Block - AutoKeras

<!doctype html> <html lang="en" class="no-js"> <head> <meta charset="utf-8"> <meta name="viewport" content="width=device-width,initial-scale=1"> <meta name="description" content="Documentation for AutoKeras."> <link rel="canonical" href="http://autokeras.com/block/"> <link rel="prev" href="../node/"> <link rel="next" href="../utils/"> <link rel="icon" href="/img/favicon.png"> <meta name="generator" content="mkdocs-1.5.3, mkdocs-material-9.5.14"> <title>Block - AutoKeras</title> <link rel="stylesheet" href="../assets/stylesheets/main.10ba22f1.min.css"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback"> <style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style> <link rel="stylesheet" href="../stylesheets/extra.css"> <script>__md_scope=new URL("..",location),__md_hash=e=>[...e].reduce((e,_)=>(e<<5)-e+_.charCodeAt(0),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script> <script id="__analytics">function __md_analytics(){function n(){dataLayer.push(arguments)}window.dataLayer=window.dataLayer||[],n("js",new Date),n("config","G-GTF9QP8DFD"),document.addEventListener("DOMContentLoaded",function(){document.forms.search&&document.forms.search.query.addEventListener("blur",function(){this.value&&n("event","search",{search_term:this.value})}),document$.subscribe(function(){var a=document.forms.feedback;if(void 0!==a)for(var e of a.querySelectorAll("[type=submit]"))e.addEventListener("click",function(e){e.preventDefault();var t=document.location.pathname,e=this.getAttribute("data-md-value");n("event","feedback",{page:t,data:e}),a.firstElementChild.disabled=!0;e=a.querySelector(".md-feedback__note [data-md-value='"+e+"']");e&&(e.hidden=!1)}),a.hidden=!1}),location$.subscribe(function(e){n("config","G-GTF9QP8DFD",{page_path:e.pathname})})});var e=document.createElement("script");e.async=!0,e.src="https://www.googletagmanager.com/gtag/js?id=G-GTF9QP8DFD",document.getElementById("__analytics").insertAdjacentElement("afterEnd",e)}</script> <script>"undefined"!=typeof __md_analytics&&__md_analytics()</script> </head> <body dir="ltr"> <input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off"> <input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off"> <label class="md-overlay" for="__drawer"></label> <div data-md-component="skip"> <a href="#convblock" class="md-skip"> Skip to content </a> </div> <div data-md-component="announce"> </div> <header class="md-header md-header--shadow" data-md-component="header"> <nav class="md-header__inner md-grid" aria-label="Header"> <a href=".." title="AutoKeras" class="md-header__button md-logo" aria-label="AutoKeras" data-md-component="logo"> <img src="/img/logo_white.svg" alt="logo"> </a> <label class="md-header__button md-icon" for="__drawer"> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3V6m0 5h18v2H3v-2m0 5h18v2H3v-2Z"/></svg> </label> <div class="md-header__title" data-md-component="header-title"> <div class="md-header__ellipsis"> <div class="md-header__topic"> <span class="md-ellipsis"> AutoKeras </span> </div> <div class="md-header__topic" data-md-component="header-topic"> <span class="md-ellipsis"> Block </span> </div> </div> </div> <script>var media,input,key,value,palette=__md_get("__palette");if(palette&&palette.color){"(prefers-color-scheme)"===palette.color.media&&(media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']"),palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent"));for([key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script> <label class="md-header__button md-icon" for="__search"> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg> </label> <div class="md-search" data-md-component="search" role="dialog"> <label class="md-search__overlay" for="__search"></label> <div class="md-search__inner" role="search"> <form class="md-search__form" name="search"> <input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required> <label class="md-search__icon md-icon" for="__search"> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z"/></svg> </label> <nav class="md-search__options" aria-label="Search"> <button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1"> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41Z"/></svg> </button> </nav> </form> <div class="md-search__output"> <div class="md-search__scrollwrap" data-md-scrollfix> <div class="md-search-result" data-md-component="search-result"> <div class="md-search-result__meta"> Initializing search </div> <ol class="md-search-result__list" role="presentation"></ol> </div> </div> </div> </div> </div> <div class="md-header__source"> <a href="https://github.com/keras-team/autokeras" title="Go to repository" class="md-source" data-md-component="source"> <div class="md-source__icon md-icon"> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg> </div> <div class="md-source__repository"> GitHub </div> </a> </div> </nav> </header> <div class="md-container" data-md-component="container"> <main class="md-main" data-md-component="main"> <div class="md-main__inner