| <!DOCTYPE html> |
| |
| <html lang="en"> |
| <head> |
| <meta charset="utf-8"/> |
| <meta content="IE=edge" http-equiv="X-UA-Compatible"/> |
| <meta content="width=device-width, initial-scale=1" name="viewport"/> |
| <meta content="mxnet.gluon.nn.conv_layers" property="og:title"> |
| <meta content="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/og-logo.png" property="og:image"> |
| <meta content="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/og-logo.png" property="og:image:secure_url"> |
| <meta content="mxnet.gluon.nn.conv_layers" property="og:description"/> |
| <title>mxnet.gluon.nn.conv_layers — mxnet documentation</title> |
| <link crossorigin="anonymous" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css" integrity="sha384-1q8mTJOASx8j1Au+a5WDVnPi2lkFfwwEAa8hDDdjZlpLegxhjVME1fgjWPGmkzs7" rel="stylesheet"/> |
| <link href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css" rel="stylesheet"/> |
| <link href="../../../../_static/basic.css" rel="stylesheet" type="text/css"> |
| <link href="../../../../_static/pygments.css" rel="stylesheet" type="text/css"> |
| <link href="../../../../_static/mxnet.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript"> |
| var DOCUMENTATION_OPTIONS = { |
| URL_ROOT: '../../../../', |
| VERSION: '', |
| COLLAPSE_INDEX: false, |
| FILE_SUFFIX: '.html', |
| HAS_SOURCE: true, |
| SOURCELINK_SUFFIX: '.txt' |
| }; |
| </script> |
| <script src="https://code.jquery.com/jquery-1.11.1.min.js" type="text/javascript"></script> |
| <script src="../../../../_static/underscore.js" type="text/javascript"></script> |
| <script src="../../../../_static/searchtools_custom.js" type="text/javascript"></script> |
| <script src="../../../../_static/doctools.js" type="text/javascript"></script> |
| <script src="../../../../_static/selectlang.js" type="text/javascript"></script> |
| <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script> |
| <script type="text/javascript"> jQuery(function() { Search.loadIndex("/versions/1.2.1/searchindex.js"); Search.init();}); </script> |
| <script> |
| (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ |
| (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new |
| Date();a=s.createElement(o), |
| m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) |
| })(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); |
| |
| ga('create', 'UA-96378503-1', 'auto'); |
| ga('send', 'pageview'); |
| |
| </script> |
| <!-- --> |
| <!-- <script type="text/javascript" src="../../../../_static/jquery.js"></script> --> |
| <!-- --> |
| <!-- <script type="text/javascript" src="../../../../_static/underscore.js"></script> --> |
| <!-- --> |
| <!-- <script type="text/javascript" src="../../../../_static/doctools.js"></script> --> |
| <!-- --> |
| <!-- <script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script> --> |
| <!-- --> |
| <link href="../../../../genindex.html" rel="index" title="Index"> |
| <link href="../../../../search.html" rel="search" title="Search"/> |
| <link href="../../../index.html" rel="up" title="Module code"/> |
| <link href="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-icon.png" rel="icon" type="image/png"/> |
| </link></link></link></meta></meta></meta></head> |
| <body background="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-background-compressed.jpeg" role="document"> |
| <div class="content-block"><div class="navbar navbar-fixed-top"> |
| <div class="container" id="navContainer"> |
| <div class="innder" id="header-inner"> |
| <h1 id="logo-wrap"> |
| <a href="../../../../" id="logo"><img src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet_logo.png"/></a> |
| </h1> |
| <nav class="nav-bar" id="main-nav"> |
| <a class="main-nav-link" href="/versions/1.2.1/install/index.html">Install</a> |
| <span id="dropdown-menu-position-anchor"> |
| <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Gluon <span class="caret"></span></a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> |
| <li><a class="main-nav-link" href="/versions/1.2.1/tutorials/gluon/gluon.html">About</a></li> |
| <li><a class="main-nav-link" href="https://www.d2l.ai/">Dive into Deep Learning</a></li> |
| <li><a class="main-nav-link" href="https://gluon-cv.mxnet.io">GluonCV Toolkit</a></li> |
| <li><a class="main-nav-link" href="https://gluon-nlp.mxnet.io/">GluonNLP Toolkit</a></li> |
| </ul> |
| </span> |
| <span id="dropdown-menu-position-anchor"> |
| <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">API <span class="caret"></span></a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> |
| <li><a class="main-nav-link" href="/versions/1.2.1/api/python/index.html">Python</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/api/c++/index.html">C++</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/api/julia/index.html">Julia</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/api/perl/index.html">Perl</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/api/r/index.html">R</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/api/scala/index.html">Scala</a></li> |
| </ul> |
| </span> |
| <span id="dropdown-menu-position-anchor-docs"> |
| <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Docs <span class="caret"></span></a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-docs"> |
| <li><a class="main-nav-link" href="/versions/1.2.1/faq/index.html">FAQ</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/tutorials/index.html">Tutorials</a> |
| <li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/1.2.1/example">Examples</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/architecture/index.html">Architecture</a></li> |
| <li><a class="main-nav-link" href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home">Developer Wiki</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/model_zoo/index.html">Model Zoo</a></li> |
| <li><a class="main-nav-link" href="https://github.com/onnx/onnx-mxnet">ONNX</a></li> |
| </li></ul> |
| </span> |
| <span id="dropdown-menu-position-anchor-community"> |
| <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Community <span class="caret"></span></a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-community"> |
| <li><a class="main-nav-link" href="http://discuss.mxnet.io">Forum</a></li> |
| <li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/1.2.1">Github</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/community/contribute.html">Contribute</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/community/powered_by.html">Powered By</a></li> |
| </ul> |
| </span> |
| <span id="dropdown-menu-position-anchor-version" style="position: relative"><a href="#" class="main-nav-link dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">1.2.1<span class="caret"></span></a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a href="/">master</a></li><li><a href="/versions/1.7/">1.7</a></li><li><a href=/versions/1.6/>1.6</a></li><li><a href=/versions/1.5.0/>1.5.0</a></li><li><a href=/versions/1.4.1/>1.4.1</a></li><li><a href=/versions/1.3.1/>1.3.1</a></li><li><a href=/versions/1.2.1/>1.2.1</a></li><li><a href=/versions/1.1.0/>1.1.0</a></li><li><a href=/versions/1.0.0/>1.0.0</a></li><li><a href=/versions/0.12.1/>0.12.1</a></li><li><a href=/versions/0.11.0/>0.11.0</a></li></ul></span></nav> |
| <script> function getRootPath(){ return "../../../../" } </script> |
| <div class="burgerIcon dropdown"> |
| <a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button">☰</a> |
| <ul class="dropdown-menu" id="burgerMenu"> |
| <li><a href="/versions/1.2.1/install/index.html">Install</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/tutorials/index.html">Tutorials</a></li> |
| <li class="dropdown-submenu dropdown"> |
| <a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">Gluon</a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> |
| <li><a class="main-nav-link" href="/versions/1.2.1/tutorials/gluon/gluon.html">About</a></li> |
| <li><a class="main-nav-link" href="http://gluon.mxnet.io">The Straight Dope (Tutorials)</a></li> |
| <li><a class="main-nav-link" href="https://gluon-cv.mxnet.io">GluonCV Toolkit</a></li> |
| <li><a class="main-nav-link" href="https://gluon-nlp.mxnet.io/">GluonNLP Toolkit</a></li> |
| </ul> |
| </li> |
| <li class="dropdown-submenu"> |
| <a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">API</a> |
| <ul class="dropdown-menu"> |
| <li><a class="main-nav-link" href="/versions/1.2.1/api/python/index.html">Python</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/api/c++/index.html">C++</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/api/julia/index.html">Julia</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/api/perl/index.html">Perl</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/api/r/index.html">R</a></li> |
| <li><a class="main-nav-link" href="/versions/1.2.1/api/scala/index.html">Scala</a></li> |
| </ul> |
| </li> |
| <li class="dropdown-submenu"> |
| <a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">Docs</a> |
| <ul class="dropdown-menu"> |
| <li><a href="/versions/1.2.1/faq/index.html" tabindex="-1">FAQ</a></li> |
| <li><a href="/versions/1.2.1/tutorials/index.html" tabindex="-1">Tutorials</a></li> |
| <li><a href="https://github.com/apache/incubator-mxnet/tree/1.2.1/example" tabindex="-1">Examples</a></li> |
| <li><a href="/versions/1.2.1/architecture/index.html" tabindex="-1">Architecture</a></li> |
| <li><a href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home" tabindex="-1">Developer Wiki</a></li> |
| <li><a href="/versions/1.2.1/model_zoo/index.html" tabindex="-1">Gluon Model Zoo</a></li> |
| <li><a href="https://github.com/onnx/onnx-mxnet" tabindex="-1">ONNX</a></li> |
| </ul> |
| </li> |
| <li class="dropdown-submenu dropdown"> |
| <a aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" role="button" tabindex="-1">Community</a> |
| <ul class="dropdown-menu"> |
| <li><a href="http://discuss.mxnet.io" tabindex="-1">Forum</a></li> |
| <li><a href="https://github.com/apache/incubator-mxnet/tree/1.2.1" tabindex="-1">Github</a></li> |
| <li><a href="/versions/1.2.1/community/contribute.html" tabindex="-1">Contribute</a></li> |
| <li><a href="/versions/1.2.1/community/powered_by.html" tabindex="-1">Powered By</a></li> |
| </ul> |
| </li> |
| <li id="dropdown-menu-position-anchor-version-mobile" class="dropdown-submenu" style="position: relative"><a href="#" tabindex="-1">1.2.1</a><ul class="dropdown-menu"><li><a tabindex="-1" href=/>master</a></li><li><a tabindex="-1" href=/versions/1.6/>1.6</a></li><li><a tabindex="-1" href=/versions/1.5.0/>1.5.0</a></li><li><a tabindex="-1" href=/versions/1.4.1/>1.4.1</a></li><li><a tabindex="-1" href=/versions/1.3.1/>1.3.1</a></li><li><a tabindex="-1" href=/versions/1.2.1/>1.2.1</a></li><li><a tabindex="-1" href=/versions/1.1.0/>1.1.0</a></li><li><a tabindex="-1" href=/versions/1.0.0/>1.0.0</a></li><li><a tabindex="-1" href=/versions/0.12.1/>0.12.1</a></li><li><a tabindex="-1" href=/versions/0.11.0/>0.11.0</a></li></ul></li></ul> |
| </div> |
| <div class="plusIcon dropdown"> |
| <a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button"><span aria-hidden="true" class="glyphicon glyphicon-plus"></span></a> |
| <ul class="dropdown-menu dropdown-menu-right" id="plusMenu"></ul> |
| </div> |
| <div id="search-input-wrap"> |
| <form action="../../../../search.html" autocomplete="off" class="" method="get" role="search"> |
| <div class="form-group inner-addon left-addon"> |
| <i class="glyphicon glyphicon-search"></i> |
| <input class="form-control" name="q" placeholder="Search" type="text"/> |
| </div> |
| <input name="check_keywords" type="hidden" value="yes"> |
| <input name="area" type="hidden" value="default"/> |
| </input></form> |
| <div id="search-preview"></div> |
| </div> |
| <div id="searchIcon"> |
| <span aria-hidden="true" class="glyphicon glyphicon-search"></span> |
| </div> |
| <!-- <div id="lang-select-wrap"> --> |
| <!-- <label id="lang-select-label"> --> |
| <!-- <\!-- <i class="fa fa-globe"></i> -\-> --> |
| <!-- <span></span> --> |
| <!-- </label> --> |
| <!-- <select id="lang-select"> --> |
| <!-- <option value="en">Eng</option> --> |
| <!-- <option value="zh">中文</option> --> |
| <!-- </select> --> |
| <!-- </div> --> |
| <!-- <a id="mobile-nav-toggle"> |
| <span class="mobile-nav-toggle-bar"></span> |
| <span class="mobile-nav-toggle-bar"></span> |
| <span class="mobile-nav-toggle-bar"></span> |
| </a> --> |
| </div> |
| </div> |
| </div> |
| <script type="text/javascript"> |
| $('body').css('background', 'white'); |
| </script> |
