index_en.html



<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
  <meta charset="utf-8">
  
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  
  <title>Image Classification Tutorial &mdash; PaddlePaddle  documentation</title>
  

    <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
  

        <link rel="index" title="Index"
              href="../../genindex.html"/>
        <link rel="search" title="Search" href="../../search.html"/>
    <link rel="top" title="PaddlePaddle  documentation" href="../../index.html"/> 

  <link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
  <link rel="stylesheet" href="../../_static/css/override.css" type="text/css" />
  <script>
  var _hmt = _hmt || [];
  (function() {
    var hm = document.createElement("script");
    hm.src = "//hm.baidu.com/hm.js?b9a314ab40d04d805655aab1deee08ba";
    var s = document.getElementsByTagName("script")[0]; 
    s.parentNode.insertBefore(hm, s);
  })();
  </script>

  
  <script src="../../_static/js/modernizr.min.js"></script>

</head>

<body class="wy-body-for-nav" role="document">

  
  <header class="site-header">
    <div class="site-logo">
      <a href="/"><img src="../../_static/images/PP_w.png"></a>
    </div>
    <div class="site-nav-links">
      <div class="site-menu">
        <a class="fork-on-github" href="https://github.com/PaddlePaddle/Paddle" target="_blank"><i class="fa fa-github"></i>Folk me on Github</a>
        <div class="language-switcher dropdown">
          <a type="button" data-toggle="dropdown">
            <span>English</span>
            <i class="fa fa-angle-up"></i>
            <i class="fa fa-angle-down"></i>
          </a>
          <ul class="dropdown-menu">
            <li><a href="/doc_cn">中文</a></li>
            <li><a href="/doc">English</a></li>
          </ul>
        </div>
        <ul class="site-page-links">
          <li><a href="/">Home</a></li>
        </ul>
      </div>
      <div class="doc-module">
        
        <ul>
<li class="toctree-l1"><a class="reference internal" href="../../getstarted/index_en.html">GET STARTED</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../howto/index_en.html">HOW TO</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/index_en.html">API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../about/index_en.html">ABOUT</a></li>
</ul>

        
<div role="search">
  <form id="rtd-search-form" class="wy-form" action="../../search.html" method="get">
    <input type="text" name="q" placeholder="Search docs" />
    <input type="hidden" name="check_keywords" value="yes" />
    <input type="hidden" name="area" value="default" />
  </form>
</div>        
      </div>
    </div>
  </header>
  
  <div class="main-content-wrap">

    
    <nav class="doc-menu-vertical" role="navigation">
        
          
          <ul>
<li class="toctree-l1"><a class="reference internal" href="../../getstarted/index_en.html">GET STARTED</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../getstarted/build_and_install/index_en.html">Install and Build</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../getstarted/build_and_install/docker_install_en.html">PaddlePaddle in Docker Containers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../getstarted/build_and_install/ubuntu_install_en.html">Debian Package installation guide</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../getstarted/build_and_install/build_from_source_en.html">Installing from Sources</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../howto/index_en.html">HOW TO</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/cmd_parameter/index_en.html">Set Command-line Parameters</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cmd_parameter/use_case_en.html">Use Case</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cmd_parameter/arguments_en.html">Argument Outline</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cmd_parameter/detail_introduction_en.html">Detail Description</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/cluster/cluster_train_en.html">Run Distributed Training</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_en.html">Paddle On Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../api/index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../api/v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/data.html">Data Reader Interface and DataSets</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../api/v2/run_logic.html">Training and Inference</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../about/index_en.html">ABOUT</a></li>
</ul>

        
    </nav>
    
    <section class="doc-content-wrap">

      
<div role="navigation" aria-label="breadcrumbs navigation">
  <ul class="wy-breadcrumbs">
      
    <li>Image Classification Tutorial</li>
  </ul>
</div>
      
      <div class="wy-nav-content" id="doc-content">
        <div class="rst-content">
          <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
           <div itemprop="articleBody">
            
