La traduzione di questa pagina non è aggiornata. Fai clic qui per vedere l'ultima versione in inglese.

Reti profonde per le immagini

Creare reti neurali profonde e addestrarle da zero

Creare nuove reti profonde per attività di classificazione e regressione delle immagini, definendo l'architettura della rete e addestrando la rete da zero.

Dopo aver definito l'architettura della rete, è possibile definire i parametri di addestramento utilizzando la funzione trainingOptions. È quindi possibile addestrare la rete utilizzando trainNetwork. Utilizzare la rete addestrata per prevedere le etichette delle classi o le risposte numeriche.

È possibile addestrare una rete neurale convoluzionale su una CPU, una GPU, più CPU o GPU, oppure in parallelo su un cluster o nel cloud. L'addestramento su GPU o in parallelo richiede Parallel Computing Toolbox™. L’utilizzo di una GPU richiede un dispositivo GPU supportato (per informazioni sui dispositivi supportati, vedere GPU Computing Requirements (Parallel Computing Toolbox)). Specificare l’ambiente di esecuzione utilizzando la funzione trainingOptions.

App

Deep Network Designer

Progetta, visualizza e addestra le reti di Deep Learning

Funzioni

espandi tutto

Addestramento della rete

`trainingOptions`	Options for training deep learning neural network
`trainNetwork`	Train deep learning neural network
`analyzeNetwork`	Analyze deep learning network architecture

Livelli

Livelli di input

`imageInputLayer`	Image input layer
`image3dInputLayer`	3-D image input layer

Livelli convoluzionali e livelli completamente connessi

`convolution2dLayer`	2-D convolutional layer
`convolution3dLayer`	3-D convolutional layer
`groupedConvolution2dLayer`	2-D grouped convolutional layer
`transposedConv2dLayer`	Transposed 2-D convolution layer
`transposedConv3dLayer`	Transposed 3-D convolution layer
`fullyConnectedLayer`	Fully connected layer

Livelli di attivazione

`reluLayer`	Livello dell’unità lineare rettificata (ReLU)
`leakyReluLayer`	Leaky Rectified Linear Unit (ReLU) layer
`clippedReluLayer`	Clipped Rectified Linear Unit (ReLU) layer
`eluLayer`	Exponential linear unit (ELU) layer
`tanhLayer`	Hyperbolic tangent (tanh) layer
`swishLayer`	Swish layer
`geluLayer`	Gaussian error linear unit (GELU) layer
`functionLayer`	Function layer

Livelli di normalizzazione, abbandono e ritaglio

`batchNormalizationLayer`	Batch normalization layer
`groupNormalizationLayer`	Group normalization layer
`instanceNormalizationLayer`	Instance normalization layer
`layerNormalizationLayer`	Layer normalization layer
`crossChannelNormalizationLayer`	Channel-wise local response normalization layer
`dropoutLayer`	Dropout layer
`crop2dLayer`	2-D crop layer
`crop3dLayer`	3-D crop layer

Livelli di pooling e unpooling

`averagePooling2dLayer`	Average pooling layer
`averagePooling3dLayer`	3-D average pooling layer
`globalAveragePooling2dLayer`	2-D global average pooling layer
`globalAveragePooling3dLayer`	3-D global average pooling layer
`globalMaxPooling2dLayer`	Global max pooling layer
`globalMaxPooling3dLayer`	3-D global max pooling layer
`maxPooling2dLayer`	Max pooling layer
`maxPooling3dLayer`	3-D max pooling layer
`maxUnpooling2dLayer`	Max unpooling layer

Livelli di combinazione

`additionLayer`	Addition layer
`multiplicationLayer`	Multiplication layer
`concatenationLayer`	Concatenation layer
`depthConcatenationLayer`	Depth concatenation layer

Livelli di output

`sigmoidLayer`	Sigmoid layer
`softmaxLayer`	Livello softmax
`classificationLayer`	Classification output layer
`regressionLayer`	Livello di output della regressione

Costruzione della rete

`layerGraph`	Graph of network layers for deep learning
`plot`	Plot neural network architecture
`addLayers`	Add layers to layer graph or network
`removeLayers`	Remove layers from layer graph or network
`replaceLayer`	Replace layer in layer graph or network
`connectLayers`	Connect layers in layer graph or network
`disconnectLayers`	Disconnect layers in layer graph or network
`DAGNetwork`	Directed acyclic graph (DAG) network for deep learning
`resnetLayers`	Create 2-D residual network
`resnet3dLayers`	Create 3-D residual network
`isequal`	Check equality of deep learning layer graphs or networks
`isequaln`	Check equality of deep learning layer graphs or networks ignoring `NaN` values

Previsione

`classify`	Classify data using trained deep learning neural network
`predict`	Predict responses using trained deep learning neural network
`activations`	Compute deep learning network layer activations
`confusionchart`	Create confusion matrix chart for classification problem
`sortClasses`	Sort classes of confusion matrix chart

Blocchi

espandi tutto

Reti neurali profonde

Predict	Predict responses using a trained deep learning neural network
Image Classifier	Classifica i dati utilizzando una rete neurale addestrata di Deep Learning

Argomenti

Creazione di una rete semplice di Deep Learning per la classificazione
Questo esempio mostra come creare e addestrare una rete neurale convoluzionale semplice per la classificazione tramite Deep Learning.
Train Convolutional Neural Network for Regression
This example shows how to fit a regression model using convolutional neural networks to predict the angles of rotation of handwritten digits.
List of Deep Learning Layers
Discover all the deep learning layers in MATLAB^®.
Specify Layers of Convolutional Neural Network
Learn about the layers of a convolutional neural network (ConvNet), and the order they appear in a ConvNet.
Build Networks with Deep Network Designer
Interactively build and edit deep learning networks in Deep Network Designer.
Set Up Parameters and Train Convolutional Neural Network
Learn how to set up training parameters for a convolutional neural network.
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.
Example Deep Learning Networks Architectures
This example shows how to define simple deep learning neural networks for classification and regression tasks.

Esempi in primo piano

Train Residual Network for Image Classification

Create a deep learning neural network with residual connections and train it on CIFAR-10 data. Residual connections are a popular element in convolutional neural network architectures. Using residual connections improves gradient flow through the network and enables training of deeper networks.

Apri live script

Convert Classification Network into Regression Network

Convert a trained classification network into a regression network.

Apri live script

Train Network on Image and Feature Data

Train a network that classifies handwritten digits using both image and feature input data.

Apri live script

Image-to-Image Regression in Deep Network Designer

Use Deep Network Designer to construct and train an image-to-image regression network for super resolution.

Apri live script

Multilabel Image Classification Using Deep Learning

Use transfer learning to train a deep learning model for multilabel image classification.

Apri live script

Lane and Vehicle Detection in Simulink Using Deep Learning

Use deep convolutional neural networks inside a Simulink® model to perform lane and vehicle detection. This example takes the frames from a traffic video as an input, outputs two lane boundaries that correspond to the left and right lanes of the ego vehicle, and detects vehicles in the frame.

Apri script

Classify ECG Signals in Simulink Using Deep Learning

Use wavelet transforms and a deep learning network within a Simulink (R) model to classify ECG signals. This example uses the pretrained convolutional neural network from the Classify Time Series Using Wavelet Analysis and Deep Learning example of the Wavelet Toolbox™ to classify ECG signals based on images from the CWT of the time series data. For information on training, see Classify Time Series Using Wavelet Analysis and Deep Learning (Wavelet Toolbox).

Apri script