| <!DOCTYPE html> |
| |
| <html lang="en"> |
| <head> |
| <meta charset="utf-8"/> |
| <meta content="IE=edge" http-equiv="X-UA-Compatible"/> |
| <meta content="width=device-width, initial-scale=1" name="viewport"/> |
| <title>mxnet.image.detection — mxnet documentation</title> |
| <link crossorigin="anonymous" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css" integrity="sha384-1q8mTJOASx8j1Au+a5WDVnPi2lkFfwwEAa8hDDdjZlpLegxhjVME1fgjWPGmkzs7" rel="stylesheet"/> |
| <link href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css" rel="stylesheet"/> |
| <link href="../../../_static/basic.css" rel="stylesheet" type="text/css"> |
| <link href="../../../_static/pygments.css" rel="stylesheet" type="text/css"> |
| <link href="../../../_static/mxnet.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript"> |
| var DOCUMENTATION_OPTIONS = { |
| URL_ROOT: '../../../', |
| VERSION: '', |
| COLLAPSE_INDEX: false, |
| FILE_SUFFIX: '.html', |
| HAS_SOURCE: true, |
| SOURCELINK_SUFFIX: '' |
| }; |
| </script> |
| <script src="https://code.jquery.com/jquery-1.11.1.min.js" type="text/javascript"></script> |
| <script src="../../../_static/underscore.js" type="text/javascript"></script> |
| <script src="../../../_static/searchtools_custom.js" type="text/javascript"></script> |
| <script src="../../../_static/doctools.js" type="text/javascript"></script> |
| <script src="../../../_static/selectlang.js" type="text/javascript"></script> |
| <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script> |
| <script type="text/javascript"> jQuery(function() { Search.loadIndex("/searchindex.js"); Search.init();}); </script> |
| <script> |
| (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ |
| (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new |
| Date();a=s.createElement(o), |
| m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) |
| })(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); |
| |
| ga('create', 'UA-96378503-1', 'auto'); |
| ga('send', 'pageview'); |
| |
| </script> |
| <!-- --> |
| <!-- <script type="text/javascript" src="../../../_static/jquery.js"></script> --> |
| <!-- --> |
| <!-- <script type="text/javascript" src="../../../_static/underscore.js"></script> --> |
| <!-- --> |
| <!-- <script type="text/javascript" src="../../../_static/doctools.js"></script> --> |
| <!-- --> |
| <!-- <script type="text/javascript" src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script> --> |
| <!-- --> |
| <link href="../../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></head> |
| <body background="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-background-compressed.jpeg" role="document"> |
| <div class="content-block"><div class="navbar navbar-fixed-top"> |
| <div class="container" id="navContainer"> |
| <div class="innder" id="header-inner"> |
| <h1 id="logo-wrap"> |
| <a href="../../../" id="logo"><img src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet_logo.png"/></a> |
| </h1> |
| <nav class="nav-bar" id="main-nav"> |
| <a class="main-nav-link" href="../../../install/index.html">Install</a> |
| <span id="dropdown-menu-position-anchor"> |
| <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Gluon <span class="caret"></span></a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> |
| <li><a class="main-nav-link" href="../../../gluon/index.html">About</a></li> |
| <li><a class="main-nav-link" href="http://gluon.mxnet.io">Tutorials</a></li> |
| </ul> |
| </span> |
| <span id="dropdown-menu-position-anchor"> |
| <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">API <span class="caret"></span></a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> |
| <li><a class="main-nav-link" href="../../../api/python/index.html">Python</a></li> |
| <li><a class="main-nav-link" href="../../../api/scala/index.html">Scala</a></li> |
| <li><a class="main-nav-link" href="../../../api/r/index.html">R</a></li> |
| <li><a class="main-nav-link" href="../../../api/julia/index.html">Julia</a></li> |
| <li><a class="main-nav-link" href="../../../api/c++/index.html">C++</a></li> |
| <li><a class="main-nav-link" href="../../../api/perl/index.html">Perl</a></li> |
| </ul> |
| </span> |
| <span id="dropdown-menu-position-anchor-docs"> |
| <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Docs <span class="caret"></span></a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-docs"> |
| <li><a class="main-nav-link" href="../../../tutorials/index.html">Tutorials</a> |
| <li><a class="main-nav-link" href="../../../faq/index.html">FAQ</a></li> |
| <li><a class="main-nav-link" href="../../../architecture/index.html">Architecture</a></li> |
| <li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/master/example">Examples</a></li> |
| <li><a class="main-nav-link" href="../../../api/python/gluon/model_zoo.html">Gluon Model Zoo</a></li> |
| </li></ul> |
| </span> |
| <a class="main-nav-link" href="https://github.com/dmlc/mxnet">Github</a> |
| <span id="dropdown-menu-position-anchor-community"> |
| <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Community <span class="caret"></span></a> |
| <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-community"> |
| <li><a class="main-nav-link" href="../../../community/index.html">Community</a></li> |
| <li><a class="main-nav-link" href="../../../community/contribute.html">Contribute</a></li> |
| <li><a class="main-nav-link" href="../../../community/powered_by.html">Powered By</a></li> |
| <li><a class="main-nav-link" href="http://discuss.mxnet.io">Discuss</a></li> |
| </ul> |
| </span> |
| <span id="dropdown-menu-position-anchor-version" style="position: relative"><a href="#" class="main-nav-link dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">Versions(master)<span class="caret"></span></a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/>1.0.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.12.1/index.html>0.12.1</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.12.0/index.html>0.12.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.11.0/index.html>0.11.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/master/index.html>master</a></li></ul></span></nav> |
| <script> function getRootPath(){ return "../../../" } </script> |
| <div class="burgerIcon dropdown"> |
| <a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button">☰</a> |
| <ul class="dropdown-menu" id="burgerMenu"> |
| <li><a href="../../../install/index.html">Install</a></li> |
| <li><a class="main-nav-link" href="../../../tutorials/index.html">Tutorials</a></li> |
| <li class="dropdown-submenu"> |
| <a href="#" tabindex="-1">Community</a> |
| <ul class="dropdown-menu"> |
| <li><a href="../../../community/index.html" tabindex="-1">Community</a></li> |
| <li><a href="../../../community/contribute.html" tabindex="-1">Contribute</a></li> |
| <li><a href="../../../community/powered_by.html" tabindex="-1">Powered By</a></li> |
| </ul> |
| </li> |
| <li class="dropdown-submenu"> |
| <a href="#" tabindex="-1">API</a> |
| <ul class="dropdown-menu"> |
| <li><a href="../../../api/python/index.html" tabindex="-1">Python</a> |
| </li> |
| <li><a href="../../../api/scala/index.html" tabindex="-1">Scala</a> |
| </li> |
| <li><a href="../../../api/r/index.html" tabindex="-1">R</a> |
| </li> |
| <li><a href="../../../api/julia/index.html" tabindex="-1">Julia</a> |
| </li> |
| <li><a href="../../../api/c++/index.html" tabindex="-1">C++</a> |
| </li> |
| <li><a href="../../../api/perl/index.html" tabindex="-1">Perl</a> |
| </li> |
| </ul> |
| </li> |
| <li class="dropdown-submenu"> |
| <a href="#" tabindex="-1">Docs</a> |
| <ul class="dropdown-menu"> |
| <li><a href="../../../tutorials/index.html" tabindex="-1">Tutorials</a></li> |
| <li><a href="../../../faq/index.html" tabindex="-1">FAQ</a></li> |
| <li><a href="../../../architecture/index.html" tabindex="-1">Architecture</a></li> |
| <li><a href="https://github.com/apache/incubator-mxnet/tree/master/example" tabindex="-1">Examples</a></li> |
| <li><a href="../../../api/python/gluon/model_zoo.html" tabindex="-1">Gluon Model Zoo</a></li> |
| </ul> |
| </li> |
| <li><a href="../../../architecture/index.html">Architecture</a></li> |
| <li><a class="main-nav-link" href="https://github.com/dmlc/mxnet">Github</a></li> |
| <li id="dropdown-menu-position-anchor-version-mobile" class="dropdown-submenu" style="position: relative"><a href="#" tabindex="-1">Versions(master)</a><ul class="dropdown-menu"><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/>1.0.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.12.1/index.html>0.12.1</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.12.0/index.html>0.12.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.11.0/index.html>0.11.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/master/index.html>master</a></li></ul></li></ul> |
| </div> |
| <div class="plusIcon dropdown"> |
| <a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button"><span aria-hidden="true" class="glyphicon glyphicon-plus"></span></a> |
| <ul class="dropdown-menu dropdown-menu-right" id="plusMenu"></ul> |
| </div> |
| <div id="search-input-wrap"> |
| <form action="../../../search.html" autocomplete="off" class="" method="get" role="search"> |
| <div class="form-group inner-addon left-addon"> |
| <i class="glyphicon glyphicon-search"></i> |
| <input class="form-control" name="q" placeholder="Search" type="text"/> |
| </div> |
| <input name="check_keywords" type="hidden" value="yes"> |
| <input name="area" type="hidden" value="default"/> |
| </input></form> |
| <div id="search-preview"></div> |
| </div> |
| <div id="searchIcon"> |
| <span aria-hidden="true" class="glyphicon glyphicon-search"></span> |
| </div> |
| <!-- <div id="lang-select-wrap"> --> |
| <!-- <label id="lang-select-label"> --> |
| <!-- <\!-- <i class="fa fa-globe"></i> -\-> --> |
| <!-- <span></span> --> |
| <!-- </label> --> |
| <!-- <select id="lang-select"> --> |
| <!-- <option value="en">Eng</option> --> |
| <!-- <option value="zh">中文</option> --> |
| <!-- </select> --> |
| <!-- </div> --> |
| <!-- <a id="mobile-nav-toggle"> |
| <span class="mobile-nav-toggle-bar"></span> |
| <span class="mobile-nav-toggle-bar"></span> |
| <span class="mobile-nav-toggle-bar"></span> |
| </a> --> |
| </div> |
| </div> |
| </div> |
| <script type="text/javascript"> |
| $('body').css('background', 'white'); |
| </script> |
| <div class="container"> |
| <div class="row"> |
| <div aria-label="main navigation" class="sphinxsidebar leftsidebar" role="navigation"> |
| <div class="sphinxsidebarwrapper"> |
| <ul> |
| <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.image.detection</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"># pylint: disable=unused-import</span> |
| <span class="sd">"""Read images and perform augmentations for object detection."""</span> |
| |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">absolute_import</span><span class="p">,</span> <span class="n">print_function</span> |
| |
| <span class="kn">import</span> <span class="nn">json</span> |
| <span class="kn">import</span> <span class="nn">logging</span> |
| <span class="kn">import</span> <span class="nn">random</span> |
| <span class="kn">import</span> <span class="nn">warnings</span> |
| |
| <span class="kn">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</span> |
| |
| <span class="kn">from</span> <span class="nn">..base</span> <span class="kn">import</span> <span class="n">numeric_types</span> |
| <span class="kn">from</span> <span class="nn">..</span> <span class="kn">import</span> <span class="n">ndarray</span> <span class="k">as</span> <span class="n">nd</span> |
| <span class="kn">from</span> <span class="nn">..ndarray._internal</span> <span class="kn">import</span> <span class="n">_cvcopyMakeBorder</span> <span class="k">as</span> <span class="n">copyMakeBorder</span> |
| <span class="kn">from</span> <span class="nn">..</span> <span class="kn">import</span> <span class="n">io</span> |
| <span class="kn">from</span> <span class="nn">.image</span> <span class="kn">import</span> <span class="n">RandomOrderAug</span><span class="p">,</span> <span class="n">ColorJitterAug</span><span class="p">,</span> <span class="n">LightingAug</span><span class="p">,</span> <span class="n">ColorNormalizeAug</span> |
| <span class="kn">from</span> <span class="nn">.image</span> <span class="kn">import</span> <span class="n">ResizeAug</span><span class="p">,</span> <span class="n">ForceResizeAug</span><span class="p">,</span> <span class="n">CastAug</span><span class="p">,</span> <span class="n">HueJitterAug</span><span class="p">,</span> <span class="n">RandomGrayAug</span> |
| <span class="kn">from</span> <span class="nn">.image</span> <span class="kn">import</span> <span class="n">fixed_crop</span><span class="p">,</span> <span class="n">ImageIter</span><span class="p">,</span> <span class="n">Augmenter</span> |
| |
| |
| <div class="viewcode-block" id="DetAugmenter"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.DetAugmenter">[docs]</a><span class="k">class</span> <span class="nc">DetAugmenter</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""Detection base augmenter"""</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</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">_kwargs</span> <span class="o">=</span> <span class="n">kwargs</span> |
| <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="n">nd</span><span class="o">.</span><span class="n">NDArray</span><span class="p">):</span> |
| <span class="n">v</span> <span class="o">=</span> <span class="n">v</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">()</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">):</span> |
| <span class="n">v</span> <span class="o">=</span> <span class="n">v</span><span class="o">.</span><span class="n">tolist</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="n">k</span><span class="p">]</span> <span class="o">=</span> <span class="n">v</span> |
| |
| <div class="viewcode-block" id="DetAugmenter.dumps"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.DetAugmenter.dumps">[docs]</a> <span class="k">def</span> <span class="nf">dumps</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Saves the Augmenter to string</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> str</span> |
| <span class="sd"> JSON formatted string that describes the Augmenter.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">([</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="o">.</span><span class="n">lower</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">])</span></div> |
| |
| <div class="viewcode-block" id="DetAugmenter.__call__"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.DetAugmenter.__call__">[docs]</a> <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span> |
| <span class="sd">"""Abstract implementation body"""</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s2">"Must override implementation."</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DetBorrowAug"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.DetBorrowAug">[docs]</a><span class="k">class</span> <span class="nc">DetBorrowAug</span><span class="p">(</span><span class="n">DetAugmenter</span><span class="p">):</span> |
