CINXE.COM

<!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/guides/sequential_model/" />  <meta property="og:title" content="Keras documentation: The Sequential model"> <meta property="og:image" content="https://keras.io/img/logo-k-keras-wb.png"> <meta name="twitter:title" content="Keras documentation: The Sequential model"> <meta name="twitter:image" content="https://keras.io/img/k-keras-social.png"> <meta name="twitter:card" content="summary"> <title>The Sequential model</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 active" href="/guides/" role="tab" aria-selected="">Developer guides</a> <a class="nav-sublink" href="/guides/functional_api/">The Functional API</a> <a class="nav-sublink active" href="/guides/sequential_model/">The Sequential model</a> <a class="nav-sublink" href="/guides/making_new_layers_and_models_via_subclassing/">Making new layers & models via subclassing</a> <a class="nav-sublink" href="/guides/training_with_built_in_methods/">Training & evaluation with the built-in methods</a> <a class="nav-sublink" href="/guides/custom_train_step_in_jax/">Customizing `fit()` with JAX</a> <a class="nav-sublink" href="/guides/custom_train_step_in_tensorflow/">Customizing `fit()` with TensorFlow</a> <a class="nav-sublink" href="/guides/custom_train_step_in_torch/">Customizing `fit()` with PyTorch</a> <a class="nav-sublink" href="/guides/writing_a_custom_training_loop_in_jax/">Writing a custom training loop in JAX</a> <a class="nav-sublink" href="/guides/writing_a_custom_training_loop_in_tensorflow/">Writing a custom training loop in TensorFlow</a> <a class="nav-sublink" href="/guides/writing_a_custom_training_loop_in_torch/">Writing a custom training loop in PyTorch</a> <a class="nav-sublink" href="/guides/serialization_and_saving/">Serialization & saving</a> <a class="nav-sublink" href="/guides/customizing_saving_and_serialization/">Customizing saving & serialization</a> <a class="nav-sublink" href="/guides/writing_your_own_callbacks/">Writing your own callbacks</a> <a class="nav-sublink" href="/guides/transfer_learning/">Transfer learning & fine-tuning</a> <a class="nav-sublink" href="/guides/distributed_training_with_jax/">Distributed training with JAX</a> <a class="nav-sublink" href="/guides/distributed_training_with_tensorflow/">Distributed training with TensorFlow</a> <a class="nav-sublink" href="/guides/distributed_training_with_torch/">Distributed training with PyTorch</a> <a class="nav-sublink" href="/guides/distribution/">Distributed training with Keras 3</a> <a class="nav-sublink" href="/guides/migrating_to_keras_3/">Migrating Keras 2 code to Keras 3</a> <a class="nav-link" href="/examples/" role="tab" aria-selected="">Code examples</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="/keras_tuner/" role="tab" aria-selected="">KerasTuner: Hyperparam Tuning</a> <a class="nav-link" href="/keras_hub/" role="tab" aria-selected="">KerasHub: Pretrained Models</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'> ► <a href='/guides/'>Developer guides</a> / The Sequential model </div> <div class='k-content'> <h1 id="the-sequential-model">The Sequential model</h1> Author: <a href="https://twitter.com/fchollet">fchollet</a> Date created: 2020/04/12 Last modified: 2023/06/25 Description: Complete guide to the Sequential model. <img class="k-inline-icon" src="https://colab.research.google.com/img/colab_favicon.ico"/> <a href="https://colab.research.google.com/github/keras-team/keras-io/blob/master/guides/ipynb/sequential_model.ipynb">View in Colab</a> •<img class="k-inline-icon" src="https://github.com/favicon.ico"/> <a href="https://github.com/keras-team/keras-io/blob/master/guides/sequential_model.py">GitHub source</a> <hr /> <h2 id="setup">Setup</h2> <div class="codehilite"><pre><code>import keras from keras import layers from keras import ops </code></pre></div> <hr /> <h2 id="when-to-use-a-sequential-model">When to use a Sequential model</h2> A <code>Sequential</code> model is appropriate for a plain stack of layers where each layer has exactly one input tensor and one output tensor. Schematically, the following <code>Sequential</code> model: <div class="codehilite"><pre><code># Define Sequential model with 3 layers model = keras.Sequential( [ layers.Dense(2, activation="relu", name="layer1"), layers.Dense(3, activation="relu", name="layer2"), layers.Dense(4, name="layer3"), ] ) # Call model on a test input x = ops.ones((3, 3)) y = model(x) </code></pre></div> is equivalent to this function: <div class="codehilite"><pre><code># Create 3 layers layer1 = layers.Dense(2, activation="relu", name="layer1") layer2 = layers.Dense(3, activation="relu", name="layer2") layer3 = layers.Dense(4, name="layer3") # Call layers on a test input x = ops.ones((3, 3)) y = layer3(layer2(layer1(x))) </code></pre></div> A Sequential model is not appropriate when: <ul> <li>Your model has multiple inputs or multiple outputs</li> <li>Any of your layers has multiple inputs or multiple outputs</li> <li>You need to do layer sharing</li> <li>You want non-linear topology (e.g. a residual connection, a