| <div class="container"> |
| <div class="row"> |
| <div aria-label="main navigation" class="sphinxsidebar leftsidebar" role="navigation"> |
| <div class="sphinxsidebarwrapper"> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api/python/index.html">Python Documents</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api/r/index.html">R Documents</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api/julia/index.html">Julia Documents</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api/c++/index.html">C++ Documents</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api/scala/index.html">Scala Documents</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api/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> |
| <h1>Source code for mxnet.gluon.nn.conv_layers</h1><div class="highlight"><pre> |
| <span></span><span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span> |
| <span class="c1"># or more contributor license agreements. See the NOTICE file</span> |
| <span class="c1"># distributed with this work for additional information</span> |
| <span class="c1"># regarding copyright ownership. The ASF licenses this file</span> |
| <span class="c1"># to you under the Apache License, Version 2.0 (the</span> |
| <span class="c1"># "License"); you may not use this file except in compliance</span> |
| <span class="c1"># with the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing,</span> |
| <span class="c1"># software distributed under the License is distributed on an</span> |
| <span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span> |
| <span class="c1"># KIND, either express or implied. See the License for the</span> |
| <span class="c1"># specific language governing permissions and limitations</span> |
| <span class="c1"># under the License.</span> |
| |
| <span class="c1"># coding: utf-8</span> |
| <span class="c1"># pylint: disable= arguments-differ, too-many-lines</span> |
| <span class="sd">"""Convolutional neural network layers."""</span> |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'Conv1D'</span><span class="p">,</span> <span class="s1">'Conv2D'</span><span class="p">,</span> <span class="s1">'Conv3D'</span><span class="p">,</span> |
| <span class="s1">'Conv1DTranspose'</span><span class="p">,</span> <span class="s1">'Conv2DTranspose'</span><span class="p">,</span> <span class="s1">'Conv3DTranspose'</span><span class="p">,</span> |
| <span class="s1">'MaxPool1D'</span><span class="p">,</span> <span class="s1">'MaxPool2D'</span><span class="p">,</span> <span class="s1">'MaxPool3D'</span><span class="p">,</span> |
| <span class="s1">'AvgPool1D'</span><span class="p">,</span> <span class="s1">'AvgPool2D'</span><span class="p">,</span> <span class="s1">'AvgPool3D'</span><span class="p">,</span> |
| <span class="s1">'GlobalMaxPool1D'</span><span class="p">,</span> <span class="s1">'GlobalMaxPool2D'</span><span class="p">,</span> <span class="s1">'GlobalMaxPool3D'</span><span class="p">,</span> |
| <span class="s1">'GlobalAvgPool1D'</span><span class="p">,</span> <span class="s1">'GlobalAvgPool2D'</span><span class="p">,</span> <span class="s1">'GlobalAvgPool3D'</span><span class="p">,</span> |
| <span class="s1">'ReflectionPad2D'</span><span class="p">]</span> |
| |
| <span class="kn">from</span> <span class="nn">..block</span> <span class="k">import</span> <span class="n">HybridBlock</span> |
| <span class="kn">from</span> <span class="nn">...</span> <span class="k">import</span> <span class="n">symbol</span> |
| <span class="kn">from</span> <span class="nn">...base</span> <span class="k">import</span> <span class="n">numeric_types</span> |
| <span class="kn">from</span> <span class="nn">.activations</span> <span class="k">import</span> <span class="n">Activation</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_infer_weight_shape</span><span class="p">(</span><span class="n">op_name</span><span class="p">,</span> <span class="n">data_shape</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">):</span> |
| <span class="n">op</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">symbol</span><span class="p">,</span> <span class="n">op_name</span><span class="p">)</span> |
| <span class="n">sym</span> <span class="o">=</span> <span class="n">op</span><span class="p">(</span><span class="n">symbol</span><span class="o">.</span><span class="n">var</span><span class="p">(</span><span class="s1">'data'</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="n">data_shape</span><span class="p">),</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">sym</span><span class="o">.</span><span class="n">infer_shape_partial</span><span class="p">()[</span><span class="mi">0</span><span class="p">]</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_Conv</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span> |
| <span class="sd">"""Abstract nD convolution layer (private, used as implementation base).</span> |
| |
| <span class="sd"> This layer creates a convolution kernel that is convolved</span> |
| <span class="sd"> with the layer input to produce a tensor of outputs.</span> |
| <span class="sd"> If `use_bias` is `True`, a bias vector is created and added to the outputs.</span> |
| <span class="sd"> Finally, if `activation` is not `None`,</span> |
| <span class="sd"> it is applied to the outputs as well.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> channels : int</span> |
| <span class="sd"> The dimensionality of the output space</span> |
| <span class="sd"> i.e. the number of output channels in the convolution.</span> |
| <span class="sd"> kernel_size : int or tuple/list of n ints</span> |
| <span class="sd"> Specifies the dimensions of the convolution window.</span> |
| <span class="sd"> strides: int or tuple/list of n ints,</span> |
| <span class="sd"> Specifies the strides of the convolution.</span> |
| <span class="sd"> padding : int or tuple/list of n ints,</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly zero-padded</span> |
| <span class="sd"> on both sides for padding number of points</span> |
| <span class="sd"> dilation: int or tuple/list of n ints,</span> |
| <span class="sd"> Specifies the dilation rate to use for dilated convolution.</span> |
| <span class="sd"> groups : int</span> |
| <span class="sd"> Controls the connections between inputs and outputs.</span> |
| <span class="sd"> At groups=1, all inputs are convolved to all outputs.</span> |
| <span class="sd"> At groups=2, the operation becomes equivalent to having two convolution</span> |
| <span class="sd"> layers side by side, each seeing half the input channels, and producing</span> |
| <span class="sd"> half the output channels, and both subsequently concatenated.</span> |
| <span class="sd"> layout : str,</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCW', 'NWC', 'NCHW',</span> |
| <span class="sd"> 'NHWC', 'NCDHW', 'NDHWC', etc. 'N', 'C', 'H', 'W', 'D' stands for</span> |
| <span class="sd"> batch, channel, height, width and depth dimensions respectively.</span> |
| <span class="sd"> Convolution is performed over 'D', 'H', and 'W' dimensions.</span> |
| <span class="sd"> in_channels : int, default 0</span> |
| <span class="sd"> The number of input channels to this layer. If not specified,</span> |
| <span class="sd"> initialization will be deferred to the first time `forward` is called</span> |
| <span class="sd"> and `in_channels` will be inferred from the shape of input data.</span> |
| <span class="sd"> activation : str</span> |
| <span class="sd"> Activation function to use. See :func:`~mxnet.ndarray.Activation`.</span> |
| <span class="sd"> If you don't specify anything, no activation is applied</span> |
| <span class="sd"> (ie. "linear" activation: `a(x) = x`).</span> |
| <span class="sd"> use_bias: bool</span> |
| <span class="sd"> Whether the layer uses a bias vector.</span> |
| <span class="sd"> weight_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the `weight` weights matrix.</span> |
| <span class="sd"> bias_initializer: str or `Initializer`</span> |
| <span class="sd"> Initializer for the bias vector.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">dilation</span><span class="p">,</span> |
| <span class="n">groups</span><span class="p">,</span> <span class="n">layout</span><span class="p">,</span> <span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">activation</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">use_bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> |
| <span class="n">op_name</span><span class="o">=</span><span class="s1">'Convolution'</span><span class="p">,</span> <span class="n">adj</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">_Conv</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">name_scope</span><span class="p">():</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_channels</span> <span class="o">=</span> <span class="n">channels</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_in_channels</span> <span class="o">=</span> <span class="n">in_channels</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">strides</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">strides</span> <span class="o">=</span> <span class="p">(</span><span class="n">strides</span><span class="p">,)</span><span class="o">*</span><span class="nb">len</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">padding</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">padding</span> <span class="o">=</span> <span class="p">(</span><span class="n">padding</span><span class="p">,)</span><span class="o">*</span><span class="nb">len</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dilation</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">dilation</span> <span class="o">=</span> <span class="p">(</span><span class="n">dilation</span><span class="p">,)</span><span class="o">*</span><span class="nb">len</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_op_name</span> <span class="o">=</span> <span class="n">op_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'kernel'</span><span class="p">:</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="s1">'stride'</span><span class="p">:</span> <span class="n">strides</span><span class="p">,</span> <span class="s1">'dilate'</span><span class="p">:</span> <span class="n">dilation</span><span class="p">,</span> |
| <span class="s1">'pad'</span><span class="p">:</span> <span class="n">padding</span><span class="p">,</span> <span class="s1">'num_filter'</span><span class="p">:</span> <span class="n">channels</span><span class="p">,</span> <span class="s1">'num_group'</span><span class="p">:</span> <span class="n">groups</span><span class="p">,</span> |
| <span class="s1">'no_bias'</span><span class="p">:</span> <span class="ow">not</span> <span class="n">use_bias</span><span class="p">,</span> <span class="s1">'layout'</span><span class="p">:</span> <span class="n">layout</span><span class="p">}</span> |
| <span class="k">if</span> <span class="n">adj</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">[</span><span class="s1">'adj'</span><span class="p">]</span> <span class="o">=</span> <span class="n">adj</span> |
| |
| <span class="n">dshape</span> <span class="o">=</span> <span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">*</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">)</span> <span class="o">+</span> <span class="mi">2</span><span class="p">)</span> |
| <span class="n">dshape</span><span class="p">[</span><span class="n">layout</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">'N'</span><span class="p">)]</span> <span class="o">=</span> <span class="mi">1</span> |
| <span class="n">dshape</span><span class="p">[</span><span class="n">layout</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">'C'</span><span class="p">)]</span> <span class="o">=</span> <span class="n">in_channels</span> |
| <span class="n">wshapes</span> <span class="o">=</span> <span class="n">_infer_weight_shape</span><span class="p">(</span><span class="n">op_name</span><span class="p">,</span> <span class="n">dshape</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">weight</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'weight'</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="n">wshapes</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> |
| <span class="n">init</span><span class="o">=</span><span class="n">weight_initializer</span><span class="p">,</span> |
