Train Deep Neural Networks

Train networks using built-in training functions or custom training loops

After defining the network architecture, you can define training parameters using the trainingOptions function. You can then train the network using trainNetwork or trainnet. Use the trained network to predict class labels or numeric responses.

You can train a neural network on a CPU, a GPU, multiple CPUs or GPUs, or in parallel on a cluster or in the cloud. Training on a GPU or in parallel requires Parallel Computing Toolbox™. Using a GPU requires a supported GPU device (for information on supported devices, see GPU Computing Requirements (Parallel Computing Toolbox)). Specify the execution environment using the trainingOptions function.

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 networks that cannot be created using layer graphs, you can define custom networks as a function. To learn more, see Define Custom Training Loops, Loss Functions, and Networks.

Categorie

Built-In Training
Train deep learning networks using built-in training functions
Custom Training Loops
Train deep learning networks using custom training loops

Esempi in primo piano

Transfer Learning con Deep Network Designer

Eseguire in modo interattivo il perfezionamento di una rete preaddestrata di Deep Learning per apprendere una nuova attività di classificazione delle immagini.

Apri live script

Train Simple Semantic Segmentation Network in Deep Network Designer

Create and train a simple semantic segmentation network using Deep Network Designer.

Apri live script

Previsione delle serie temporali tramite il Deep Learning

Questo esempio mostra come prevedere i dati delle serie temporali utilizzando una rete con memoria a breve e lungo termine (LSTM).

Apri live script

Train Residual Network for Image Classification

Create a deep learning neural network with residual connections and train it on CIFAR-10 data. Residual connections are a popular element in convolutional neural network architectures. Using residual connections improves gradient flow through the network and enables training of deeper networks.

Apri live script