Get Started with Deep Learning Toolbox
Deep Learning Toolbox™ provides a framework for designing and implementing deep neural networks with algorithms, pretrained models, and apps. You can use convolutional neural networks (ConvNets, CNNs) and long short-term memory (LSTM) networks to perform classification and regression on image, time-series, and text data. You can build network architectures such as generative adversarial networks (GANs) and Siamese networks using automatic differentiation, custom training loops, and shared weights. With the Deep Network Designer app, you can design, analyze, and train networks graphically. The Experiment Manager app helps you manage multiple deep learning experiments, keep track of training parameters, analyze results, and compare code from different experiments. You can visualize layer activations and graphically monitor training progress.
You can import networks and layer graphs from TensorFlow™ 2, TensorFlow-Keras, and PyTorch®, the ONNX™ (Open Neural Network Exchange) model format, and Caffe. You can also export Deep Learning Toolbox networks and layer graphs to TensorFlow 2 and the ONNX model format. The toolbox supports transfer learning with DarkNet-53, ResNet-50, NASNet, SqueezeNet and many other pretrained models.
You can speed up training on a single- or multiple-GPU workstation (with Parallel Computing Toolbox™), or scale up to clusters and clouds, including NVIDIA® GPU Cloud and Amazon EC2® GPU instances (with MATLAB® Parallel Server™).
Tutoriels
- Introduction au Deep Network Designer
Cet exemple montre comment utiliser Deep Network Designer pour adapter un réseau GoogLeNet préentraîné dans le but de classer une nouvelle collection d’images. - En savoir plus sur l’apprentissage par transfert
Cet exemple indique comment utiliser l’apprentissage par transfert pour entraîner à nouveau SqueezeNet, un réseau de neurones à convolution préentraîné, afin de classer un nouveau jeu d’images. - Créer un réseau simple de classification d’images avec Deep Network Designer
Cet exemple montre comment utiliser Deep Network Designer pour créer et entraîner un réseau de neurones à convolution simple pour la classification du Deep Learning. - Utiliser Deep Network Designer pour créer un réseau simple de classification de séquences
Cet exemple montre comment utiliser Deep Network Designer pour créer un réseau LSTM (long short-term memory) simple. - Essayer le Deep Learning en 10 lignes de code MATLAB
Découvrez comment utiliser le Deep Learning pour identifier des objets sur une webcam live avec le réseau préentraîné AlexNet. - Classer une image avec un réseau préentraîné
Cet exemple indique comment classer une image avec le réseau de neurones à convolution préentraîné GoogLeNet. - Créer un réseau simple de classification d’image
Cet exemple montre comment créer et entraîner un réseau de neurones à convolution simple pour la classification Deep Learning.
App Workflows
Command-Line Workflows
Exemples présentés
Apprentissage interactif
Deep Learning Onramp
This free, two-hour deep learning tutorial provides an interactive introduction to practical deep learning methods. You will learn to use deep learning techniques in MATLAB for image recognition.
Vidéos
Interactively Modify a Deep Learning Network for Transfer Learning
Deep Network Designer is a point-and-click tool for creating or modifying deep neural networks. This video shows how to use the app in a transfer learning workflow. It demonstrates the ease with which you can use the tool to modify the last few layers in the imported network as opposed to modifying the layers in the command line. You can check the modified architecture for errors in connections and property assignments using a network analyzer.
Deep Learning with MATLAB: Deep Learning in 11 Lines of MATLAB Code
See how to use MATLAB, a simple webcam, and a deep neural network to identify objects in your surroundings.
Deep Learning with MATLAB: Transfer Learning in 10 Lines of MATLAB Code
Learn how to use transfer learning in MATLAB to re-train deep learning networks created by experts for your own data or task.