| <span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">use_bias</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'bias'</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="n">wshapes</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> |
| <span class="n">init</span><span class="o">=</span><span class="n">bias_initializer</span><span class="p">,</span> |
| <span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="k">if</span> <span class="n">activation</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="o">=</span> <span class="n">Activation</span><span class="p">(</span><span class="n">activation</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="n">activation</span><span class="o">+</span><span class="s1">'_'</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">weight</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">bias</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">act</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_op_name</span><span class="p">)(</span><span class="n">x</span><span class="p">,</span> <span class="n">weight</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">'fwd'</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">act</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_op_name</span><span class="p">)(</span><span class="n">x</span><span class="p">,</span> <span class="n">weight</span><span class="p">,</span> <span class="n">bias</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">'fwd'</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">act</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span><span class="p">(</span><span class="n">act</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">act</span> |
| |
| <span class="k">def</span> <span class="nf">_alias</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="s1">'conv'</span> |
| |
| <span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">s</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{mapping}</span><span class="s1">, kernel_size=</span><span class="si">{kernel}</span><span class="s1">, stride=</span><span class="si">{stride}</span><span class="s1">'</span> |
| <span class="n">len_kernel_size</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">[</span><span class="s1">'kernel'</span><span class="p">])</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">[</span><span class="s1">'pad'</span><span class="p">]</span> <span class="o">!=</span> <span class="p">(</span><span class="mi">0</span><span class="p">,)</span> <span class="o">*</span> <span class="n">len_kernel_size</span><span class="p">:</span> |
| <span class="n">s</span> <span class="o">+=</span> <span class="s1">', padding=</span><span class="si">{pad}</span><span class="s1">'</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">[</span><span class="s1">'dilate'</span><span class="p">]</span> <span class="o">!=</span> <span class="p">(</span><span class="mi">1</span><span class="p">,)</span> <span class="o">*</span> <span class="n">len_kernel_size</span><span class="p">:</span> |
| <span class="n">s</span> <span class="o">+=</span> <span class="s1">', dilation=</span><span class="si">{dilate}</span><span class="s1">'</span> |
| <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s1">'out_pad'</span><span class="p">)</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">out_pad</span> <span class="o">!=</span> <span class="p">(</span><span class="mi">0</span><span class="p">,)</span> <span class="o">*</span> <span class="n">len_kernel_size</span><span class="p">:</span> |
| <span class="n">s</span> <span class="o">+=</span> <span class="s1">', output_padding=</span><span class="si">{out_pad}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">out_pad</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">out_pad</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">[</span><span class="s1">'num_group'</span><span class="p">]</span> <span class="o">!=</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="n">s</span> <span class="o">+=</span> <span class="s1">', groups=</span><span class="si">{num_group}</span><span class="s1">'</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">bias</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">s</span> <span class="o">+=</span> <span class="s1">', bias=False'</span> |
| <span class="n">s</span> <span class="o">+=</span> <span class="s1">')'</span> |
| <span class="n">shape</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">shape</span> |
| <span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> |
| <span class="n">mapping</span><span class="o">=</span><span class="s1">'</span><span class="si">{0}</span><span class="s1"> -> </span><span class="si">{1}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">if</span> <span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">else</span> <span class="kc">None</span><span class="p">,</span> <span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]),</span> |
| <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="Conv1D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.Conv1D">[docs]</a><span class="k">class</span> <span class="nc">Conv1D</span><span class="p">(</span><span class="n">_Conv</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""1D convolution layer (e.g. temporal convolution).</span> |
| |
| <span class="sd"> This layer creates a convolution kernel that is convolved</span> |
| <span class="sd"> with the layer input over a single spatial (or temporal) dimension</span> |
| <span class="sd"> to produce a tensor of outputs.</span> |
| <span class="sd"> If `use_bias` is True, a bias vector is created and added to the outputs.</span> |
| <span class="sd"> Finally, if `activation` is not `None`,</span> |
| <span class="sd"> it is applied to the outputs as well.</span> |
| |
| <span class="sd"> If `in_channels` is not specified, `Parameter` initialization will be</span> |
| <span class="sd"> deferred to the first time `forward` is called and `in_channels` will be</span> |
| <span class="sd"> inferred from the shape of input data.</span> |
| |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> channels : int</span> |
| <span class="sd"> The dimensionality of the output space, i.e. the number of output</span> |
| <span class="sd"> channels (filters) in the convolution.</span> |
| <span class="sd"> kernel_size :int or tuple/list of 1 int</span> |
| <span class="sd"> Specifies the dimensions of the convolution window.</span> |
| <span class="sd"> strides : int or tuple/list of 1 int,</span> |
| <span class="sd"> Specify the strides of the convolution.</span> |
| <span class="sd"> padding : int or a tuple/list of 1 int,</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly zero-padded</span> |
| <span class="sd"> on both sides for padding number of points</span> |
| <span class="sd"> dilation : int or tuple/list of 1 int</span> |
| <span class="sd"> Specifies the dilation rate to use for dilated convolution.</span> |
| <span class="sd"> groups : int</span> |
| <span class="sd"> Controls the connections between inputs and outputs.</span> |
| <span class="sd"> At groups=1, all inputs are convolved to all outputs.</span> |
| <span class="sd"> At groups=2, the operation becomes equivalent to having two conv</span> |
| <span class="sd"> layers side by side, each seeing half the input channels, and producing</span> |
| <span class="sd"> half the output channels, and both subsequently concatenated.</span> |
| <span class="sd"> layout: str, default 'NCW'</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCW', 'NWC', etc.</span> |
| <span class="sd"> 'N', 'C', 'W' stands for batch, channel, and width (time) dimensions</span> |
| <span class="sd"> respectively. Convolution is applied on the 'W' dimension.</span> |
| <span class="sd"> in_channels : int, default 0</span> |
| <span class="sd"> The number of input channels to this layer. If not specified,</span> |
| <span class="sd"> initialization will be deferred to the first time `forward` is called</span> |
| <span class="sd"> and `in_channels` will be inferred from the shape of input data.</span> |
| <span class="sd"> activation : str</span> |
| <span class="sd"> Activation function to use. See :func:`~mxnet.ndarray.Activation`.</span> |
| <span class="sd"> If you don't specify anything, no activation is applied</span> |
| <span class="sd"> (ie. "linear" activation: `a(x) = x`).</span> |
| <span class="sd"> use_bias : bool</span> |
| <span class="sd"> Whether the layer uses a bias vector.</span> |
| <span class="sd"> weight_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the `weight` weights matrix.</span> |
| <span class="sd"> bias_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the bias vector.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: 3D input tensor with shape `(batch_size, in_channels, width)`</span> |
| <span class="sd"> when `layout` is `NCW`. For other layouts shape is permuted accordingly.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: 3D output tensor with shape `(batch_size, channels, out_width)`</span> |
| <span class="sd"> when `layout` is `NCW`. out_width is calculated as::</span> |
| |
| <span class="sd"> out_width = floor((width+2*padding-dilation*(kernel_size-1)-1)/stride)+1</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">dilation</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> |
| <span class="n">groups</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCW'</span><span class="p">,</span> <span class="n">activation</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">use_bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> |
| <span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">kernel_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">kernel_size</span><span class="p">,)</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">"kernel_size must be a number or a list of 1 ints"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">Conv1D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">dilation</span><span class="p">,</span> <span class="n">groups</span><span class="p">,</span> <span class="n">layout</span><span class="p">,</span> |
| <span class="n">in_channels</span><span class="p">,</span> <span class="n">activation</span><span class="p">,</span> <span class="n">use_bias</span><span class="p">,</span> <span class="n">weight_initializer</span><span class="p">,</span> <span class="n">bias_initializer</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="Conv2D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.Conv2D">[docs]</a><span class="k">class</span> <span class="nc">Conv2D</span><span class="p">(</span><span class="n">_Conv</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""2D convolution layer (e.g. spatial convolution over images).</span> |
| |
| <span class="sd"> This layer creates a convolution kernel that is convolved</span> |
| <span class="sd"> with the layer input to produce a tensor of</span> |
| <span class="sd"> outputs. If `use_bias` is True,</span> |
| <span class="sd"> a bias vector is created and added to the outputs. Finally, if</span> |
| <span class="sd"> `activation` is not `None`, it is applied to the outputs as well.</span> |
| |
| <span class="sd"> If `in_channels` is not specified, `Parameter` initialization will be</span> |
| <span class="sd"> deferred to the first time `forward` is called and `in_channels` will be</span> |
| <span class="sd"> inferred from the shape of input data.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> channels : int</span> |
| <span class="sd"> The dimensionality of the output space, i.e. the number of output</span> |
| <span class="sd"> channels (filters) in the convolution.</span> |
| <span class="sd"> kernel_size :int or tuple/list of 2 int</span> |
| <span class="sd"> Specifies the dimensions of the convolution window.</span> |
| <span class="sd"> strides : int or tuple/list of 2 int,</span> |
| <span class="sd"> Specify the strides of the convolution.</span> |
| <span class="sd"> padding : int or a tuple/list of 2 int,</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly zero-padded</span> |
| <span class="sd"> on both sides for padding number of points</span> |
| <span class="sd"> dilation : int or tuple/list of 2 int</span> |
| <span class="sd"> Specifies the dilation rate to use for dilated convolution.</span> |
| <span class="sd"> groups : int</span> |
| <span class="sd"> Controls the connections between inputs and outputs.</span> |
| <span class="sd"> At groups=1, all inputs are convolved to all outputs.</span> |