| <span class="sd">"""Borrow standard augmenter from image classification.</span> |
| <span class="sd"> Which is good once you know label won't be affected after this augmenter.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> augmenter : mx.image.Augmenter</span> |
| <span class="sd"> The borrowed standard augmenter which has no effect on label</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">augmenter</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">augmenter</span><span class="p">,</span> <span class="n">Augmenter</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s1">'Borrowing from invalid Augmenter'</span><span class="p">)</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">DetBorrowAug</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">augmenter</span><span class="o">=</span><span class="n">augmenter</span><span class="o">.</span><span class="n">dumps</span><span class="p">())</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">augmenter</span> <span class="o">=</span> <span class="n">augmenter</span> |
| |
| <span class="k">def</span> <span class="nf">dumps</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Override the default one to avoid duplicate dump."""</span> |
| <span class="k">return</span> <span class="p">[</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="o">.</span><span class="n">lower</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">augmenter</span><span class="o">.</span><span class="n">dumps</span><span class="p">()]</span> |
| |
| <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span> |
| <span class="sd">"""Augmenter implementation body"""</span> |
| <span class="n">src</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">augmenter</span><span class="p">(</span><span class="n">src</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="DetRandomSelectAug"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.DetRandomSelectAug">[docs]</a><span class="k">class</span> <span class="nc">DetRandomSelectAug</span><span class="p">(</span><span class="n">DetAugmenter</span><span class="p">):</span> |
| <span class="sd">"""Randomly select one augmenter to apply, with chance to skip all.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> aug_list : list of DetAugmenter</span> |
| <span class="sd"> The random selection will be applied to one of the augmenters</span> |
| <span class="sd"> skip_prob : float</span> |
| <span class="sd"> The probability to skip all augmenters and return input directly</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">aug_list</span><span class="p">,</span> <span class="n">skip_prob</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">DetRandomSelectAug</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">skip_prob</span><span class="o">=</span><span class="n">skip_prob</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">aug_list</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span> |
| <span class="n">aug_list</span> <span class="o">=</span> <span class="p">[</span><span class="n">aug_list</span><span class="p">]</span> |
| <span class="k">for</span> <span class="n">aug</span> <span class="ow">in</span> <span class="n">aug_list</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">aug</span><span class="p">,</span> <span class="n">DetAugmenter</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Allow DetAugmenter in list only'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">aug_list</span><span class="p">:</span> |
| <span class="n">skip_prob</span> <span class="o">=</span> <span class="mi">1</span> <span class="c1"># disabled</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">aug_list</span> <span class="o">=</span> <span class="n">aug_list</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">skip_prob</span> <span class="o">=</span> <span class="n">skip_prob</span> |
| |
| <span class="k">def</span> <span class="nf">dumps</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Override default."""</span> |
| <span class="k">return</span> <span class="p">[</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="o">.</span><span class="n">lower</span><span class="p">(),</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">dumps</span><span class="p">()</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">aug_list</span><span class="p">]]</span> |
| |
| <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span> |
| <span class="sd">"""Augmenter implementation body"""</span> |
| <span class="k">if</span> <span class="n">random</span><span class="o">.</span><span class="n">random</span><span class="p">()</span> <span class="o"><</span> <span class="bp">self</span><span class="o">.</span><span class="n">skip_prob</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">random</span><span class="o">.</span><span class="n">shuffle</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">aug_list</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">aug_list</span><span class="p">[</span><span class="mi">0</span><span class="p">](</span><span class="n">src</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="DetHorizontalFlipAug"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.DetHorizontalFlipAug">[docs]</a><span class="k">class</span> <span class="nc">DetHorizontalFlipAug</span><span class="p">(</span><span class="n">DetAugmenter</span><span class="p">):</span> |
| <span class="sd">"""Random horizontal flipping.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> p : float</span> |
| <span class="sd"> chance [0, 1] to flip</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">p</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">DetHorizontalFlipAug</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">p</span><span class="o">=</span><span class="n">p</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">p</span> <span class="o">=</span> <span class="n">p</span> |
| |
| <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span> |
| <span class="sd">"""Augmenter implementation"""</span> |
| <span class="k">if</span> <span class="n">random</span><span class="o">.</span><span class="n">random</span><span class="p">()</span> <span class="o"><</span> <span class="bp">self</span><span class="o">.</span><span class="n">p</span><span class="p">:</span> |
| <span class="n">src</span> <span class="o">=</span> <span class="n">nd</span><span class="o">.</span><span class="n">flip</span><span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_flip_label</span><span class="p">(</span><span class="n">label</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_flip_label</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span> |
| <span class="sd">"""Helper function to flip label."""</span> |
| <span class="n">tmp</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">-</span> <span class="n">label</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">]</span> |
| <span class="n">label</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">]</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">-</span> <span class="n">label</span><span class="p">[:,</span> <span class="mi">3</span><span class="p">]</span> |
| <span class="n">label</span><span class="p">[:,</span> <span class="mi">3</span><span class="p">]</span> <span class="o">=</span> <span class="n">tmp</span></div> |
| |
| |
| <div class="viewcode-block" id="DetRandomCropAug"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.DetRandomCropAug">[docs]</a><span class="k">class</span> <span class="nc">DetRandomCropAug</span><span class="p">(</span><span class="n">DetAugmenter</span><span class="p">):</span> |
| <span class="sd">"""Random cropping with constraints</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> min_object_covered : float, default=0.1</span> |
| <span class="sd"> The cropped area of the image must contain at least this fraction of</span> |
| <span class="sd"> any bounding box supplied. The value of this parameter should be non-negative.</span> |
| <span class="sd"> In the case of 0, the cropped area does not need to overlap any of the</span> |
| <span class="sd"> bounding boxes supplied.</span> |
| <span class="sd"> min_eject_coverage : float, default=0.3</span> |
| <span class="sd"> The minimum coverage of cropped sample w.r.t its original size. With this</span> |
| <span class="sd"> constraint, objects that have marginal area after crop will be discarded.</span> |
| <span class="sd"> aspect_ratio_range : tuple of floats, default=(0.75, 1.33)</span> |
| <span class="sd"> The cropped area of the image must have an aspect ratio = width / height</span> |
| <span class="sd"> within this range.</span> |
| <span class="sd"> area_range : tuple of floats, default=(0.05, 1.0)</span> |
| <span class="sd"> The cropped area of the image must contain a fraction of the supplied</span> |
| <span class="sd"> image within in this range.</span> |
| <span class="sd"> max_attempts : int, default=50</span> |
| <span class="sd"> Number of attempts at generating a cropped/padded region of the image of the</span> |
| <span class="sd"> specified constraints. After max_attempts failures, return the original image.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">min_object_covered</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">aspect_ratio_range</span><span class="o">=</span><span class="p">(</span><span class="mf">0.75</span><span class="p">,</span> <span class="mf">1.33</span><span class="p">),</span> |
| <span class="n">area_range</span><span class="o">=</span><span class="p">(</span><span class="mf">0.05</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span> <span class="n">min_eject_coverage</span><span class="o">=</span><span class="mf">0.3</span><span class="p">,</span> <span class="n">max_attempts</span><span class="o">=</span><span class="mi">50</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">aspect_ratio_range</span><span class="p">,</span> <span class="p">(</span><span class="nb">tuple</span><span class="p">,</span> <span class="nb">list</span><span class="p">)):</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">aspect_ratio_range</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">)</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Using fixed aspect ratio: </span><span class="si">%s</span><span class="s1"> in DetRandomCropAug'</span><span class="p">,</span> |
| <span class="nb">str</span><span class="p">(</span><span class="n">aspect_ratio_range</span><span class="p">))</span> |
| <span class="n">aspect_ratio_range</span> <span class="o">=</span> <span class="p">(</span><span class="n">aspect_ratio_range</span><span class="p">,</span> <span class="n">aspect_ratio_range</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">area_range</span><span class="p">,</span> <span class="p">(</span><span class="nb">tuple</span><span class="p">,</span> <span class="nb">list</span><span class="p">)):</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">area_range</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">)</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Using fixed area range: </span><span class="si">%s</span><span class="s1"> in DetRandomCropAug'</span><span class="p">,</span> <span class="n">area_range</span><span class="p">)</span> |
| <span class="n">area_range</span> <span class="o">=</span> <span class="p">(</span><span class="n">area_range</span><span class="p">,</span> <span class="n">area_range</span><span class="p">)</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">DetRandomCropAug</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">min_object_covered</span><span class="o">=</span><span class="n">min_object_covered</span><span class="p">,</span> |
| <span class="n">aspect_ratio_range</span><span class="o">=</span><span class="n">aspect_ratio_range</span><span class="p">,</span> |
| <span class="n">area_range</span><span class="o">=</span><span class="n">area_range</span><span class="p">,</span> |
| <span class="n">min_eject_coverage</span><span class="o">=</span><span class="n">min_eject_coverage</span><span class="p">,</span> |
| <span class="n">max_attempts</span><span class="o">=</span><span class="n">max_attempts</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">min_object_covered</span> <span class="o">=</span> <span class="n">min_object_covered</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">min_eject_coverage</span> <span class="o">=</span> <span class="n">min_eject_coverage</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">max_attempts</span> <span class="o">=</span> <span class="n">max_attempts</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">aspect_ratio_range</span> <span class="o">=</span> <span class="n">aspect_ratio_range</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">area_range</span> <span class="o">=</span> <span class="n">area_range</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">enabled</span> <span class="o">=</span> <span class="bp">False</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">area_range</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o"><=</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">area_range</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">></span> <span class="n">area_range</span><span class="p">[</span><span class="mi">1</span><span class="p">]):</span> |
| <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s1">'Skip DetRandomCropAug due to invalid area_range: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">area_range</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="p">(</span><span class="n">aspect_ratio_range</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">></span> <span class="n">aspect_ratio_range</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="ow">or</span> <span class="n">aspect_ratio_range</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o"><=</span> <span class="mi">0</span><span class="p">):</span> |
| <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s1">'Skip DetRandomCropAug due to invalid aspect_ratio_range: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> |
| <span class="n">aspect_ratio_range</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">enabled</span> <span class="o">=</span> <span class="bp">True</span> |
| |
| <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span> |
| <span class="sd">"""Augmenter implementation body"""</span> |
| <span class="n">crop</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_random_crop_proposal</span><span class="p">(</span><span class="n">label</span><span class="p">,</span> <span class="n">src</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">src</span><span class="o">.</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">crop</span><span class="p">:</span> |
| <span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">label</span> <span class="o">=</span> <span class="n">crop</span> |
