Endpoint layer pattern

<!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/examples/keras_recipes/endpoint_layer_pattern/" />  <meta property="og:title" content="Keras documentation: Endpoint layer pattern"> <meta property="og:image" content="https://keras.io/img/logo-k-keras-wb.png"> <meta name="twitter:title" content="Keras documentation: Endpoint layer pattern"> <meta name="twitter:image" content="https://keras.io/img/k-keras-social.png"> <meta name="twitter:card" content="summary"> <title>Endpoint layer pattern</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="/examples/" role="tab" aria-selected="">Code examples</a> <a class="nav-sublink" href="/examples/vision/">Computer Vision</a> <a class="nav-sublink" href="/examples/nlp/">Natural Language Processing</a> <a class="nav-sublink" href="/examples/structured_data/">Structured Data</a> <a class="nav-sublink" href="/examples/timeseries/">Timeseries</a> <a class="nav-sublink" href="/examples/generative/">Generative Deep Learning</a> <a class="nav-sublink" href="/examples/audio/">Audio Data</a> <a class="nav-sublink" href="/examples/rl/">Reinforcement Learning</a> <a class="nav-sublink" href="/examples/graph/">Graph Data</a> <a class="nav-sublink active" href="/examples/keras_recipes/">Quick Keras Recipes</a> <a class="nav-sublink2" href="/examples/keras_recipes/parameter_efficient_finetuning_of_gemma_with_lora_and_qlora/">Parameter-efficient fine-tuning of Gemma with LoRA and QLoRA</a> <a class="nav-sublink2" href="/examples/keras_recipes/float8_training_and_inference_with_transformer/">Float8 training and inference with a simple Transformer model</a> <a class="nav-sublink2" href="/examples/keras_recipes/tf_serving/">Serving TensorFlow models with TFServing</a> <a class="nav-sublink2" href="/examples/keras_recipes/debugging_tips/">Keras debugging tips</a> <a class="nav-sublink2" href="/examples/keras_recipes/subclassing_conv_layers/">Customizing the convolution operation of a Conv2D layer</a> <a class="nav-sublink2" href="/examples/keras_recipes/trainer_pattern/">Trainer pattern</a> <a class="nav-sublink2 active" href="/examples/keras_recipes/endpoint_layer_pattern/">Endpoint layer pattern</a> <a class="nav-sublink2" href="/examples/keras_recipes/reproducibility_recipes/">Reproducibility in Keras Models</a> <a class="nav-sublink2" href="/examples/keras_recipes/tensorflow_numpy_models/">Writing Keras Models With TensorFlow NumPy</a> <a class="nav-sublink2" href="/examples/keras_recipes/antirectifier/">Simple custom layer example: Antirectifier</a> <a class="nav-sublink2" href="/examples/keras_recipes/sample_size_estimate/">Estimating required sample size for model training</a> <a class="nav-sublink2" href="/examples/keras_recipes/memory_efficient_embeddings/">Memory-efficient embeddings for recommendation systems</a> <a class="nav-sublink2" href="/examples/keras_recipes/creating_tfrecords/">Creating TFRecords</a> <a class="nav-sublink2" href="/examples/keras_recipes/packaging_keras_models_for_wide_distribution/">Packaging Keras models for wide distribution using Functional Subclassing</a> <a class="nav-sublink2" href="/examples/keras_recipes/approximating_non_function_mappings/">Approximating non-Function Mappings with Mixture Density Networks</a> <a class="nav-sublink2" href="/examples/keras_recipes/bayesian_neural_networks/">Probabilistic Bayesian Neural Networks</a> <a class="nav-sublink2" href="/examples/keras_recipes/better_knowledge_distillation/">Knowledge distillation recipes</a> <a class="nav-sublink2" href="/examples/keras_recipes/sklearn_metric_callbacks/">Evaluating and exporting scikit-learn metrics in a Keras callback</a> <a class="nav-sublink2" href="/examples/keras_recipes/tfrecord/">How to train a Keras model on TFRecord files</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='/examples/'>Code examples</a> / <a href='/examples/keras_recipes/'>Quick Keras Recipes</a> / Endpoint layer pattern </div> <div class='k-content'> <h1 id="endpoint-layer-pattern">Endpoint layer pattern</h1> Author: <a href="https://twitter.com/fchollet">fchollet</a> Date created: 2019/05/10 Last modified: 2023/11/22 Description: Demonstration of the "endpoint layer" pattern (layer that handles loss management). <div class='example_version_banner keras_3'>ⓘ This example uses Keras 3</div> <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/examples/keras_recipes/ipynb/endpoint_layer_pattern.