| <span class="sd"> At groups=2, the operation becomes equivalent to having two conv</span> |
| <span class="sd"> layers side by side, each seeing half the input channels, and producing</span> |
| <span class="sd"> half the output channels, and both subsequently concatenated.</span> |
| <span class="sd"> layout : str, default 'NCHW'</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCHW', 'NHWC', etc.</span> |
| <span class="sd"> 'N', 'C', 'H', 'W' stands for batch, channel, height, and width</span> |
| <span class="sd"> dimensions respectively. Convolution is applied on the 'H' and</span> |
| <span class="sd"> 'W' dimensions.</span> |
| <span class="sd"> in_channels : int, default 0</span> |
| <span class="sd"> The number of input channels to this layer. If not specified,</span> |
| <span class="sd"> initialization will be deferred to the first time `forward` is called</span> |
| <span class="sd"> and `in_channels` will be inferred from the shape of input data.</span> |
| <span class="sd"> activation : str</span> |
| <span class="sd"> Activation function to use. See :func:`~mxnet.ndarray.Activation`.</span> |
| <span class="sd"> If you don't specify anything, no activation is applied</span> |
| <span class="sd"> (ie. "linear" activation: `a(x) = x`).</span> |
| <span class="sd"> use_bias : bool</span> |
| <span class="sd"> Whether the layer uses a bias vector.</span> |
| <span class="sd"> weight_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the `weight` weights matrix.</span> |
| <span class="sd"> bias_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the bias vector.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: 4D input tensor with shape</span> |
| <span class="sd"> `(batch_size, in_channels, height, width)` when `layout` is `NCW`.</span> |
| <span class="sd"> For other layouts shape is permuted accordingly.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: 4D output tensor with shape</span> |
| <span class="sd"> `(batch_size, channels, out_height, out_width)` when `layout` is `NCW`.</span> |
| <span class="sd"> out_height and out_width are calculated as::</span> |
| |
| <span class="sd"> out_height = floor((height+2*padding[0]-dilation[0]*(kernel_size[0]-1)-1)/stride[0])+1</span> |
| <span class="sd"> out_width = floor((width+2*padding[1]-dilation[1]*(kernel_size[1]-1)-1)/stride[1])+1</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="o">=</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">padding</span><span class="o">=</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span> |
| <span class="n">dilation</span><span class="o">=</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">groups</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCHW'</span><span class="p">,</span> |
| <span class="n">activation</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">use_bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> <span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">kernel_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">kernel_size</span><span class="p">,)</span><span class="o">*</span><span class="mi">2</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">,</span> <span class="s2">"kernel_size must be a number or a list of 2 ints"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">Conv2D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">dilation</span><span class="p">,</span> <span class="n">groups</span><span class="p">,</span> <span class="n">layout</span><span class="p">,</span> |
| <span class="n">in_channels</span><span class="p">,</span> <span class="n">activation</span><span class="p">,</span> <span class="n">use_bias</span><span class="p">,</span> <span class="n">weight_initializer</span><span class="p">,</span> <span class="n">bias_initializer</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="Conv3D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.Conv3D">[docs]</a><span class="k">class</span> <span class="nc">Conv3D</span><span class="p">(</span><span class="n">_Conv</span><span class="p">):</span> |
| <span class="sd">"""3D convolution layer (e.g. spatial convolution over volumes).</span> |
| |
| <span class="sd"> This layer creates a convolution kernel that is convolved</span> |
| <span class="sd"> with the layer input to produce a tensor of</span> |
| <span class="sd"> outputs. If `use_bias` is `True`,</span> |
| <span class="sd"> a bias vector is created and added to the outputs. Finally, if</span> |
| <span class="sd"> `activation` is not `None`, it is applied to the outputs as well.</span> |
| |
| <span class="sd"> If `in_channels` is not specified, `Parameter` initialization will be</span> |
| <span class="sd"> deferred to the first time `forward` is called and `in_channels` will be</span> |
| <span class="sd"> inferred from the shape of input data.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> channels : int</span> |
| <span class="sd"> The dimensionality of the output space, i.e. the number of output</span> |
| <span class="sd"> channels (filters) in the convolution.</span> |
| <span class="sd"> kernel_size :int or tuple/list of 3 int</span> |
| <span class="sd"> Specifies the dimensions of the convolution window.</span> |
| <span class="sd"> strides : int or tuple/list of 3 int,</span> |
| <span class="sd"> Specify the strides of the convolution.</span> |
| <span class="sd"> padding : int or a tuple/list of 3 int,</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly zero-padded</span> |
| <span class="sd"> on both sides for padding number of points</span> |
| <span class="sd"> dilation : int or tuple/list of 3 int</span> |
| <span class="sd"> Specifies the dilation rate to use for dilated convolution.</span> |
| <span class="sd"> groups : int</span> |
| <span class="sd"> Controls the connections between inputs and outputs.</span> |
| <span class="sd"> At groups=1, all inputs are convolved to all outputs.</span> |
| <span class="sd"> At groups=2, the operation becomes equivalent to having two conv</span> |
| <span class="sd"> layers side by side, each seeing half the input channels, and producing</span> |
| <span class="sd"> half the output channels, and both subsequently concatenated.</span> |
| <span class="sd"> layout : str, default 'NCDHW'</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCDHW', 'NDHWC', etc.</span> |
| <span class="sd"> 'N', 'C', 'H', 'W', 'D' stands for batch, channel, height, width and</span> |
| <span class="sd"> depth dimensions respectively. Convolution is applied on the 'D',</span> |
| <span class="sd"> 'H' and 'W' dimensions.</span> |
| <span class="sd"> in_channels : int, default 0</span> |
| <span class="sd"> The number of input channels to this layer. If not specified,</span> |
| <span class="sd"> initialization will be deferred to the first time `forward` is called</span> |
| <span class="sd"> and `in_channels` will be inferred from the shape of input data.</span> |
| <span class="sd"> activation : str</span> |
| <span class="sd"> Activation function to use. See :func:`~mxnet.ndarray.Activation`.</span> |
| <span class="sd"> If you don't specify anything, no activation is applied</span> |
| <span class="sd"> (ie. "linear" activation: `a(x) = x`).</span> |
| <span class="sd"> use_bias : bool</span> |
| <span class="sd"> Whether the layer uses a bias vector.</span> |
| <span class="sd"> weight_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the `weight` weights matrix.</span> |
| <span class="sd"> bias_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the bias vector.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: 5D input tensor with shape</span> |
| <span class="sd"> `(batch_size, in_channels, depth, height, width)` when `layout` is `NCW`.</span> |
| <span class="sd"> For other layouts shape is permuted accordingly.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: 5D output tensor with shape</span> |
| <span class="sd"> `(batch_size, channels, out_depth, out_height, out_width)` when `layout` is `NCW`.</span> |
| <span class="sd"> out_depth, out_height and out_width are calculated as::</span> |
| |
| <span class="sd"> out_depth = floor((depth+2*padding[0]-dilation[0]*(kernel_size[0]-1)-1)/stride[0])+1</span> |
| <span class="sd"> out_height = floor((height+2*padding[1]-dilation[1]*(kernel_size[1]-1)-1)/stride[1])+1</span> |
| <span class="sd"> out_width = floor((width+2*padding[2]-dilation[2]*(kernel_size[2]-1)-1)/stride[2])+1</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="o">=</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">padding</span><span class="o">=</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span> |
| <span class="n">dilation</span><span class="o">=</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">groups</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCDHW'</span><span class="p">,</span> <span class="n">activation</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">use_bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> |
| <span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">kernel_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">kernel_size</span><span class="p">,)</span><span class="o">*</span><span class="mi">3</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">"kernel_size must be a number or a list of 3 ints"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">Conv3D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">dilation</span><span class="p">,</span> <span class="n">groups</span><span class="p">,</span> <span class="n">layout</span><span class="p">,</span> |
| <span class="n">in_channels</span><span class="p">,</span> <span class="n">activation</span><span class="p">,</span> <span class="n">use_bias</span><span class="p">,</span> <span class="n">weight_initializer</span><span class="p">,</span> <span class="n">bias_initializer</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="Conv1DTranspose"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.Conv1DTranspose">[docs]</a><span class="k">class</span> <span class="nc">Conv1DTranspose</span><span class="p">(</span><span class="n">_Conv</span><span class="p">):</span> |
| <span class="sd">"""Transposed 1D convolution layer (sometimes called Deconvolution).</span> |
| |
| <span class="sd"> The need for transposed convolutions generally arises</span> |
| <span class="sd"> from the desire to use a transformation going in the opposite direction</span> |
| <span class="sd"> of a normal convolution, i.e., from something that has the shape of the</span> |
| <span class="sd"> output of some convolution to something that has the shape of its input</span> |
| <span class="sd"> while maintaining a connectivity pattern that is compatible with</span> |
| <span class="sd"> said convolution.</span> |
| |
| <span class="sd"> If `in_channels` is not specified, `Parameter` initialization will be</span> |
| <span class="sd"> deferred to the first time `forward` is called and `in_channels` will be</span> |
| <span class="sd"> inferred from the shape of input data.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> channels : int</span> |
| <span class="sd"> The dimensionality of the output space, i.e. the number of output</span> |
| <span class="sd"> channels (filters) in the convolution.</span> |
| <span class="sd"> kernel_size :int or tuple/list of 3 int</span> |
| <span class="sd"> Specifies the dimensions of the convolution window.</span> |
| <span class="sd"> strides : int or tuple/list of 3 int,</span> |
| <span class="sd"> Specify the strides of the convolution.</span> |
| <span class="sd"> padding : int or a tuple/list of 3 int,</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly zero-padded</span> |
| <span class="sd"> on both sides for padding number of points</span> |
| <span class="sd"> dilation : int or tuple/list of 3 int</span> |
| <span class="sd"> Specifies the dilation rate to use for dilated convolution.</span> |
| <span class="sd"> groups : int</span> |
| <span class="sd"> Controls the connections between inputs and outputs.</span> |
| <span class="sd"> At groups=1, all inputs are convolved to all outputs.</span> |
| <span class="sd"> At groups=2, the operation becomes equivalent to having two conv</span> |
| <span class="sd"> layers side by side, each seeing half the input channels, and producing</span> |
| <span class="sd"> half the output channels, and both subsequently concatenated.</span> |
| <span class="sd"> layout : str, default 'NCW'</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCW', 'NWC', etc.</span> |