| <span class="n">src</span> <span class="o">=</span> <span class="n">fixed_crop</span><span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="bp">None</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_calculate_areas</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span> |
| <span class="sd">"""Calculate areas for multiple labels"""</span> |
| <span class="n">heights</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">maximum</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">label</span><span class="p">[:,</span> <span class="mi">3</span><span class="p">]</span> <span class="o">-</span> <span class="n">label</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">])</span> |
| <span class="n">widths</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">maximum</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">label</span><span class="p">[:,</span> <span class="mi">2</span><span class="p">]</span> <span class="o">-</span> <span class="n">label</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">])</span> |
| <span class="k">return</span> <span class="n">heights</span> <span class="o">*</span> <span class="n">widths</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_intersect</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">xmin</span><span class="p">,</span> <span class="n">ymin</span><span class="p">,</span> <span class="n">xmax</span><span class="p">,</span> <span class="n">ymax</span><span class="p">):</span> |
| <span class="sd">"""Calculate intersect areas, normalized."""</span> |
| <span class="n">left</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">maximum</span><span class="p">(</span><span class="n">label</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">],</span> <span class="n">xmin</span><span class="p">)</span> |
| <span class="n">right</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">minimum</span><span class="p">(</span><span class="n">label</span><span class="p">[:,</span> <span class="mi">2</span><span class="p">],</span> <span class="n">xmax</span><span class="p">)</span> |
| <span class="n">top</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">maximum</span><span class="p">(</span><span class="n">label</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">],</span> <span class="n">ymin</span><span class="p">)</span> |
| <span class="n">bot</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">minimum</span><span class="p">(</span><span class="n">label</span><span class="p">[:,</span> <span class="mi">3</span><span class="p">],</span> <span class="n">ymax</span><span class="p">)</span> |
| <span class="n">invalid</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">logical_or</span><span class="p">(</span><span class="n">left</span> <span class="o">>=</span> <span class="n">right</span><span class="p">,</span> <span class="n">top</span> <span class="o">>=</span> <span class="n">bot</span><span class="p">))[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="n">out</span> <span class="o">=</span> <span class="n">label</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span> |
| <span class="n">out</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">]</span> <span class="o">=</span> <span class="n">left</span> |
| <span class="n">out</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">]</span> <span class="o">=</span> <span class="n">top</span> |
| <span class="n">out</span><span class="p">[:,</span> <span class="mi">2</span><span class="p">]</span> <span class="o">=</span> <span class="n">right</span> |
| <span class="n">out</span><span class="p">[:,</span> <span class="mi">3</span><span class="p">]</span> <span class="o">=</span> <span class="n">bot</span> |
| <span class="n">out</span><span class="p">[</span><span class="n">invalid</span><span class="p">,</span> <span class="p">:]</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">return</span> <span class="n">out</span> |
| |
| <span class="k">def</span> <span class="nf">_check_satisfy_constraints</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">xmin</span><span class="p">,</span> <span class="n">ymin</span><span class="p">,</span> <span class="n">xmax</span><span class="p">,</span> <span class="n">ymax</span><span class="p">,</span> <span class="n">width</span><span class="p">,</span> <span class="n">height</span><span class="p">):</span> |
| <span class="sd">"""Check if constrains are satisfied"""</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">xmax</span> <span class="o">-</span> <span class="n">xmin</span><span class="p">)</span> <span class="o">*</span> <span class="p">(</span><span class="n">ymax</span> <span class="o">-</span> <span class="n">ymin</span><span class="p">)</span> <span class="o"><</span> <span class="mi">2</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">False</span> <span class="c1"># only 1 pixel</span> |
| <span class="n">x1</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">xmin</span><span class="p">)</span> <span class="o">/</span> <span class="n">width</span> |
| <span class="n">y1</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">ymin</span><span class="p">)</span> <span class="o">/</span> <span class="n">height</span> |
| <span class="n">x2</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">xmax</span><span class="p">)</span> <span class="o">/</span> <span class="n">width</span> |
| <span class="n">y2</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">ymax</span><span class="p">)</span> <span class="o">/</span> <span class="n">height</span> |
| <span class="n">object_areas</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_calculate_areas</span><span class="p">(</span><span class="n">label</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">:])</span> |
| <span class="n">valid_objects</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="n">object_areas</span> <span class="o">*</span> <span class="n">width</span> <span class="o">*</span> <span class="n">height</span> <span class="o">></span> <span class="mi">2</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">valid_objects</span><span class="o">.</span><span class="n">size</span> <span class="o"><</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">False</span> |
| <span class="n">intersects</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_intersect</span><span class="p">(</span><span class="n">label</span><span class="p">[</span><span class="n">valid_objects</span><span class="p">,</span> <span class="mi">1</span><span class="p">:],</span> <span class="n">x1</span><span class="p">,</span> <span class="n">y1</span><span class="p">,</span> <span class="n">x2</span><span class="p">,</span> <span class="n">y2</span><span class="p">)</span> |
| <span class="n">coverages</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_calculate_areas</span><span class="p">(</span><span class="n">intersects</span><span class="p">)</span> <span class="o">/</span> <span class="n">object_areas</span><span class="p">[</span><span class="n">valid_objects</span><span class="p">]</span> |
| <span class="n">coverages</span> <span class="o">=</span> <span class="n">coverages</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="n">coverages</span> <span class="o">></span> <span class="mi">0</span><span class="p">)[</span><span class="mi">0</span><span class="p">]]</span> |
| <span class="k">return</span> <span class="n">coverages</span><span class="o">.</span><span class="n">size</span> <span class="o">></span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">np</span><span class="o">.</span><span class="n">amin</span><span class="p">(</span><span class="n">coverages</span><span class="p">)</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">min_object_covered</span> |
| |
| <span class="k">def</span> <span class="nf">_update_labels</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">crop_box</span><span class="p">,</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">):</span> |
| <span class="sd">"""Convert labels according to crop box"""</span> |
| <span class="n">xmin</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">crop_box</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="o">/</span> <span class="n">width</span> |
| <span class="n">ymin</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">crop_box</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> <span class="o">/</span> <span class="n">height</span> |
| <span class="n">w</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">crop_box</span><span class="p">[</span><span class="mi">2</span><span class="p">])</span> <span class="o">/</span> <span class="n">width</span> |
| <span class="n">h</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">crop_box</span><span class="p">[</span><span class="mi">3</span><span class="p">])</span> <span class="o">/</span> <span class="n">height</span> |
| <span class="n">out</span> <span class="o">=</span> <span class="n">label</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span> |
| <span class="n">out</span><span class="p">[:,</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">)]</span> <span class="o">-=</span> <span class="n">xmin</span> |
| <span class="n">out</span><span class="p">[:,</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">4</span><span class="p">)]</span> <span class="o">-=</span> <span class="n">ymin</span> |
| <span class="n">out</span><span class="p">[:,</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">)]</span> <span class="o">/=</span> <span class="n">w</span> |
| <span class="n">out</span><span class="p">[:,</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">4</span><span class="p">)]</span> <span class="o">/=</span> <span class="n">h</span> |
| <span class="n">out</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">:</span><span class="mi">5</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">maximum</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">out</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">:</span><span class="mi">5</span><span class="p">])</span> |
| <span class="n">out</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">:</span><span class="mi">5</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">minimum</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">out</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">:</span><span class="mi">5</span><span class="p">])</span> |
| <span class="n">coverage</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_calculate_areas</span><span class="p">(</span><span class="n">out</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">:])</span> <span class="o">*</span> <span class="n">w</span> <span class="o">*</span> <span class="n">h</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">_calculate_areas</span><span class="p">(</span><span class="n">label</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">:])</span> |
| <span class="n">valid</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">logical_and</span><span class="p">(</span><span class="n">out</span><span class="p">[:,</span> <span class="mi">3</span><span class="p">]</span> <span class="o">></span> <span class="n">out</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">],</span> <span class="n">out</span><span class="p">[:,</span> <span class="mi">4</span><span class="p">]</span> <span class="o">></span> <span class="n">out</span><span class="p">[:,</span> <span class="mi">2</span><span class="p">])</span> |
| <span class="n">valid</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">logical_and</span><span class="p">(</span><span class="n">valid</span><span class="p">,</span> <span class="n">coverage</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">min_eject_coverage</span><span class="p">)</span> |
| <span class="n">valid</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="n">valid</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">valid</span><span class="o">.</span><span class="n">size</span> <span class="o"><</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">None</span> |
| <span class="n">out</span> <span class="o">=</span> <span class="n">out</span><span class="p">[</span><span class="n">valid</span><span class="p">,</span> <span class="p">:]</span> |
| <span class="k">return</span> <span class="n">out</span> |
| |
| <span class="k">def</span> <span class="nf">_random_crop_proposal</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">):</span> |
| <span class="sd">"""Propose cropping areas"""</span> |
| <span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">sqrt</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">enabled</span> <span class="ow">or</span> <span class="n">height</span> <span class="o"><=</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">width</span> <span class="o"><=</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">()</span> |
| <span class="n">min_area</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">area_range</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="n">height</span> <span class="o">*</span> <span class="n">width</span> |
| <span class="n">max_area</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">area_range</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">*</span> <span class="n">height</span> <span class="o">*</span> <span class="n">width</span> |
| <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">max_attempts</span><span class="p">):</span> |
| <span class="n">ratio</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">aspect_ratio_range</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">ratio</span> <span class="o"><=</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">continue</span> |
| <span class="n">h</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">sqrt</span><span class="p">(</span><span class="n">min_area</span> <span class="o">/</span> <span class="n">ratio</span><span class="p">)))</span> |
| <span class="n">max_h</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">sqrt</span><span class="p">(</span><span class="n">max_area</span> <span class="o">/</span> <span class="n">ratio</span><span class="p">)))</span> |
| <span class="k">if</span> <span class="nb">round</span><span class="p">(</span><span class="n">max_h</span> <span class="o">*</span> <span class="n">ratio</span><span class="p">)</span> <span class="o">></span> <span class="n">width</span><span class="p">:</span> |
| <span class="c1"># find smallest max_h satifying round(max_h * ratio) <= width</span> |
| <span class="n">max_h</span> <span class="o">=</span> <span class="nb">int</span><span class="p">((</span><span class="n">width</span> <span class="o">+</span> <span class="mf">0.4999999</span><span class="p">)</span> <span class="o">/</span> <span class="n">ratio</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">max_h</span> <span class="o">></span> <span class="n">height</span><span class="p">:</span> |
| <span class="n">max_h</span> <span class="o">=</span> <span class="n">height</span> |
| <span class="k">if</span> <span class="n">h</span> <span class="o">></span> <span class="n">max_h</span><span class="p">:</span> |
| <span class="n">h</span> <span class="o">=</span> <span class="n">max_h</span> |