  <div class="section" id="image-classification-tutorial">
<span id="image-classification-tutorial"></span><h1>Image Classification Tutorial<a class="headerlink" href="#image-classification-tutorial" title="Permalink to this headline">¶</a></h1>
<p>This tutorial will guide you through training a convolutional neural network to classify objects using the CIFAR-10 image classification dataset.
As shown in the following figure, the convolutional neural network can recognize the main object in images, and output the classification result.</p>
<p><center><img alt="Image Classification" src="../../_images/image_classification.png" /></center></p>
<div class="section" id="data-preparation">
<span id="data-preparation"></span><h2>Data Preparation<a class="headerlink" href="#data-preparation" title="Permalink to this headline">¶</a></h2>
<p>First, download CIFAR-10 dataset. CIFAR-10 dataset can be downloaded from its official website.</p>
<p><a class="reference external" href="https://www.cs.toronto.edu/~kriz/cifar.html">https://www.cs.toronto.edu/~kriz/cifar.html</a></p>
<p>We have prepared a script to download and process CIFAR-10 dataset. The script will download CIFAR-10 dataset from the official dataset.
It will convert it to jpeg images and organize them into a directory with the required structure for the tutorial. Make sure that you have installed pillow and its dependents.
Consider the following commands:</p>
<ol class="simple">
<li>install pillow dependents</li>
</ol>
<div class="highlight-bash"><div class="highlight"><pre><span></span>sudo apt-get install libjpeg-dev
pip install pillow
</pre></div>
</div>
<ol class="simple">
<li>download data and preparation</li>
</ol>
<div class="highlight-bash"><div class="highlight"><pre><span></span><span class="nb">cd</span> demo/image_classification/data/
sh download_cifar.sh
</pre></div>
</div>
<p>The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.</p>
<p>Here are the classes in the dataset, as well as 10 random images from each:
<center><img alt="Image Classification" src="../../_images/cifar.png" /></center></p>
<p>After downloading and converting, we should find a directory (cifar-out) containing the dataset in the following format:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">train</span>
<span class="o">---</span><span class="n">airplane</span>
<span class="o">---</span><span class="n">automobile</span>
<span class="o">---</span><span class="n">bird</span>
<span class="o">---</span><span class="n">cat</span>
<span class="o">---</span><span class="n">deer</span>
<span class="o">---</span><span class="n">dog</span>
<span class="o">---</span><span class="n">frog</span>
<span class="o">---</span><span class="n">horse</span>
<span class="o">---</span><span class="n">ship</span>
<span class="o">---</span><span class="n">truck</span>
<span class="n">test</span>
<span class="o">---</span><span class="n">airplane</span>
<span class="o">---</span><span class="n">automobile</span>
<span class="o">---</span><span class="n">bird</span>
<span class="o">---</span><span class="n">cat</span>
<span class="o">---</span><span class="n">deer</span>
<span class="o">---</span><span class="n">dog</span>
<span class="o">---</span><span class="n">frog</span>
<span class="o">---</span><span class="n">horse</span>
<span class="o">---</span><span class="n">ship</span>
<span class="o">---</span><span class="n">truck</span>
</pre></div>
</div>
<p>It has two directories:<code class="docutils literal"><span class="pre">train</span></code> and <code class="docutils literal"><span class="pre">test</span></code>. These two directories contain training data and testing data of CIFAR-10, respectively. Each of these two folders contains 10 sub-folders, ranging from <code class="docutils literal"><span class="pre">airplane</span></code> to <code class="docutils literal"><span class="pre">truck</span></code>. Each sub-folder contains images with the corresponding label. After the images are organized into this structure, we are ready to train an image classification model.</p>
</div>
<div class="section" id="preprocess">
<span id="preprocess"></span><h2>Preprocess<a class="headerlink" href="#preprocess" title="Permalink to this headline">¶</a></h2>
<p>After the data has been downloaded, it needs to be pre-processed into the Paddle format. We can run the following command for preprocessing.</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">cd</span> <span class="n">demo</span><span class="o">/</span><span class="n">image_classification</span><span class="o">/</span>
<span class="n">sh</span> <span class="n">preprocess</span><span class="o">.</span><span class="n">sh</span>
</pre></div>
</div>