| <span class="sd"> 'N', 'C', 'W' stands for batch, channel, and width (time) dimensions</span> |
| <span class="sd"> respectively. Convolution is applied on the 'W' dimension.</span> |
| <span class="sd"> in_channels : int, default 0</span> |
| <span class="sd"> The number of input channels to this layer. If not specified,</span> |
| <span class="sd"> initialization will be deferred to the first time `forward` is called</span> |
| <span class="sd"> and `in_channels` will be inferred from the shape of input data.</span> |
| <span class="sd"> activation : str</span> |
| <span class="sd"> Activation function to use. See :func:`~mxnet.ndarray.Activation`.</span> |
| <span class="sd"> If you don't specify anything, no activation is applied</span> |
| <span class="sd"> (ie. "linear" activation: `a(x) = x`).</span> |
| <span class="sd"> use_bias : bool</span> |
| <span class="sd"> Whether the layer uses a bias vector.</span> |
| <span class="sd"> weight_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the `weight` weights matrix.</span> |
| <span class="sd"> bias_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the bias vector.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: 3D input tensor with shape `(batch_size, in_channels, width)`</span> |
| <span class="sd"> when `layout` is `NCW`. For other layouts shape is permuted accordingly.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: 3D output tensor with shape `(batch_size, channels, out_width)`</span> |
| <span class="sd"> when `layout` is `NCW`. out_width is calculated as::</span> |
| |
| <span class="sd"> out_width = (width-1)*strides-2*padding+kernel_size+output_padding</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">output_padding</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">dilation</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">groups</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCW'</span><span class="p">,</span> <span class="n">activation</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">use_bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> |
| <span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">kernel_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">kernel_size</span><span class="p">,)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">output_padding</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">output_padding</span> <span class="o">=</span> <span class="p">(</span><span class="n">output_padding</span><span class="p">,)</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">"kernel_size must be a number or a list of 1 ints"</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">output_padding</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">"output_padding must be a number or a list of 1 ints"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">Conv1DTranspose</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">dilation</span><span class="p">,</span> <span class="n">groups</span><span class="p">,</span> <span class="n">layout</span><span class="p">,</span> |
| <span class="n">in_channels</span><span class="p">,</span> <span class="n">activation</span><span class="p">,</span> <span class="n">use_bias</span><span class="p">,</span> <span class="n">weight_initializer</span><span class="p">,</span> |
| <span class="n">bias_initializer</span><span class="p">,</span> <span class="n">op_name</span><span class="o">=</span><span class="s1">'Deconvolution'</span><span class="p">,</span> <span class="n">adj</span><span class="o">=</span><span class="n">output_padding</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">outpad</span> <span class="o">=</span> <span class="n">output_padding</span></div> |
| |
| |
| <div class="viewcode-block" id="Conv2DTranspose"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.Conv2DTranspose">[docs]</a><span class="k">class</span> <span class="nc">Conv2DTranspose</span><span class="p">(</span><span class="n">_Conv</span><span class="p">):</span> |
| <span class="sd">"""Transposed 2D convolution layer (sometimes called Deconvolution).</span> |
| |
| <span class="sd"> The need for transposed convolutions generally arises</span> |
| <span class="sd"> from the desire to use a transformation going in the opposite direction</span> |
| <span class="sd"> of a normal convolution, i.e., from something that has the shape of the</span> |
| <span class="sd"> output of some convolution to something that has the shape of its input</span> |
| <span class="sd"> while maintaining a connectivity pattern that is compatible with</span> |
| <span class="sd"> said convolution.</span> |
| |
| <span class="sd"> If `in_channels` is not specified, `Parameter` initialization will be</span> |
| <span class="sd"> deferred to the first time `forward` is called and `in_channels` will be</span> |
| <span class="sd"> inferred from the shape of input data.</span> |
| |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> channels : int</span> |
| <span class="sd"> The dimensionality of the output space, i.e. the number of output</span> |
| <span class="sd"> channels (filters) in the convolution.</span> |
| <span class="sd"> kernel_size :int or tuple/list of 3 int</span> |
| <span class="sd"> Specifies the dimensions of the convolution window.</span> |
| <span class="sd"> strides : int or tuple/list of 3 int,</span> |
| <span class="sd"> Specify the strides of the convolution.</span> |
| <span class="sd"> padding : int or a tuple/list of 3 int,</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly zero-padded</span> |
| <span class="sd"> on both sides for padding number of points</span> |
| <span class="sd"> dilation : int or tuple/list of 3 int</span> |
| <span class="sd"> Specifies the dilation rate to use for dilated convolution.</span> |
| <span class="sd"> groups : int</span> |
| <span class="sd"> Controls the connections between inputs and outputs.</span> |
| <span class="sd"> At groups=1, all inputs are convolved to all outputs.</span> |
| <span class="sd"> At groups=2, the operation becomes equivalent to having two conv</span> |
| <span class="sd"> layers side by side, each seeing half the input channels, and producing</span> |
| <span class="sd"> half the output channels, and both subsequently concatenated.</span> |
| <span class="sd"> layout : str, default 'NCHW'</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCHW', 'NHWC', etc.</span> |
| <span class="sd"> 'N', 'C', 'H', 'W' stands for batch, channel, height, and width</span> |
| <span class="sd"> dimensions respectively. Convolution is applied on the 'H' and</span> |
| <span class="sd"> 'W' dimensions.</span> |
| <span class="sd"> in_channels : int, default 0</span> |
| <span class="sd"> The number of input channels to this layer. If not specified,</span> |
| <span class="sd"> initialization will be deferred to the first time `forward` is called</span> |
| <span class="sd"> and `in_channels` will be inferred from the shape of input data.</span> |
| <span class="sd"> activation : str</span> |
| <span class="sd"> Activation function to use. See :func:`~mxnet.ndarray.Activation`.</span> |
| <span class="sd"> If you don't specify anything, no activation is applied</span> |
| <span class="sd"> (ie. "linear" activation: `a(x) = x`).</span> |
| <span class="sd"> use_bias : bool</span> |
| <span class="sd"> Whether the layer uses a bias vector.</span> |
| <span class="sd"> weight_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the `weight` weights matrix.</span> |
| <span class="sd"> bias_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the bias vector.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: 4D input tensor with shape</span> |
| <span class="sd"> `(batch_size, in_channels, height, width)` when `layout` is `NCW`.</span> |
| <span class="sd"> For other layouts shape is permuted accordingly.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: 4D output tensor with shape</span> |
| <span class="sd"> `(batch_size, channels, out_height, out_width)` when `layout` is `NCW`.</span> |
| <span class="sd"> out_height and out_width are calculated as::</span> |
| |
| <span class="sd"> out_height = (height-1)*strides[0]-2*padding[0]+kernel_size[0]+output_padding[0]</span> |
| <span class="sd"> out_width = (width-1)*strides[1]-2*padding[1]+kernel_size[1]+output_padding[1]</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="o">=</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">padding</span><span class="o">=</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span> |
| <span class="n">output_padding</span><span class="o">=</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span> <span class="n">dilation</span><span class="o">=</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">groups</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCHW'</span><span class="p">,</span> |
| <span class="n">activation</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">use_bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> <span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">kernel_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">kernel_size</span><span class="p">,)</span><span class="o">*</span><span class="mi">2</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">output_padding</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">output_padding</span> <span class="o">=</span> <span class="p">(</span><span class="n">output_padding</span><span class="p">,)</span><span class="o">*</span><span class="mi">2</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">,</span> <span class="s2">"kernel_size must be a number or a list of 2 ints"</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">output_padding</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">,</span> <span class="s2">"output_padding must be a number or a list of 2 ints"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">Conv2DTranspose</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">dilation</span><span class="p">,</span> <span class="n">groups</span><span class="p">,</span> <span class="n">layout</span><span class="p">,</span> |
| <span class="n">in_channels</span><span class="p">,</span> <span class="n">activation</span><span class="p">,</span> <span class="n">use_bias</span><span class="p">,</span> <span class="n">weight_initializer</span><span class="p">,</span> |
| <span class="n">bias_initializer</span><span class="p">,</span> <span class="n">op_name</span><span class="o">=</span><span class="s1">'Deconvolution'</span><span class="p">,</span> <span class="n">adj</span><span class="o">=</span><span class="n">output_padding</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">outpad</span> <span class="o">=</span> <span class="n">output_padding</span></div> |
| |
| |
| <div class="viewcode-block" id="Conv3DTranspose"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.Conv3DTranspose">[docs]</a><span class="k">class</span> <span class="nc">Conv3DTranspose</span><span class="p">(</span><span class="n">_Conv</span><span class="p">):</span> |
| <span class="sd">"""Transposed 3D convolution layer (sometimes called Deconvolution).</span> |
| |
| <span class="sd"> The need for transposed convolutions generally arises</span> |
| <span class="sd"> from the desire to use a transformation going in the opposite direction</span> |
| <span class="sd"> of a normal convolution, i.e., from something that has the shape of the</span> |
| <span class="sd"> output of some convolution to something that has the shape of its input</span> |
| <span class="sd"> while maintaining a connectivity pattern that is compatible with</span> |
| <span class="sd"> said convolution.</span> |
| |
| <span class="sd"> If `in_channels` is not specified, `Parameter` initialization will be</span> |
| <span class="sd"> deferred to the first time `forward` is called and `in_channels` will be</span> |
| <span class="sd"> inferred from the shape of input data.</span> |
| |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> channels : int</span> |
| <span class="sd"> The dimensionality of the output space, i.e. the number of output</span> |
| <span class="sd"> channels (filters) in the convolution.</span> |
| <span class="sd"> kernel_size :int or tuple/list of 3 int</span> |
| <span class="sd"> Specifies the dimensions of the convolution window.</span> |
| <span class="sd"> strides : int or tuple/list of 3 int,</span> |
| <span class="sd"> Specify the strides of the convolution.</span> |
| <span class="sd"> padding : int or a tuple/list of 3 int,</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly zero-padded</span> |
