Convolutional autoencoder for image denoising

<!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/vision/autoencoder/" />  <meta property="og:title" content="Keras documentation: Convolutional autoencoder for image denoising"> <meta property="og:image" content="https://keras.io/img/logo-k-keras-wb.png"> <meta name="twitter:title" content="Keras documentation: Convolutional autoencoder for image denoising"> <meta name="twitter:image" content="https://keras.io/img/k-keras-social.png"> <meta name="twitter:card" content="summary"> <title>Convolutional autoencoder for image denoising</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 active" href="/examples/vision/">Computer Vision</a> <a class="nav-sublink2" href="/examples/vision/image_classification_from_scratch/">Image classification from scratch</a> <a class="nav-sublink2" href="/examples/vision/mnist_convnet/">Simple MNIST convnet</a> <a class="nav-sublink2" href="/examples/vision/image_classification_efficientnet_fine_tuning/">Image classification via fine-tuning with EfficientNet</a> <a class="nav-sublink2" href="/examples/vision/image_classification_with_vision_transformer/">Image classification with Vision Transformer</a> <a class="nav-sublink2" href="/examples/vision/attention_mil_classification/">Classification using Attention-based Deep Multiple Instance Learning</a> <a class="nav-sublink2" href="/examples/vision/mlp_image_classification/">Image classification with modern MLP models</a> <a class="nav-sublink2" href="/examples/vision/mobilevit/">A mobile-friendly Transformer-based model for image classification</a> <a class="nav-sublink2" href="/examples/vision/xray_classification_with_tpus/">Pneumonia Classification on TPU</a> <a class="nav-sublink2" href="/examples/vision/cct/">Compact Convolutional Transformers</a> <a class="nav-sublink2" href="/examples/vision/convmixer/">Image classification with ConvMixer</a> <a class="nav-sublink2" href="/examples/vision/eanet/">Image classification with EANet (External Attention Transformer)</a> <a class="nav-sublink2" href="/examples/vision/involution/">Involutional neural networks</a> <a class="nav-sublink2" href="/examples/vision/perceiver_image_classification/">Image classification with Perceiver</a> <a class="nav-sublink2" href="/examples/vision/reptile/">Few-Shot learning with Reptile</a> <a class="nav-sublink2" href="/examples/vision/semisupervised_simclr/">Semi-supervised image classification using contrastive pretraining with SimCLR</a> <a class="nav-sublink2" href="/examples/vision/swin_transformers/">Image classification with Swin Transformers</a> <a class="nav-sublink2" href="/examples/vision/vit_small_ds/">Train a Vision Transformer on small datasets</a> <a class="nav-sublink2" href="/examples/vision/shiftvit/">A Vision Transformer without Attention</a> <a class="nav-sublink2" href="/examples/vision/image_classification_using_global_context_vision_transformer/">Image Classification using Global Context Vision Transformer</a> <a class="nav-sublink2" href="/examples/vision/oxford_pets_image_segmentation/">Image segmentation with a U-Net-like architecture</a> <a class="nav-sublink2" href="/examples/vision/deeplabv3_plus/">Multiclass semantic segmentation using DeepLabV3+</a> <a class="nav-sublink2" href="/examples/vision/basnet_segmentation/">Highly accurate boundaries segmentation using BASNet</a> <a class="nav-sublink2" href="/examples/vision/fully_convolutional_network/">Image Segmentation using Composable Fully-Convolutional Networks</a> <a class="nav-sublink2" href="/examples/vision/retinanet/">Object Detection with RetinaNet</a> <a class="nav-sublink2" href="/examples/vision/keypoint_detection/">Keypoint Detection with Transfer Learning</a> <a class="nav-sublink2" href="/examples/vision/object_detection_using_vision_transformer/">Object detection with Vision Transformers</a> <a class="nav-sublink2" href="/examples/vision/3D_image_classification/">3D image classification from CT scans</a> <a class="nav-sublink2" href="/examples/vision/depth_estimation/">Monocular depth estimation</a> <a class="nav-sublink2" href="/examples/vision/nerf/">3D volumetric rendering with NeRF</a> <a class="nav-sublink2" href="/examples/vision/pointnet_segmentation/">Point cloud segmentation with PointNet</a> <a class="nav-sublink2" href="/examples/vision/pointnet/">Point cloud classification</a> <a class="nav-sublink2" href="/examples/vision/captcha_ocr/">OCR model for reading Captchas</a> <a class="nav-sublink2" href="/examples/vision/handwriting_recognition/">Handwriting recognition</a> <a class="nav-sublink2 active" href="/examples/vision/autoencoder/">Convolutional autoencoder for image denoising</a> <a class="nav-sublink2" href="/examples/vision/mirnet/">Low-light image enhancement using MIRNet</a> <a class="nav-sublink2" href="/examples/vision/super_resolution_sub_pixel/">Image Super-Resolution using an Efficient Sub-Pixel CNN</a> <a class="nav-sublink2" href="/examples/vision/edsr/">Enhanced Deep Residual Networks for single-image super-resolution</a> <a class="nav-sublink2" href="/examples/vision/zero_dce/">Zero-DCE