La traducción de esta página aún no se ha actualizado a la versión más reciente. Haga clic aquí para ver la última versión en inglés.

Redes profundas para imágenes

Cree redes neuronales profundas y entrénelas desde cero.

Cree nuevas redes profundas para tareas de clasificación y regresión de imágenes definiendo la arquitectura de la red y entrenando la red desde cero.

Después de definir la arquitectura de red, podrá definir los parámetros de entrenamiento con la función trainingOptions. Luego, podrá entrenar la red con trainNetwork. Utilice la red entrenada para predecir etiquetas de clase o respuestas numéricas.

Puede entrenar una red neuronal convolucional en una CPU, una GPU, varias CPU o GPU, o en paralelo en un cluster o en la nube. Para entrenar una red en una GPU o en paralelo, es necesario utilizar Parallel Computing Toolbox™. Para usar una GPU, es necesario contar con un dispositivo con GPU compatible (para obtener información sobre los dispositivos compatibles, consulte GPU Computing Requirements (Parallel Computing Toolbox)). Especifique el entorno de ejecución con la función trainingOptions.

Apps

Deep Network Designer

Diseñar, visualizar y entrenar redes de deep learning

Funciones

expandir todo

Entrenar la red

`trainingOptions`	Opciones para entrenar una red neuronal de deep learning
`trainNetwork`	Entrenar redes neuronales de deep learning
`analyzeNetwork`	Analyze deep learning network architecture

Capas

Capas de entrada

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

Convolución y capas totalmente conectadas

`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

Capas de activación

`reluLayer`	Capa de unidad lineal rectificada (ReLU)
`leakyReluLayer`	Leaky Rectified Linear Unit (ReLU) layer
`clippedReluLayer`	Clipped Rectified Linear Unit (ReLU) layer
`eluLayer`	Exponential linear unit (ELU) layer
`tanhLayer`	Capa de tangente hiperbólica (tanh)
`swishLayer`	Swish layer
`geluLayer`	Gaussian error linear unit (GELU) layer
`functionLayer`	Function layer

Capas de normalización, abandono y recorte

`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

Agrupar y desagrupar capas

`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

Capas de combinación

`additionLayer`	Capa de suma
`multiplicationLayer`	Multiplication layer
`concatenationLayer`	Capa de concatenación
`depthConcatenationLayer`	Capa de concatenación de profundidad

Capas de salida

`sigmoidLayer`	Sigmoid layer
`softmaxLayer`	Capa softmax
`classificationLayer`	Capa de clasificación de salida
`regressionLayer`	Capa de salida de regresión

Crear una red

`layerGraph`	Gráfica de capas de red de deep learning
`plot`	Representar una arquitectura de red neuronal
`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`	Red DAG de 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

Predicción

`classify`	Classify data using trained deep learning neural network
`predict`	Predict responses using trained deep learning neural network
`activations`	Calcular las activaciones de las capas de una red de deep learning
`confusionchart`	Create confusion matrix chart for classification problem
`sortClasses`	Sort classes of confusion matrix chart

Bloques

expandir todo

Redes neuronales profundas

Predict	Predecir respuestas usando una red neuronal de deep learning entrenada
Image Classifier	Clasificar datos con una red neuronal de deep learning entrenada

Temas

Crear una red de deep learning sencilla para clasificación
Este ejemplo muestra cómo crear y entrenar una red neuronal convolucional sencilla para la clasificación mediante deep learning.
Entrenar una red neuronal convolucional para regresión
Este ejemplo muestra cómo ajustar un modelo de regresión mediante redes neuronales convolucionales para predecir los ángulos de rotación de dígitos manuscritos.
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.

Ejemplos destacados

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.

Abrir script en vivo

Convert Classification Network into Regression Network

Convert a trained classification network into a regression network.

Abrir script en vivo

Train Network on Image and Feature Data

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

Abrir script en vivo

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.

Abrir script en vivo

Multilabel Image Classification Using Deep Learning

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

Abrir script en vivo

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.

Abrir 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).

Abrir script