Deep Learning Toolbox
Deep Learning Toolbox™ provides functions, apps, and Simulink® blocks for designing, implementing, and simulating deep neural networks. The toolbox provides a framework to create and use many types of networks, such as convolutional neural networks (CNNs) and transformers. You can visualize and interpret network predictions, verify network properties, and compress networks with quantization, projection, or pruning.
With the Deep Network Designer app, you can design, edit, and analyze networks interactively, import pretrained models, and export networks to Simulink. The toolbox lets you interoperate with other deep learning frameworks. You can import PyTorch®, TensorFlow™, and ONNX™ models for inference, transfer learning, simulation, and deployment. You can also export models to TensorFlow and ONNX.
You can automatically generate C/C++, CUDA® and HDL code for trained networks.
Get Started
Learn the basics of Deep Learning Toolbox
Applications
Extend deep learning workflows with computer vision, image processing, automated driving, signals, audio, text analytics, and computational finance
Deep Learning Fundamentals
Import, build, train, tune, visualize, verify, and export deep neural networks
Image Data Workflows
Use pretrained networks or create and train networks from scratch for image classification and regression
Sequence and Numeric Feature Data Workflows
Create and train classification, regression, and forecasting neural networks for sequence and tabular data
Parallel and Cloud
Scale up deep learning with multiple GPUs locally or in the cloud and train multiple networks interactively or in batch jobs
Automatic Differentiation
Customize deep learning layers, networks, training loops, and loss functions
Deep Learning with Simulink
Extend deep learning workflows using Simulink
Code Generation
Generate C/C++, CUDA, or HDL code and deploy deep learning networks
Function Approximation, Clustering, and Control
Perform regression, classification, clustering, and model nonlinear dynamic systems using shallow neural networks