| <span class="k">if</span> <span class="n">h</span> <span class="o"><</span> <span class="n">max_h</span><span class="p">:</span> |
| <span class="c1"># generate random h in range [h, max_h]</span> |
| <span class="n">h</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="n">h</span><span class="p">,</span> <span class="n">max_h</span><span class="p">)</span> |
| <span class="n">w</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">h</span> <span class="o">*</span> <span class="n">ratio</span><span class="p">))</span> |
| <span class="k">assert</span> <span class="n">w</span> <span class="o"><=</span> <span class="n">width</span> |
| |
| <span class="c1"># trying to fix rounding problems</span> |
| <span class="n">area</span> <span class="o">=</span> <span class="n">w</span> <span class="o">*</span> <span class="n">h</span> |
| <span class="k">if</span> <span class="n">area</span> <span class="o"><</span> <span class="n">min_area</span><span class="p">:</span> |
| <span class="n">h</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="n">w</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">h</span> <span class="o">*</span> <span class="n">ratio</span><span class="p">))</span> |
| <span class="n">area</span> <span class="o">=</span> <span class="n">w</span> <span class="o">*</span> <span class="n">h</span> |
| <span class="k">if</span> <span class="n">area</span> <span class="o">></span> <span class="n">max_area</span><span class="p">:</span> |
| <span class="n">h</span> <span class="o">-=</span> <span class="mi">1</span> |
| <span class="n">w</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">h</span> <span class="o">*</span> <span class="n">ratio</span><span class="p">))</span> |
| <span class="n">area</span> <span class="o">=</span> <span class="n">w</span> <span class="o">*</span> <span class="n">h</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">area</span> <span class="o"><</span> <span class="n">min_area</span> <span class="ow">or</span> <span class="n">area</span> <span class="o">></span> <span class="n">max_area</span> <span class="ow">or</span> <span class="n">w</span> <span class="o">></span> <span class="n">width</span> <span class="ow">or</span> <span class="n">h</span> <span class="o">></span> <span class="n">height</span> \ |
| <span class="ow">or</span> <span class="n">w</span> <span class="o"><=</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">h</span> <span class="o"><=</span> <span class="mi">0</span><span class="p">):</span> |
| <span class="k">continue</span> |
| |
| <span class="n">y</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="nb">max</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">height</span> <span class="o">-</span> <span class="n">h</span><span class="p">))</span> |
| <span class="n">x</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="nb">max</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">width</span> <span class="o">-</span> <span class="n">w</span><span class="p">))</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_check_satisfy_constraints</span><span class="p">(</span><span class="n">label</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">x</span> <span class="o">+</span> <span class="n">w</span><span class="p">,</span> <span class="n">y</span> <span class="o">+</span> <span class="n">h</span><span class="p">,</span> <span class="n">width</span><span class="p">,</span> <span class="n">height</span><span class="p">):</span> |
| <span class="n">new_label</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_labels</span><span class="p">(</span><span class="n">label</span><span class="p">,</span> <span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">h</span><span class="p">),</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">new_label</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">new_label</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">()</span></div> |
| |
| |
| <div class="viewcode-block" id="DetRandomPadAug"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.DetRandomPadAug">[docs]</a><span class="k">class</span> <span class="nc">DetRandomPadAug</span><span class="p">(</span><span class="n">DetAugmenter</span><span class="p">):</span> |
| <span class="sd">"""Random padding augmenter.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> aspect_ratio_range : tuple of floats, default=(0.75, 1.33)</span> |
| <span class="sd"> The padded area of the image must have an aspect ratio = width / height</span> |
| <span class="sd"> within this range.</span> |
| <span class="sd"> area_range : tuple of floats, default=(1.0, 3.0)</span> |
| <span class="sd"> The padded area of the image must be larger than the original area</span> |
| <span class="sd"> max_attempts : int, default=50</span> |
| <span class="sd"> Number of attempts at generating a padded region of the image of the</span> |
| <span class="sd"> specified constraints. After max_attempts failures, return the original image.</span> |
| <span class="sd"> pad_val: float or tuple of float, default=(128, 128, 128)</span> |
| <span class="sd"> pixel value to be filled when padding is enabled.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">aspect_ratio_range</span><span class="o">=</span><span class="p">(</span><span class="mf">0.75</span><span class="p">,</span> <span class="mf">1.33</span><span class="p">),</span> <span class="n">area_range</span><span class="o">=</span><span class="p">(</span><span class="mf">1.0</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">),</span> |
| <span class="n">max_attempts</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span> <span class="n">pad_val</span><span class="o">=</span><span class="p">(</span><span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">,</span> <span class="mi">128</span><span class="p">)):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pad_val</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pad_val</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">)</span> |
| <span class="n">pad_val</span> <span class="o">=</span> <span class="p">(</span><span class="n">pad_val</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">aspect_ratio_range</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">aspect_ratio_range</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">)</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Using fixed aspect ratio: </span><span class="si">%s</span><span class="s1"> in DetRandomPadAug'</span><span class="p">,</span> |
| <span class="nb">str</span><span class="p">(</span><span class="n">aspect_ratio_range</span><span class="p">))</span> |
| <span class="n">aspect_ratio_range</span> <span class="o">=</span> <span class="p">(</span><span class="n">aspect_ratio_range</span><span class="p">,</span> <span class="n">aspect_ratio_range</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">area_range</span><span class="p">,</span> <span class="p">(</span><span class="nb">tuple</span><span class="p">,</span> <span class="nb">list</span><span class="p">)):</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">area_range</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">)</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Using fixed area range: </span><span class="si">%s</span><span class="s1"> in DetRandomPadAug'</span><span class="p">,</span> <span class="n">area_range</span><span class="p">)</span> |
| <span class="n">area_range</span> <span class="o">=</span> <span class="p">(</span><span class="n">area_range</span><span class="p">,</span> <span class="n">area_range</span><span class="p">)</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">DetRandomPadAug</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">aspect_ratio_range</span><span class="o">=</span><span class="n">aspect_ratio_range</span><span class="p">,</span> |
| <span class="n">area_range</span><span class="o">=</span><span class="n">area_range</span><span class="p">,</span> <span class="n">max_attempts</span><span class="o">=</span><span class="n">max_attempts</span><span class="p">,</span> |
| <span class="n">pad_val</span><span class="o">=</span><span class="n">pad_val</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">pad_val</span> <span class="o">=</span> <span class="n">pad_val</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">aspect_ratio_range</span> <span class="o">=</span> <span class="n">aspect_ratio_range</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">area_range</span> <span class="o">=</span> <span class="n">area_range</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">max_attempts</span> <span class="o">=</span> <span class="n">max_attempts</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">enabled</span> <span class="o">=</span> <span class="bp">False</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">area_range</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o"><=</span> <span class="mf">1.0</span> <span class="ow">or</span> <span class="n">area_range</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">></span> <span class="n">area_range</span><span class="p">[</span><span class="mi">1</span><span class="p">]):</span> |
| <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s1">'Skip DetRandomPadAug due to invalid parameters: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">area_range</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="p">(</span><span class="n">aspect_ratio_range</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o"><=</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">aspect_ratio_range</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">></span> <span class="n">aspect_ratio_range</span><span class="p">[</span><span class="mi">1</span><span class="p">]):</span> |
| <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s1">'Skip DetRandomPadAug due to invalid aspect_ratio_range: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> |
| <span class="n">aspect_ratio_range</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">enabled</span> <span class="o">=</span> <span class="bp">True</span> |
| |
| <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span> |
| <span class="sd">"""Augmenter body"""</span> |
| <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">src</span><span class="o">.</span><span class="n">shape</span> |
| <span class="n">pad</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_random_pad_proposal</span><span class="p">(</span><span class="n">label</span><span class="p">,</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">pad</span><span class="p">:</span> |
| <span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">label</span> <span class="o">=</span> <span class="n">pad</span> |
| <span class="n">src</span> <span class="o">=</span> <span class="n">copyMakeBorder</span><span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">h</span><span class="o">-</span><span class="n">y</span><span class="o">-</span><span class="n">height</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">w</span><span class="o">-</span><span class="n">x</span><span class="o">-</span><span class="n">width</span><span class="p">,</span> <span class="mi">16</span><span class="p">,</span> <span class="n">values</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">pad_val</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_update_labels</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">pad_box</span><span class="p">,</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">):</span> |
| <span class="sd">"""Update label according to padding region"""</span> |
| <span class="n">out</span> <span class="o">=</span> <span class="n">label</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span> |
| <span class="n">out</span><span class="p">[:,</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">)]</span> <span class="o">=</span> <span class="p">(</span><span class="n">out</span><span class="p">[:,</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">)]</span> <span class="o">*</span> <span class="n">width</span> <span class="o">+</span> <span class="n">pad_box</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="o">/</span> <span class="n">pad_box</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span> |
| <span class="n">out</span><span class="p">[:,</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">4</span><span class="p">)]</span> <span class="o">=</span> <span class="p">(</span><span class="n">out</span><span class="p">[:,</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">4</span><span class="p">)]</span> <span class="o">*</span> <span class="n">height</span> <span class="o">+</span> <span class="n">pad_box</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> <span class="o">/</span> <span class="n">pad_box</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span> |
| <span class="k">return</span> <span class="n">out</span> |
| |
| <span class="k">def</span> <span class="nf">_random_pad_proposal</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">):</span> |
| <span class="sd">"""Generate random padding region"""</span> |
| <span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">sqrt</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">enabled</span> <span class="ow">or</span> <span class="n">height</span> <span class="o"><=</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">width</span> <span class="o"><=</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">()</span> |
| <span class="n">min_area</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">area_range</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="n">height</span> <span class="o">*</span> <span class="n">width</span> |
| <span class="n">max_area</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">area_range</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">*</span> <span class="n">height</span> <span class="o">*</span> <span class="n">width</span> |
| <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">max_attempts</span><span class="p">):</span> |
| <span class="n">ratio</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">aspect_ratio_range</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">ratio</span> <span class="o"><=</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">continue</span> |
| <span class="n">h</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">sqrt</span><span class="p">(</span><span class="n">min_area</span> <span class="o">/</span> <span class="n">ratio</span><span class="p">)))</span> |
| <span class="n">max_h</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">sqrt</span><span class="p">(</span><span class="n">max_area</span> <span class="o">/</span> <span class="n">ratio</span><span class="p">)))</span> |
| <span class="k">if</span> <span class="nb">round</span><span class="p">(</span><span class="n">h</span> <span class="o">*</span> <span class="n">ratio</span><span class="p">)</span> <span class="o"><</span> <span class="n">width</span><span class="p">:</span> |