md-grid"> <div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" > <div class="md-sidebar__scrollwrap"> <div class="md-sidebar__inner"> <nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0"> <label class="md-nav__title" for="__drawer"> <a href=".." title="AutoKeras" class="md-nav__button md-logo" aria-label="AutoKeras" data-md-component="logo"> <img src="/img/logo_white.svg" alt="logo"> </a> AutoKeras </label> <div class="md-nav__source"> <a href="https://github.com/keras-team/autokeras" title="Go to repository" class="md-source" data-md-component="source"> <div class="md-source__icon md-icon"> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg> </div> <div class="md-source__repository"> GitHub </div> </a> </div> <ul class="md-nav__list" data-md-scrollfix> <li class="md-nav__item"> <a href=".." class="md-nav__link"> <span class="md-ellipsis"> Home </span> </a> </li> <li class="md-nav__item"> <a href="../install/" class="md-nav__link"> <span class="md-ellipsis"> Installation </span> </a> </li> <li class="md-nav__item md-nav__item--nested"> <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3" > <label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0"> <span class="md-ellipsis"> Tutorials </span> <span class="md-nav__icon md-icon"></span> </label> <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false"> <label class="md-nav__title" for="__nav_3"> <span class="md-nav__icon md-icon"></span> Tutorials </label> <ul class="md-nav__list" data-md-scrollfix> <li class="md-nav__item"> <a href="../tutorial/overview/" class="md-nav__link"> <span class="md-ellipsis"> Overview </span> </a> </li> <li class="md-nav__item"> <a href="../tutorial/image_classification/" class="md-nav__link"> <span class="md-ellipsis"> Image Classification </span> </a> </li> <li class="md-nav__item"> <a href="../tutorial/image_regression/" class="md-nav__link"> <span class="md-ellipsis"> Image Regression </span> </a> </li> <li class="md-nav__item"> <a href="../tutorial/text_classification/" class="md-nav__link"> <span class="md-ellipsis"> Text Classification </span> </a> </li> <li class="md-nav__item"> <a href="../tutorial/text_regression/" class="md-nav__link"> <span class="md-ellipsis"> Text Regression </span> </a> </li> <li class="md-nav__item"> <a href="../tutorial/multi/" class="md-nav__link"> <span class="md-ellipsis"> Multi-Modal and Multi-Task </span> </a> </li> <li class="md-nav__item"> <a href="../tutorial/customized/" class="md-nav__link"> <span class="md-ellipsis"> Customized Model </span> </a> </li> <li class="md-nav__item"> <a href="../tutorial/export/" class="md-nav__link"> <span class="md-ellipsis"> Export Model </span> </a> </li> <li class="md-nav__item"> <a href="../tutorial/load/" class="md-nav__link"> <span class="md-ellipsis"> Load Data from Disk </span> </a> </li> <li class="md-nav__item"> <a href="../tutorial/faq/" class="md-nav__link"> <span class="md-ellipsis"> FAQ </span> </a> </li> </ul> </nav> </li> <li class="md-nav__item md-nav__item--nested"> <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" > <label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0"> <span class="md-ellipsis"> Extensions </span> <span class="md-nav__icon md-icon"></span> </label> <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false"> <label class="md-nav__title" for="__nav_4"> <span class="md-nav__icon md-icon"></span> Extensions </label> <ul class="md-nav__list" data-md-scrollfix> <li class="md-nav__item"> <a href="../extensions/tf_cloud/" class="md-nav__link"> <span class="md-ellipsis"> TensorFlow Cloud </span> </a> </li> <li class="md-nav__item"> <a href="../extensions/trains/" class="md-nav__link"> <span class="md-ellipsis"> TRAINS </span> </a> </li> </ul> </nav> </li> <li class="md-nav__item"> <a href="../docker/" class="md-nav__link"> <span class="md-ellipsis"> Docker </span> </a> </li> <li class="md-nav__item"> <a href="../contributing/" class="md-nav__link"> <span class="md-ellipsis"> Contributing Guide </span> </a> </li> <li class="md-nav__item md-nav__item--active md-nav__item--nested"> <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" checked> <label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0"> <span class="md-ellipsis"> Documentation </span> <span class="md-nav__icon md-icon"></span> </label> <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="true"> <label class="md-nav__title" for="__nav_7"> <span class="md-nav__icon md-icon"></span> Documentation </label> <ul class="md-nav__list" data-md-scrollfix> <li class="md-nav__item"> <a href="../image_classifier/" class="md-nav__link"> <span class="md-ellipsis"> ImageClassifier </span> </a> </li> <li class="md-nav__item"> <a href="../image_regressor/" class="md-nav__link"> <span class="md-ellipsis"> ImageRegressor </span> </a> </li> <li class="md-nav__item"> <a href="../text_classifier/" class="md-nav__link"> <span class="md-ellipsis"> TextClassifier </span> </a> </li> <li class="md-nav__item"> <a href="../text_regressor/" class="md-nav__link"> <span class="md-ellipsis"> TextRegressor </span> </a> </li> <li class="md-nav__item"> <a href="../auto_model/" class="md-nav__link"> <span class="md-ellipsis"> AutoModel </span> </a> </li> <li class="md-nav__item"> <a href="../base/" class="md-nav__link"> <span class="md-ellipsis"> Base Class </span> </a> </li> <li class="md-nav__item"> <a href="../node/" class="md-nav__link"> <span class="md-ellipsis"> Node </span> </a> </li> <li class="md-nav__item md-nav__item--active"> <input class="md-nav__toggle md-toggle" type="checkbox" id="__toc"> <label class="md-nav__link md-nav__link--active" for="__toc"> <span class="md-ellipsis"> Block </span> <span class="md-nav__icon md-icon"></span> </label> <a href="./" class="md-nav__link md-nav__link--active"> <span class="md-ellipsis"> Block </span> </a> <nav class="md-nav md-nav--secondary" aria-label="Table of contents"> <label class="md-nav__title" for="__toc"> <span class="md-nav__icon md-icon"></span> Table of contents </label> <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix> <li class="md-nav__item"> <a href="#convblock" class="md-nav__link"> <span class="md-ellipsis"> ConvBlock </span> </a> </li> <li class="md-nav__item"> <a href="#denseblock" class="md-nav__link"> <span class="md-ellipsis"> DenseBlock </span> </a> </li> <li class="md-nav__item"> <a href="#merge" class="md-nav__link"> <span class="md-ellipsis"> Merge </span> </a> </li> <li class="md-nav__item"> <a href="#resnetblock" class="md-nav__link"> <span class="md-ellipsis"> ResNetBlock </span> </a> </li> <li class="md-nav__item"> <a href="#rnnblock" class="md-nav__link"> <span class="md-ellipsis"> RNNBlock </span> </a> </li> <li class="md-nav__item"> <a href="#spatialreduction" class="md-nav__link"> <span class="md-ellipsis"> SpatialReduction </span> </a> </li> <li class="md-nav__item"> <a href="#temporalreduction" class="md-nav__link"> <span class="md-ellipsis"> TemporalReduction </span> </a> </li> <li class="md-nav__item"> <a href="#xceptionblock" class="md-nav__link"> <span class="md-ellipsis"> XceptionBlock </span> </a> </li> <li class="md-nav__item"> <a href="#imageblock" class="md-nav__link"> <span class="md-ellipsis"> ImageBlock </span> </a> </li> <li class="md-nav__item"> <a href="#textblock" class="md-nav__link"> <span class="md-ellipsis"> TextBlock </span> </a> </li> <li class="md-nav__item"> <a href="#imageaugmentation" class="md-nav__link"> <span class="md-ellipsis"> ImageAugmentation </span> </a> </li> <li class="md-nav__item"> <a href="#normalization" class="md-nav__link"> <span class="md-ellipsis"> Normalization </span> </a> </li> <li class="md-nav__item"> <a href="#classificationhead" class="md-nav__link"> <span class="md-ellipsis"> ClassificationHead </span> </a> </li> <li class="md-nav__item"> <a href="#regressionhead" class="md-nav__link"> <span class="md-ellipsis"> RegressionHead </span> </a> </li> </ul> </nav> </li> <li class="md-nav__item"> <a href="../utils/" class="md-nav__link"> <span class="md-ellipsis"> Utils </span> </a> </li> </ul> </nav> </li> <li class="md-nav__item"> <a href="../benchmarks/" class="md-nav__link"> <span class="md-ellipsis"> Benchmarks </span> </a> </li> <li class="md-nav__item"> <a href="../about/" class="md-nav__link"> <span class="md-ellipsis"> About </span> </a> </li> </ul> </nav> </div> </div> </div> <div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" > <div class="md-sidebar__scrollwrap"> <div class="md-sidebar__inner"> <nav class="md-nav md-nav--secondary" aria-label="Table of contents"> <label class="md-nav__title" for="__toc"> <span class="md-nav__icon md-icon"></span> Table of contents </label> <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix> <li class="md-nav__item"> <a href="#convblock" class="md-nav__link"> <span class="md-ellipsis"> ConvBlock </span> </a> </li> <li class="md-nav__item"> <a href="#denseblock" class="md-nav__link"> <span class="md-ellipsis"> DenseBlock </span> </a> </li> <li class="md-nav__item"> <a href="#merge" class="md-nav__link"> <span class="md-ellipsis"> Merge </span> </a> </li> <li class="md-nav__item"> <a href="#resnetblock" class="md-nav__link"> <span class="md-ellipsis"> ResNetBlock </span> </a> </li> <li class="md-nav__item"> <a href="#rnnblock" class="md-nav__link"> <span class="md-ellipsis"> RNNBlock </span> </a> </li> <li class="md-nav__item"> <a href="#spatialreduction" class="md-nav__link"> <span class="md-ellipsis"> SpatialReduction </span> </a> </li> <li class="md-nav__item"> <a href="#temporalreduction" class="md-nav__link"> <span class="md-ellipsis"> TemporalReduction </span> </a> </li> <li class="md-nav__item"> <a href="#xceptionblock" class="md-nav__link"> <span class="md-ellipsis"> XceptionBlock </span> </a> </li> <li class="md-nav__item"> <a href="#imageblock" class="md-nav__link"> <span class="md-ellipsis"> ImageBlock </span> </a> </li> <li class="md-nav__item"> <a href="#textblock" class="md-nav__link"> <span class="md-ellipsis"> TextBlock </span> </a> </li> <li class="md-nav__item"> <a href="#imageaugmentation" class="md-nav__link"> <span