for low-light image enhancement</a> <a class="nav-sublink2" href="/examples/vision/cutmix/">CutMix data augmentation for image classification</a> <a class="nav-sublink2" href="/examples/vision/mixup/">MixUp augmentation for image classification</a> <a class="nav-sublink2" href="/examples/vision/randaugment/">RandAugment for Image Classification for Improved Robustness</a> <a class="nav-sublink2" href="/examples/vision/image_captioning/">Image captioning</a> <a class="nav-sublink2" href="/examples/vision/nl_image_search/">Natural language image search with a Dual Encoder</a> <a class="nav-sublink2" href="/examples/vision/visualizing_what_convnets_learn/">Visualizing what convnets learn</a> <a class="nav-sublink2" href="/examples/vision/integrated_gradients/">Model interpretability with Integrated Gradients</a> <a class="nav-sublink2" href="/examples/vision/probing_vits/">Investigating Vision Transformer representations</a> <a class="nav-sublink2" href="/examples/vision/grad_cam/">Grad-CAM class activation visualization</a> <a class="nav-sublink2" href="/examples/vision/near_dup_search/">Near-duplicate image search</a> <a class="nav-sublink2" href="/examples/vision/semantic_image_clustering/">Semantic Image Clustering</a> <a class="nav-sublink2" href="/examples/vision/siamese_contrastive/">Image similarity estimation using a Siamese Network with a contrastive loss</a> <a class="nav-sublink2" href="/examples/vision/siamese_network/">Image similarity estimation using a Siamese Network with a triplet loss</a> <a class="nav-sublink2" href="/examples/vision/metric_learning/">Metric learning for image similarity search</a> <a class="nav-sublink2" href="/examples/vision/metric_learning_tf_similarity/">Metric learning for image similarity search using TensorFlow Similarity</a> <a class="nav-sublink2" href="/examples/vision/nnclr/">Self-supervised contrastive learning with NNCLR</a> <a class="nav-sublink2" href="/examples/vision/video_classification/">Video Classification with a CNN-RNN Architecture</a> <a class="nav-sublink2" href="/examples/vision/conv_lstm/">Next-Frame Video Prediction with Convolutional LSTMs</a> <a class="nav-sublink2" href="/examples/vision/video_transformers/">Video Classification with Transformers</a> <a class="nav-sublink2" href="/examples/vision/vivit/">Video Vision Transformer</a> <a class="nav-sublink2" href="/examples/vision/bit/">Image Classification using BigTransfer (BiT)</a> <a class="nav-sublink2" href="/examples/vision/gradient_centralization/">Gradient Centralization for Better Training Performance</a> <a class="nav-sublink2" href="/examples/vision/token_learner/">Learning to tokenize in Vision Transformers</a> <a class="nav-sublink2" href="/examples/vision/knowledge_distillation/">Knowledge Distillation</a> <a class="nav-sublink2" href="/examples/vision/fixres/">FixRes: Fixing train-test resolution discrepancy</a> <a class="nav-sublink2" href="/examples/vision/cait/">Class Attention Image Transformers with LayerScale</a> <a class="nav-sublink2" href="/examples/vision/patch_convnet/">Augmenting convnets with aggregated attention</a> <a class="nav-sublink2" href="/examples/vision/learnable_resizer/">Learning to Resize</a> <a class="nav-sublink2" href="/examples/vision/adamatch/">Semi-supervision and domain adaptation with AdaMatch</a> <a class="nav-sublink2" href="/examples/vision/barlow_twins/">Barlow Twins for Contrastive SSL</a> <a class="nav-sublink2" href="/examples/vision/consistency_training/">Consistency training with supervision</a> <a class="nav-sublink2" href="/examples/vision/deit/">Distilling Vision Transformers</a> <a class="nav-sublink2" href="/examples/vision/focal_modulation_network/">Focal Modulation: A replacement for Self-Attention</a> <a class="nav-sublink2" href="/examples/vision/forwardforward/">Using the Forward-Forward Algorithm for Image Classification</a> <a class="nav-sublink2" href="/examples/vision/masked_image_modeling/">Masked image modeling with Autoencoders</a> <a class="nav-sublink2" href="/examples/vision/sam/">Segment Anything Model with 🤗Transformers</a> <a class="nav-sublink2" href="/examples/vision/segformer/">Semantic segmentation with SegFormer and Hugging Face Transformers</a> <a class="nav-sublink2" href="/examples/vision/simsiam/">Self-supervised contrastive learning with SimSiam</a> <a class="nav-sublink2" href="/examples/vision/supervised-contrastive-learning/">Supervised Contrastive Learning</a> <a class="nav-sublink2" href="/examples/vision/temporal_latent_bottleneck/">When Recurrence meets Transformers</a> <a class="nav-sublink2" href="/examples/vision/yolov8/">Efficient Object Detection with YOLOV8 and KerasCV</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" href="/examples/keras_recipes/">Quick Keras Recipes</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/vision/'>Computer Vision</a> / Convolutional autoencoder for image denoising </div> <div class='k-content'> <h1 id="convolutional-autoencoder-for-image-denoising">Convolutional autoencoder for image denoising</h1> Author: <a href="https://twitter.com/svpino">Santiago L. Valdarrama</a> Date created: 2021/03/01 Last modified: 2021/03/01 Description: How to train a deep convolutional autoencoder for image denoising. <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/vision/ipynb/autoencoder.