HyperImageAugment

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1"> <meta name="description" content="Keras documentation"> <meta name="author" content="Keras Team"> <link rel="shortcut icon" href="https://keras.io/img/favicon.ico"> <link rel="canonical" href="https://keras.io/api/keras_tuner/hypermodels/hyper_image_augment/" />  <meta property="og:title" content="Keras documentation: HyperImageAugment"> <meta property="og:image" content="https://keras.io/img/logo-k-keras-wb.png"> <meta name="twitter:title" content="Keras documentation: HyperImageAugment"> <meta name="twitter:image" content="https://keras.io/img/k-keras-social.png"> <meta name="twitter:card" content="summary"> <title>HyperImageAugment</title>  <link href="/css/bootstrap.min.css" rel="stylesheet">  <link href="https://fonts.googleapis.com/css2?family=Open+Sans:wght@400;600;700;800&display=swap" rel="stylesheet">  <link href="/css/docs.css" rel="stylesheet"> <link href="/css/monokai.css" rel="stylesheet">  <script>(function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start': new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0], j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src= 'https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f); })(window,document,'script','dataLayer','GTM-5DNGF4N'); </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-175165319-128', 'auto'); ga('send', 'pageview'); </script>  <script async defer src="https://buttons.github.io/buttons.js"></script> </head> <body>  <noscript><iframe src="https://www.googletagmanager.com/ns.html?id=GTM-5DNGF4N" height="0" width="0" style="display:none;visibility:hidden"></iframe></noscript>  <div class='k-page'> <div class="k-nav" id="nav-menu"> <a href='/'><img src='/img/logo-small.png' class='logo-small' /></a> <div class="nav flex-column nav-pills" role="tablist" aria-orientation="vertical"> <a class="nav-link" href="/about/" role="tab" aria-selected="">About Keras</a> <a class="nav-link" href="/getting_started/" role="tab" aria-selected="">Getting started</a> <a class="nav-link" href="/guides/" role="tab" aria-selected="">Developer guides</a> <a class="nav-link active" href="/api/" role="tab" aria-selected="">Keras 3 API documentation</a> <a class="nav-sublink" href="/api/models/">Models API</a> <a class="nav-sublink" href="/api/layers/">Layers API</a> <a class="nav-sublink" href="/api/callbacks/">Callbacks API</a> <a class="nav-sublink" href="/api/ops/">Ops API</a> <a class="nav-sublink" href="/api/optimizers/">Optimizers</a> <a class="nav-sublink" href="/api/metrics/">Metrics</a> <a class="nav-sublink" href="/api/losses/">Losses</a> <a class="nav-sublink" href="/api/data_loading/">Data loading</a> <a class="nav-sublink" href="/api/datasets/">Built-in small datasets</a> <a class="nav-sublink" href="/api/applications/">Keras Applications</a> <a class="nav-sublink" href="/api/mixed_precision/">Mixed precision</a> <a class="nav-sublink" href="/api/distribution/">Multi-device distribution</a> <a class="nav-sublink" href="/api/random/">RNG API</a> <a class="nav-sublink" href="/api/utils/">Utilities</a> <a class="nav-sublink active" href="/api/keras_tuner/">KerasTuner</a> <a class="nav-sublink2" href="/api/keras_tuner/hyperparameters/">HyperParameters</a> <a class="nav-sublink2" href="/api/keras_tuner/tuners/">Tuners</a> <a class="nav-sublink2" href="/api/keras_tuner/oracles/">Oracles</a> <a class="nav-sublink2 active" href="/api/keras_tuner/hypermodels/">HyperModels</a> <a class="nav-sublink2" href="/api/keras_tuner/errors/">Errors</a> <a class="nav-sublink" href="/api/keras_cv/">KerasCV</a> <a class="nav-sublink" href="/api/keras_nlp/">KerasNLP</a> <a class="nav-sublink" href="/api/keras_hub/">KerasHub</a> <a class="nav-link" href="/2.18/api/" role="tab" aria-selected="">Keras 2 API documentation</a> <a class="nav-link" href="/examples/" role="tab" aria-selected="">Code examples</a> <a class="nav-link" href="/keras_tuner/" role="tab" aria-selected="">KerasTuner: Hyperparameter Tuning</a> <a class="nav-link" href="/keras_hub/" role="tab" aria-selected="">KerasHub: Pretrained Models</a> <a class="nav-link" href="/keras_cv/" role="tab" aria-selected="">KerasCV: Computer Vision Workflows</a> <a class="nav-link" href="/keras_nlp/" role="tab" aria-selected="">KerasNLP: Natural Language Workflows</a> </div> </div> <div class='k-main'> <div class='k-main-top'> <script> function displayDropdownMenu() { e = document.getElementById("nav-menu"); if (e.style.display == "block") { e.style.display = "none"; } else { e.style.display = "block"; document.getElementById("dropdown-nav").style.display = "block"; } } function resetMobileUI() { if (window.innerWidth <= 840) { document.getElementById("nav-menu").style.display = "none"; document.getElementById("dropdown-nav").style.display = "block"; } else { document.getElementById("nav-menu").style.display = "block"; document.getElementById("dropdown-nav").style.display = "none"; } var navmenu = document.getElementById("nav-menu"); var menuheight = navmenu.clientHeight; var kmain = document.getElementById("k-main-id"); kmain.style.minHeight = (menuheight + 100) + 'px'; } window.onresize = resetMobileUI; window.addEventListener("load", (event) => { resetMobileUI() }); </script> <div id='dropdown-nav' onclick="displayDropdownMenu();"> <svg viewBox="-20 -20 120 120" width="60" height="60"> <rect width="100" height="20"></rect> <rect y="30" width="100" height="20"></rect> <rect y="60" width="100" height="20"></rect> </svg> </div> <form class="bd-search d-flex align-items-center k-search-form" id="search-form"> <input type="search" class="k-search-input" id="search-input" placeholder="Search Keras documentation..." aria-label="Search Keras documentation..." autocomplete="off"> <button class="k-search-btn"> <svg width="13" height="13" viewBox="0 0 13 13"><title>search</title><path d="m4.8495 7.8226c0.82666 0 1.5262-0.29146 2.0985-0.87438 0.57232-0.58292 0.86378-1.2877 0.87438-2.1144 0.010599-0.82666-0.28086-1.5262-0.87438-2.0985-0.59352-0.57232-1.293-0.86378-2.0985-0.87438-0.8055-0.010599-1.5103 0.28086-2.1144 0.87438-0.60414 0.59352-0.8956 1.293-0.87438 2.0985 0.021197 0.8055 0.31266 1.5103 0.87438 2.1144 0.56172 0.60414 1.2665 0.8956 2.1144 0.87438zm4.4695 0.2115 3.681 3.6819-1.259 1.284-3.6817-3.7 0.0019784-0.69479-0.090043-0.098846c-0.87973 0.76087-1.92 1.1413-3.1207 1.1413-1.3553 0-2.5025-0.46363-3.4417-1.3909s-1.4088-2.0686-1.4088-3.4239c0-1.3553 0.4696-2.4966 1.4088-3.4239 0.9392-0.92727 2.0864-1.3969 3.4417-1.4088 1.3553-0.011889 2.4906 0.45771 3.406 1.4088 0.9154 0.95107 1.379 2.0924 1.3909 3.4239 0 1.2126-0.38043 2.2588-1.1413 3.1385l0.098834 0.090049z"></path></svg> </button> </form> <script> var form = document.getElementById('search-form'); form.onsubmit = function(e) { e.preventDefault(); var query = document.getElementById('search-input').value; window.location.href = '/search.html?query=' + query; return False } </script> </div> <div class='k-main-inner' id='k-main-id'> <div class='k-location-slug'> <span class="k-location-slug-pointer">►</span> <a href='/api/'>Keras 3 API documentation</a> / <a href='/api/keras_tuner/'>KerasTuner</a> / <a href='/api/keras_tuner/hypermodels/'>HyperModels</a> / HyperImageAugment </div> <div class='k-content'> <h1 id="hyperimageaugment">HyperImageAugment</h1> <p><span style="float:right;"><a href="https://github.com/keras-team/keras-tuner/tree/v1.4.7/keras_tuner/src/applications/augment.py#L69">[source]</a></span></p> <h3 id="hyperimageaugment-class"><code>HyperImageAugment</code> class</h3> <div class="codehilite"><pre><span></span><code><span class="n">keras_tuner</span><span class="o">.</span><span class="n">applications</span><span class="o">.</span><span class="n">HyperImageAugment</span><span class="p">(</span> <span class="n">input_shape</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">input_tensor</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">rotate</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">translate_x</span><span class="o">=</span><span class="mf">0.4</span><span class="p">,</span> <span class="n">translate_y</span><span class="o">=</span><span class="mf">0.4</span><span class="p">,</span> <span class="n">contrast</span><span class="o">=</span><span class="mf">0.3</span><span class="p">,</span> <span class="n">augment_layers</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span> <span class="p">)</span> </code></pre></div> <p>A image augmentation hypermodel.</p> <p>The <code>HyperImageAugment</code> class searches for the best combination of image augmentation operations in Keras preprocessing layers. The input shape of the model should be (height, width, channels). The output of the model is of the same shape as the input.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>input_shape</strong>: Optional shape tuple, e.g. <code>(256, 256, 3)</code>.</li> <li><strong>input_tensor</strong>: Optional Keras tensor (i.e. output of <code>layers.Input()</code>) to use as image input for the model.</li> <li><strong>rotate</strong>: A number between [0, 1], a list of two numbers between [0, 1] or None. Configures the search space of the factor of random rotation transform in the augmentation. A factor is chosen for each trial. It sets maximum of clockwise and counterclockwise rotation in terms of fraction of pi, among all samples in the trial. Default is 0.5. When <code>rotate</code> is a single number, the search range is [0, <code>rotate</code>]. The transform is off when set to None.</li> <li><strong>translate_x</strong>: A number between [0, 1], a list of two numbers between [0, 1] or None. Configures the search space of the factor of random horizontal translation transform in the augmentation. A factor is chosen for each trial. It sets maximum of horizontal translation in terms of ratio over the width among all samples in the trial. Default is 0.4. When <code>translate_x</code> is a single number, the search range is [0, <code>translate_x</code>]. The transform is off when set to None.