class="md-ellipsis"> ImageAugmentation </span> </a> </li> <li class="md-nav__item"> <a href="#normalization" class="md-nav__link"> <span class="md-ellipsis"> Normalization </span> </a> </li> <li class="md-nav__item"> <a href="#classificationhead" class="md-nav__link"> <span class="md-ellipsis"> ClassificationHead </span> </a> </li> <li class="md-nav__item"> <a href="#regressionhead" class="md-nav__link"> <span class="md-ellipsis"> RegressionHead </span> </a> </li> </ul> </nav> </div> </div> </div> <div class="md-content" data-md-component="content"> <article class="md-content__inner md-typeset"> <h1>Block</h1> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/basic.py#L256">[source]</a></span></p> <h3 id="convblock">ConvBlock</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">ConvBlock</span><span class="p">(</span> <span class="n">kernel_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">num_blocks</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">num_layers</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">filters</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">max_pooling</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">separable</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">dropout</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span> <span class="p">)</span> </code></pre></div> <p>Block for vanilla ConvNets.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>kernel_size</strong> <code>int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: Int or keras_tuner.engine.hyperparameters.Choice. The size of the kernel. If left unspecified, it will be tuned automatically.</li> <li><strong>num_blocks</strong> <code>int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: Int or keras_tuner.engine.hyperparameters.Choice. The number of conv blocks, each of which may contain convolutional, max pooling, dropout, and activation. If left unspecified, it will be tuned automatically.</li> <li><strong>num_layers</strong> <code>int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: Int or hyperparameters.Choice. The number of convolutional layers in each block. If left unspecified, it will be tuned automatically.</li> <li><strong>filters</strong> <code>int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: Int or keras_tuner.engine.hyperparameters.Choice. The number of filters in the convolutional layers. If left unspecified, it will be tuned automatically.</li> <li><strong>max_pooling</strong> <code>bool | None</code>: Boolean. Whether to use max pooling layer in each block. If left unspecified, it will be tuned automatically.</li> <li><strong>separable</strong> <code>bool | None</code>: Boolean. Whether to use separable conv layers. If left unspecified, it will be tuned automatically.</li> <li><strong>dropout</strong> <code>float | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: Float or kerastuner.engine.hyperparameters. Choice range Between 0 and 1. The dropout rate after convolutional layers. If left unspecified, it will be tuned automatically.</li> </ul> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/basic.py#L57">[source]</a></span></p> <h3 id="denseblock">DenseBlock</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">DenseBlock</span><span class="p">(</span><span class="n">num_layers</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">num_units</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">use_batchnorm</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">dropout</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> </code></pre></div> <p>Block for Dense layers.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>num_layers</strong> <code>int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: Int or keras_tuner.engine.hyperparameters.Choice. The number of Dense layers in the block. If left unspecified, it will be tuned automatically.</li> <li><strong>num_units</strong> <code>int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: Int or keras_tuner.engine.hyperparameters.Choice. The number of units in each dense layer. If left unspecified, it will be tuned automatically.</li> <li><strong>use_bn</strong>: Boolean. Whether to use BatchNormalization layers. If left unspecified, it will be tuned automatically.</li> <li><strong>dropout</strong> <code>float | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: Float or keras_tuner.engine.hyperparameters.Choice. The dropout rate for the layers. If left unspecified, it will be tuned automatically.</li> </ul> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/reduction.py#L39">[source]</a></span></p> <h3 id="merge">Merge</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">Merge</span><span class="p">(</span><span class="n">merge_type</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> </code></pre></div> <p>Merge block to merge multiple nodes into one.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>merge_type</strong> <code>str | None</code>: String. 'add' or 'concatenate'. If left unspecified, it will be tuned automatically.