| <span class="sd"> on both sides for padding number of points</span> |
| <span class="sd"> dilation : int or tuple/list of 3 int</span> |
| <span class="sd"> Specifies the dilation rate to use for dilated convolution.</span> |
| <span class="sd"> groups : int</span> |
| <span class="sd"> Controls the connections between inputs and outputs.</span> |
| <span class="sd"> At groups=1, all inputs are convolved to all outputs.</span> |
| <span class="sd"> At groups=2, the operation becomes equivalent to having two conv</span> |
| <span class="sd"> layers side by side, each seeing half the input channels, and producing</span> |
| <span class="sd"> half the output channels, and both subsequently concatenated.</span> |
| <span class="sd"> layout : str, default 'NCDHW'</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCDHW', 'NDHWC', etc.</span> |
| <span class="sd"> 'N', 'C', 'H', 'W', 'D' stands for batch, channel, height, width and</span> |
| <span class="sd"> depth dimensions respectively. Convolution is applied on the 'D',</span> |
| <span class="sd"> 'H', and 'W' dimensions.</span> |
| <span class="sd"> in_channels : int, default 0</span> |
| <span class="sd"> The number of input channels to this layer. If not specified,</span> |
| <span class="sd"> initialization will be deferred to the first time `forward` is called</span> |
| <span class="sd"> and `in_channels` will be inferred from the shape of input data.</span> |
| <span class="sd"> activation : str</span> |
| <span class="sd"> Activation function to use. See :func:`~mxnet.ndarray.Activation`.</span> |
| <span class="sd"> If you don't specify anything, no activation is applied</span> |
| <span class="sd"> (ie. "linear" activation: `a(x) = x`).</span> |
| <span class="sd"> use_bias : bool</span> |
| <span class="sd"> Whether the layer uses a bias vector.</span> |
| <span class="sd"> weight_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the `weight` weights matrix.</span> |
| <span class="sd"> bias_initializer : str or `Initializer`</span> |
| <span class="sd"> Initializer for the bias vector.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: 5D input tensor with shape</span> |
| <span class="sd"> `(batch_size, in_channels, depth, height, width)` when `layout` is `NCW`.</span> |
| <span class="sd"> For other layouts shape is permuted accordingly.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: 5D output tensor with shape</span> |
| <span class="sd"> `(batch_size, channels, out_depth, out_height, out_width)` when `layout` is `NCW`.</span> |
| <span class="sd"> out_depth, out_height and out_width are calculated as::</span> |
| |
| <span class="sd"> out_depth = (depth-1)*strides[0]-2*padding[0]+kernel_size[0]+output_padding[0]</span> |
| <span class="sd"> out_height = (height-1)*strides[1]-2*padding[1]+kernel_size[1]+output_padding[1]</span> |
| <span class="sd"> out_width = (width-1)*strides[2]-2*padding[2]+kernel_size[2]+output_padding[2]</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="o">=</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">padding</span><span class="o">=</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span> |
| <span class="n">output_padding</span><span class="o">=</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span> <span class="n">dilation</span><span class="o">=</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="n">groups</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCDHW'</span><span class="p">,</span> |
| <span class="n">activation</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">use_bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> <span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">kernel_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">kernel_size</span><span class="p">,)</span><span class="o">*</span><span class="mi">3</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">output_padding</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">output_padding</span> <span class="o">=</span> <span class="p">(</span><span class="n">output_padding</span><span class="p">,)</span><span class="o">*</span><span class="mi">3</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">"kernel_size must be a number or a list of 3 ints"</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">output_padding</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">"output_padding must be a number or a list of 3 ints"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">Conv3DTranspose</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">dilation</span><span class="p">,</span> <span class="n">groups</span><span class="p">,</span> <span class="n">layout</span><span class="p">,</span> |
| <span class="n">in_channels</span><span class="p">,</span> <span class="n">activation</span><span class="p">,</span> <span class="n">use_bias</span><span class="p">,</span> <span class="n">weight_initializer</span><span class="p">,</span> <span class="n">bias_initializer</span><span class="p">,</span> |
| <span class="n">op_name</span><span class="o">=</span><span class="s1">'Deconvolution'</span><span class="p">,</span> <span class="n">adj</span><span class="o">=</span><span class="n">output_padding</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">outpad</span> <span class="o">=</span> <span class="n">output_padding</span></div> |
| |
| |
| <span class="k">class</span> <span class="nc">_Pooling</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span> |
| <span class="sd">"""Abstract class for different pooling layers."""</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pool_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">ceil_mode</span><span class="p">,</span> <span class="n">global_pool</span><span class="p">,</span> |
| <span class="n">pool_type</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">strides</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">strides</span> <span class="o">=</span> <span class="n">pool_size</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">strides</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">strides</span> <span class="o">=</span> <span class="p">(</span><span class="n">strides</span><span class="p">,)</span><span class="o">*</span><span class="nb">len</span><span class="p">(</span><span class="n">pool_size</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">padding</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">padding</span> <span class="o">=</span> <span class="p">(</span><span class="n">padding</span><span class="p">,)</span><span class="o">*</span><span class="nb">len</span><span class="p">(</span><span class="n">pool_size</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'kernel'</span><span class="p">:</span> <span class="n">pool_size</span><span class="p">,</span> <span class="s1">'stride'</span><span class="p">:</span> <span class="n">strides</span><span class="p">,</span> <span class="s1">'pad'</span><span class="p">:</span> <span class="n">padding</span><span class="p">,</span> |
| <span class="s1">'global_pool'</span><span class="p">:</span> <span class="n">global_pool</span><span class="p">,</span> <span class="s1">'pool_type'</span><span class="p">:</span> <span class="n">pool_type</span><span class="p">,</span> |
| <span class="s1">'pooling_convention'</span><span class="p">:</span> <span class="s1">'full'</span> <span class="k">if</span> <span class="n">ceil_mode</span> <span class="k">else</span> <span class="s1">'valid'</span><span class="p">}</span> |
| |
| <span class="k">def</span> <span class="nf">_alias</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="s1">'pool'</span> |
| |
| <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">Pooling</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">'fwd'</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">s</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(size=</span><span class="si">{kernel}</span><span class="s1">, stride=</span><span class="si">{stride}</span><span class="s1">, padding=</span><span class="si">{pad}</span><span class="s1">, ceil_mode=</span><span class="si">{ceil_mode}</span><span class="s1">)'</span> |
| <span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> |
| <span class="n">ceil_mode</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">[</span><span class="s1">'pooling_convention'</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'full'</span><span class="p">,</span> |
| <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="MaxPool1D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.MaxPool1D">[docs]</a><span class="k">class</span> <span class="nc">MaxPool1D</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">):</span> |
| <span class="sd">"""Max pooling operation for one dimensional data.</span> |
| |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> pool_size: int</span> |
| <span class="sd"> Size of the max pooling windows.</span> |
| <span class="sd"> strides: int, or None</span> |
| <span class="sd"> Factor by which to downscale. E.g. 2 will halve the input size.</span> |
| <span class="sd"> If `None`, it will default to `pool_size`.</span> |
| <span class="sd"> padding: int</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly</span> |
| <span class="sd"> zero-padded on both sides for padding number of points.</span> |
| <span class="sd"> layout : str, default 'NCW'</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCW', 'NWC', etc.</span> |
| <span class="sd"> 'N', 'C', 'W' stands for batch, channel, and width (time) dimensions</span> |
| <span class="sd"> respectively. Pooling is applied on the W dimension.</span> |
| <span class="sd"> ceil_mode : bool, default False</span> |
| <span class="sd"> When `True`, will use ceil instead of floor to compute the output shape.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: 3D input tensor with shape `(batch_size, in_channels, width)`</span> |
| <span class="sd"> when `layout` is `NCW`. For other layouts shape is permuted accordingly.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: 3D output tensor with shape `(batch_size, channels, out_width)`</span> |
| <span class="sd"> when `layout` is `NCW`. out_width is calculated as::</span> |
| |
| <span class="sd"> out_width = floor((width+2*padding-pool_size)/strides)+1</span> |
| |
| <span class="sd"> When `ceil_mode` is `True`, ceil will be used instead of floor in this</span> |
| <span class="sd"> equation.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pool_size</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">strides</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCW'</span><span class="p">,</span> |
| <span class="n">ceil_mode</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NCW'</span><span class="p">,</span> <span class="s2">"Only supports NCW layout for now"</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pool_size</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">pool_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">pool_size</span><span class="p">,)</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">pool_size</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">"pool_size must be a number or a list of 1 ints"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">MaxPool1D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">pool_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">ceil_mode</span><span class="p">,</span> <span class="kc">False</span><span class="p">,</span> <span class="s1">'max'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="MaxPool2D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.MaxPool2D">[docs]</a><span class="k">class</span> <span class="nc">MaxPool2D</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">):</span> |
| <span class="sd">"""Max pooling operation for two dimensional (spatial) data.</span> |
| |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> pool_size: int or list/tuple of 2 ints,</span> |
| <span class="sd"> Size of the max pooling windows.</span> |
| <span class="sd"> strides: int, list/tuple of 2 ints, or None.</span> |
| <span class="sd"> Factor by which to downscale. E.g. 2 will halve the input size.</span> |
| <span class="sd"> If `None`, it will default to `pool_size`.</span> |
| <span class="sd"> padding: int or list/tuple of 2 ints,</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly</span> |
| <span class="sd"> zero-padded on both sides for padding number of points.</span> |