| <span class="n">h</span> <span class="o">=</span> <span class="nb">int</span><span class="p">((</span><span class="n">width</span> <span class="o">+</span> <span class="mf">0.499999</span><span class="p">)</span> <span class="o">/</span> <span class="n">ratio</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">h</span> <span class="o"><</span> <span class="n">height</span><span class="p">:</span> |
| <span class="n">h</span> <span class="o">=</span> <span class="n">height</span> |
| <span class="k">if</span> <span class="n">h</span> <span class="o">></span> <span class="n">max_h</span><span class="p">:</span> |
| <span class="n">h</span> <span class="o">=</span> <span class="n">max_h</span> |
| <span class="k">if</span> <span class="n">h</span> <span class="o"><</span> <span class="n">max_h</span><span class="p">:</span> |
| <span class="n">h</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="n">h</span><span class="p">,</span> <span class="n">max_h</span><span class="p">)</span> |
| <span class="n">w</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">h</span> <span class="o">*</span> <span class="n">ratio</span><span class="p">))</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">h</span> <span class="o">-</span> <span class="n">height</span><span class="p">)</span> <span class="o"><</span> <span class="mi">2</span> <span class="ow">or</span> <span class="p">(</span><span class="n">w</span> <span class="o">-</span> <span class="n">width</span><span class="p">)</span> <span class="o"><</span> <span class="mi">2</span><span class="p">:</span> |
| <span class="k">continue</span> <span class="c1"># marginal padding is not helpful</span> |
| |
| <span class="n">y</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="nb">max</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">h</span> <span class="o">-</span> <span class="n">height</span><span class="p">))</span> |
| <span class="n">x</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="nb">max</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">w</span> <span class="o">-</span> <span class="n">width</span><span class="p">))</span> |
| <span class="n">new_label</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_labels</span><span class="p">(</span><span class="n">label</span><span class="p">,</span> <span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">h</span><span class="p">),</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">new_label</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">()</span></div> |
| |
| |
| <span class="k">def</span> <span class="nf">CreateMultiRandCropAugmenter</span><span class="p">(</span><span class="n">min_object_covered</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">aspect_ratio_range</span><span class="o">=</span><span class="p">(</span><span class="mf">0.75</span><span class="p">,</span> <span class="mf">1.33</span><span class="p">),</span> |
| <span class="n">area_range</span><span class="o">=</span><span class="p">(</span><span class="mf">0.05</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span> <span class="n">min_eject_coverage</span><span class="o">=</span><span class="mf">0.3</span><span class="p">,</span> |
| <span class="n">max_attempts</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span> <span class="n">skip_prob</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span> |
| <span class="sd">"""Helper function to create multiple random crop augmenters.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> min_object_covered : float or list of float, default=0.1</span> |
| <span class="sd"> The cropped area of the image must contain at least this fraction of</span> |
| <span class="sd"> any bounding box supplied. The value of this parameter should be non-negative.</span> |
| <span class="sd"> In the case of 0, the cropped area does not need to overlap any of the</span> |
| <span class="sd"> bounding boxes supplied.</span> |
| <span class="sd"> min_eject_coverage : float or list of float, default=0.3</span> |
| <span class="sd"> The minimum coverage of cropped sample w.r.t its original size. With this</span> |
| <span class="sd"> constraint, objects that have marginal area after crop will be discarded.</span> |
| <span class="sd"> aspect_ratio_range : tuple of floats or list of tuple of floats, default=(0.75, 1.33)</span> |
| <span class="sd"> The cropped area of the image must have an aspect ratio = width / height</span> |
| <span class="sd"> within this range.</span> |
| <span class="sd"> area_range : tuple of floats or list of tuple of floats, default=(0.05, 1.0)</span> |
| <span class="sd"> The cropped area of the image must contain a fraction of the supplied</span> |
| <span class="sd"> image within in this range.</span> |
| <span class="sd"> max_attempts : int or list of int, default=50</span> |
| <span class="sd"> Number of attempts at generating a cropped/padded region of the image of the</span> |
| <span class="sd"> specified constraints. After max_attempts failures, return the original image.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> # An example of creating multiple random crop augmenters</span> |
| <span class="sd"> >>> min_object_covered = [0.1, 0.3, 0.5, 0.7, 0.9] # use 5 augmenters</span> |
| <span class="sd"> >>> aspect_ratio_range = (0.75, 1.33) # use same range for all augmenters</span> |
| <span class="sd"> >>> area_range = [(0.1, 1.0), (0.2, 1.0), (0.2, 1.0), (0.3, 0.9), (0.5, 1.0)]</span> |
| <span class="sd"> >>> min_eject_coverage = 0.3</span> |
| <span class="sd"> >>> max_attempts = 50</span> |
| <span class="sd"> >>> aug = mx.image.det.CreateMultiRandCropAugmenter(min_object_covered=min_object_covered,</span> |
| <span class="sd"> aspect_ratio_range=aspect_ratio_range, area_range=area_range,</span> |
| <span class="sd"> min_eject_coverage=min_eject_coverage, max_attempts=max_attempts,</span> |
| <span class="sd"> skip_prob=0)</span> |
| <span class="sd"> >>> aug.dumps() # show some details</span> |
| |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">align_parameters</span><span class="p">(</span><span class="n">params</span><span class="p">):</span> |
| <span class="sd">"""Align parameters as pairs"""</span> |
| <span class="n">out_params</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">num</span> <span class="o">=</span> <span class="mi">1</span> |
| <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">params</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">p</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span> |
| <span class="n">p</span> <span class="o">=</span> <span class="p">[</span><span class="n">p</span><span class="p">]</span> |
| <span class="n">out_params</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">p</span><span class="p">)</span> |
| <span class="n">num</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="n">num</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">p</span><span class="p">))</span> |
| <span class="c1"># align for each param</span> |
| <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">p</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">out_params</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">p</span><span class="p">)</span> <span class="o">!=</span> <span class="n">num</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">p</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> |
| <span class="n">out_params</span><span class="p">[</span><span class="n">k</span><span class="p">]</span> <span class="o">=</span> <span class="n">p</span> <span class="o">*</span> <span class="n">num</span> |
| <span class="k">return</span> <span class="n">out_params</span> |
| |
| <span class="n">aligned_params</span> <span class="o">=</span> <span class="n">align_parameters</span><span class="p">([</span><span class="n">min_object_covered</span><span class="p">,</span> <span class="n">aspect_ratio_range</span><span class="p">,</span> <span class="n">area_range</span><span class="p">,</span> |
| <span class="n">min_eject_coverage</span><span class="p">,</span> <span class="n">max_attempts</span><span class="p">])</span> |
| <span class="n">augs</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">moc</span><span class="p">,</span> <span class="n">arr</span><span class="p">,</span> <span class="n">ar</span><span class="p">,</span> <span class="n">mec</span><span class="p">,</span> <span class="n">ma</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="n">aligned_params</span><span class="p">):</span> |
| <span class="n">augs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">DetRandomCropAug</span><span class="p">(</span><span class="n">min_object_covered</span><span class="o">=</span><span class="n">moc</span><span class="p">,</span> <span class="n">aspect_ratio_range</span><span class="o">=</span><span class="n">arr</span><span class="p">,</span> |
| <span class="n">area_range</span><span class="o">=</span><span class="n">ar</span><span class="p">,</span> <span class="n">min_eject_coverage</span><span class="o">=</span><span class="n">mec</span><span class="p">,</span> <span class="n">max_attempts</span><span class="o">=</span><span class="n">ma</span><span class="p">))</span> |
| <span class="k">return</span> <span class="n">DetRandomSelectAug</span><span class="p">(</span><span class="n">augs</span><span class="p">,</span> <span class="n">skip_prob</span><span class="o">=</span><span class="n">skip_prob</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">CreateDetAugmenter</span><span class="p">(</span><span class="n">data_shape</span><span class="p">,</span> <span class="n">resize</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">rand_crop</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">rand_pad</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">rand_gray</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">rand_mirror</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">mean</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">std</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">brightness</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">contrast</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">saturation</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">pca_noise</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">hue</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">inter_method</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">min_object_covered</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> |
| <span class="n">aspect_ratio_range</span><span class="o">=</span><span class="p">(</span><span class="mf">0.75</span><span class="p">,</span> <span class="mf">1.33</span><span class="p">),</span> <span class="n">area_range</span><span class="o">=</span><span class="p">(</span><span class="mf">0.05</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">),</span> |
| <span class="n">min_eject_coverage</span><span class="o">=</span><span class="mf">0.3</span><span class="p">,</span> <span class="n">max_attempts</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span> <span class="n">pad_val</span><span class="o">=</span><span class="p">(</span><span class="mi">127</span><span class="p">,</span> <span class="mi">127</span><span class="p">,</span> <span class="mi">127</span><span class="p">)):</span> |
| <span class="sd">"""Create augmenters for detection.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data_shape : tuple of int</span> |
| <span class="sd"> Shape for output data</span> |
| <span class="sd"> resize : int</span> |
| <span class="sd"> Resize shorter edge if larger than 0 at the begining</span> |
| <span class="sd"> rand_crop : float</span> |
| <span class="sd"> [0, 1], probability to apply random cropping</span> |
| <span class="sd"> rand_pad : float</span> |
| <span class="sd"> [0, 1], probability to apply random padding</span> |
| <span class="sd"> rand_gray : float</span> |
| <span class="sd"> [0, 1], probability to convert to grayscale for all channels</span> |
| <span class="sd"> rand_mirror : bool</span> |
| <span class="sd"> Whether to apply horizontal flip to image with probability 0.5</span> |
| <span class="sd"> mean : np.ndarray or None</span> |
| <span class="sd"> Mean pixel values for [r, g, b]</span> |
| <span class="sd"> std : np.ndarray or None</span> |
| <span class="sd"> Standard deviations for [r, g, b]</span> |
| <span class="sd"> brightness : float</span> |
| <span class="sd"> Brightness jittering range (percent)</span> |
| <span class="sd"> contrast : float</span> |
| <span class="sd"> Contrast jittering range (percent)</span> |
| <span class="sd"> saturation : float</span> |
| <span class="sd"> Saturation jittering range (percent)</span> |
| <span class="sd"> hue : float</span> |
| <span class="sd"> Hue jittering range (percent)</span> |
| <span class="sd"> pca_noise : float</span> |
| <span class="sd"> Pca noise level (percent)</span> |
| <span class="sd"> inter_method : int, default=2(Area-based)</span> |
| <span class="sd"> Interpolation method for all resizing operations</span> |
| |
| <span class="sd"> Possible values:</span> |
| <span class="sd"> 0: Nearest Neighbors Interpolation.</span> |
| <span class="sd"> 1: Bilinear interpolation.</span> |
| <span class="sd"> 2: Area-based (resampling using pixel area relation). It may be a</span> |
| <span class="sd"> preferred method for image decimation, as it gives moire-free</span> |
| <span class="sd"> results. But when the image is zoomed, it is similar to the Nearest</span> |
| <span class="sd"> Neighbors method. (used by default).</span> |
| <span class="sd"> 3: Bicubic interpolation over 4x4 pixel neighborhood.</span> |
| <span class="sd"> 4: Lanczos interpolation over 8x8 pixel neighborhood.</span> |
| <span class="sd"> 9: Cubic for enlarge, area for shrink, bilinear for others</span> |
| <span class="sd"> 10: Random select from interpolation method metioned above.</span> |
| <span class="sd"> Note:</span> |
| <span class="sd"> When shrinking an image, it will generally look best with AREA-based</span> |
| <span class="sd"> interpolation, whereas, when enlarging an image, it will generally look best</span> |
| <span class="sd"> with Bicubic (slow) or Bilinear (faster but still looks OK).</span> |
| <span class="sd"> min_object_covered : float</span> |
| <span class="sd"> The cropped area of the image must contain at least this fraction of</span> |
| <span class="sd"> any bounding box supplied. The value of this parameter should be non-negative.</span> |
| <span class="sd"> In the case of 0, the cropped area does not need to overlap any of the</span> |
| <span class="sd"> bounding boxes supplied.</span> |
| <span class="sd"> min_eject_coverage : float</span> |
| <span class="sd"> The minimum coverage of cropped sample w.r.t its original size. With this</span> |
| <span class="sd"> constraint, objects that have marginal area after crop will be discarded.</span> |
| <span class="sd"> aspect_ratio_range : tuple of floats</span> |
| <span class="sd"> The cropped area of the image must have an aspect ratio = width / height</span> |
| <span class="sd"> within this range.</span> |
| <span class="sd"> area_range : tuple of floats</span> |