</li> </ul> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/basic.py#L474">[source]</a></span></p> <h3 id="resnetblock">ResNetBlock</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">ResNetBlock</span><span class="p">(</span><span class="n">version</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> </code></pre></div> <p>Block for ResNet.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>version</strong> <code>str | None</code>: String. 'v1', 'v2'. The type of ResNet to use. If left unspecified, it will be tuned automatically.</li> <li><strong>pretrained</strong> <code>bool | None</code>: Boolean. Whether to use ImageNet pretrained weights. If left unspecified, it will be tuned automatically.</li> </ul> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/basic.py#L149">[source]</a></span></p> <h3 id="rnnblock">RNNBlock</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">RNNBlock</span><span class="p">(</span> <span class="n">return_sequences</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">bidirectional</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">num_layers</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">layer_type</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span> <span class="p">)</span> </code></pre></div> <p>An RNN Block.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>return_sequences</strong> <code>bool</code>: Boolean. Whether to return the last output in the output sequence, or the full sequence. Defaults to False.</li> <li><strong>bidirectional</strong> <code>bool | keras_tuner.src.engine.hyperparameters.hp_types.boolean_hp.Boolean | None</code>: Boolean or keras_tuner.engine.hyperparameters.Boolean. Bidirectional RNN. If left unspecified, it will be tuned automatically.</li> <li><strong>num_layers</strong> <code>int | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: Int or keras_tuner.engine.hyperparameters.Choice. The number of layers in RNN. If left unspecified, it will be tuned automatically.</li> <li><strong>layer_type</strong> <code>str | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: String or or keras_tuner.engine.hyperparameters.Choice. 'gru' or 'lstm'. If left unspecified, it will be tuned automatically.</li> </ul> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/reduction.py#L142">[source]</a></span></p> <h3 id="spatialreduction">SpatialReduction</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">SpatialReduction</span><span class="p">(</span><span class="n">reduction_type</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> </code></pre></div> <p>Reduce the dimension of a spatial tensor, e.g. image, to a vector.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>reduction_type</strong> <code>str | None</code>: String. 'flatten', 'global_max' or 'global_avg'. If left unspecified, it will be tuned automatically.</li> </ul> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/reduction.py#L164">[source]</a></span></p> <h3 id="temporalreduction">TemporalReduction</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">TemporalReduction</span><span class="p">(</span><span class="n">reduction_type</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> </code></pre></div> <p>Reduce the dim of a temporal tensor, e.g. output of RNN, to a vector.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>reduction_type</strong> <code>str | None</code>: String. 'flatten', 'global_max' or 'global_avg'. If left unspecified, it will be tuned automatically.</li> </ul> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/basic.py#L512">[source]</a></span></p> <h3 id="xceptionblock">XceptionBlock</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">XceptionBlock</span><span class="p">(</span><span class="n">pretrained</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> </code></pre></div> <p>Block for XceptionNet.</p> <p>An Xception structure, used for specifying your model with specific datasets.</p> <p>The original Xception architecture is from <a href="https://arxiv.org/abs/1610.02357">https://arxiv.org/abs/1610.02357</a>. The data first goes through the entry flow, then through the middle flow which is repeated eight times, and finally through the exit flow.</p> <p>This XceptionBlock returns a similar architecture as Xception except without the last (optional) fully connected layer(s) and logistic regression. The size of this architecture could be decided by <code>HyperParameters</code>, to get an architecture with a half, an identical, or a double size of the original one.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>pretrained</strong> <code>bool | None</code>: Boolean. Whether to use ImageNet pretrained weights. If left unspecified, it will be tuned automatically.