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/vision/autoencoder.py">GitHub source</a> <hr /> <h2 id="introduction">Introduction</h2> This example demonstrates how to implement a deep convolutional autoencoder for image denoising, mapping noisy digits images from the MNIST dataset to clean digits images. This implementation is based on an original blog post titled <a href="https://blog.keras.io/building-autoencoders-in-keras.html">Building Autoencoders in Keras</a> by <a href="https://twitter.com/fchollet">François Chollet</a>. <hr /> <h2 id="setup">Setup</h2> <div class="codehilite"><pre><code>import numpy as np import matplotlib.pyplot as plt from keras import layers from keras.datasets import mnist from keras.models import Model def preprocess(array): """Normalizes the supplied array and reshapes it.""" array = array.astype("float32") / 255.0 array = np.reshape(array, (len(array), 28, 28, 1)) return array def noise(array): """Adds random noise to each image in the supplied array.""" noise_factor = 0.4 noisy_array = array + noise_factor * np.random.normal( loc=0.0, scale=1.0, size=array.shape ) return np.clip(noisy_array, 0.0, 1.0) def display(array1, array2): """Displays ten random images from each array.""" n = 10 indices = np.random.randint(len(array1), size=n) images1 = array1[indices, :] images2 = array2[indices, :] plt.figure(figsize=(20, 4)) for i, (image1, image2) in enumerate(zip(images1, images2)): ax = plt.subplot(2, n, i + 1) plt.imshow(image1.reshape(28, 28)) plt.gray() ax.get_xaxis().set_visible(False) ax.get_yaxis().set_visible(False) ax = plt.subplot(2, n, i + 1 + n) plt.imshow(image2.reshape(28, 28)) plt.gray() ax.get_xaxis().set_visible(False) ax.get_yaxis().set_visible(False) plt.show() </code></pre></div> <hr /> <h2 id="prepare-the-data">Prepare the data</h2> <div class="codehilite"><pre><code># Since we only need images from the dataset to encode and decode, we # won't use the labels. (train_data, _), (test_data, _) = mnist.load_data() # Normalize and reshape the data train_data = preprocess(train_data) test_data = preprocess(test_data) # Create a copy of the data with added noise noisy_train_data = noise(train_data) noisy_test_data = noise(test_data) # Display the train data and a version of it with added noise display(train_data, noisy_train_data) </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code>Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz 11490434/11490434 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step </code></pre></div> </div> <img alt="png" src="/img/examples/vision/autoencoder/autoencoder_5_1.png" /> <hr /> <h2 id="build-the-autoencoder">Build the autoencoder</h2> We are going to use the Functional API to build our convolutional autoencoder. <div class="codehilite"><pre><code>input = layers.Input(shape=(28, 28, 1)) # Encoder x = layers.Conv2D(32, (3, 3), activation="relu", padding="same")(input) x = layers.MaxPooling2D((2, 2), padding="same")(x) x = layers.Conv2D(32, (3, 3), activation="relu", padding="same")(x) x = layers.MaxPooling2D((2, 2), padding="same")(x) # Decoder x = layers.Conv2DTranspose(32, (3, 3), strides=2, activation="relu", padding="same")(x) x = layers.Conv2DTranspose(32, (3, 3), strides=2, activation="relu", padding="same")(x) x = layers.Conv2D(1, (3, 3), activation="sigmoid", padding="same")(x) # Autoencoder autoencoder = Model(input, x) autoencoder.compile(optimizer="adam", loss="binary_crossentropy") autoencoder.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: "functional_1" </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 # ┃ ┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩ │ input_layer (InputLayer) │ (None, 28, 28, 1) │ 0 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ conv2d (Conv2D) │ (None, 28, 28, 32) │ 320 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ max_pooling2d (MaxPooling2D) │ (None, 14, 14, 32) │ 0 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ conv2d_1 (Conv2D) │ (None, 14, 14, 32) │ 9,248 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ max_pooling2d_1 (MaxPooling2D) │ (None, 7, 7, 32) │ 0 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ conv2d_transpose │ (None, 14, 14, 32) │ 9,248 │ │ (Conv2DTranspose) │ │ │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ conv2d_transpose_1 │ (None, 28, 28, 32) │ 9,248 │ │ (Conv2DTranspose) │ │ │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ conv2d_2 (Conv2D) │ (None, 28, 28, 1) │ 289 │ └─────────────────────────────────┴───────────────────────────┴────────────┘ </pre> <pre style="white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace"> Total params: 28,353 (110.75 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: 28,353 (110.75 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> Now we can train our autoencoder