thumbnail</strong> (<em>bool, default False</em>) – Enable thumbnail.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.model_zoo.vision.SqueezeNet"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">SqueezeNet</code><span class="sig-paren">(</span><em>version</em>, <em>classes=1000</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/squeezenet.html#SqueezeNet"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.SqueezeNet" title="Permalink to this definition">¶</a></dt> |
| <dd><p>SqueezeNet model from the <a class="reference external" href="https://arxiv.org/abs/1602.07360">“SqueezeNet: AlexNet-level accuracy with 50x fewer parameters |
| and <0.5MB model size”</a> paper. |
| SqueezeNet 1.1 model from the <a class="reference external" href="https://github.com/DeepScale/SqueezeNet/tree/master/SqueezeNet_v1.1">official SqueezeNet repo</a>. |
| SqueezeNet 1.1 has 2.4x less computation and slightly fewer parameters |
| than SqueezeNet 1.0, without sacrificing accuracy.</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>version</strong> (<em>str</em>) – Version of squeezenet. Options are ‘1.0’, ‘1.1’.</li> |
| <li><strong>classes</strong> (<em>int, default 1000</em>) – Number of classification classes.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="class"> |
| <dt id="mxnet.gluon.model_zoo.vision.VGG"> |
| <em class="property">class </em><code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">VGG</code><span class="sig-paren">(</span><em>layers</em>, <em>filters</em>, <em>classes=1000</em>, <em>batch_norm=False</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/vgg.html#VGG"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.VGG" title="Permalink to this definition">¶</a></dt> |
| <dd><p>VGG model from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</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>layers</strong> (<em>list of int</em>) – Numbers of layers in each feature block.</li> |
| <li><strong>filters</strong> (<em>list of int</em>) – Numbers of filters in each feature block. List length should match the layers.</li> |
| <li><strong>classes</strong> (<em>int, default 1000</em>) – Number of classification classes.</li> |
| <li><strong>batch_norm</strong> (<em>bool, default False</em>) – Use batch normalization.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.alexnet"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">alexnet</code><span class="sig-paren">(</span><em>pretrained=False</em>, <em>ctx=cpu(0)</em>, <em>root='~/.mxnet/models'</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/alexnet.html#alexnet"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.alexnet" title="Permalink to this definition">¶</a></dt> |
| <dd><p>AlexNet model from the <a class="reference external" href="https://arxiv.org/abs/1404.5997">“One weird trick...”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.densenet121"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">densenet121</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/densenet.html#densenet121"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.densenet121" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Densenet-BC 121-layer model from the |
| <a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">“Densely Connected Convolutional Networks”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.densenet161"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">densenet161</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/densenet.html#densenet161"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.densenet161" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Densenet-BC 161-layer model from the |
| <a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">“Densely Connected Convolutional Networks”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.densenet169"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">densenet169</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/densenet.html#densenet169"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.densenet169" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Densenet-BC 169-layer model from the |
| <a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">“Densely Connected Convolutional Networks”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.densenet201"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">densenet201</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/densenet.html#densenet201"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.densenet201" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Densenet-BC 201-layer model from the |
| <a class="reference external" href="https://arxiv.org/pdf/1608.06993.pdf">“Densely Connected Convolutional Networks”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.get_mobilenet"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">get_mobilenet</code><span class="sig-paren">(</span><em>multiplier</em>, <em>pretrained=False</em>, <em>ctx=cpu(0)</em>, <em>root='~/.mxnet/models'</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/mobilenet.html#get_mobilenet"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.get_mobilenet" title="Permalink to this definition">¶</a></dt> |
| <dd><p>MobileNet model from the |
| <a class="reference external" href="https://arxiv.org/abs/1704.04861">“MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”</a> paper.</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>multiplier</strong> (<em>float</em>) – The width multiplier for controling the model size. Only multipliers that are no |
| less than 0.25 are supported. The actual number of channels is equal to the original |
| channel size multiplied by this multiplier.</li> |
| <li><strong>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.get_resnet"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">get_resnet</code><span class="sig-paren">(</span><em>version</em>, <em>num_layers</em>, <em>pretrained=False</em>, <em>ctx=cpu(0)</em>, <em>root='~/.mxnet/models'</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#get_resnet"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.get_resnet" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper. |
| ResNet V2 model from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</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>version</strong> (<em>int</em>) – Version of ResNet. Options are 1, 2.</li> |