| <span class="sd"> The cropped area of the image must contain a fraction of the supplied</span> |
| <span class="sd"> image within in this range.</span> |
| <span class="sd"> max_attempts : int</span> |
| <span class="sd"> Number of attempts at generating a cropped/padded region of the image of the</span> |
| <span class="sd"> specified constraints. After max_attempts failures, return the original image.</span> |
| <span class="sd"> pad_val: float</span> |
| <span class="sd"> Pixel value to be filled when padding is enabled. pad_val will automatically</span> |
| <span class="sd"> be subtracted by mean and divided by std if applicable.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> # An example of creating multiple augmenters</span> |
| <span class="sd"> >>> augs = mx.image.CreateDetAugmenter(data_shape=(3, 300, 300), rand_crop=0.5,</span> |
| <span class="sd"> ... rand_pad=0.5, rand_mirror=True, mean=True, brightness=0.125, contrast=0.125,</span> |
| <span class="sd"> ... saturation=0.125, pca_noise=0.05, inter_method=10, min_object_covered=[0.3, 0.5, 0.9],</span> |
| <span class="sd"> ... area_range=(0.3, 3.0))</span> |
| <span class="sd"> >>> # dump the details</span> |
| <span class="sd"> >>> for aug in augs:</span> |
| <span class="sd"> ... aug.dumps()</span> |
| <span class="sd"> """</span> |
| <span class="n">auglist</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <span class="k">if</span> <span class="n">resize</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">auglist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">DetBorrowAug</span><span class="p">(</span><span class="n">ResizeAug</span><span class="p">(</span><span class="n">resize</span><span class="p">,</span> <span class="n">inter_method</span><span class="p">)))</span> |
| |
| <span class="k">if</span> <span class="n">rand_crop</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">crop_augs</span> <span class="o">=</span> <span class="n">CreateMultiRandCropAugmenter</span><span class="p">(</span><span class="n">min_object_covered</span><span class="p">,</span> <span class="n">aspect_ratio_range</span><span class="p">,</span> |
| <span class="n">area_range</span><span class="p">,</span> <span class="n">min_eject_coverage</span><span class="p">,</span> |
| <span class="n">max_attempts</span><span class="p">,</span> <span class="n">skip_prob</span><span class="o">=</span><span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">rand_crop</span><span class="p">))</span> |
| <span class="n">auglist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">crop_augs</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">rand_mirror</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">auglist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">DetHorizontalFlipAug</span><span class="p">(</span><span class="mf">0.5</span><span class="p">))</span> |
| |
| <span class="c1"># apply random padding as late as possible to save computation</span> |
| <span class="k">if</span> <span class="n">rand_pad</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">pad_aug</span> <span class="o">=</span> <span class="n">DetRandomPadAug</span><span class="p">(</span><span class="n">aspect_ratio_range</span><span class="p">,</span> |
| <span class="p">(</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">area_range</span><span class="p">[</span><span class="mi">1</span><span class="p">]),</span> <span class="n">max_attempts</span><span class="p">,</span> <span class="n">pad_val</span><span class="p">)</span> |
| <span class="n">auglist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">DetRandomSelectAug</span><span class="p">([</span><span class="n">pad_aug</span><span class="p">],</span> <span class="mi">1</span> <span class="o">-</span> <span class="n">rand_pad</span><span class="p">))</span> |
| |
| <span class="c1"># force resize</span> |
| <span class="n">auglist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">DetBorrowAug</span><span class="p">(</span><span class="n">ForceResizeAug</span><span class="p">((</span><span class="n">data_shape</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">data_shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]),</span> <span class="n">inter_method</span><span class="p">)))</span> |
| |
| <span class="n">auglist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">DetBorrowAug</span><span class="p">(</span><span class="n">CastAug</span><span class="p">()))</span> |
| |
| <span class="k">if</span> <span class="n">brightness</span> <span class="ow">or</span> <span class="n">contrast</span> <span class="ow">or</span> <span class="n">saturation</span><span class="p">:</span> |
| <span class="n">auglist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">DetBorrowAug</span><span class="p">(</span><span class="n">ColorJitterAug</span><span class="p">(</span><span class="n">brightness</span><span class="p">,</span> <span class="n">contrast</span><span class="p">,</span> <span class="n">saturation</span><span class="p">)))</span> |
| |
| <span class="k">if</span> <span class="n">hue</span><span class="p">:</span> |
| <span class="n">auglist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">DetBorrowAug</span><span class="p">(</span><span class="n">HueJitterAug</span><span class="p">(</span><span class="n">hue</span><span class="p">)))</span> |
| |
| <span class="k">if</span> <span class="n">pca_noise</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">eigval</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">55.46</span><span class="p">,</span> <span class="mf">4.794</span><span class="p">,</span> <span class="mf">1.148</span><span class="p">])</span> |
| <span class="n">eigvec</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([[</span><span class="o">-</span><span class="mf">0.5675</span><span class="p">,</span> <span class="mf">0.7192</span><span class="p">,</span> <span class="mf">0.4009</span><span class="p">],</span> |
| <span class="p">[</span><span class="o">-</span><span class="mf">0.5808</span><span class="p">,</span> <span class="o">-</span><span class="mf">0.0045</span><span class="p">,</span> <span class="o">-</span><span class="mf">0.8140</span><span class="p">],</span> |
| <span class="p">[</span><span class="o">-</span><span class="mf">0.5836</span><span class="p">,</span> <span class="o">-</span><span class="mf">0.6948</span><span class="p">,</span> <span class="mf">0.4203</span><span class="p">]])</span> |
| <span class="n">auglist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">DetBorrowAug</span><span class="p">(</span><span class="n">LightingAug</span><span class="p">(</span><span class="n">pca_noise</span><span class="p">,</span> <span class="n">eigval</span><span class="p">,</span> <span class="n">eigvec</span><span class="p">)))</span> |
| |
| <span class="k">if</span> <span class="n">rand_gray</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">auglist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">DetBorrowAug</span><span class="p">(</span><span class="n">RandomGrayAug</span><span class="p">(</span><span class="n">rand_gray</span><span class="p">)))</span> |
| |
| <span class="k">if</span> <span class="n">mean</span> <span class="ow">is</span> <span class="bp">True</span><span class="p">:</span> |
| <span class="n">mean</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">123.68</span><span class="p">,</span> <span class="mf">116.28</span><span class="p">,</span> <span class="mf">103.53</span><span class="p">])</span> |
| <span class="k">elif</span> <span class="n">mean</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">mean</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">)</span> <span class="ow">and</span> <span class="n">mean</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">in</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">std</span> <span class="ow">is</span> <span class="bp">True</span><span class="p">:</span> |
| <span class="n">std</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">58.395</span><span class="p">,</span> <span class="mf">57.12</span><span class="p">,</span> <span class="mf">57.375</span><span class="p">])</span> |
| <span class="k">elif</span> <span class="n">std</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">std</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">)</span> <span class="ow">and</span> <span class="n">std</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">in</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">mean</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span> <span class="ow">or</span> <span class="n">std</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span> |
| <span class="n">auglist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">DetBorrowAug</span><span class="p">(</span><span class="n">ColorNormalizeAug</span><span class="p">(</span><span class="n">mean</span><span class="p">,</span> <span class="n">std</span><span class="p">)))</span> |
| |
| <span class="k">return</span> <span class="n">auglist</span> |
| |
| |
| <div class="viewcode-block" id="ImageDetIter"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.ImageDetIter">[docs]</a><span class="k">class</span> <span class="nc">ImageDetIter</span><span class="p">(</span><span class="n">ImageIter</span><span class="p">):</span> |
| <span class="sd">"""Image iterator with a large number of augmentation choices for detection.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> aug_list : list or None</span> |
| <span class="sd"> Augmenter list for generating distorted images</span> |
| <span class="sd"> batch_size : int</span> |
| <span class="sd"> Number of examples per batch.</span> |
| <span class="sd"> data_shape : tuple</span> |
| <span class="sd"> Data shape in (channels, height, width) format.</span> |
| <span class="sd"> For now, only RGB image with 3 channels is supported.</span> |
| <span class="sd"> path_imgrec : str</span> |
| <span class="sd"> Path to image record file (.rec).</span> |
| <span class="sd"> Created with tools/im2rec.py or bin/im2rec.</span> |
| <span class="sd"> path_imglist : str</span> |
| <span class="sd"> Path to image list (.lst).</span> |
| <span class="sd"> Created with tools/im2rec.py or with custom script.</span> |
| <span class="sd"> Format: Tab separated record of index, one or more labels and relative_path_from_root.</span> |
| <span class="sd"> imglist: list</span> |
| <span class="sd"> A list of images with the label(s).</span> |
| <span class="sd"> Each item is a list [imagelabel: float or list of float, imgpath].</span> |
| <span class="sd"> path_root : str</span> |
| <span class="sd"> Root folder of image files.</span> |
| <span class="sd"> path_imgidx : str</span> |
| <span class="sd"> Path to image index file. Needed for partition and shuffling when using .rec source.</span> |
| <span class="sd"> shuffle : bool</span> |
| <span class="sd"> Whether to shuffle all images at the start of each iteration or not.</span> |
| <span class="sd"> Can be slow for HDD.</span> |
| <span class="sd"> part_index : int</span> |
| <span class="sd"> Partition index.</span> |
| <span class="sd"> num_parts : int</span> |
| <span class="sd"> Total number of partitions.</span> |
| <span class="sd"> data_name : str</span> |
| <span class="sd"> Data name for provided symbols.</span> |
| <span class="sd"> label_name : str</span> |
| <span class="sd"> Name for detection labels</span> |
| <span class="sd"> kwargs : ...</span> |
| <span class="sd"> More arguments for creating augmenter. See mx.image.CreateDetAugmenter.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">,</span> <span class="n">data_shape</span><span class="p">,</span> |
| <span class="n">path_imgrec</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">path_imglist</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">path_root</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">path_imgidx</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> |
| <span class="n">shuffle</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">part_index</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_parts</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">aug_list</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">imglist</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> |
| <span class="n">data_name</span><span class="o">=</span><span class="s1">'data'</span><span class="p">,</span> <span class="n">label_name</span><span class="o">=</span><span class="s1">'label'</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">ImageDetIter</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">batch_size</span><span class="o">=</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">data_shape</span><span class="o">=</span><span class="n">data_shape</span><span class="p">,</span> |
| <span class="n">path_imgrec</span><span class="o">=</span><span class="n">path_imgrec</span><span class="p">,</span> <span class="n">path_imglist</span><span class="o">=</span><span class="n">path_imglist</span><span class="p">,</span> |
| <span class="n">path_root</span><span class="o">=</span><span class="n">path_root</span><span class="p">,</span> <span class="n">path_imgidx</span><span class="o">=</span><span class="n">path_imgidx</span><span class="p">,</span> |
| <span class="n">shuffle</span><span class="o">=</span><span class="n">shuffle</span><span class="p">,</span> <span class="n">part_index</span><span class="o">=</span><span class="n">part_index</span><span class="p">,</span> |
| <span class="n">num_parts</span><span class="o">=</span><span class="n">num_parts</span><span class="p">,</span> <span class="n">aug_list</span><span class="o">=</span><span class="p">[],</span> <span class="n">imglist</span><span class="o">=</span><span class="n">imglist</span><span class="p">,</span> |
| <span class="n">data_name</span><span class="o">=</span><span class="n">data_name</span><span class="p">,</span> <span class="n">label_name</span><span class="o">=</span><span class="n">label_name</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">aug_list</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">auglist</span> <span class="o">=</span> <span class="n">CreateDetAugmenter</span><span class="p">(</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">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">auglist</span> <span class="o">=</span> <span class="n">aug_list</span> |
| |
| <span class="c1"># went through all labels to get the proper label shape</span> |
| <span class="n">label_shape</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_estimate_label_shape</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">provide_label</span> <span class="o">=</span> <span class="p">[(</span><span class="n">label_name</span><span class="p">,</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">label_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">label_shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]))]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">label_shape</span> <span class="o">=</span> <span class="n">label_shape</span> |
