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.

Bucles de entrenamiento de deep learning personalizados

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

Redes personalizadas

`dlnetwork`	Deep learning network for custom training loops
`resetState`	Reset state parameters of neural network
`plot`	Representar una arquitectura de red neuronal
`addInputLayer`	Add input layer to network
`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
`initialize`	Initialize learnable and state parameters of a `dlnetwork`
`networkDataLayout`	Deep learning network data layout for learnable parameter initialization

Bucles de entrenamiento personalizados

`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
`padsequences`	Pad or truncate sequence data to same length
`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
`dims`	Etiquetas de dimensión de `dlarray`
`finddim`	Find dimensions with specified label
`stripdims`	Remove `dlarray` data format
`extractdata`	Extraer datos de `dlarray`
`isdlarray`	Check if object is `dlarray`
`functionToLayerGraph`	(To be removed) Convert deep learning model function to a layer graph

Operaciones de deep learning

`dlconv`	Deep learning convolution
`dltranspconv`	Deep learning transposed convolution
`lstm`	Long short-term memory
`gru`	Gated recurrent unit
`attention`	Dot-product attention
`embed`	Embed discrete data
`fullyconnect`	Sum all weighted input data and apply a bias
`dlode45`	Deep learning solution of nonstiff ordinary differential equation (ODE)
`relu`	Aplicar la activación de unidad lineal rectificada
`leakyrelu`	Apply leaky rectified linear unit activation
`gelu`	Apply Gaussian error linear unit (GELU) activation
`batchnorm`	Normalize data across all observations for each channel independently
`crosschannelnorm`	Cross channel square-normalize using local responses
`groupnorm`	Normalize data across grouped subsets of channels for each observation independently
`instancenorm`	Normalize across each channel for each observation independently
`layernorm`	Normalize data across all channels for each observation independently
`avgpool`	Pool data to average values over spatial dimensions
`maxpool`	Pool data to maximum value
`maxunpool`	Unpool the output of a maximum pooling operation
`softmax`	Apply softmax activation to channel dimension
`sigmoid`	Aplicar la activación sigmoide

Operaciones de pérdida de deep learning

`sigmoid`	Aplicar la activación sigmoide
`crossentropy`	Cross-entropy loss for classification tasks
`l1loss`	L₁ loss for regression tasks
`l2loss`	L₂ loss for regression tasks
`huber`	Huber loss for regression tasks
`mse`	Half mean squared error
`ctc`	Connectionist temporal classification (CTC) loss for unaligned sequence classification

Aceleración de funciones de deep learning

`dlaccelerate`	Accelerate deep learning function for custom training loops
`AcceleratedFunction`	Accelerated deep learning function
`clearCache`	Clear accelerated deep learning function trace cache

Temas

Bucles de entrenamiento personalizados

Train Deep Learning Model in MATLAB
Learn how to training deep learning models in MATLAB^®.
Define Custom Training Loops, Loss Functions, and Networks
Learn how to define and customize deep learning training loops, loss functions, and networks using automatic differentiation.
Train Network Using Custom Training Loop
This example shows how to train a network that classifies handwritten digits with a custom learning rate schedule.
Specify Training Options in Custom Training Loop
Learn how to specify common training options in a custom training loop.
Define Model Loss Function for Custom Training Loop
Learn how to define a model loss function for a custom training loop.
Update Batch Normalization Statistics in Custom Training Loop
This example shows how to update the network state in a custom training loop.
Make Predictions Using dlnetwork Object
This example shows how to make predictions using a dlnetwork object by splitting data into mini-batches.
Monitor Custom Training Loop Progress
Track and plot custom training loop progress.
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.
Classify Videos Using Deep Learning with Custom Training Loop
This example shows how to create a network for video classification by combining a pretrained image classification model and a sequence classification network.
Train Image Classification Network Robust to Adversarial Examples
This example shows how to train a neural network that is robust to adversarial examples using fast gradient sign method (FGSM) adversarial training.
Train Neural ODE Network
This example shows how to train an augmented neural ordinary differential equation (ODE) network.
Train Robust Deep Learning Network with Jacobian Regularization
This example shows how to train a neural network that is robust to adversarial examples using a Jacobian regularization scheme [1].
Solve Ordinary Differential Equation Using Neural Network
This example shows how to solve an ordinary differential equation (ODE) using a neural network.
Assemble Multiple-Output Network for Prediction
This example shows how to assemble a multiple output network for prediction.
Run Custom Training Loops on a GPU and in Parallel
Speed up custom training loops by running on a GPU, in parallel using multiple GPUs, or on a cluster.

Funciones de modelos

Train Network Using Model Function
This example shows how to create and train a deep learning network by using functions rather than a layer graph or a dlnetwork.
Update Batch Normalization Statistics Using Model Function
This example shows how to update the network state in a network defined as a function.
Make Predictions Using Model Function
This example shows how to make predictions using a model function by splitting data into mini-batches.
Initialize Learnable Parameters for Model Function
Learn how to initialize learnable parameters for custom training loops using a model function.
Train Latent ODE Network with Irregularly Sampled Time-Series Data
This example shows how to train a latent ordinary differential equation (ODE) autoencoder with time-series data that is sampled at irregular time intervals.
Multivariate Time Series Anomaly Detection Using Graph Neural Network
This example shows how to detect anomalies in multivariate time series data using a graph neural network (GNN).

Diferenciación automática

List of Functions with dlarray Support
View the list of functions that support dlarray objects.
Automatic Differentiation Background
Learn how automatic differentiation works.
Use Automatic Differentiation In Deep Learning Toolbox
How to use automatic differentiation in deep learning.

Aceleración de funciones de deep learning

Deep Learning Function Acceleration for Custom Training Loops
Accelerate model functions and model loss functions for custom training loops by caching and reusing traces.
Accelerate Custom Training Loop Functions
This example shows how to accelerate deep learning custom training loop and prediction functions.
Check Accelerated Deep Learning Function Outputs
This example shows how to check that the outputs of accelerated functions match the outputs of the underlying function.
Evaluate Performance of Accelerated Deep Learning Function
This example shows how to evaluate the performance gains of using an accelerated function.

Ejemplos destacados

Train Generative Adversarial Network (GAN)

Train a generative adversarial network to generate images.

Bucles de entrenamiento de deep learning personalizados

Funciones

Redes personalizadas

Bucles de entrenamiento personalizados

Diferenciación automática

Operaciones de deep learning

Operaciones de pérdida de deep learning

Aceleración de funciones de deep learning

Temas

Bucles de entrenamiento personalizados

Funciones de modelos

Diferenciación automática

Aceleración de funciones de deep learning

Ejemplos destacados

Train Generative Adversarial Network (GAN)

Train Conditional Generative Adversarial Network (CGAN)

Train Wasserstein GAN with Gradient Penalty (WGAN-GP)

Train Fast Style Transfer Network

Train Network Using Custom Training Loop

Train Network Using Model Function

Train a Siamese Network for Dimensionality Reduction

Train a Siamese Network to Compare Images

Image Captioning Using Attention

Multilabel Text Classification Using Deep Learning

Sequence-to-Sequence Translation Using Attention

Train Network in Parallel with Custom Training Loop

Train Variational Autoencoder (VAE) to Generate Images

Train Network Using Cyclical Learning Rate for Snapshot Ensembling

Solve Partial Differential Equations Using Deep Learning

Solve Partial Differential Equation with L-BFGS Method and Deep Learning

Train Neural ODE Network

Dynamical System Modeling Using Neural ODE

Node Classification Using Graph Convolutional Network

Multilabel Graph Classification Using Graph Attention Networks

Train Network Using Federated Learning