| <span class="sd"> layout : str, default 'NCHW'</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCHW', 'NHWC', etc.</span> |
| <span class="sd"> 'N', 'C', 'H', 'W' stands for batch, channel, height, and width</span> |
| <span class="sd"> dimensions respectively. padding is applied on 'H' and 'W' dimension.</span> |
| <span class="sd"> ceil_mode : bool, default False</span> |
| <span class="sd"> When `True`, will use ceil instead of floor to compute the output shape.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: 4D input tensor with shape</span> |
| <span class="sd"> `(batch_size, in_channels, height, width)` when `layout` is `NCW`.</span> |
| <span class="sd"> For other layouts shape is permuted accordingly.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: 4D output tensor with shape</span> |
| <span class="sd"> `(batch_size, channels, out_height, out_width)` when `layout` is `NCW`.</span> |
| <span class="sd"> out_height and out_width are calculated as::</span> |
| |
| <span class="sd"> out_height = floor((height+2*padding[0]-pool_size[0])/strides[0])+1</span> |
| <span class="sd"> out_width = floor((width+2*padding[1]-pool_size[1])/strides[1])+1</span> |
| |
| <span class="sd"> When `ceil_mode` is `True`, ceil will be used instead of floor in this</span> |
| <span class="sd"> equation.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pool_size</span><span class="o">=</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">),</span> <span class="n">strides</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCHW'</span><span class="p">,</span> |
| <span class="n">ceil_mode</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NCHW'</span><span class="p">,</span> <span class="s2">"Only supports NCHW layout for now"</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pool_size</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">pool_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">pool_size</span><span class="p">,)</span><span class="o">*</span><span class="mi">2</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">pool_size</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">,</span> <span class="s2">"pool_size must be a number or a list of 2 ints"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">MaxPool2D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">pool_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">ceil_mode</span><span class="p">,</span> <span class="kc">False</span><span class="p">,</span> <span class="s1">'max'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="MaxPool3D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.MaxPool3D">[docs]</a><span class="k">class</span> <span class="nc">MaxPool3D</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">):</span> |
| <span class="sd">"""Max pooling operation for 3D data (spatial or spatio-temporal).</span> |
| |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> pool_size: int or list/tuple of 3 ints,</span> |
| <span class="sd"> Size of the max pooling windows.</span> |
| <span class="sd"> strides: int, list/tuple of 3 ints, or None.</span> |
| <span class="sd"> Factor by which to downscale. E.g. 2 will halve the input size.</span> |
| <span class="sd"> If `None`, it will default to `pool_size`.</span> |
| <span class="sd"> padding: int or list/tuple of 3 ints,</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly</span> |
| <span class="sd"> zero-padded on both sides for padding number of points.</span> |
| <span class="sd"> layout : str, default 'NCDHW'</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCDHW', 'NDHWC', etc.</span> |
| <span class="sd"> 'N', 'C', 'H', 'W', 'D' stands for batch, channel, height, width and</span> |
| <span class="sd"> depth dimensions respectively. padding is applied on 'D', 'H' and 'W'</span> |
| <span class="sd"> dimension.</span> |
| <span class="sd"> ceil_mode : bool, default False</span> |
| <span class="sd"> When `True`, will use ceil instead of floor to compute the output shape.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: 5D input tensor with shape</span> |
| <span class="sd"> `(batch_size, in_channels, depth, height, width)` when `layout` is `NCW`.</span> |
| <span class="sd"> For other layouts shape is permuted accordingly.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: 5D output tensor with shape</span> |
| <span class="sd"> `(batch_size, channels, out_depth, out_height, out_width)` when `layout` is `NCW`.</span> |
| <span class="sd"> out_depth, out_height and out_width are calculated as::</span> |
| |
| <span class="sd"> out_depth = floor((depth+2*padding[0]-pool_size[0])/strides[0])+1</span> |
| <span class="sd"> out_height = floor((height+2*padding[1]-pool_size[1])/strides[1])+1</span> |
| <span class="sd"> out_width = floor((width+2*padding[2]-pool_size[2])/strides[2])+1</span> |
| |
| <span class="sd"> When `ceil_mode` is `True`, ceil will be used instead of floor in this</span> |
| <span class="sd"> equation.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pool_size</span><span class="o">=</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">),</span> <span class="n">strides</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">ceil_mode</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCDHW'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NCDHW'</span><span class="p">,</span> <span class="s2">"Only supports NCDHW layout for now"</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pool_size</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">pool_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">pool_size</span><span class="p">,)</span><span class="o">*</span><span class="mi">3</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">pool_size</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">"pool_size must be a number or a list of 3 ints"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">MaxPool3D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">pool_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">ceil_mode</span><span class="p">,</span> <span class="kc">False</span><span class="p">,</span> <span class="s1">'max'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="AvgPool1D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.AvgPool1D">[docs]</a><span class="k">class</span> <span class="nc">AvgPool1D</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">):</span> |
| <span class="sd">"""Average pooling operation for temporal data.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> pool_size: int</span> |
| <span class="sd"> Size of the max pooling windows.</span> |
| <span class="sd"> strides: int, or None</span> |
| <span class="sd"> Factor by which to downscale. E.g. 2 will halve the input size.</span> |
| <span class="sd"> If `None`, it will default to `pool_size`.</span> |
| <span class="sd"> padding: int</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly</span> |
| <span class="sd"> zero-padded on both sides for padding number of points.</span> |
| <span class="sd"> layout : str, default 'NCW'</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCW', 'NWC', etc.</span> |
| <span class="sd"> 'N', 'C', 'W' stands for batch, channel, and width (time) dimensions</span> |
| <span class="sd"> respectively. padding is applied on 'W' dimension.</span> |
| <span class="sd"> ceil_mode : bool, default False</span> |
| <span class="sd"> When `True`, will use ceil instead of floor to compute the output shape.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: 3D input tensor with shape `(batch_size, in_channels, width)`</span> |
| <span class="sd"> when `layout` is `NCW`. For other layouts shape is permuted accordingly.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: 3D output tensor with shape `(batch_size, channels, out_width)`</span> |
| <span class="sd"> when `layout` is `NCW`. out_width is calculated as::</span> |
| |
| <span class="sd"> out_width = floor((width+2*padding-pool_size)/strides)+1</span> |
| |
| <span class="sd"> When `ceil_mode` is `True`, ceil will be used instead of floor in this</span> |
| <span class="sd"> equation.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pool_size</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">strides</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCW'</span><span class="p">,</span> |
| <span class="n">ceil_mode</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NCW'</span><span class="p">,</span> <span class="s2">"Only supports NCW layout for now"</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pool_size</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">pool_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">pool_size</span><span class="p">,)</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">pool_size</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">"pool_size must be a number or a list of 1 ints"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">AvgPool1D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">pool_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">ceil_mode</span><span class="p">,</span> <span class="kc">False</span><span class="p">,</span> <span class="s1">'avg'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="AvgPool2D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.AvgPool2D">[docs]</a><span class="k">class</span> <span class="nc">AvgPool2D</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">):</span> |
| <span class="sd">"""Average pooling operation for spatial data.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> pool_size: int or list/tuple of 2 ints,</span> |
| <span class="sd"> Size of the max pooling windows.</span> |
| <span class="sd"> strides: int, list/tuple of 2 ints, or None.</span> |
| <span class="sd"> Factor by which to downscale. E.g. 2 will halve the input size.</span> |
| <span class="sd"> If `None`, it will default to `pool_size`.</span> |
| <span class="sd"> padding: int or list/tuple of 2 ints,</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly</span> |
| <span class="sd"> zero-padded on both sides for padding number of points.</span> |
| <span class="sd"> layout : str, default 'NCHW'</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCHW', 'NHWC', etc.</span> |
| <span class="sd"> 'N', 'C', 'H', 'W' stands for batch, channel, height, and width</span> |
| <span class="sd"> dimensions respectively. padding is applied on 'H' and 'W' dimension.</span> |
| <span class="sd"> ceil_mode : bool, default False</span> |
| <span class="sd"> When True, will use ceil instead of floor to compute the output shape.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: 4D input tensor with shape</span> |
| <span class="sd"> `(batch_size, in_channels, height, width)` when `layout` is `NCW`.</span> |
| <span class="sd"> For other layouts shape is permuted accordingly.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: 4D output tensor with shape</span> |
| <span class="sd"> `(batch_size, channels, out_height, out_width)` when `layout` is `NCW`.</span> |
| <span class="sd"> out_height and out_width are calculated as::</span> |
| |
| <span class="sd"> out_height = floor((height+2*padding[0]-pool_size[0])/strides[0])+1</span> |
| <span class="sd"> out_width = floor((width+2*padding[1]-pool_size[1])/strides[1])+1</span> |
| |
| <span class="sd"> When `ceil_mode` is `True`, ceil will be used instead of floor in this</span> |
| <span class="sd"> equation.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pool_size</span><span class="o">=</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">),</span> <span class="n">strides</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">ceil_mode</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCHW'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NCHW'</span><span class="p">,</span> <span class="s2">"Only supports NCHW layout for now"</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pool_size</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">pool_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">pool_size</span><span class="p">,)</span><span class="o">*</span><span class="mi">2</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">pool_size</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">,</span> <span class="s2">"pool_size must be a number or a list of 2 ints"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">AvgPool2D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">pool_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">ceil_mode</span><span class="p">,</span> <span class="kc">False</span><span class="p">,</span> <span class="s1">'avg'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="AvgPool3D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.AvgPool3D">[docs]</a><span class="k">class</span> <span class="nc">AvgPool3D</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">):</span> |