</li> </ul> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/wrapper.py#L34">[source]</a></span></p> <h3 id="imageblock">ImageBlock</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">ImageBlock</span><span class="p">(</span><span class="n">block_type</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">normalize</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">augment</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> </code></pre></div> <p>Block for image data.</p> <p>The image blocks is a block choosing from ResNetBlock, XceptionBlock, ConvBlock, which is controlled by a hyperparameter, 'block_type'.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>block_type</strong> <code>str | None</code>: String. 'resnet', 'xception', 'vanilla'. The type of Block to use. If unspecified, it will be tuned automatically.</li> <li><strong>normalize</strong> <code>bool | None</code>: Boolean. Whether to channel-wise normalize the images. If unspecified, it will be tuned automatically.</li> <li><strong>augment</strong> <code>bool | None</code>: Boolean. Whether to do image augmentation. If unspecified, it will be tuned automatically.</li> </ul> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/wrapper.py#L116">[source]</a></span></p> <h3 id="textblock">TextBlock</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">TextBlock</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> </code></pre></div> <p>Block for text data.</p> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/preprocessing.py#L55">[source]</a></span></p> <h3 id="imageaugmentation">ImageAugmentation</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">ImageAugmentation</span><span class="p">(</span> <span class="n">translation_factor</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">vertical_flip</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">horizontal_flip</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">rotation_factor</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">zoom_factor</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">contrast_factor</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span> <span class="p">)</span> </code></pre></div> <p>Collection of various image augmentation methods.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>translation_factor</strong> <code>float | Tuple[float, float] | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: A positive float represented as fraction value, or a tuple of 2 representing fraction for translation vertically and horizontally, or a kerastuner.engine.hyperparameters.Choice range of positive floats. For instance, <code>translation_factor=0.2</code> result in a random translation factor within 20% of the width and height. If left unspecified, it will be tuned automatically.</li> <li><strong>vertical_flip</strong> <code>bool | None</code>: Boolean. Whether to flip the image vertically. If left unspecified, it will be tuned automatically.</li> <li><strong>horizontal_flip</strong> <code>bool | None</code>: Boolean. Whether to flip the image horizontally. If left unspecified, it will be tuned automatically.</li> <li><strong>rotation_factor</strong> <code>float | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: Float or kerastuner.engine.hyperparameters.Choice range between [0, 1]. A positive float represented as fraction of 2pi upper bound for rotating clockwise and counter-clockwise. When represented as a single float, lower = upper. If left unspecified, it will be tuned automatically.</li> <li><strong>zoom_factor</strong> <code>float | Tuple[float, float] | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: A positive float represented as fraction value, or a tuple of 2 representing fraction for zooming vertically and horizontally, or a kerastuner.engine.hyperparameters.Choice range of positive floats. For instance, <code>zoom_factor=0.2</code> result in a random zoom factor from 80% to 120%. If left unspecified, it will be tuned automatically.</li> <li><strong>contrast_factor</strong> <code>float | Tuple[float, float] | keras_tuner.src.engine.hyperparameters.hp_types.choice_hp.Choice | None</code>: A positive float represented as fraction of value, or a tuple of size 2 representing lower and upper bound, or a kerastuner.engine.hyperparameters.Choice range of floats to find the optimal value. When represented as a single float, lower = upper. The contrast factor will be randomly picked between [1.0 - lower, 1.0 + upper]. If left unspecified, it will be tuned automatically.</li> </ul> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/preprocessing.py#L28">[source]</a></span></p> <h3 id="normalization">Normalization</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">Normalization</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="o">**</span><span class="n">kwargs</span><span class="p">)</span> </code></pre></div> <p>Perform feature-wise normalization on data.</p> <p>Refer to Normalization layer in keras preprocessing layers for more information.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>axis</strong> <code>int</code>: Integer or tuple of integers, the axis or axes that should be normalized (typically the features axis). We will normalize each element in the specified axis. The default is '-1' (the innermost axis); 0 (the batch axis) is not allowed.