| |
| <span class="k">def</span> <span class="nf">_check_valid_label</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span> |
| <span class="sd">"""Validate label and its shape."""</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">label</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">2</span> <span class="ow">or</span> <span class="n">label</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o"><</span> <span class="mi">5</span><span class="p">:</span> |
| <span class="n">msg</span> <span class="o">=</span> <span class="s2">"Label with shape (1+, 5+) required, </span><span class="si">%s</span><span class="s2"> received."</span> <span class="o">%</span> <span class="nb">str</span><span class="p">(</span><span class="n">label</span><span class="p">)</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="n">msg</span><span class="p">)</span> |
| <span class="n">valid_label</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">logical_and</span><span class="p">(</span><span class="n">label</span><span class="p">[:,</span> <span class="mi">0</span><span class="p">]</span> <span class="o">>=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">label</span><span class="p">[:,</span> <span class="mi">3</span><span class="p">]</span> <span class="o">></span> <span class="n">label</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">],</span> |
| <span class="n">label</span><span class="p">[:,</span> <span class="mi">4</span><span class="p">]</span> <span class="o">></span> <span class="n">label</span><span class="p">[:,</span> <span class="mi">2</span><span class="p">]))[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">valid_label</span><span class="o">.</span><span class="n">size</span> <span class="o"><</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s1">'Invalid label occurs.'</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_estimate_label_shape</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Helper function to estimate label shape"""</span> |
| <span class="n">max_count</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="k">while</span> <span class="bp">True</span><span class="p">:</span> |
| <span class="n">label</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">next_sample</span><span class="p">()</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parse_label</span><span class="p">(</span><span class="n">label</span><span class="p">)</span> |
| <span class="n">max_count</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="n">max_count</span><span class="p">,</span> <span class="n">label</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="k">except</span> <span class="ne">StopIteration</span><span class="p">:</span> |
| <span class="k">pass</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">max_count</span><span class="p">,</span> <span class="n">label</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> |
| |
| <span class="k">def</span> <span class="nf">_parse_label</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span> |
| <span class="sd">"""Helper function to parse object detection label.</span> |
| |
| <span class="sd"> Format for raw label:</span> |
| <span class="sd"> n \t k \t ... \t [id \t xmin\t ymin \t xmax \t ymax \t ...] \t [repeat]</span> |
| <span class="sd"> where n is the width of header, 2 or larger</span> |
| <span class="sd"> k is the width of each object annotation, can be arbitrary, at least 5</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">label</span><span class="p">,</span> <span class="n">nd</span><span class="o">.</span><span class="n">NDArray</span><span class="p">):</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="n">label</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">()</span> |
| <span class="n">raw</span> <span class="o">=</span> <span class="n">label</span><span class="o">.</span><span class="n">ravel</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">raw</span><span class="o">.</span><span class="n">size</span> <span class="o"><</span> <span class="mi">7</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s2">"Label shape is invalid: "</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">raw</span><span class="o">.</span><span class="n">shape</span><span class="p">))</span> |
| <span class="n">header_width</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">raw</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="n">obj_width</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">raw</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">raw</span><span class="o">.</span><span class="n">size</span> <span class="o">-</span> <span class="n">header_width</span><span class="p">)</span> <span class="o">%</span> <span class="n">obj_width</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">msg</span> <span class="o">=</span> <span class="s2">"Label shape </span><span class="si">%s</span><span class="s2"> inconsistent with annotation width </span><span class="si">%d</span><span class="s2">."</span> \ |
| <span class="o">%</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">raw</span><span class="o">.</span><span class="n">shape</span><span class="p">),</span> <span class="n">obj_width</span><span class="p">)</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="n">msg</span><span class="p">)</span> |
| <span class="n">out</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">raw</span><span class="p">[</span><span class="n">header_width</span><span class="p">:],</span> <span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="n">obj_width</span><span class="p">))</span> |
| <span class="c1"># remove bad ground-truths</span> |
| <span class="n">valid</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">logical_and</span><span class="p">(</span><span class="n">out</span><span class="p">[:,</span> <span class="mi">3</span><span class="p">]</span> <span class="o">></span> <span class="n">out</span><span class="p">[:,</span> <span class="mi">1</span><span class="p">],</span> <span class="n">out</span><span class="p">[:,</span> <span class="mi">4</span><span class="p">]</span> <span class="o">></span> <span class="n">out</span><span class="p">[:,</span> <span class="mi">2</span><span class="p">]))[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">valid</span><span class="o">.</span><span class="n">size</span> <span class="o"><</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s1">'Encounter sample with no valid label.'</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">out</span><span class="p">[</span><span class="n">valid</span><span class="p">,</span> <span class="p">:]</span> |
| |
| <div class="viewcode-block" id="ImageDetIter.reshape"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.ImageDetIter.reshape">[docs]</a> <span class="k">def</span> <span class="nf">reshape</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data_shape</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">label_shape</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span> |
| <span class="sd">"""Reshape iterator for data_shape or label_shape.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data_shape : tuple or None</span> |
| <span class="sd"> Reshape the data_shape to the new shape if not None</span> |
| <span class="sd"> label_shape : tuple or None</span> |
| <span class="sd"> Reshape label shape to new shape if not None</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">data_shape</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">check_data_shape</span><span class="p">(</span><span class="n">data_shape</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">provide_data</span> <span class="o">=</span> <span class="p">[(</span><span class="bp">self</span><span class="o">.</span><span class="n">provide_data</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="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span><span class="p">,)</span> <span class="o">+</span> <span class="n">data_shape</span><span class="p">)]</span> |
| <span class="k">if</span> <span class="n">label_shape</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">check_label_shape</span><span class="p">(</span><span class="n">label_shape</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">provide_label</span> <span class="o">=</span> <span class="p">[(</span><span class="bp">self</span><span class="o">.</span><span class="n">provide_label</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="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span><span class="p">,)</span> <span class="o">+</span> <span class="n">label_shape</span><span class="p">)]</span></div> |
| |
| <div class="viewcode-block" id="ImageDetIter.next"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.ImageDetIter.next">[docs]</a> <span class="k">def</span> <span class="nf">next</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Override the function for returning next batch."""</span> |
| <span class="n">batch_size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span> |
| <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_shape</span> |
| <span class="n">batch_data</span> <span class="o">=</span> <span class="n">nd</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">))</span> |
| <span class="n">batch_label</span> <span class="o">=</span> <span class="n">nd</span><span class="o">.</span><span class="n">empty</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">provide_label</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="mi">1</span><span class="p">])</span> |
| <span class="n">batch_label</span><span class="p">[:]</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span> |
| <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="k">while</span> <span class="n">i</span> <span class="o"><</span> <span class="n">batch_size</span><span class="p">:</span> |
| <span class="n">label</span><span class="p">,</span> <span class="n">s</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">next_sample</span><span class="p">()</span> |
| <span class="n">data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">imdecode</span><span class="p">(</span><span class="n">s</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">check_valid_image</span><span class="p">([</span><span class="n">data</span><span class="p">])</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parse_label</span><span class="p">(</span><span class="n">label</span><span class="p">)</span> |
| <span class="n">data</span><span class="p">,</span> <span class="n">label</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">augmentation_transform</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_check_valid_label</span><span class="p">(</span><span class="n">label</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">RuntimeError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">'Invalid image, skipping: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">))</span> |
| <span class="k">continue</span> |
| <span class="k">for</span> <span class="n">datum</span> <span class="ow">in</span> <span class="p">[</span><span class="n">data</span><span class="p">]:</span> |
| <span class="k">assert</span> <span class="n">i</span> <span class="o"><</span> <span class="n">batch_size</span><span class="p">,</span> <span class="s1">'Batch size must be multiples of augmenter output length'</span> |
| <span class="n">batch_data</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">postprocess_data</span><span class="p">(</span><span class="n">datum</span><span class="p">)</span> |
| <span class="n">num_object</span> <span class="o">=</span> <span class="n">label</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="n">batch_label</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">0</span><span class="p">:</span><span class="n">num_object</span><span class="p">]</span> <span class="o">=</span> <span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">label</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">num_object</span> <span class="o"><</span> <span class="n">batch_label</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span> |
| <span class="n">batch_label</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="n">num_object</span><span class="p">:]</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span> |
| <span class="n">i</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">except</span> <span class="ne">StopIteration</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">i</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">StopIteration</span> |
| |
| <span class="k">return</span> <span class="n">io</span><span class="o">.</span><span class="n">DataBatch</span><span class="p">([</span><span class="n">batch_data</span><span class="p">],</span> <span class="p">[</span><span class="n">batch_label</span><span class="p">],</span> <span class="n">batch_size</span> <span class="o">-</span> <span class="n">i</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ImageDetIter.augmentation_transform"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.ImageDetIter.augmentation_transform">[docs]</a> <span class="k">def</span> <span class="nf">augmentation_transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span> <span class="c1"># pylint: disable=arguments-differ</span> |
| <span class="sd">"""Override Transforms input data with specified augmentations."""</span> |
| <span class="k">for</span> <span class="n">aug</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">auglist</span><span class="p">:</span> |
| <span class="n">data</span><span class="p">,</span> <span class="n">label</span> <span class="o">=</span> <span class="n">aug</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ImageDetIter.check_label_shape"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.ImageDetIter.check_label_shape">[docs]</a> <span class="k">def</span> <span class="nf">check_label_shape</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label_shape</span><span class="p">):</span> |
| <span class="sd">"""Checks if the new label shape is valid"""</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">len</span><span class="p">(</span><span class="n">label_shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'label_shape should have length 2'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">label_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">label_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span> |
| <span class="n">msg</span> <span class="o">=</span> <span class="s1">'Attempts to reduce label count from </span><span class="si">%d</span><span class="s1"> to </span><span class="si">%d</span><span class="s1">, not allowed.'</span> \ |
| <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">label_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">label_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="n">msg</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">label_shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">!=</span> <span class="bp">self</span><span class="o">.</span><span class="n">provide_label</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="mi">1</span><span class="p">][</span><span class="mi">2</span><span class="p">]:</span> |