| <span class="sd">"""Average pooling operation for 3D data (spatial or spatio-temporal).</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> pool_size: int or list/tuple of 3 ints,</span> |
| <span class="sd"> Size of the max pooling windows.</span> |
| <span class="sd"> strides: int, list/tuple of 3 ints, or None.</span> |
| <span class="sd"> Factor by which to downscale. E.g. 2 will halve the input size.</span> |
| <span class="sd"> If `None`, it will default to `pool_size`.</span> |
| <span class="sd"> padding: int or list/tuple of 3 ints,</span> |
| <span class="sd"> If padding is non-zero, then the input is implicitly</span> |
| <span class="sd"> zero-padded on both sides for padding number of points.</span> |
| <span class="sd"> layout : str, default 'NCDHW'</span> |
| <span class="sd"> Dimension ordering of data and weight. Can be 'NCDHW', 'NDHWC', etc.</span> |
| <span class="sd"> 'N', 'C', 'H', 'W', 'D' stands for batch, channel, height, width and</span> |
| <span class="sd"> depth dimensions respectively. padding is applied on 'D', 'H' and 'W'</span> |
| <span class="sd"> dimension.</span> |
| <span class="sd"> ceil_mode : bool, default False</span> |
| <span class="sd"> When True, will use ceil instead of floor to compute the output shape.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: 5D input tensor with shape</span> |
| <span class="sd"> `(batch_size, in_channels, depth, height, width)` when `layout` is `NCW`.</span> |
| <span class="sd"> For other layouts shape is permuted accordingly.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: 5D output tensor with shape</span> |
| <span class="sd"> `(batch_size, channels, out_depth, out_height, out_width)` when `layout` is `NCW`.</span> |
| <span class="sd"> out_depth, out_height and out_width are calculated as::</span> |
| |
| <span class="sd"> out_depth = floor((depth+2*padding[0]-pool_size[0])/strides[0])+1</span> |
| <span class="sd"> out_height = floor((height+2*padding[1]-pool_size[1])/strides[1])+1</span> |
| <span class="sd"> out_width = floor((width+2*padding[2]-pool_size[2])/strides[2])+1</span> |
| |
| <span class="sd"> When `ceil_mode` is `True,` ceil will be used instead of floor in this</span> |
| <span class="sd"> equation.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pool_size</span><span class="o">=</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">),</span> <span class="n">strides</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">ceil_mode</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCDHW'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NCDHW'</span><span class="p">,</span> <span class="s2">"Only supports NCDHW layout for now"</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pool_size</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">pool_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">pool_size</span><span class="p">,)</span><span class="o">*</span><span class="mi">3</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">pool_size</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">"pool_size must be a number or a list of 3 ints"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">AvgPool3D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">pool_size</span><span class="p">,</span> <span class="n">strides</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">ceil_mode</span><span class="p">,</span> <span class="kc">False</span><span class="p">,</span> <span class="s1">'avg'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="GlobalMaxPool1D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.GlobalMaxPool1D">[docs]</a><span class="k">class</span> <span class="nc">GlobalMaxPool1D</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">):</span> |
| <span class="sd">"""Global max pooling operation for temporal data."""</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCW'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NCW'</span><span class="p">,</span> <span class="s2">"Only supports NCW layout for now"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">GlobalMaxPool1D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="p">(</span><span class="mi">1</span><span class="p">,),</span> <span class="kc">None</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="s1">'max'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="GlobalMaxPool2D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.GlobalMaxPool2D">[docs]</a><span class="k">class</span> <span class="nc">GlobalMaxPool2D</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">):</span> |
| <span class="sd">"""Global max pooling operation for spatial data."""</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCHW'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NCHW'</span><span class="p">,</span> <span class="s2">"Only supports NCHW layout for now"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">GlobalMaxPool2D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="kc">None</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="s1">'max'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="GlobalMaxPool3D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.GlobalMaxPool3D">[docs]</a><span class="k">class</span> <span class="nc">GlobalMaxPool3D</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">):</span> |
| <span class="sd">"""Global max pooling operation for 3D data."""</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCDHW'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NCDHW'</span><span class="p">,</span> <span class="s2">"Only supports NCDHW layout for now"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">GlobalMaxPool3D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="kc">None</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="s1">'max'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="GlobalAvgPool1D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.GlobalAvgPool1D">[docs]</a><span class="k">class</span> <span class="nc">GlobalAvgPool1D</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">):</span> |
| <span class="sd">"""Global average pooling operation for temporal data."""</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCW'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NCW'</span><span class="p">,</span> <span class="s2">"Only supports NCW layout for now"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">GlobalAvgPool1D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="p">(</span><span class="mi">1</span><span class="p">,),</span> <span class="kc">None</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="s1">'avg'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="GlobalAvgPool2D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.GlobalAvgPool2D">[docs]</a><span class="k">class</span> <span class="nc">GlobalAvgPool2D</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">):</span> |
| <span class="sd">"""Global average pooling operation for spatial data."""</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCHW'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NCHW'</span><span class="p">,</span> <span class="s2">"Only supports NCHW layout for now"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">GlobalAvgPool2D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="kc">None</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="s1">'avg'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="GlobalAvgPool3D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.GlobalAvgPool3D">[docs]</a><span class="k">class</span> <span class="nc">GlobalAvgPool3D</span><span class="p">(</span><span class="n">_Pooling</span><span class="p">):</span> |
| <span class="sd">"""Global max pooling operation for 3D data."""</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NCDHW'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NCDHW'</span><span class="p">,</span> <span class="s2">"Only supports NCDHW layout for now"</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">GlobalAvgPool3D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="kc">None</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="kc">True</span><span class="p">,</span> <span class="s1">'avg'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="ReflectionPad2D"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.ReflectionPad2D">[docs]</a><span class="k">class</span> <span class="nc">ReflectionPad2D</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""Pads the input tensor using the reflection of the input boundary.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> padding: int</span> |
| <span class="sd"> An integer padding size</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **data**: input tensor with the shape :math:`(N, C, H_{in}, W_{in})`.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **out**: output tensor with the shape :math:`(N, C, H_{out}, W_{out})`, where</span> |
| |
| <span class="sd"> .. math::</span> |
| |
| <span class="sd"> H_{out} = H_{in} + 2 \cdot padding</span> |
| |
| <span class="sd"> W_{out} = W_{in} + 2 \cdot padding</span> |
| |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> m = nn.ReflectionPad2D(3)</span> |
| <span class="sd"> >>> input = mx.nd.random.normal(shape=(16, 3, 224, 224))</span> |
| <span class="sd"> >>> output = m(input)</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">ReflectionPad2D</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">padding</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">):</span> |
| <span class="n">padding</span> <span class="o">=</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">padding</span><span class="p">)</span> |
| <span class="k">assert</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">padding</span><span class="p">)</span> <span class="o">==</span> <span class="mi">8</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_padding</span> <span class="o">=</span> <span class="n">padding</span> |
| |
| <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">pad</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="s1">'reflect'</span><span class="p">,</span> <span class="n">pad_width</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_padding</span><span class="p">)</span></div> |
| </pre></div> |
| </div> |
| </div> |
| <div aria-label="main navigation" class="sphinxsidebar rightsidebar" role="navigation"> |
| <div class="sphinxsidebarwrapper"> |
| </div> |
| </div> |
| </div><div class="footer"> |
| <div class="section-disclaimer"> |
| <div class="container"> |
| <div> |
| <img height="60" src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/apache_incubator_logo.png"/> |
| <p> |
| Apache MXNet is an effort undergoing incubation at The Apache Software Foundation (ASF), <strong>sponsored by the <i>Apache Incubator</i></strong>. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF. |
| </p> |
| <p> |
| "Copyright © 2017-2018, The Apache Software Foundation |
| Apache MXNet, MXNet, Apache, the Apache feather, and the Apache MXNet project logo are either registered trademarks or trademarks of the Apache Software Foundation." |
| </p> |
| </div> |
| </div> |
| </div> |
| </div> <!-- pagename != index --> |
| </div> |
| <script crossorigin="anonymous" integrity="sha384-0mSbJDEHialfmuBBQP6A4Qrprq5OVfW37PRR3j5ELqxss1yVqOtnepnHVP9aJ7xS" src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/js/bootstrap.min.js"></script> |
| <script src="../../../../_static/js/sidebar.js" type="text/javascript"></script> |
| <script src="../../../../_static/js/search.js" type="text/javascript"></script> |
| <script src="../../../../_static/js/navbar.js" type="text/javascript"></script> |
| <script src="../../../../_static/js/clipboard.min.js" type="text/javascript"></script> |
| <script src="../../../../_static/js/copycode.js" type="text/javascript"></script> |
| <script src="../../../../_static/js/page.js" type="text/javascript"></script> |
| <script src="../../../../_static/js/docversion.js" type="text/javascript"></script> |
| <script type="text/javascript"> |
| $('body').ready(function () { |
| $('body').css('visibility', 'visible'); |
| }); |
| </script> |
| </body> |
| </html> |