| <li><strong>num_layers</strong> (<em>int</em>) – Numbers of layers. Options are 18, 34, 50, 101, 152.</li> |
| <li><strong>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.get_vgg"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">get_vgg</code><span class="sig-paren">(</span><em>num_layers</em>, <em>pretrained=False</em>, <em>ctx=cpu(0)</em>, <em>root='~/.mxnet/models'</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/vgg.html#get_vgg"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.get_vgg" title="Permalink to this definition">¶</a></dt> |
| <dd><p>VGG model from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</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>num_layers</strong> (<em>int</em>) – Number of layers for the variant of densenet. Options are 11, 13, 16, 19.</li> |
| <li><strong>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.inception_v3"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">inception_v3</code><span class="sig-paren">(</span><em>pretrained=False</em>, <em>ctx=cpu(0)</em>, <em>root='~/.mxnet/models'</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/inception.html#inception_v3"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.inception_v3" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Inception v3 model from |
| <a class="reference external" href="http://arxiv.org/abs/1512.00567">“Rethinking the Inception Architecture for Computer Vision”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.mobilenet0_25"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">mobilenet0_25</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/mobilenet.html#mobilenet0_25"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.mobilenet0_25" title="Permalink to this definition">¶</a></dt> |
| <dd><p>MobileNet model from the |
| <a class="reference external" href="https://arxiv.org/abs/1704.04861">“MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”</a> paper, with width multiplier 0.25.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.mobilenet0_5"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">mobilenet0_5</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/mobilenet.html#mobilenet0_5"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.mobilenet0_5" title="Permalink to this definition">¶</a></dt> |
| <dd><p>MobileNet model from the |
| <a class="reference external" href="https://arxiv.org/abs/1704.04861">“MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”</a> paper, with width multiplier 0.5.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.mobilenet0_75"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">mobilenet0_75</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/mobilenet.html#mobilenet0_75"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.mobilenet0_75" title="Permalink to this definition">¶</a></dt> |
| <dd><p>MobileNet model from the |
| <a class="reference external" href="https://arxiv.org/abs/1704.04861">“MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”</a> paper, with width multiplier 0.75.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.mobilenet1_0"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">mobilenet1_0</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/mobilenet.html#mobilenet1_0"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.mobilenet1_0" title="Permalink to this definition">¶</a></dt> |
| <dd><p>MobileNet model from the |
| <a class="reference external" href="https://arxiv.org/abs/1704.04861">“MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”</a> paper, with width multiplier 1.0.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.resnet101_v1"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">resnet101_v1</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#resnet101_v1"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.resnet101_v1" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet-101 V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.resnet101_v2"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">resnet101_v2</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#resnet101_v2"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.resnet101_v2" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet-101 V2 model from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.resnet152_v1"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">resnet152_v1</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#resnet152_v1"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.resnet152_v1" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet-152 V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.resnet152_v2"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">resnet152_v2</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#resnet152_v2"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.resnet152_v2" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet-152 V2 model from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.resnet18_v1"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">resnet18_v1</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#resnet18_v1"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.resnet18_v1" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet-18 V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.resnet18_v2"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">resnet18_v2</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#resnet18_v2"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.resnet18_v2" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet-18 V2 model from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.resnet34_v1"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">resnet34_v1</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#resnet34_v1"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.resnet34_v1" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet-34 V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.resnet34_v2"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">resnet34_v2</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#resnet34_v2"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.resnet34_v2" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet-34 V2 model from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.resnet50_v1"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">resnet50_v1</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#resnet50_v1"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.resnet50_v1" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet-50 V1 model from <a class="reference external" href="http://arxiv.org/abs/1512.03385">“Deep Residual Learning for Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.resnet50_v2"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">resnet50_v2</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/resnet.html#resnet50_v2"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.resnet50_v2" title="Permalink to this definition">¶</a></dt> |