multi-branch model)</li> </ul> <hr /> <h2 id="creating-a-sequential-model">Creating a Sequential model</h2> You can create a Sequential model by passing a list of layers to the Sequential constructor: <div class="codehilite"><pre><code>model = keras.Sequential( [ layers.Dense(2, activation="relu"), layers.Dense(3, activation="relu"), layers.Dense(4), ] ) </code></pre></div> Its layers are accessible via the <code>layers</code> attribute: <div class="codehilite"><pre><code>model.layers </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code>[<Dense name=dense, built=False>, <Dense name=dense_1, built=False>, <Dense name=dense_2, built=False>] </code></pre></div> </div> You can also create a Sequential model incrementally via the <code>add()</code> method: <div class="codehilite"><pre><code>model = keras.Sequential() model.add(layers.Dense(2, activation="relu")) model.add(layers.Dense(3, activation="relu")) model.add(layers.Dense(4)) </code></pre></div> Note that there's also a corresponding <code>pop()</code> method to remove layers: a Sequential model behaves very much like a list of layers. <div class="codehilite"><pre><code>model.pop() print(len(model.layers)) # 2 </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code>2 </code></pre></div> </div> Also note that the Sequential constructor accepts a <code>name</code> argument, just like any layer or model in Keras. This is useful to annotate TensorBoard graphs with semantically meaningful names. <div class="codehilite"><pre><code>model = keras.Sequential(name="my_sequential") model.add(layers.Dense(2, activation="relu", name="layer1")) model.add(layers.Dense(3, activation="relu", name="layer2")) model.add(layers.Dense(4, name="layer3")) </code></pre></div> <hr /> <h2 id="specifying-the-input-shape-in-advance">Specifying the input shape in advance</h2> Generally, all layers in Keras need to know the shape of their inputs in order to be able to create their weights. So when you create a layer like this, initially, it has no weights: <div class="codehilite"><pre><code>layer = layers.Dense(3) layer.weights # Empty </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code>[] </code></pre></div> </div> It creates its weights the first time it is called on an input, since the shape of the weights depends on the shape of the inputs: <div class="codehilite"><pre><code># Call layer on a test input x = ops.ones((1, 4)) y = layer(x) layer.weights # Now it has weights, of shape (4, 3) and (3,) </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code>[<KerasVariable shape=(4, 3), dtype=float32, path=dense_6/kernel>, <KerasVariable shape=(3,), dtype=float32, path=dense_6/bias>] </code></pre></div> </div> Naturally, this also applies to Sequential models. When you instantiate a Sequential model without an input shape, it isn't "built": it has no weights (and calling <code>model.weights</code> results in an error stating just this). The weights are created when the model first sees some input data: <div class="codehilite"><pre><code>model = keras.Sequential( [ layers.Dense(2, activation="relu"), layers.Dense(3, activation="relu"), layers.Dense(4), ] ) # No weights at this stage! # At this point, you can't do this: # model.weights # You also can't do this: # model.summary() # Call the model on a test input x = ops.ones((1, 4)) y = model(x) print("Number of weights after calling the model:", len(model.weights)) # 6 </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code>Number of weights after calling the model: 6 </code></pre></div> </div> Once a model is "built", you can call its <code>summary()</code> method to display its contents: <div class="codehilite"><pre><code>model.summary() </code></pre></div> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace">Model: "sequential_3" </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓ ┃ Layer (type) ┃ Output Shape ┃ Param # ┃ ┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩ │ dense_7 (Dense) │ (1, 2) │ 10 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ dense_8 (Dense) │ (1, 3) │ 9 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ dense_9 (Dense) │ (1, 4) │ 16 │ └─────────────────────────────────┴───────────────────────────┴────────────┘ </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Total params: 35 (140.00 B) </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Trainable params: 35 (140.00 B) </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Non-trainable params: 0 (0.00 B) </pre> However, it can be very useful when building a Sequential model incrementally to be able to display the summary of the model so far, including the current output shape. In this case, you should start your model by passing an <code>Input</code> object to your model, so that it knows its input shape from the start: <div class="codehilite"><pre><code>model = keras.Sequential() model.add(keras.Input(shape=(4,))) model.add(layers.Dense(2, activation="relu")) model.summary() </code></pre></div> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace">Model: "sequential_4" </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓ ┃ Layer (type) ┃ Output Shape ┃ Param # ┃ ┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩ │ dense_10 (Dense) │ (None, 2) │ 10 │ └─────────────────────────────────┴───────────────────────────┴────────────┘ </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Total params: 10 (40.00 B) </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Trainable params: 10 (40.00 B) </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Non-trainable params: 0 (0.00 B) </pre> Note that the <code>Input</code> object is not displayed as part of <code>model.layers</code>, since it isn't a layer: <div class="codehilite"><pre><code>model.layers </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code>[<Dense name=dense_10, built=True>] </code></pre></div> </div> Models built with a predefined input shape like this always have weights (even before seeing any data) and always have a defined output shape. In general, it's a recommended best practice to always specify the input shape of a Sequential model in advance if you know what it is. <hr /> <h2 id="a-common-debugging-workflow-add--summary">A common debugging workflow: <code>add()</code> + <code>summary()</code></h2> When building a new Sequential architecture, it's useful to incrementally stack layers with <code>add()</code> and frequently print model summaries. For instance, this enables you to monitor how a stack of <code>Conv2D</code> and <code>MaxPooling2D</code> layers is downsampling image feature maps: <div class="codehilite"><pre><code>model = keras.Sequential() model.add(keras.Input(shape=(250, 250, 3))) # 250x250 RGB images model.add(layers.Conv2D(32, 5, strides=2, activation="relu")) model.add(layers.Conv2D(32, 3, activation="relu")) model.add(layers.MaxPooling2D(3)) # Can you guess what the current output shape is at this point? Probably not. # Let's just print it: model.summary() # The answer was: (40, 40, 32), so we can keep downsampling... model.add(layers.Conv2D(32, 3, activation="relu")) model.add(layers.Conv2D(32, 3, activation="relu")) model.add(layers.MaxPooling2D(3)) model.add(layers.Conv2D(32, 3, activation="relu")) model.add(layers.Conv2D(32, 3, activation="relu")) model.add(layers.MaxPooling2D(2)) # And now? model.summary() # Now that we have 4x4 feature maps, time to apply global max pooling. model.add(layers.GlobalMaxPooling2D()) # Finally, we add a classification layer. model.add(layers.Dense(10)) </code></pre></div> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace">Model: "sequential_5" </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓ ┃ Layer (type) ┃ Output Shape ┃ Param # ┃ ┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩ │ conv2d (Conv2D) │ (None, 123, 123, 32) │ 2,432 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ conv2d_1 (Conv2D) │ (None, 121, 121, 32) │ 9,248 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ max_pooling2d (MaxPooling2D) │ (None, 40, 40, 32) │ 0 │ └─────────────────────────────────┴───────────────────────────┴────────────┘ </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Total params: 11,680 (45.62 KB) </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Trainable params: 11,680 (45.62 KB) </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Non-trainable params: 0 (0.00 B) </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace">Model: "sequential_5" </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓ ┃ Layer (type) ┃ Output Shape ┃ Param # ┃ ┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩ │ conv2d (Conv2D) │ (None, 123, 123, 32) │ 2,432 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ conv2d_1 (Conv2D) │ (None, 121, 121, 32) │ 9,248 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ max_pooling2d (MaxPooling2D) │ (None, 40, 40, 32) │ 0 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ conv2d_2 (Conv2D) │ (None, 38, 38, 32) │ 9,248 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ conv2d_3 (Conv2D) │ (None, 36, 36, 32) │ 9,248 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ max_pooling2d_1 (MaxPooling2D) │ (None, 12, 12, 32) │ 0 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ conv2d_4 (Conv2D) │ (None, 10, 10, 32) │ 9,248 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ conv2d_5 (Conv2D) │ (None, 8, 8, 32) │ 9,248 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ max_pooling2d_2 (MaxPooling2D) │ (None, 4, 4, 32) │ 0 │ └─────────────────────────────────┴───────────────────────────┴────────────┘ </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Total params: 48,672 (190.12 KB) </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Trainable params: 48,672 (190.12 KB) </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Non-trainable params: 0 (0.00 B) </pre> Very practical, right? <hr /> <h2 id="what-to-do-once-you-have-a-model">What to do once you have a model</h2> Once your model architecture is ready, you will want to: <ul> <li>Train your model, evaluate it, and run inference. See our <a href="/guides/training_with_built_in_methods/">guide to training & evaluation with the built-in loops</a></li> <li>Save your model to disk and restore it. See our <a href="/guides/serialization_and_saving/">guide to serialization & saving</a>.