using <code>train_data</code> as both our input data and target. Notice we are setting up the validation data using the same format. <div class="codehilite"><pre><code>autoencoder.fit( x=train_data, y=train_data, epochs=50, batch_size=128, shuffle=True, validation_data=(test_data, test_data), ) </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code>Epoch 1/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 8s 9ms/step - loss: 0.2537 - val_loss: 0.0723 Epoch 2/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0718 - val_loss: 0.0691 Epoch 3/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0695 - val_loss: 0.0677 Epoch 4/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0682 - val_loss: 0.0669 Epoch 5/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0673 - val_loss: 0.0664 Epoch 6/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0668 - val_loss: 0.0660 Epoch 7/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0664 - val_loss: 0.0657 Epoch 8/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0661 - val_loss: 0.0654 Epoch 9/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0657 - val_loss: 0.0651 Epoch 10/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0655 - val_loss: 0.0648 Epoch 11/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0653 - val_loss: 0.0646 Epoch 12/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0651 - val_loss: 0.0644 Epoch 13/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0649 - val_loss: 0.0643 Epoch 14/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0647 - val_loss: 0.0641 Epoch 15/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0646 - val_loss: 0.0640 Epoch 16/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0645 - val_loss: 0.0639 Epoch 17/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0642 - val_loss: 0.0638 Epoch 18/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0641 - val_loss: 0.0638 Epoch 19/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0640 - val_loss: 0.0636 Epoch 20/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0639 - val_loss: 0.0637 Epoch 21/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0639 - val_loss: 0.0634 Epoch 22/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0637 - val_loss: 0.0634 Epoch 23/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0636 - val_loss: 0.0633 Epoch 24/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0637 - val_loss: 0.0632 Epoch 25/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0635 - val_loss: 0.0632 Epoch 26/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0635 - val_loss: 0.0631 Epoch 27/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0635 - val_loss: 0.0630 Epoch 28/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0635 - val_loss: 0.0629 Epoch 29/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0634 - val_loss: 0.0630 Epoch 30/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0633 - val_loss: 0.0629 Epoch 31/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0633 - val_loss: 0.0628 Epoch 32/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0632 - val_loss: 0.0628 Epoch 33/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0631 - val_loss: 0.0627 Epoch 34/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0631 - val_loss: 0.0627 Epoch 35/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0630 - val_loss: 0.0627 Epoch 36/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0631 - val_loss: 0.0626 Epoch 37/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0629 - val_loss: 0.0626 Epoch 38/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0630 - val_loss: 0.0627 Epoch 39/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0630 - val_loss: 0.0625 Epoch 40/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0629 - val_loss: 0.0625 Epoch 41/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0628 - val_loss: 0.0625 Epoch 42/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0629 - val_loss: 0.0625 Epoch 43/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0629 - val_loss: 0.0624 Epoch 44/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0628 - val_loss: 0.0624 Epoch 45/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0628 - val_loss: 0.0624 Epoch 46/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0627 - val_loss: 0.0625 Epoch 47/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0628 - val_loss: 0.0623 Epoch 48/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0627 - val_loss: 0.0623 Epoch 49/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0626 - val_loss: 0.0623 Epoch 50/50 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0626 - val_loss: 0.0622 <keras.src.callbacks.history.History at 0x7ff5889d9930> </code></pre></div> </div> Let's predict on our test dataset and display the original image together with the prediction from our autoencoder. Notice how the predictions are pretty close to the original images, although not quite the same. <div class="codehilite"><pre><code>predictions = autoencoder.predict(test_data) display(test_data, predictions) </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code> 