Esta página es para la versión anterior. La página correspondiente en inglés ha sido eliminada en la versión actual.

Personalización de redes profundas para imágenes

Personalice bucles de entrenamiento y funciones de pérdida de deep learning

Si la función trainingOptions no proporciona las opciones de entrenamiento que necesita para la tarea, o si las capas de salida personalizadas no son compatibles con las funciones de pérdida que necesita, puede definir un bucle de entrenamiento personalizado. En el caso de las redes que no se pueden crear mediante gráficas de capa, puede definir redes personalizadas como una función. Para obtener más información, consulte Define Custom Training Loops, Loss Functions, and Networks.

Funciones

expandir todo

Bucles de entrenamiento personalizados

`dlnetwork`	Deep learning network for custom training loops
`forward`	Compute deep learning network output for training
`predict`	Compute deep learning network output for inference
`adamupdate`	Update parameters using adaptive moment estimation (Adam)
`rmspropupdate`	Update parameters using root mean squared propagation (RMSProp)
`sgdmupdate`	Update parameters using stochastic gradient descent with momentum (SGDM)
`dlupdate`	Update parameters using custom function
`minibatchqueue`	Create mini-batches for deep learning
`onehotencode`	Encode data labels into one-hot vectors
`onehotdecode`	Decode probability vectors into class labels
`initialize`	Initialize learnable and state parameters of a `dlnetwork`
`plot`	Representar una arquitectura de red neuronal
`addLayers`	Add layers to layer graph or network
`removeLayers`	Remove layers from layer graph or network
`connectLayers`	Connect layers in layer graph or network
`disconnectLayers`	Disconnect layers in layer graph or network
`replaceLayer`	Replace layer in layer graph or network
`summary`	Print network summary
`trainingProgressMonitor`	Monitor and plot training progress for deep learning custom training loops

Diferenciación automática

`dlarray`	Deep learning array for customization
`dlgradient`	Compute gradients for custom training loops using automatic differentiation
`dlfeval`	Evaluate deep learning model for custom training loops

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

Temas

Train Network Using Custom Training Loop
This example shows how to train a network that classifies handwritten digits with a custom learning rate schedule.
Multiple-Input and Multiple-Output Networks
Learn how to define and train deep learning networks with multiple inputs or multiple outputs.
Train Network with Multiple Outputs
This example shows how to train a deep learning network with multiple outputs that predict both labels and angles of rotations of handwritten digits.
Train a Siamese Network to Compare Images
This example shows how to train a Siamese network to identify similar images of handwritten characters.
Example Deep Learning Networks Architectures
This example shows how to define simple deep learning neural networks for classification and regression tasks.
Data Sets for Deep Learning
Discover data sets for various deep learning tasks.