</li> </ul> <hr /> <h2 id="feature-extraction-with-a-sequential-model">Feature extraction with a Sequential model</h2> Once a Sequential model has been built, it behaves like a <a href="/guides/functional_api/">Functional API model</a>. This means that every layer has an <code>input</code> and <code>output</code> attribute. These attributes can be used to do neat things, like quickly creating a model that extracts the outputs of all intermediate layers in a Sequential model: <div class="codehilite"><pre><code>initial_model = keras.Sequential( [ keras.Input(shape=(250, 250, 3)), layers.Conv2D(32, 5, strides=2, activation="relu"), layers.Conv2D(32, 3, activation="relu"), layers.Conv2D(32, 3, activation="relu"), ] ) feature_extractor = keras.Model( inputs=initial_model.inputs, outputs=[layer.output for layer in initial_model.layers], ) # Call feature extractor on test input. x = ops.ones((1, 250, 250, 3)) features = feature_extractor(x) </code></pre></div> Here's a similar example that only extract features from one layer: <div class="codehilite"><pre><code>initial_model = keras.Sequential( [ keras.Input(shape=(250, 250, 3)), layers.Conv2D(32, 5, strides=2, activation="relu"), layers.Conv2D(32, 3, activation="relu", name="my_intermediate_layer"), layers.Conv2D(32, 3, activation="relu"), ] ) feature_extractor = keras.Model( inputs=initial_model.inputs, outputs=initial_model.get_layer(name="my_intermediate_layer").output, ) # Call feature extractor on test input. x = ops.ones((1, 250, 250, 3)) features = feature_extractor(x) </code></pre></div> <hr /> <h2 id="transfer-learning-with-a-sequential-model">Transfer learning with a Sequential model</h2> Transfer learning consists of freezing the bottom layers in a model and only training the top layers. If you aren't familiar with it, make sure to read our <a href="/guides/transfer_learning/">guide to transfer learning</a>. Here are two common transfer learning blueprint involving Sequential models. First, let's say that you have a Sequential model, and you want to freeze all layers except the last one. In this case, you would simply iterate over <code>model.layers</code> and set <code>layer.trainable = False</code> on each layer, except the last one. Like this: <div class="codehilite"><pre><code>model = keras.Sequential([ keras.Input(shape=(784)), layers.Dense(32, activation='relu'), layers.Dense(32, activation='relu'), layers.Dense(32, activation='relu'), layers.Dense(10), ]) # Presumably you would want to first load pre-trained weights. model.load_weights(...) # Freeze all layers except the last one. for layer in model.layers[:-1]: layer.trainable = False # Recompile and train (this will only update the weights of the last layer). model.compile(...) model.fit(...) </code></pre></div> Another common blueprint is to use a Sequential model to stack a pre-trained model and some freshly initialized classification layers. Like this: <div class="codehilite"><pre><code># Load a convolutional base with pre-trained weights base_model = keras.applications.Xception( weights='imagenet', include_top=False, pooling='avg') # Freeze the base model base_model.trainable = False # Use a Sequential model to add a trainable classifier on top model = keras.Sequential([ base_model, layers.Dense(1000), ]) # Compile & train model.compile(...) model.fit(...) </code></pre></div> If you do transfer learning, you will probably find yourself frequently using these two patterns. That's about all you need to know about Sequential models! To find out more about building models in Keras, see: <ul> <li><a href="/guides/functional_api/">Guide to the Functional API</a></li> <li><a href="/guides/making_new_layers_and_models_via_subclassing/">Guide to making new Layers & Models via subclassing</a></li> </ul> </div> <div class='k-outline'> <div class='k-outline-depth-1'> <a href='#the-sequential-model'>The Sequential model</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#setup'>Setup</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#when-to-use-a-sequential-model'>When to use a Sequential model</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#creating-a-sequential-model'>Creating a Sequential model</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#specifying-the-input-shape-in-advance'>Specifying the input shape in advance</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#a-common-debugging-workflow-add--summary'>A common debugging workflow: <code>add()</code> + <code>summary()</code></a> </div> <div class='k-outline-depth-2'> ◆ <a href='#what-to-do-once-you-have-a-model'>What to do once you have a model</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#feature-extraction-with-a-sequential-model'>Feature extraction with a Sequential model</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#transfer-learning-with-a-sequential-model'>Transfer learning with a Sequential model</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>