Centro de ayuda Centro de ayuda

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 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. Para los modelos no admitidos por las gráficas de capa, puede definir un modelo personalizado como una función. Para obtener más información, consulte Define Custom Training Loops, Loss Functions, and Networks.

Funciones

Redes personalizadas

`dlnetwork`	Deep learning network for custom training loops (desde R2019b)
`resetState`	Reset state parameters of neural network
`plot`	Representar una arquitectura de red neuronal
`addInputLayer`	Add input layer to network (desde R2022b)
`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`	Imprimir un resumen de la red (desde R2022b)
`initialize`	Initialize learnable and state parameters of a `dlnetwork` (desde R2021a)
`networkDataLayout`	Deep learning network data layout for learnable parameter initialization (desde R2022b)
`layerGraph`	Gráfica de capas de red de deep learning
`setL2Factor`	Set L2 regularization factor of layer learnable parameter
`getL2Factor`	Get L2 regularization factor of layer learnable parameter
`setLearnRateFactor`	Set learn rate factor of layer learnable parameter
`getLearnRateFactor`	Get learn rate factor of layer learnable parameter

Bucles de entrenamiento personalizados

`forward`	Compute deep learning network output for training (desde R2019b)
`predict`	Compute deep learning network output for inference (desde R2019b)
`adamupdate`	Update parameters using adaptive moment estimation (Adam) (desde R2019b)
`rmspropupdate`	Update parameters using root mean squared propagation (RMSProp) (desde R2019b)
`sgdmupdate`	Update parameters using stochastic gradient descent with momentum (SGDM) (desde R2019b)
`lbfgsupdate`	Update parameters using limited-memory BFGS (L-BFGS) (desde R2023a)
`lbfgsState`	State of limited-memory BFGS (L-BFGS) solver (desde R2023a)
`dlupdate`	Update parameters using custom function (desde R2019b)
`trainingProgressMonitor`	Monitor and plot training progress for deep learning custom training loops (desde R2022b)
`updateInfo`	Update information values for custom training loops (desde R2022b)
`recordMetrics`	Record metric values for custom training loops (desde R2022b)
`groupSubPlot`	Group metrics in training plot (desde R2022b)

Procesamiento de datos

`padsequences`	Pad or truncate sequence data to same length (desde R2021a)
`minibatchqueue`	Create mini-batches for deep learning (desde R2020b)
`onehotencode`	Encode data labels into one-hot vectors (desde R2020b)
`onehotdecode`	Decode probability vectors into class labels (desde R2020b)
`next`	Obtain next mini-batch of data from minibatchqueue (desde R2020b)
`reset`	Reset minibatchqueue to start of data (desde R2020b)
`shuffle`	Shuffle data in minibatchqueue (desde R2020b)
`hasdata`	Determine if minibatchqueue can return mini-batch (desde R2020b)
`partition`	Partition minibatchqueue (desde R2020b)

Diferenciación automática

`dlarray`	Arreglo de deep learning para personalización (desde R2019b)
`dlgradient`	Compute gradients for custom training loops using automatic differentiation (desde R2019b)
`dlfeval`	Evaluate deep learning model for custom training loops (desde R2019b)
`dims`	Etiquetas de dimensión de `dlarray` (desde R2019b)
`finddim`	Find dimensions with specified label (desde R2019b)
`stripdims`	Remove `dlarray` data format (desde R2019b)
`extractdata`	Extraer datos de `dlarray` (desde R2019b)
`isdlarray`	Check if object is `dlarray` (desde R2020b)

Operaciones de pérdida

`crossentropy`	Cross-entropy loss for classification tasks (desde R2019b)
`l1loss`	L₁ loss for regression tasks (desde R2021b)
`l2loss`	L₂ loss for regression tasks (desde R2021b)
`huber`	Huber loss for regression tasks (desde R2021a)
`mse`	Half mean squared error (desde R2019b)
`ctc`	Connectionist temporal classification (CTC) loss for unaligned sequence classification (desde R2021a)

Aceleración de funciones

`dlaccelerate`	Accelerate deep learning function for custom training loops (desde R2021a)
`AcceleratedFunction`	Accelerated deep learning function (desde R2021a)
`clearCache`	Clear accelerated deep learning function trace cache (desde R2021a)

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.
Train Sequence Classification Network Using Custom Training Loop
This example shows how to train a network that classifies sequences 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.
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.
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
Train a neural network that is robust to adversarial examples using a Jacobian regularization scheme.
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.
Train Network in Parallel with Custom Training Loop
This example shows how to set up a custom training loop to train a network in parallel.
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.