313/313 ━━━━━━━━━━━━━━━━━━━━ 1s 1ms/step </code></pre></div> </div> <img alt="png" src="/img/examples/vision/autoencoder/autoencoder_11_1.png" /> Now that we know that our autoencoder works, let's retrain it using the noisy data as our input and the clean data as our target. We want our autoencoder to learn how to denoise the images. <div class="codehilite"><pre><code>autoencoder.fit( x=noisy_train_data, y=train_data, epochs=100, batch_size=128, shuffle=True, validation_data=(noisy_test_data, test_data), ) </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code>Epoch 1/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.1110 - val_loss: 0.0922 Epoch 2/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0925 - val_loss: 0.0904 Epoch 3/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0910 - val_loss: 0.0895 Epoch 4/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0900 - val_loss: 0.0888 Epoch 5/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0892 - val_loss: 0.0882 Epoch 6/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0887 - val_loss: 0.0878 Epoch 7/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0884 - val_loss: 0.0874 Epoch 8/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0880 - val_loss: 0.0871 Epoch 9/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0876 - val_loss: 0.0869 Epoch 10/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0875 - val_loss: 0.0868 Epoch 11/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0872 - val_loss: 0.0864 Epoch 12/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0870 - val_loss: 0.0863 Epoch 13/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0869 - val_loss: 0.0860 Epoch 14/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0868 - val_loss: 0.0859 Epoch 15/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0865 - val_loss: 0.0857 Epoch 16/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0863 - val_loss: 0.0857 Epoch 17/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0863 - val_loss: 0.0858 Epoch 18/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0862 - val_loss: 0.0854 Epoch 19/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0859 - val_loss: 0.0856 Epoch 20/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0859 - val_loss: 0.0853 Epoch 21/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0858 - val_loss: 0.0851 Epoch 22/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0857 - val_loss: 0.0851 Epoch 23/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0856 - val_loss: 0.0850 Epoch 24/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0855 - val_loss: 0.0850 Epoch 25/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0853 - val_loss: 0.0849 Epoch 26/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0855 - val_loss: 0.0849 Epoch 27/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0853 - val_loss: 0.0849 Epoch 28/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0853 - val_loss: 0.0848 Epoch 29/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0853 - val_loss: 0.0850 Epoch 30/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0854 - val_loss: 0.0847 Epoch 31/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0851 - val_loss: 0.0846 Epoch 32/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0851 - val_loss: 0.0846 Epoch 33/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0849 - val_loss: 0.0846 Epoch 34/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0851 - val_loss: 0.0847 Epoch 35/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0849 - val_loss: 0.0846 Epoch 36/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0849 - val_loss: 0.0844 Epoch 37/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0849 - val_loss: 0.0845 Epoch 38/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0848 - val_loss: 0.0844 Epoch 39/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0849 - val_loss: 0.0843 Epoch 40/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0849 - val_loss: 0.0844 Epoch 41/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0848 - val_loss: 0.0844 Epoch 42/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0848 - val_loss: 0.0844 Epoch 43/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0849 - val_loss: 0.0846 Epoch 44/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0846 - val_loss: 0.0843 Epoch 45/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0847 - val_loss: 0.0845 Epoch 46/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0846 - val_loss: 0.0843 Epoch 47/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0845 - val_loss: 0.0842 Epoch 48/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0846 - val_loss: 0.0842 Epoch 49/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0847 - val_loss: 0.0846 Epoch 50/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0847 - val_loss: 0.0843 Epoch 51/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0846 - val_loss: 0.0842 Epoch 52/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0846 - val_loss: 