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 the trainnet function. 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 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.

After you identify some good starting options, you can automate sweeping of hyperparameters or try Bayesian optimization using Experiment Manager. Use Experiment Manager to test different training configurations at the same time by running your experiment in parallel and monitor your progress by using training plots.

Categories

Featured Examples

Create Simple Deep Learning Neural Network for Classification

Create Simple Deep Learning Neural Network for Classification

Create and train a simple convolutional neural network for deep learning classification.

Prepare Network for Transfer Learning Using Deep Network Designer

Prepare Network for Transfer Learning Using Deep Network Designer

Interactively fine-tune a pretrained deep learning network to learn a new image classification task.

Time Series Forecasting Using Deep Learning

Time Series Forecasting Using Deep Learning

Forecast time series data using a long short-term memory (LSTM) network.

Train Residual Network for Image Classification

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.

Train Convolutional Neural Network for Regression

Train Convolutional Neural Network for Regression

Train a convolutional neural network to predict the angles of rotation of handwritten digits.

Classify Videos Using Deep Learning

Classify Videos Using Deep Learning

Create a network for video classification by combining a pretrained image classification model and an LSTM network.

Train Network on Image and Feature Data

Train Network on Image and Feature Data

Train a network that classifies handwritten digits using both image and feature input data.

Train Network Using Custom Training Loop

Train Network Using Custom Training Loop

Train a network that classifies handwritten digits with a custom learning rate schedule.

Train Generative Adversarial Network (GAN)

Train Generative Adversarial Network (GAN)

Train a generative adversarial network to generate images.

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].

Image Captioning Using Attention

Image Captioning Using Attention

Train a deep learning model for image captioning using attention.

Generate Images Using Diffusion

Generate Images Using Diffusion

Generate new images using a diffusion model.

Resume Training from Checkpoint Network

Resume Training from Checkpoint Network

Save checkpoint networks while training a deep learning network and resume training from a previously saved network.

Try Multiple Pretrained Networks for Transfer Learning

Try Multiple Pretrained Networks for Transfer Learning

Configure an experiment that replaces layers of different pretrained networks for transfer learning.

Experiment with Weight Initializers for Transfer Learning

Experiment with Weight Initializers for Transfer Learning

Configure an experiment that initializes the weights of convolution and fully connected layers using different weight initializers.

Use Experiment Manager to Train Generative Adversarial Networks (GANs)

Use Experiment Manager to Train Generative Adversarial Networks (GANs)

Create a custom training experiment to generate images of flowers.

Detect Issues During Deep Neural Network Training

Detect Issues During Deep Neural Network Training

Automatically detect issues while training a deep neural network.