| <dd><p>ResNet-50 V2 model from <a class="reference external" href="https://arxiv.org/abs/1603.05027">“Identity Mappings in Deep Residual Networks”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.squeezenet1_0"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">squeezenet1_0</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/squeezenet.html#squeezenet1_0"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.squeezenet1_0" title="Permalink to this definition">¶</a></dt> |
| <dd><p>SqueezeNet 1.0 model from the <a class="reference external" href="https://arxiv.org/abs/1602.07360">“SqueezeNet: AlexNet-level accuracy with 50x fewer parameters |
| and <0.5MB model size”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.squeezenet1_1"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">squeezenet1_1</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/squeezenet.html#squeezenet1_1"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.squeezenet1_1" title="Permalink to this definition">¶</a></dt> |
| <dd><p>SqueezeNet 1.1 model from the <a class="reference external" href="https://github.com/DeepScale/SqueezeNet/tree/master/SqueezeNet_v1.1">official SqueezeNet repo</a>. |
| SqueezeNet 1.1 has 2.4x less computation and slightly fewer parameters |
| than SqueezeNet 1.0, without sacrificing accuracy.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.vgg11"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">vgg11</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/vgg.html#vgg11"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.vgg11" title="Permalink to this definition">¶</a></dt> |
| <dd><p>VGG-11 model from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.vgg11_bn"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">vgg11_bn</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/vgg.html#vgg11_bn"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.vgg11_bn" title="Permalink to this definition">¶</a></dt> |
| <dd><p>VGG-11 model with batch normalization from the |
| <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.vgg13"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">vgg13</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/vgg.html#vgg13"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.vgg13" title="Permalink to this definition">¶</a></dt> |
| <dd><p>VGG-13 model from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.vgg13_bn"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">vgg13_bn</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/vgg.html#vgg13_bn"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.vgg13_bn" title="Permalink to this definition">¶</a></dt> |
| <dd><p>VGG-13 model with batch normalization from the |
| <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.vgg16"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">vgg16</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/vgg.html#vgg16"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.vgg16" title="Permalink to this definition">¶</a></dt> |
| <dd><p>VGG-16 model from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.vgg16_bn"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">vgg16_bn</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/vgg.html#vgg16_bn"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.vgg16_bn" title="Permalink to this definition">¶</a></dt> |
| <dd><p>VGG-16 model with batch normalization from the |
| <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.vgg19"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">vgg19</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/vgg.html#vgg19"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.vgg19" title="Permalink to this definition">¶</a></dt> |
| <dd><p>VGG-19 model from the <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| <dl class="function"> |
| <dt id="mxnet.gluon.model_zoo.vision.vgg19_bn"> |
| <code class="descclassname">mxnet.gluon.model_zoo.vision.</code><code class="descname">vgg19_bn</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/model_zoo/vision/vgg.html#vgg19_bn"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.model_zoo.vision.vgg19_bn" title="Permalink to this definition">¶</a></dt> |
| <dd><p>VGG-19 model with batch normalization from the |
| <a class="reference external" href="https://arxiv.org/abs/1409.1556">“Very Deep Convolutional Networks for Large-Scale Image Recognition”</a> paper.</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>pretrained</strong> (<em>bool, default False</em>) – Whether to load the pretrained weights for model.</li> |
| <li><strong>ctx</strong> (<em>Context, default CPU</em>) – The context in which to load the pretrained weights.</li> |
| <li><strong>root</strong> (<em>str, default '~/.mxnet/models'</em>) – Location for keeping the model parameters.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </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 Model Zoo</a><ul> |
| <li><a class="reference internal" href="#overview">Overview</a><ul> |
| <li><a class="reference internal" href="#module-mxnet.gluon.model_zoo.vision">Vision</a><ul> |
| <li><a class="reference internal" href="#resnet">ResNet</a></li> |
| <li><a class="reference internal" href="#vgg">VGG</a></li> |
| <li><a class="reference internal" href="#alexnet">Alexnet</a></li> |
| <li><a class="reference internal" href="#densenet">DenseNet</a></li> |
| <li><a class="reference internal" href="#squeezenet">SqueezeNet</a></li> |
| <li><a class="reference internal" href="#inception">Inception</a></li> |
| <li><a class="reference internal" href="#mobilenet">MobileNet</a></li> |
| </ul> |
| </li> |
| </ul> |
| </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 type="text/javascript"> |
| $('body').ready(function () { |
| $('body').css('visibility', 'visible'); |
| }); |
| </script> |
| </body> |
| </html> |
