Main Content

Deep Network Designer App

Interactively create and train deep learning networks

Build, visualize, and train deep learning networks interactively. Use the start page to load pretrained image classification networks suitable for transfer learning. Analyze your network to check that you have defined the architecture correctly and detect problems before training. Import and visualize training data, specify training options, and track network training using animated plots of training progress. Generate code to recreate network construction and training, and export trained networks to Simulink®.

This flow chart shows common workflows for building and training deep learning models in the Deep Network Designer app. You can train your network in Deep Network Designer or export your untrained network for training at the command line.

Deep learning workflow. Step 1. Design network. Step 2. Import data. Step 3. Select training options. Step 4. Train network. Step 5. Export network.

Apps

Deep Network DesignerDesign, visualize, and train deep learning networks

Functions

trainingOptionsOptions for training deep learning neural network
trainNetworkTrain neural network
trainnetTrain deep learning neural network (Since R2023b)

Topics