Questa pagina si riferisce alla release precedente. La corrispondente pagina in inglese è stata rimossa nella release attuale.

Personalizzazione della rete profonda per le immagini

Personalizzare i loop di addestramento Deep Learning e le funzioni di perdita

Se la funzione trainingOptions non fornisce le opzioni di addestramento necessarie per l’attività, o se i livelli di output non supportano le funzioni di perdita necessarie, è possibile definire un loop di addestramento personalizzato. Per le reti che non possono essere create utilizzando i grafici di livello, è possibile definire reti personalizzate come una funzione. Per saperne di più, vedere Define Custom Training Loops, Loss Functions, and Networks.

Funzioni

espandi tutto

Personalizzazione dei loop di addestramento

`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`	Plot neural network architecture
`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

Differenziazione automatica

`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

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

Argomenti

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.