Custom Training Loops

Customize deep learning training loops and loss functions

If the trainingOptions function does not provide the training options that you need for your task, or custom output layers do not support the loss functions that you need, then you can define a custom training loop. For models that cannot be specified as networks of layers, you can define the model as a function. To learn more, see Define Custom Training Loops, Loss Functions, and Networks.

Functions

expand all

Network Building

`dlnetwork`	Deep learning neural network
`imagePretrainedNetwork`	Pretrained neural network for images (Since R2024a)
`resnetNetwork`	2-D residual neural network (Since R2024a)
`resnet3dNetwork`	3-D residual neural network (Since R2024a)
`addLayers`	Add layers to neural network
`removeLayers`	Remove layers from neural network
`replaceLayer`	Replace layer in neural network
`connectLayers`	Connect layers in neural network
`disconnectLayers`	Disconnect layers in neural network
`addInputLayer`	Add input layer to network (Since R2022b)
`initialize`	Initialize learnable and state parameters of a `dlnetwork` (Since R2021a)
`networkDataLayout`	Deep learning network data layout for learnable parameter initialization (Since R2022b)
`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

Network Information

`plot`	Plot neural network architecture
`summary`	Print network summary (Since R2022b)
`analyzeNetwork`	Analyze deep learning network architecture
`checkLayer`	Check validity of custom or function layer
`isequal`	Check equality of neural networks (Since R2021a)
`isequaln`	Check equality of neural networks ignoring `NaN` values (Since R2021a)

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)
`lbfgsupdate`	Update parameters using limited-memory BFGS (L-BFGS) (Since R2023a)
`lbfgsState`	State of limited-memory BFGS (L-BFGS) solver (Since R2023a)
`dlupdate`	Update parameters using custom function
`trainingProgressMonitor`	Monitor and plot training progress for deep learning custom training loops (Since R2022b)
`updateInfo`	Update information values for custom training loops (Since R2022b)
`recordMetrics`	Record metric values for custom training loops (Since R2022b)
`groupSubPlot`	Group metrics in training plot (Since R2022b)
`deep.gpu.deterministicAlgorithms`	Set determinism of deep learning operations on the GPU to get reproducible results (Since R2024b)

Data Processing

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

Automatic Differentiation

`dlarray`	Deep learning array for customization
`dlgradient`	Compute gradients for custom training loops using automatic differentiation
`dljacobian`	Jacobian matrix deep learning operation (Since R2024b)
`dldivergence`	Divergence of deep learning data (Since R2024b)
`dllaplacian`	Laplacian of deep learning data (Since R2024b)
`dlfeval`	Evaluate deep learning model for custom training loops
`dims`	Data format of `dlarray` object
`finddim`	Find dimensions with specified label
`stripdims`	Remove `dlarray` data format
`extractdata`	Extract data from `dlarray`
`isdlarray`	Check if object is `dlarray` (Since R2020b)

Loss Operations

`crossentropy`	Cross-entropy loss for classification tasks
`indexcrossentropy`	Index cross-entropy loss for classification tasks (Since R2024b)
`l1loss`	L₁ loss for regression tasks (Since R2021b)
`l2loss`	L₂ loss for regression tasks (Since R2021b)
`huber`	Huber loss for regression tasks (Since R2021a)
`ctc`	Connectionist temporal classification (CTC) loss for unaligned sequence classification (Since R2021a)
`mse`	Half mean squared error

Function Acceleration

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

Topics

Custom Training Loops

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 models.
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 looping over 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 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.
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.
Speed Up Deep Neural Network Training
Learn how to accelerate deep neural network training.

Automatic Differentiation

Deep Learning Data Formats
Learn about deep learning data formats.
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.

Deep Learning Function Acceleration

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.

Related Information

Operations

Featured Examples

Train Generative Adversarial Network (GAN)

Train a generative adversarial network to generate images.

Open Live Script

Train Conditional Generative Adversarial Network (CGAN)

Train a conditional generative adversarial network to generate images.

Open Live Script

Train Wasserstein GAN with Gradient Penalty (WGAN-GP)

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

Open Live Script

Generate Images Using Diffusion

Generate new images using a diffusion model.

Since R2023b
Open Live Script

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].

Open Live Script

Train a Twin Network for Dimensionality Reduction

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

Open Live Script

Train a Twin Neural Network to Compare Images

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

Open Live Script

Image Captioning Using Attention

Train a deep learning model for image captioning using attention.

Open Live Script

Sequence-to-Sequence Translation Using Attention

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

Open Live Script

Train Network in Parallel with Custom Training Loop

Set up a custom training loop to train a network in parallel.

Open Live Script

Train Variational Autoencoder (VAE) to Generate Images

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

Open Live Script

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.

Open Live Script

Solve PDE Using Physics-Informed Neural Network

Train a physics-informed neural network (PINN) to predict the solutions of the Burger's equation.

Open Live Script

Dynamical System Modeling Using Neural ODE

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

Open Live Script

Reduced Order Modeling Using Continuous-Time Echo State Network

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

Open Live Script

Node Classification Using Graph Convolutional Network

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

Open Live Script

Multilabel Graph Classification Using Graph Attention Networks

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

Open Live Script

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].

Open Live Script