<p><code class="docutils literal"><span class="pre">preprocess.sh</span></code> calls <code class="docutils literal"><span class="pre">./demo/image_classification/preprocess.py</span></code> to preprocess image data.</p>
<div class="highlight-sh"><div class="highlight"><pre><span></span><span class="nb">export</span> <span class="nv">PYTHONPATH</span><span class="o">=</span><span class="nv">$PYTHONPATH</span>:../../
<span class="nv">data_dir</span><span class="o">=</span>./data/cifar-out
python preprocess.py -i <span class="nv">$data_dir</span> -s <span class="m">32</span> -c <span class="m">1</span>
</pre></div>
</div>
<p><code class="docutils literal"><span class="pre">./demo/image_classification/preprocess.py</span></code> has the following arguments</p>
<ul class="simple">
<li><code class="docutils literal"><span class="pre">-i</span></code> or <code class="docutils literal"><span class="pre">--input</span></code> specifes  the input data directory.</li>
<li><code class="docutils literal"><span class="pre">-s</span></code> or <code class="docutils literal"><span class="pre">--size</span></code> specifies the processed size of images.</li>
<li><code class="docutils literal"><span class="pre">-c</span></code> or <code class="docutils literal"><span class="pre">--color</span></code> specifes whether images are color images or gray images.</li>
</ul>
</div>
<div class="section" id="model-training">
<span id="model-training"></span><h2>Model Training<a class="headerlink" href="#model-training" title="Permalink to this headline">¶</a></h2>
<p>We need to create a model config file before training the model. An example of the config file (vgg_16_cifar.py) is listed below. <strong>Note</strong>, it is slightly different from the <code class="docutils literal"><span class="pre">vgg_16_cifar.py</span></code> which also applies to the prediction.</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">paddle.trainer_config_helpers</span> <span class="kn">import</span> <span class="o">*</span>
<span class="n">data_dir</span><span class="o">=</span><span class="s1">&#39;data/cifar-out/batches/&#39;</span>
<span class="n">meta_path</span><span class="o">=</span><span class="n">data_dir</span><span class="o">+</span><span class="s1">&#39;batches.meta&#39;</span>
<span class="n">args</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;meta&#39;</span><span class="p">:</span><span class="n">meta_path</span><span class="p">,</span> <span class="s1">&#39;mean_img_size&#39;</span><span class="p">:</span> <span class="mi">32</span><span class="p">,</span>
        <span class="s1">&#39;img_size&#39;</span><span class="p">:</span> <span class="mi">32</span><span class="p">,</span> <span class="s1">&#39;num_classes&#39;</span><span class="p">:</span> <span class="mi">10</span><span class="p">,</span>
        <span class="s1">&#39;use_jpeg&#39;</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span> <span class="s1">&#39;color&#39;</span><span class="p">:</span> <span class="s2">&quot;color&quot;</span><span class="p">}</span>
<span class="n">define_py_data_sources2</span><span class="p">(</span><span class="n">train_list</span><span class="o">=</span><span class="n">data_dir</span><span class="o">+</span><span class="s2">&quot;train.list&quot;</span><span class="p">,</span>
                        <span class="n">test_list</span><span class="o">=</span><span class="n">data_dir</span><span class="o">+</span><span class="s1">&#39;test.list&#39;</span><span class="p">,</span>
                        <span class="n">module</span><span class="o">=</span><span class="s1">&#39;image_provider&#39;</span><span class="p">,</span>
                        <span class="n">obj</span><span class="o">=</span><span class="s1">&#39;processData&#39;</span><span class="p">,</span>
                        <span class="n">args</span><span class="o">=</span><span class="n">args</span><span class="p">)</span>
<span class="n">settings</span><span class="p">(</span>
    <span class="n">batch_size</span> <span class="o">=</span> <span class="mi">128</span><span class="p">,</span>
    <span class="n">learning_rate</span> <span class="o">=</span> <span class="mf">0.1</span> <span class="o">/</span> <span class="mf">128.0</span><span class="p">,</span>
    <span class="n">learning_method</span> <span class="o">=</span> <span class="n">MomentumOptimizer</span><span class="p">(</span><span class="mf">0.9</span><span class="p">),</span>
    <span class="n">regularization</span> <span class="o">=</span> <span class="n">L2Regularization</span><span class="p">(</span><span class="mf">0.0005</span> <span class="o">*</span> <span class="mi">128</span><span class="p">))</span>

