Custom Training Loops

Customize deep learning training loops and loss functions for sequence and tabular data

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.

Funzioni

espandi tutto

Custom Training Loops

`dlnetwork`	Deep learning neural network (Da R2019b)
`trainingProgressMonitor`	Monitor and plot training progress for deep learning custom training loops (Da R2022b)
`minibatchqueue`	Create mini-batches for deep learning (Da R2020b)
`padsequences`	Pad or truncate sequence data to same length (Da R2021a)
`dlarray`	Deep learning array for customization (Da R2019b)
`dlgradient`	Compute gradients for custom training loops using automatic differentiation (Da R2019b)
`dlfeval`	Evaluate deep learning model for custom training loops (Da R2019b)

Loss Operations

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

Deep Learning Operations

`dlconv`	Deep learning convolution (Da R2019b)
`dltranspconv`	Deep learning transposed convolution (Da R2019b)
`lstm`	Long short-term memory (Da R2019b)
`gru`	Gated recurrent unit (Da R2020a)
`attention`	Dot-product attention (Da R2022b)
`embed`	Embed discrete data (Da R2020b)
`fullyconnect`	Sum all weighted input data and apply a bias (Da R2019b)
`dlode45`	Deep learning solution of nonstiff ordinary differential equation (ODE) (Da R2021b)
`batchnorm`	Normalize data across all observations for each channel independently (Da R2019b)
`crosschannelnorm`	Cross channel square-normalize using local responses (Da R2020a)
`groupnorm`	Normalize data across grouped subsets of channels for each observation independently (Da R2020b)
`instancenorm`	Normalize across each channel for each observation independently (Da R2021a)
`layernorm`	Normalize data across all channels for each observation independently (Da R2021a)
`avgpool`	Pool data to average values over spatial dimensions (Da R2019b)
`maxpool`	Pool data to maximum value (Da R2019b)
`maxunpool`	Unpool the output of a maximum pooling operation (Da R2019b)

Activations

`relu`	Applicare l'attivazione dell'unità lineare rettificata (Da R2019b)
`leakyrelu`	Apply leaky rectified linear unit activation (Da R2019b)
`gelu`	Apply Gaussian error linear unit (GELU) activation (Da R2022b)
`softmax`	Apply softmax activation to channel dimension (Da R2019b)
`sigmoid`	Applica l’attivazione sigmoidea (Da R2019b)

Argomenti

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 Sequence Classification Network Using Custom Training Loop
This example shows how to train a network that classifies sequences with a custom learning rate schedule.
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 Neural ODE Network
This example shows how to train an augmented neural ordinary differential equation (ODE) network.
Solve Ordinary Differential Equation Using Neural Network
This example shows how to solve an ordinary differential equation (ODE) using a neural network.
Speed Up Deep Neural Network Training
Learn how to accelerate deep neural network training.

Automatic Differentiation

Create Bidirectional LSTM (BiLSTM) Function
This example shows how to create a bidirectional long-short term memory (BiLSTM) function for custom deep learning functions. (Da R2023b)
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.

Esempi in primo piano

Solve Partial Differential Equations Using Deep Learning

Solve Burger's equation using deep learning.

Apri live script

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.

Apri live script