</li> <li><strong>translate_y</strong>: A number between [0, 1], a list of two numbers between [0, 1] or None. Configures the search space of the factor of random vertical translation transform in the augmentation. A factor is chosen for each trial. It sets maximum of vertical translation in terms of ratio over the height among all samples in the trial. Default is 0.4. When <code>translate_y</code> is a single number ,the search range is [0, <code>translate_y</code>]. The transform is off when set to None.</li> <li><strong>contrast</strong>: A number between [0, 1], a list of two numbers between [0, 1] or None. Configures the search space of the factor of random contrast transform in the augmentation. A factor is chosen for each trial. It sets maximum ratio of contrast change among all samples in the trial. Default is 0.3. When <code>contrast</code> is a single number, the search rnage is [0, <code>contrast</code>]. The transform is off when set to None.</li> <li><strong>augment_layers</strong>: None, int or list of two ints, controlling the number of augment applied. Default is 3. When <code>augment_layers</code> is 0, all transform are applied sequentially. When <code>augment_layers</code> is nonzero, or a list of two ints, a simple version of RandAugment(https://arxiv.org/abs/1909.13719) is used. A search space for 'augment_layers' is created to search [0, <code>augment_layers</code>], or between the two ints if a <code>augment_layers</code> is a list. For each trial, the hyperparameter 'augment_layers' determines number of layers of augment transforms are applied, each randomly picked from all available transform types with equal probability on each sample.</li> <li><strong>**kwargs</strong>: Additional keyword arguments that apply to all hypermodels. See <a href="/api/keras_tuner/hypermodels/base_hypermodel#hypermodel-class"><code>keras_tuner.HyperModel</code></a>.</li> </ul> <p><strong>Example</strong></p> <div class="codehilite"><pre><span></span><code><span class="n">hm_aug</span> <span class="o">=</span> <span class="n">HyperImageAugment</span><span class="p">(</span><span class="n">input_shape</span><span class="o">=</span><span class="p">(</span><span class="mi">32</span><span class="p">,</span> <span class="mi">32</span><span class="p">,</span> <span class="mi">3</span><span class="p">),</span> <span class="n">augment_layers</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">rotate</span><span class="o">=</span><span class="p">[</span><span class="mf">0.2</span><span class="p">,</span> <span class="mf">0.3</span><span class="p">],</span> <span class="n">translate_x</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">translate_y</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">contrast</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> </code></pre></div> <p>Then the hypermodel <code>hm_aug</code> will search 'factor_rotate' between [0.2, 0.3] and 'factor_translate_x' between [0, 0.1]. These two augments are applied on all samples with factor picked per each trial.</p> <div class="codehilite"><pre><span></span><code><span class="n">hm_aug</span> <span class="o">=</span> <span class="n">HyperImageAugment</span><span class="p">(</span><span class="n">input_shape</span><span class="o">=</span><span class="p">(</span><span class="mi">32</span><span class="p">,</span> <span class="mi">32</span><span class="p">,</span> <span class="mi">3</span><span class="p">),</span> <span class="n">translate_x</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">translate_y</span><span class="o">=</span><span class="p">[</span><span class="mf">0.2</span><span class="p">,</span> <span class="mf">0.4</span><span class="p">]</span> <span class="n">contrast</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> </code></pre></div> <p>Then the hypermodel <code>hm_aug</code> will search 'factor_rotate' between [0, 0.2], 'factor_translate_x' between [0, 0.5], 'factor_translate_y' between [0.2, 0.4]. It will use RandAugment, searching 'augment_layers' between [0, 3]. Each layer on each sample will be chosen from rotate, translate_x and translate_y.</p> <hr /> </div> <div class='k-outline'> <div class='k-outline-depth-1'> <a href='#hyperimageaugment'>HyperImageAugment</a> </div> <div class='k-outline-depth-3'> <a href='#hyperimageaugment-class'><code>HyperImageAugment</code> class</a> </div> </div> </div> </div> </div> </body> <footer style="float: left; width: 100%; padding: 1em; border-top: solid 1px #bbb;"> <a href="https://policies.google.com/terms">Terms</a> | <a href="https://policies.google.com/privacy">Privacy</a> </footer> </html>

CINXE.COM

HyperImageAugment