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/examples/keras_recipes/endpoint_layer_pattern.py">GitHub source</a> <hr /> <h2 id="setup">Setup</h2> <div class="codehilite"><pre><code>import os os.environ["KERAS_BACKEND"] = "tensorflow" import tensorflow as tf import keras import numpy as np </code></pre></div> <hr /> <h2 id="usage-of-endpoint-layers-in-the-functional-api">Usage of endpoint layers in the Functional API</h2> An "endpoint layer" has access to the model's targets, and creates arbitrary losses in <code>call()</code> using <code>self.add_loss()</code> and <code>Metric.update_state()</code>. This enables you to define losses and metrics that don't match the usual signature <code>fn(y_true, y_pred, sample_weight=None)</code>. Note that you could have separate metrics for training and eval with this pattern. <div class="codehilite"><pre><code>class LogisticEndpoint(keras.layers.Layer): def __init__(self, name=None): super().__init__(name=name) self.loss_fn = keras.losses.BinaryCrossentropy(from_logits=True) self.accuracy_metric = keras.metrics.BinaryAccuracy(name="accuracy") def call(self, logits, targets=None, sample_weight=None): if targets is not None: # Compute the training-time loss value and add it # to the layer using `self.add_loss()`. loss = self.loss_fn(targets, logits, sample_weight) self.add_loss(loss) # Log the accuracy as a metric (we could log arbitrary metrics, # including different metrics for training and inference.) self.accuracy_metric.update_state(targets, logits, sample_weight) # Return the inference-time prediction tensor (for `.predict()`). return tf.nn.softmax(logits) inputs = keras.Input((764,), name="inputs") logits = keras.layers.Dense(1)(inputs) targets = keras.Input((1,), name="targets") sample_weight = keras.Input((1,), name="sample_weight") preds = LogisticEndpoint()(logits, targets, sample_weight) model = keras.Model([inputs, targets, sample_weight], preds) data = { "inputs": np.random.random((1000, 764)), "targets": np.random.random((1000, 1)), "sample_weight": np.random.random((1000, 1)), } model.compile(keras.optimizers.Adam(1e-3)) model.fit(data, epochs=2) </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code>Epoch 1/2 27/32 ━━━━━━━━━━━━━━━━[37m━━━━ 0s 2ms/step - loss: 0.3664 WARNING: All log messages before absl::InitializeLog() is called are written to STDERR I0000 00:00:1700705222.380735 3351467 device_compiler.h:186] Compiled cluster using XLA! This line is logged at most once for the lifetime of the process. 32/32 ━━━━━━━━━━━━━━━━━━━━ 2s 31ms/step - loss: 0.3663 Epoch 2/2 32/32 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - loss: 0.3627 <keras.src.callbacks.history.History at 0x7f13401b1e10> </code></pre></div> </div> <hr /> <h2 id="exporting-an-inferenceonly-model">Exporting an inference-only model</h2> Simply don't include <code>targets</code> in the model. The weights stay the same. <div class="codehilite"><pre><code>inputs = keras.Input((764,), name="inputs") logits = keras.layers.Dense(1)(inputs) preds = LogisticEndpoint()(logits, targets=None, sample_weight=None) inference_model = keras.Model(inputs, preds) inference_model.set_weights(model.get_weights()) preds = inference_model.predict(np.random.random((1000, 764))) </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code> 32/32 ━━━━━━━━━━━━━━━━━━━━ 0s 6ms/step </code></pre></div> </div> <hr /> <h2 id="usage-of-loss-endpoint-layers-in-subclassed-models">Usage of loss endpoint layers in subclassed models</h2> <div class="codehilite"><pre><code>class LogReg(keras.Model): def __init__(self): super().__init__() self.dense = keras.layers.Dense(1) self.logistic_endpoint = LogisticEndpoint() def call(self, inputs): # Note that all inputs should be in the first argument # since we want to be able to call `model.fit(inputs)`. logits = self.dense(inputs["inputs"]) preds = self.logistic_endpoint( logits=logits, targets=inputs["targets"], sample_weight=inputs["sample_weight"], ) return preds model = LogReg() data = { "inputs": np.random.random((1000, 764)), "targets": np.random.random((1000, 1)), "sample_weight": np.random.random((1000, 1)), } model.compile(keras.optimizers.Adam(1e-3)) model.fit(data, epochs=2) </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code>Epoch 1/2 32/32 ━━━━━━━━━━━━━━━━━━━━ 1s 9ms/step - loss: 0.3529 Epoch 2/2 32/32 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - loss: 0.3509 <keras.src.callbacks.history.History at 0x7f132c1d1450> </code></pre></div> </div> </div> <div class='k-outline'> <div class='k-outline-depth-1'> <a href='#endpoint-layer-pattern'>Endpoint layer pattern</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#setup'>Setup</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#usage-of-endpoint-layers-in-the-functional-api'>Usage of endpoint layers in the Functional API</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#exporting-an-inferenceonly-model'>Exporting an inference-only model</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#usage-of-loss-endpoint-layers-in-subclassed-models'>Usage of loss endpoint layers in subclassed models</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

Endpoint layer pattern