</li> </ul> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/heads.py#L34">[source]</a></span></p> <h3 id="classificationhead">ClassificationHead</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">ClassificationHead</span><span class="p">(</span> <span class="n">num_classes</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">multi_label</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">loss</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">metrics</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">dropout</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span> <span class="p">)</span> </code></pre></div> <p>Classification Dense layers.</p> <p>Use sigmoid and binary crossentropy for binary classification and multi-label classification. Use softmax and categorical crossentropy for multi-class (more than 2) classification. Use Accuracy as metrics by default.</p> <p>The targets passing to the head would have to be tf.data.Dataset, np.ndarray, pd.DataFrame or pd.Series. It can be raw labels, one-hot encoded if more than two classes, or binary encoded for binary classification.</p> <p>The raw labels will be encoded to one column if two classes were found, or one-hot encoded if more than two classes were found.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>num_classes</strong> <code>int | None</code>: Int. Defaults to None. If None, it will be inferred from the data.</li> <li><strong>multi_label</strong> <code>bool</code>: Boolean. Defaults to False.</li> <li><strong>loss</strong> <code>str | Callable | tensorflow.keras.losses.Loss | None</code>: A Keras loss function. Defaults to use <code>binary_crossentropy</code> or <code>categorical_crossentropy</code> based on the number of classes.</li> <li><strong>metrics</strong> <code>List[str | Callable | tensorflow.keras.metrics.Metric] | List[List[str | Callable | tensorflow.keras.metrics.Metric]] | Dict[str, str | Callable | tensorflow.keras.metrics.Metric] | None</code>: A list of Keras metrics. Defaults to use 'accuracy'.</li> <li><strong>dropout</strong> <code>float | None</code>: Float. The dropout rate for the layers. If left unspecified, it will be tuned automatically.</li> </ul> <hr /> <p><span style="float:right;"><a href="https://github.com/keras-team/autokeras/blob/master/autokeras/blocks/heads.py#L197">[source]</a></span></p> <h3 id="regressionhead">RegressionHead</h3> <div class="highlight"><pre><span></span><code><span class="n">autokeras</span><span class="o">.</span><span class="n">RegressionHead</span><span class="p">(</span> <span class="n">output_dim</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">loss</span><span class="o">=</span><span class="s2">"mean_squared_error"</span><span class="p">,</span> <span class="n">metrics</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">dropout</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span> <span class="p">)</span> </code></pre></div> <p>Regression Dense layers.</p> <p>The targets passing to the head would have to be tf.data.Dataset, np.ndarray, pd.DataFrame or pd.Series. It can be single-column or multi-column. The values should all be numerical.</p> <p><strong>Arguments</strong></p> <ul> <li><strong>output_dim</strong> <code>int | None</code>: Int. The number of output dimensions. Defaults to None. If None, it will be inferred from the data.</li> <li><strong>multi_label</strong>: Boolean. Defaults to False.</li> <li><strong>loss</strong> <code>str | Callable | tensorflow.keras.losses.Loss</code>: A Keras loss function. Defaults to use <code>mean_squared_error</code>.</li> <li><strong>metrics</strong> <code>List[str | Callable | tensorflow.keras.metrics.Metric] | List[List[str | Callable | tensorflow.keras.metrics.Metric]] | Dict[str, str | Callable | tensorflow.keras.metrics.Metric] | None</code>: A list of Keras metrics. Defaults to use <code>mean_squared_error</code>.</li> <li><strong>dropout</strong> <code>float | None</code>: Float. The dropout rate for the layers. If left unspecified, it will be tuned automatically.</li> </ul> <hr /> </article> </div> <script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script> </div> </main> <footer class="md-footer"> <div class="md-footer-meta md-typeset"> <div class="md-footer-meta__inner md-grid"> <div class="md-copyright"> Made with <a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener"> Material for MkDocs </a> </div> </div> </div> </footer> </div> <div class="md-dialog" data-md-component="dialog"> <div class="md-dialog__inner md-typeset"></div> </div> <script id="__config" type="application/json">{"base": "..", "features": [], "search": "../assets/javascripts/workers/search.b8dbb3d2.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}}</script> <script src="../assets/javascripts/bundle.bd41221c.min.js"></script> <script src="https://unpkg.com/mermaid@8.4.4/dist/mermaid.min.js"></script> </body> </html>

CINXE.COM

Block - AutoKeras