KerasHub

<!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/keras_hub/" />  <meta property="og:title" content="Keras documentation: KerasHub"> <meta property="og:image" content="https://keras.io/img/logo-k-keras-wb.png"> <meta name="twitter:title" content="Keras documentation: KerasHub"> <meta name="twitter:image" content="https://keras.io/img/k-keras-social.png"> <meta name="twitter:card" content="summary"> <title>KerasHub</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" href="/api/" role="tab" aria-selected="">Keras 3 API documentation</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 active" 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'> ► KerasHub </div> <div class='k-content'> <h1 id="kerashub">KerasHub</h1> <a class="github-button" href="https://github.com/keras-team/keras-hub" data-size="large" data-show-count="true" aria-label="Star keras-team/keras-hub on GitHub">Star</a> KerasHub is a pretrained modeling library that aims to be simple, flexible, and fast. The library provides <a href="https://keras.io/keras_3/">Keras 3</a> implementations of popular model architectures, paired with a collection of pretrained checkpoints available on <a href="https://kaggle.com/models/">Kaggle Models</a>. Models can be use for both training and inference, on any of the TensorFlow, Jax, and Torch backends. KerasHub is an extension of the core Keras API; KerasHub components are provide as <a href="/api/layers/"><code>Layers</code></a> and <a href="/api/models/"><code>Models</code></a>. If you are familiar with Keras, congratulations! You already understand most of KerasHub. See our <a href="/guides/keras_hub/getting_started">Getting Started guide</a> to start learning our API. We welcome <a href="https://github.com/keras-team/keras-hub/issues/1835">contributions</a>. <hr /> <h2 id="quick-links">Quick links</h2> <ul> <li><a href="/api/keras_hub/">KerasHub API reference</a></li> <li><a href="https://github.com/keras-team/keras-hub">KerasHub on GitHub</a></li> <li><a href="https://www.kaggle.com/organizations/keras/models">KerasHub models on Kaggle</a></li> <li><a href="/api/keras_hub/models/">List of available pretrained models</a></li> </ul> <h2 id="guides">Guides</h2> <ul> <li><a href="/guides/keras_hub/getting_started/">Getting Started with KerasHub</a></li> <li><a href="/guides/keras_hub/classification_with_keras_hub/">Classification with KerasHub</a></li> <li><a href="/guides/keras_hub/segment_anything_in_keras_hub/">Segment Anything in KerasHub</a></li> <li><a href="/guides/keras_hub/semantic_segmentation_deeplab_v3/">Semantic Segmentation with KerasHub</a></li> <li><a href="/guides/keras_hub/stable_diffusion_3_in_keras_hub/">Stable Diffusion 3 in KerasHub</a></li> <li><a href="/guides/keras_hub/transformer_pretraining/">Pretraining a Transformer from scratch with KerasHub</a></li> <li><a href="/guides/keras_hub/upload/">Uploading Models with KerasHub</a></li> </ul> <hr /> <h2 id="installation">Installation</h2> To install the latest KerasHub release with Keras 3, simply run: <div class="codehilite"><pre><code>pip install --upgrade keras-hub </code></pre></div> To install the latest nightly changes for both KerasHub and Keras, you can use our nightly package. <div class="codehilite"><pre><code>pip install --upgrade keras-hub-nightly </code></pre></div> Note that currently, installing KerasHub will always pull in TensorFlow for use of the <a href="https://www.tensorflow.org/api_docs/python/tf/data"><code>tf.data</code></a> API for preprocessing. Even when pre-processing with <a href="https://www.tensorflow.org/api_docs/python/tf/data"><code>tf.data</code></a>, training can still happen on any backend. Read <a href="https://keras.io/getting_started/">Getting started with Keras</a> for more information on installing Keras 3 and compatibility with different frameworks. Note: We recommend using KerasHub with TensorFlow 2.16 or later, as TF 2.16 packages Keras 3 by default. <hr /> <h2 id="quickstart">Quickstart</h2> Below is a quick example using ResNet to predict an image, and BERT to train a classifier: <div class="codehilite"><pre><code>import os os.environ["KERAS_BACKEND"] = "jax" # Or "tensorflow" or "torch"! import keras import keras_hub import numpy as np import tensorflow_datasets as tfds # Load a ResNet model. classifier = keras_hub.models.ImageClassifier.from_preset( "resnet_50_imagenet", activation="softmax", ) # Predict a label for a single image. image_url = "https://upload.wikimedia.org/wikipedia/commons/a/aa/California_quail.jpg" image_path = keras.utils.get_file(origin=image_url) image = keras.utils.load_img(image_path) batch = np.array([image]) preds = classifier.predict(batch) print(keras_hub.utils.decode_imagenet_predictions(preds)) # Load a BERT model. classifier = keras_hub.models.BertClassifier.from_preset( "bert_base_en_uncased", activation="softmax", num_classes=2, ) # Fine-tune on IMDb movie reviews. imdb_train, imdb_test = tfds.load( "imdb_reviews", split=["train", "test"], as_supervised=True, batch_size=16, ) classifier.fit(imdb_train, validation_data=imdb_test) # Predict two new examples. preds = classifier.predict( ["What an amazing movie!", "A total waste of my time."] ) print(preds) </code></pre></div> <hr /> <h2 id="compatibility">Compatibility</h2> We follow <a href="https://semver.org/">Semantic Versioning</a>, and plan to provide backwards compatibility guarantees both for code and saved models built with our components. While we continue with pre-release <code>0.y.z</code> development, we may break compatibility at any time and APIs should not be consider stable. <h2 id="disclaimer">Disclaimer</h2> KerasHub provides access to pre-trained models via the <code>keras_hub.models</code> API. These pre-trained models are provided on an "as is" basis, without warranties or conditions of any kind. <h2 id="citing-kerashub">Citing KerasHub</h2> If KerasHub helps your research, we appreciate your citations. Here is the BibTeX entry: <div class="codehilite"><pre><code>@misc{kerashub2024, title={KerasHub}, author={Watson, Matthew, and Chollet, Fran\c{c}ois and Sreepathihalli, Divyashree, and Saadat, Samaneh and Sampath, Ramesh, and Rasskin, Gabriel and and Zhu, Scott and Singh, Varun and Wood, Luke and Tan, Zhenyu and Stenbit, Ian and Qian, Chen, and Bischof, Jonathan and others}, year={2024}, howpublished={\url{https://github.com/keras-team/keras-hub}}, } </code></pre></div> </div> <div class='k-outline'> <div class='k-outline-depth-1'> <a href='#kerashub'>KerasHub</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#quick-links'>Quick links</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#guides'>Guides</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#installation'>Installation</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#quickstart'>Quickstart</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#compatibility'>Compatibility</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#disclaimer'>Disclaimer</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#citing-kerashub'>Citing KerasHub</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

KerasHub