<span class="n">img</span> <span class="o">=</span> <span class="n">data_layer</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;image&#39;</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">3</span><span class="o">*</span><span class="mi">32</span><span class="o">*</span><span class="mi">32</span><span class="p">)</span>
<span class="n">lbl</span> <span class="o">=</span> <span class="n">data_layer</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s2">&quot;label&quot;</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span>
<span class="c1"># small_vgg is predined in trainer_config_helpers.network</span>
<span class="n">predict</span> <span class="o">=</span> <span class="n">small_vgg</span><span class="p">(</span><span class="n">input_image</span><span class="o">=</span><span class="n">img</span><span class="p">,</span> <span class="n">num_channels</span><span class="o">=</span><span class="mi">3</span><span class="p">)</span>
<span class="n">outputs</span><span class="p">(</span><span class="n">classification_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">predict</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="n">lbl</span><span class="p">))</span>
</pre></div>
</div>
<p>The first line imports python functions for defining networks.</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">paddle.trainer_config_helpers</span> <span class="kn">import</span> <span class="o">*</span>
</pre></div>
</div>
<p>Then define an <code class="docutils literal"><span class="pre">define_py_data_sources2</span></code> which use python data provider
interface. The arguments in <code class="docutils literal"><span class="pre">args</span></code> are used in <code class="docutils literal"><span class="pre">image_provider.py</span></code> which
yeilds image data and transform them to Paddle.</p>
<ul class="simple">
<li><code class="docutils literal"><span class="pre">meta</span></code>: the mean value of training set.</li>
<li><code class="docutils literal"><span class="pre">mean_img_size</span></code>: the size of mean feature map.</li>
<li><code class="docutils literal"><span class="pre">img_size</span></code>: the height and width of input image.</li>
<li><code class="docutils literal"><span class="pre">num_classes</span></code>: the number of classes.</li>
<li><code class="docutils literal"><span class="pre">use_jpeg</span></code>: the data storage type when preprocessing.</li>
<li><code class="docutils literal"><span class="pre">color</span></code>: specify color image.</li>
</ul>
<p><code class="docutils literal"><span class="pre">settings</span></code> specifies the training algorithm. In the following example,
it specifies learning rate as 0.1, but divided by batch size, and the weight decay
is 0.0005 and multiplied by batch size.</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">settings</span><span class="p">(</span>
    <span class="n">batch_size</span> <span class="o">=</span> <span class="mi">128</span><span class="p">,</span>
    <span class="n">learning_rate</span> <span class="o">=</span> <span class="mf">0.1</span> <span class="o">/</span> <span class="mf">128.0</span><span class="p">,</span>
    <span class="n">learning_method</span> <span class="o">=</span> <span class="n">MomentumOptimizer</span><span class="p">(</span><span class="mf">0.9</span><span class="p">),</span>
    <span class="n">regularization</span> <span class="o">=</span> <span class="n">L2Regularization</span><span class="p">(</span><span class="mf">0.0005</span> <span class="o">*</span> <span class="mi">128</span><span class="p">)</span>
<span class="p">)</span>
</pre></div>
</div>
<p>The <code class="docutils literal"><span class="pre">small_vgg</span></code> specifies the network. We use a small version of VGG convolutional network as our network
for classification. A description of VGG network can be found here <a class="reference external" href="http://www.robots.ox.ac.uk/~vgg/research/very_deep/">http://www.robots.ox.ac.uk/~vgg/research/very_deep/</a>.</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="c1"># small_vgg is predined in trainer_config_helpers.network</span>
<span class="n">predict</span> <span class="o">=</span> <span class="n">small_vgg</span><span class="p">(</span><span class="n">input_image</span><span class="o">=</span><span class="n">img</span><span class="p">,</span> <span class="n">num_channels</span><span class="o">=</span><span class="mi">3</span><span class="p">)</span>
</pre></div>
</div>
<p>After writing the config, we can train the model by running the script train.sh.</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span><span class="nv">config</span><span class="o">=</span>vgg_16_cifar.py
<span class="nv">output</span><span class="o">=</span>./cifar_vgg_model
<span class="nv">log</span><span class="o">=</span>train.log