| <span class="n">msg</span> <span class="o">=</span> <span class="s1">'label_shape object width inconsistent: </span><span class="si">%d</span><span class="s1"> vs </span><span class="si">%d</span><span class="s1">.'</span> \ |
| <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">provide_label</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="mi">1</span><span class="p">][</span><span class="mi">2</span><span class="p">],</span> <span class="n">label_shape</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="n">msg</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ImageDetIter.draw_next"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.ImageDetIter.draw_next">[docs]</a> <span class="k">def</span> <span class="nf">draw_next</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">color</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">thickness</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">mean</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">std</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">clip</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> |
| <span class="n">waitKey</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">window_name</span><span class="o">=</span><span class="s1">'draw_next'</span><span class="p">):</span> |
| <span class="sd">"""Display next image with bounding boxes drawn.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> color : tuple</span> |
| <span class="sd"> Bounding box color in RGB, use None for random color</span> |
| <span class="sd"> thickness : int</span> |
| <span class="sd"> Bounding box border thickness</span> |
| <span class="sd"> mean : True or numpy.ndarray</span> |
| <span class="sd"> Compensate for the mean to have better visual effect</span> |
| <span class="sd"> std : True or numpy.ndarray</span> |
| <span class="sd"> Revert standard deviations</span> |
| <span class="sd"> clip : bool</span> |
| <span class="sd"> If true, clip to [0, 255] for better visual effect</span> |
| <span class="sd"> waitKey : None or int</span> |
| <span class="sd"> Hold the window for waitKey milliseconds if set, skip ploting if None</span> |
| <span class="sd"> window_name : str</span> |
| <span class="sd"> Plot window name if waitKey is set.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> numpy.ndarray</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> # use draw_next to get images with bounding boxes drawn</span> |
| <span class="sd"> >>> iterator = mx.image.ImageDetIter(1, (3, 600, 600), path_imgrec='train.rec')</span> |
| <span class="sd"> >>> for image in iterator.draw_next(waitKey=None):</span> |
| <span class="sd"> ... # display image</span> |
| <span class="sd"> >>> # or let draw_next display using cv2 module</span> |
| <span class="sd"> >>> for image in iterator.draw_next(waitKey=0, window_name='disp'):</span> |
| <span class="sd"> ... pass</span> |
| <span class="sd"> """</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">cv2</span> |
| <span class="k">except</span> <span class="ne">ImportError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s1">'Unable to import cv2, skip drawing: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">))</span> |
| <span class="k">raise</span> <span class="ne">StopIteration</span> |
| <span class="n">count</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="k">while</span> <span class="bp">True</span><span class="p">:</span> |
| <span class="n">label</span><span class="p">,</span> <span class="n">s</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">next_sample</span><span class="p">()</span> |
| <span class="n">data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">imdecode</span><span class="p">(</span><span class="n">s</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">check_valid_image</span><span class="p">([</span><span class="n">data</span><span class="p">])</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parse_label</span><span class="p">(</span><span class="n">label</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">RuntimeError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">'Invalid image, skipping: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">))</span> |
| <span class="k">continue</span> |
| <span class="n">count</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="n">data</span><span class="p">,</span> <span class="n">label</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">augmentation_transform</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span> |
| <span class="n">image</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">()</span> |
| |
| <span class="c1"># revert color_normalize</span> |
| <span class="k">if</span> <span class="n">std</span> <span class="ow">is</span> <span class="bp">True</span><span class="p">:</span> |
| <span class="n">std</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">58.395</span><span class="p">,</span> <span class="mf">57.12</span><span class="p">,</span> <span class="mf">57.375</span><span class="p">])</span> |
| <span class="k">elif</span> <span class="n">std</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">std</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">)</span> <span class="ow">and</span> <span class="n">std</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">in</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">std</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span> |
| <span class="n">image</span> <span class="o">*=</span> <span class="n">std</span> |
| |
| <span class="k">if</span> <span class="n">mean</span> <span class="ow">is</span> <span class="bp">True</span><span class="p">:</span> |
| <span class="n">mean</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">123.68</span><span class="p">,</span> <span class="mf">116.28</span><span class="p">,</span> <span class="mf">103.53</span><span class="p">])</span> |
| <span class="k">elif</span> <span class="n">mean</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">mean</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">)</span> <span class="ow">and</span> <span class="n">mean</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">in</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">mean</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span> |
| <span class="n">image</span> <span class="o">+=</span> <span class="n">mean</span> |
| |
| <span class="c1"># swap RGB</span> |
| <span class="n">image</span><span class="p">[:,</span> <span class="p">:,</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">)]</span> <span class="o">=</span> <span class="n">image</span><span class="p">[:,</span> <span class="p">:,</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">)]</span> |
| <span class="k">if</span> <span class="n">clip</span><span class="p">:</span> |
| <span class="n">image</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">maximum</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">minimum</span><span class="p">(</span><span class="mi">255</span><span class="p">,</span> <span class="n">image</span><span class="p">))</span> |
| <span class="k">if</span> <span class="n">color</span><span class="p">:</span> |
| <span class="n">color</span> <span class="o">=</span> <span class="n">color</span><span class="p">[::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> |
| <span class="n">image</span> <span class="o">=</span> <span class="n">image</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span> |
| <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">image</span><span class="o">.</span><span class="n">shape</span> |
| <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">label</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]):</span> |
| <span class="n">x1</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">label</span><span class="p">[</span><span class="n">i</span><span class="p">,</span> <span class="mi">1</span><span class="p">]</span> <span class="o">*</span> <span class="n">width</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">x1</span> <span class="o"><</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">continue</span> |
| <span class="n">y1</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">label</span><span class="p">[</span><span class="n">i</span><span class="p">,</span> <span class="mi">2</span><span class="p">]</span> <span class="o">*</span> <span class="n">height</span><span class="p">)</span> |
| <span class="n">x2</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">label</span><span class="p">[</span><span class="n">i</span><span class="p">,</span> <span class="mi">3</span><span class="p">]</span> <span class="o">*</span> <span class="n">width</span><span class="p">)</span> |
| <span class="n">y2</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">label</span><span class="p">[</span><span class="n">i</span><span class="p">,</span> <span class="mi">4</span><span class="p">]</span> <span class="o">*</span> <span class="n">height</span><span class="p">)</span> |
| <span class="n">bc</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">3</span><span class="p">)</span> <span class="o">*</span> <span class="mi">255</span> <span class="k">if</span> <span class="ow">not</span> <span class="n">color</span> <span class="k">else</span> <span class="n">color</span> |
| <span class="n">cv2</span><span class="o">.</span><span class="n">rectangle</span><span class="p">(</span><span class="n">image</span><span class="p">,</span> <span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">y1</span><span class="p">),</span> <span class="p">(</span><span class="n">x2</span><span class="p">,</span> <span class="n">y2</span><span class="p">),</span> <span class="n">bc</span><span class="p">,</span> <span class="n">thickness</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">waitKey</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span> |
| <span class="n">cv2</span><span class="o">.</span><span class="n">imshow</span><span class="p">(</span><span class="n">window_name</span><span class="p">,</span> <span class="n">image</span><span class="p">)</span> |
| <span class="n">cv2</span><span class="o">.</span><span class="n">waitKey</span><span class="p">(</span><span class="n">waitKey</span><span class="p">)</span> |
| <span class="k">yield</span> <span class="n">image</span> |
| <span class="k">except</span> <span class="ne">StopIteration</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">count</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">StopIteration</span></div> |
| |
| <div class="viewcode-block" id="ImageDetIter.sync_label_shape"><a class="viewcode-back" href="../../../api/python/image/image.html#mxnet.image.ImageDetIter.sync_label_shape">[docs]</a> <span class="k">def</span> <span class="nf">sync_label_shape</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">it</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="bp">False</span><span class="p">):</span> |
| <span class="sd">"""Synchronize label shape with the input iterator. This is useful when</span> |
| <span class="sd"> train/validation iterators have different label padding.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> it : ImageDetIter</span> |
| <span class="sd"> The other iterator to synchronize</span> |
| <span class="sd"> verbose : bool</span> |
| <span class="sd"> Print verbose log if true</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> ImageDetIter</span> |
| <span class="sd"> The synchronized other iterator, the internal label shape is updated as well.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> train_iter = mx.image.ImageDetIter(32, (3, 300, 300), path_imgrec='train.rec')</span> |
| <span class="sd"> >>> val_iter = mx.image.ImageDetIter(32, (3, 300, 300), path.imgrec='val.rec')</span> |
| <span class="sd"> >>> train_iter.label_shape</span> |
| <span class="sd"> (30, 6)</span> |
| <span class="sd"> >>> val_iter.label_shape</span> |
| <span class="sd"> (25, 6)</span> |
| <span class="sd"> >>> val_iter = train_iter.sync_label_shape(val_iter, verbose=False)</span> |
| <span class="sd"> >>> train_iter.label_shape</span> |
| <span class="sd"> (30, 6)</span> |
| <span class="sd"> >>> val_iter.label_shape</span> |
| <span class="sd"> (30, 6)</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">it</span><span class="p">,</span> <span class="n">ImageDetIter</span><span class="p">),</span> <span class="s1">'Synchronize with invalid iterator.'</span> |
| <span class="n">train_label_shape</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">label_shape</span> |
| <span class="n">val_label_shape</span> <span class="o">=</span> <span class="n">it</span><span class="o">.</span><span class="n">label_shape</span> |
| <span class="k">assert</span> <span class="n">train_label_shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="n">val_label_shape</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="s2">"object width mismatch."</span> |
| <span class="n">max_count</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="n">train_label_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">val_label_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="k">if</span> <span class="n">max_count</span> <span class="o">></span> <span class="n">train_label_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="bp">None</span><span class="p">,</span> <span class="p">(</span><span class="n">max_count</span><span class="p">,</span> <span class="n">train_label_shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]))</span> |
| <span class="k">if</span> <span class="n">max_count</span> <span class="o">></span> <span class="n">val_label_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span> |
| <span class="n">it</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="bp">None</span><span class="p">,</span> <span class="p">(</span><span class="n">max_count</span><span class="p">,</span> <span class="n">val_label_shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]))</span> |
| <span class="k">if</span> <span class="n">verbose</span> <span class="ow">and</span> <span class="n">max_count</span> <span class="o">></span> <span class="nb">min</span><span class="p">(</span><span class="n">train_label_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">val_label_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]):</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Resized label_shape to (</span><span class="si">%d</span><span class="s1">, </span><span class="si">%d</span><span class="s1">).'</span><span class="p">,</span> <span class="n">max_count</span><span class="p">,</span> <span class="n">train_label_shape</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> |
| <span class="k">return</span> <span class="n">it</span></div></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 type="text/javascript"> |
| $('body').ready(function () { |
| $('body').css('visibility', 'visible'); |
| }); |
| </script> |
| </body> |
| </html> |