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.

Información relacionada

Operaciones

Ejemplos destacados

Train Generative Adversarial Network (GAN)

Train Generative Adversarial Network (GAN)

Train a generative adversarial network to generate images.

Abrir script en vivo

Train Conditional Generative Adversarial Network (CGAN)

Train Conditional Generative Adversarial Network (CGAN)

Train a conditional generative adversarial network to generate images.

Abrir script en vivo

Train Wasserstein GAN with Gradient Penalty (WGAN-GP)

Train Wasserstein GAN with Gradient Penalty (WGAN-GP)

Train a Wasserstein generative adversarial network with a gradient penalty (WGAN-GP) to generate images.

Abrir script en vivo

Train Fast Style Transfer Network

Train Fast Style Transfer Network

Train a network to transfer the style of an image to a second image. It is based on the architecture defined in [1].

Abrir script en vivo

Train a Twin Network for Dimensionality Reduction

Train a Twin Network for Dimensionality Reduction

Train a twin neural network with shared weights to compare handwritten digits using dimensionality reduction.

Abrir script en vivo

Train a Twin Neural Network to Compare Images

Train a Twin Neural Network to Compare Images

Train a twin neural network with shared weights to identify similar images of handwritten characters.

Abrir script en vivo

Image Captioning Using Attention

Image Captioning Using Attention

Train a deep learning model for image captioning using attention.

Abrir script en vivo

Sequence-to-Sequence Translation Using Attention

Sequence-to-Sequence Translation Using Attention

Convert decimal strings to Roman numerals using a recurrent sequence-to-sequence encoder-decoder model with attention.

Abrir script en vivo

Train Network in Parallel with Custom Training Loop

Train Network in Parallel with Custom Training Loop

Set up a custom training loop to train a network in parallel. In this example, parallel workers train on portions of the overall mini-batch. If you have a GPU, then training happens on the GPU. During training, a DataQueue object sends training progress information back to the MATLAB client.

Abrir script en vivo

Train Variational Autoencoder (VAE) to Generate Images

Train Variational Autoencoder (VAE) to Generate Images

Train a deep learning variational autoencoder (VAE) to generate images.

Abrir script en vivo

Train Network Using Cyclical Learning Rate for Snapshot Ensembling

Train Network Using Cyclical Learning Rate for Snapshot Ensembling

Train a network to classify images of objects using a cyclical learning rate schedule and snapshot ensembling for better test accuracy. In the example, you learn how to use a cosine function for the learning rate schedule, take snapshots of the network during training to create a model ensemble, and add L2-norm regularization (weight decay) to the training loss.

Abrir script en vivo

Solve Partial Differential Equations Using Deep Learning

Solve Partial Differential Equations Using Deep Learning

Solve Burger's equation using deep learning.

Abrir script en vivo

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

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

Train a physics informed neural network (PINN) to numerically compute the solution of the Burger's equation by using the limited-memory BFGS (L-BFGS) algorithm.

Abrir script en vivo

Train Neural ODE Network

Train Neural ODE Network

Train an augmented neural ordinary differential equation (ODE) network.

Abrir script en vivo

Dynamical System Modeling Using Neural ODE

Dynamical System Modeling Using Neural ODE

Train a neural network with neural ordinary differential equations (ODEs) to learn the dynamics of a physical system.

Abrir script en vivo

Reduced Order Modeling Using Continuous-Time Echo State Network

Reduced Order Modeling Using Continuous-Time Echo State Network

Train a continuous-time echo state network (CTESN) model to solve Robertson's equation.

Abrir script en vivo

Node Classification Using Graph Convolutional Network

Node Classification Using Graph Convolutional Network

Classify nodes in a graph using a graph convolutional network (GCN).

Abrir script en vivo

Multilabel Graph Classification Using Graph Attention Networks

Multilabel Graph Classification Using Graph Attention Networks

Classify graphs that have multiple independent labels using graph attention networks (GATs).

Abrir script en vivo

Train Network Using Federated Learning

Train Network Using Federated Learning

Train a network using federated learning. Federated learning is a technique that enables you to train a network in a distributed, decentralized way [1].

Abrir script en vivo