Pretrained Networks

Use pretrained image networks to quickly learn new tasks

Use transfer learning to take advantage of the knowledge provided by a pretrained network to learn new patterns in new image data. Fine-tuning a pretrained image classification network with transfer learning is typically much faster and easier than training from scratch. Using pretrained deep networks enables you to quickly create models for new tasks without defining and training a new network, having millions of images, or having a powerful GPU. To explore the pretrained networks available, use Deep Network Designer.

Apps

Deep Network Designer

Design and visualize deep learning networks

Functions

expand all

Train and Test Network

`trainingOptions`	Options for training deep learning neural network
`trainnet`	Train deep learning neural network (Since R2023b)
`testnet`	Test deep learning neural network (Since R2024b)

Pretrained Networks

imagePretrainedNetwork Pretrained neural network for images (Since R2024a)

Prediction

`predict`	Compute deep learning network output for inference
`minibatchpredict`	Mini-batched neural network prediction (Since R2024a)
`scores2label`	Convert prediction scores to labels (Since R2024a)
`confusionchart`	Create confusion matrix chart for classification problem
`sortClasses`	Sort classes of confusion matrix chart

Blocks

expand all

Deep Neural Networks

Predict	Predict responses using a trained deep learning neural network (Since R2020b)
Image Classifier	Classify data using a trained deep learning neural network (Since R2020b)

Topics

Classify Webcam Images Using Deep Learning
This example shows how to classify images from a webcam in real time using the pretrained deep convolutional neural network GoogLeNet.
Retrain Neural Network to Classify New Images
This example shows how to retrain a pretrained SqueezeNet neural network to perform classification on a new collection of images.
Pretrained Deep Neural Networks
Learn how to download and use pretrained convolutional neural networks for classification, transfer learning and feature extraction.
Deep Learning in MATLAB
Discover deep learning capabilities in MATLAB^® using convolutional neural networks for classification and regression, including pretrained networks and transfer learning, and training on GPUs, CPUs, clusters, and clouds.
Deep Learning Tips and Tricks
Learn how to improve the accuracy of deep learning networks.
Data Sets for Deep Learning
Discover data sets for various deep learning tasks.

Featured Examples

Classify Image Using GoogLeNet

Classify an image using the pretrained deep convolutional neural network GoogLeNet.

Open Live Script

Extract Image Features Using Pretrained Network

Extract learned image features from a pretrained convolutional neural network and use those features to train an image classifier. Feature extraction is the easiest and fastest way to use the representational power of pretrained deep networks. For example, you can train a support vector machine (SVM) using fitcecoc (Statistics and Machine Learning Toolbox™) on the extracted features. Because feature extraction only requires a single pass through the data, it is a good starting point if you do not have a GPU to accelerate network training with.

Open Live Script

Prepare Network for Transfer Learning Using Deep Network Designer

Interactively fine-tune a pretrained deep learning network to learn a new image classification task.

Open Live Script

New

Build Simple App For Deep Learning Inference Using App Designer

Use App Designer to create an app that can classify images using a deep neural network.

Since R2024b
Open Live Script

Convert Classification Network into Regression Network

Convert a trained classification network into a regression network.

Open Live Script

Classify Images in Simulink Using GoogLeNet

Classify an image in Simulink® using the Image Classifier block. The example uses the pretrained deep convolutional neural network GoogLeNet to perform the classification.

Open Script