0.0844 Epoch 53/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0844 - val_loss: 0.0842 Epoch 54/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0845 - val_loss: 0.0842 Epoch 55/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0845 - val_loss: 0.0841 Epoch 56/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0844 Epoch 57/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0845 - val_loss: 0.0841 Epoch 58/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0843 Epoch 59/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0842 Epoch 60/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0844 - val_loss: 0.0847 Epoch 61/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0846 - val_loss: 0.0840 Epoch 62/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0840 Epoch 63/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0841 Epoch 64/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0844 - val_loss: 0.0841 Epoch 65/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0841 Epoch 66/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0841 Epoch 67/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0840 Epoch 68/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0841 Epoch 69/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0840 Epoch 70/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0841 Epoch 71/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0844 - val_loss: 0.0841 Epoch 72/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0842 - val_loss: 0.0840 Epoch 73/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0841 Epoch 74/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0844 - val_loss: 0.0840 Epoch 75/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0842 - val_loss: 0.0840 Epoch 76/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0842 Epoch 77/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0842 - val_loss: 0.0841 Epoch 78/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0841 Epoch 79/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0840 Epoch 80/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0843 - val_loss: 0.0839 Epoch 81/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0842 - val_loss: 0.0842 Epoch 82/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0842 - val_loss: 0.0839 Epoch 83/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0841 - val_loss: 0.0840 Epoch 84/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0841 - val_loss: 0.0839 Epoch 85/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0841 - val_loss: 0.0839 Epoch 86/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0840 - val_loss: 0.0838 Epoch 87/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0841 - val_loss: 0.0839 Epoch 88/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0842 - val_loss: 0.0838 Epoch 89/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0842 - val_loss: 0.0838 Epoch 90/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0841 - val_loss: 0.0840 Epoch 91/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0841 - val_loss: 0.0839 Epoch 92/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0842 - val_loss: 0.0838 Epoch 93/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0841 - val_loss: 0.0838 Epoch 94/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0841 - val_loss: 0.0838 Epoch 95/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0840 - val_loss: 0.0837 Epoch 96/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0841 - val_loss: 0.0838 Epoch 97/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0841 - val_loss: 0.0838 Epoch 98/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0841 - val_loss: 0.0837 Epoch 99/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0841 - val_loss: 0.0838 Epoch 100/100 469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - loss: 0.0839 - val_loss: 0.0839 <keras.src.callbacks.history.History at 0x7ff5889da230> </code></pre></div> </div> Let's now predict on the noisy data and display the results of our autoencoder. Notice how the autoencoder does an amazing job at removing the noise from the input images. <div class="codehilite"><pre><code>predictions = autoencoder.predict(noisy_test_data) display(noisy_test_data, predictions) </code></pre></div> <div class="k-default-codeblock"> <div class="codehilite"><pre><code> 313/313 ━━━━━━━━━━━━━━━━━━━━ 0s 523us/step </code></pre></div> </div> <img alt="png" src="/img/examples/vision/autoencoder/autoencoder_15_1.png" /> </div> <div class='k-outline'> <div class='k-outline-depth-1'> <a href='#convolutional-autoencoder-for-image-denoising'>Convolutional autoencoder for image denoising</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#introduction'>Introduction</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#setup'>Setup</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#prepare-the-data'>Prepare the data</a> </div> <div class='k-outline-depth-2'> ◆ <a href='#build-the-autoencoder'>Build the autoencoder</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

Convolutional autoencoder for image denoising