paddle train <span class="se">\</span>
--config<span class="o">=</span><span class="nv">$config</span> <span class="se">\</span>
--dot_period<span class="o">=</span><span class="m">10</span> <span class="se">\</span>
--log_period<span class="o">=</span><span class="m">100</span> <span class="se">\</span>
--test_all_data_in_one_period<span class="o">=</span><span class="m">1</span> <span class="se">\</span>
--use_gpu<span class="o">=</span><span class="m">1</span> <span class="se">\</span>
--save_dir<span class="o">=</span><span class="nv">$output</span> <span class="se">\</span>
<span class="m">2</span>&gt;<span class="p">&amp;</span><span class="m">1</span> <span class="p">|</span> tee <span class="nv">$log</span>

python -m paddle.utils.plotcurve -i <span class="nv">$log</span> &gt; plot.png
</pre></div>
</div>
<ul class="simple">
<li>Here we use GPU mode to train. If you have no gpu environment, just set <code class="docutils literal"><span class="pre">use_gpu=0</span></code>.</li>
<li><code class="docutils literal"><span class="pre">./demo/image_classification/vgg_16_cifar.py</span></code> is the network and data configuration file. The meaning of the other flags can be found in the documentation of the command line flags.</li>
<li>The script <code class="docutils literal"><span class="pre">plotcurve.py</span></code> requires the python module of <code class="docutils literal"><span class="pre">matplotlib</span></code>, so if it fails, maybe you need to install <code class="docutils literal"><span class="pre">matplotlib</span></code>.</li>
</ul>
<p>After training finishes, the training and testing error curves will be saved to <code class="docutils literal"><span class="pre">plot.png</span></code> using <code class="docutils literal"><span class="pre">plotcurve.py</span></code> script. An example of the plot is shown below:</p>
<p><center><img alt="Training and testing curves." src="../../_images/plot.png" /></center></p>
</div>
<div class="section" id="prediction">
<span id="prediction"></span><h2>Prediction<a class="headerlink" href="#prediction" title="Permalink to this headline">¶</a></h2>
<p>After we train the model, the model file as well as the model parameters are stored in path <code class="docutils literal"><span class="pre">./cifar_vgg_model/pass-%05d</span></code>. For example, the model of the 300-th pass is stored at <code class="docutils literal"><span class="pre">./cifar_vgg_model/pass-00299</span></code>.</p>
<p>To make a prediction for an image, one can run <code class="docutils literal"><span class="pre">predict.sh</span></code> as follows. The script will output the label of the classfiication.</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">sh</span> <span class="n">predict</span><span class="o">.</span><span class="n">sh</span>
</pre></div>
</div>
<p>predict.sh:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span>model=cifar_vgg_model/pass-00299/
image=data/cifar-out/test/airplane/seaplane_s_000978.png
use_gpu=1
python prediction.py $model $image $use_gpu
</pre></div>
</div>
</div>
<div class="section" id="exercise">
<span id="exercise"></span><h2>Exercise<a class="headerlink" href="#exercise" title="Permalink to this headline">¶</a></h2>
<p>Train a image classification of birds using VGG model and CUB-200 dataset. The birds dataset can be downloaded here. It contains an image dataset with photos of 200 bird species (mostly North American).</p>
<p><a class="reference external" href="http://www.vision.caltech.edu/visipedia/CUB-200.html">http://www.vision.caltech.edu/visipedia/CUB-200.html</a></p>
</div>
<div class="section" id="delve-into-details">
<span id="delve-into-details"></span><h2>Delve into Details<a class="headerlink" href="#delve-into-details" title="Permalink to this headline">¶</a></h2>
<div class="section" id="convolutional-neural-network">
<span id="convolutional-neural-network"></span><h3>Convolutional Neural Network<a class="headerlink" href="#convolutional-neural-network" title="Permalink to this headline">¶</a></h3>
<p>A Convolutional Neural Network is a feedforward neural network that uses convolution layers. It is very suitable for building neural networks that process and understand images. A standard convolutional neural network is shown below:</p>
<p><img alt="Convolutional Neural Network" src="../../_images/lenet.png" /></p>
<p>Convolutional Neural Network contains the following layers:</p>
<ul class="simple">
<li>Convolutional layer: It uses convolution operation to extract features from an image or a feature map.</li>
<li>Pooling layer: It uses max-pooling to downsample feature maps.</li>
<li>Fully Connected layer: It uses fully connected connections to transform features.</li>
</ul>
<p>Convolutional Neural Network achieves amazing performance for image classification because it exploits two important characteristics of images: <em>local correlation</em> and <em>spatial invariance</em>. By iteratively applying convolution and max-pooing operations, convolutional neural network can well represent these two characteristics of images.</p>
<p>For more details of how to define layers and their connections, please refer to the documentation of layers.</p>
</div>
</div>
</div>


           </div>
          </div>
          <footer>
  

  <hr/>

  <div role="contentinfo">
    <p>
        &copy; Copyright 2016, PaddlePaddle developers.

    </p>
  </div>
  Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. 

</footer>

        </div>
      </div>

    </section>

  </div>
  

    <script type="text/javascript">
        var DOCUMENTATION_OPTIONS = {
            URL_ROOT:'../../',
            VERSION:'',
            COLLAPSE_INDEX:false,
            FILE_SUFFIX:'.html',
            HAS_SOURCE:  true,
            SOURCELINK_SUFFIX: ".txt",
        };
    </script>
      <script type="text/javascript" src="../../_static/jquery.js"></script>
      <script type="text/javascript" src="../../_static/underscore.js"></script>
      <script type="text/javascript" src="../../_static/doctools.js"></script>
      <script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
       
  
    <script type="text/javascript" src="../../_static/js/theme.js"></script>
  
  
  <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js" integrity="sha384-Tc5IQib027qvyjSMfHjOMaLkfuWVxZxUPnCJA7l2mCWNIpG9mGCD8wGNIcPD7Txa" crossorigin="anonymous"></script>
  <script src="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/js/perfect-scrollbar.jquery.min.js"></script>
  <script src="../../_static/js/paddle_doc_init.js"></script> 

</body>
</html>