MATLAB for Deep Learning

Data preparation, design, simulation, and deployment for deep neural networks

Download a free trial

With just a few lines of MATLAB^®code, you can apply deep learning techniques to your work whether you’re designing algorithms, preparing and labeling data, or generating code and deploying to embedded systems.

With MATLAB, you can:

Create, modify, and analyze deep learning architectures usingapps and visualization tools.
Preprocess data and automateground-truth labelingof image, video, and audio data using apps.
Accelerate algorithms onNVIDIA^®GPUs, cloud, and datacenter resources without specialized programming.
Collaborate with peers using frameworks likeTensorFlow, PyTorch,and MxNet.
Simulate and train dynamic system behavior withreinforcement learning.
Generatesimulation-basedtraining and test data from MATLAB and Simulink^®models of physical systems.

2:16

Top 5 Reasons to Use MATLAB for Deep Learning

See How Others Use MATLAB for Deep Learning

Shell

Uses semantic segmentation for terrain recognition in hyperspectral satellite data.

Autoliv

Labels LIDAR for verification of a radar-based automated driving system.

Ritsumeikan University

Trains convolutional neural networks on CT images to reduce radiation exposure risk.

With just a few lines of MATLAB^®code, you can build deep learning models without having to be an expert. Explore how MATLAB can help you perform deep learning tasks.

容易访问最新的模型,包括GoogLeNet,VGG-16,VGG-19,AlexNet, ResNet-50, ResNet-101, and Inception-v3.
Accelerate algorithms onNVIDIA^®GPUs, cloud, and datacenter resources without specialized programming.
Create, modify, and analyze complex deep neural network architectures using MATLAB apps andvisualizationtools.
Automateground-truth labelingof image, video, and audio data using apps.
Work with models fromCaffeandTensorFlow-Keras.
MATLAB supportsONNX™, so you can collaborate with peers using frameworks likePyTorchandMxNet.

3:06

Deep Learning for Computer Vision Using MATLAB

Why Use MATLAB for Deep Learning?

Interoperability

It’s not an either/or choicebetween MATLAB and Python-based frameworks. MATLAB supports interoperability with open source deep learning frameworks using ONNX import and export capabilities. Use MATLAB tools where it matters most – accessing capabilities and prebuilt functions and apps not available in Python.

Use labeling apps for deep learning workflows likesemantic segmentation.

Apps for Preprocessing

Get to network training quickly. Preprocess datasets fast with domain-specific apps for audio, video, and image data. Visualize, check, and fix problems before training using the Deep Network Designer app to create complex network architectures or modify pretrained networks for transfer learning.

Multi-Platform Deployment

Deploy deep learning models anywhereincludingCUDA, C code, enterprise systems, or the cloud. When performance matters, you can generate code that leverages optimized libraries from Intel^®(MKL-DNN), NVIDIA (TensorRT, cuDNN), and ARM^®(ARM Compute Library) to create deployable models with high-performance inference speed.

Design, Train, and Evaluate Models

Start with a complete set of algorithms and prebuilt models, then create and modify deep learning models using the Deep Network Designer app. Incorporate deep learning models for domain-specific problems without having to create complex network architectures from scratch.

Use techniques to find the optimal network hyperparameters and Parallel Computing Toolbox™ and high-performance NVIDIA GPUs to accelerate these computationally intensive algorithms. Use visualization tools in MATLAB and techniques like Grad-CAM and occlusion sensitivity to gain insights into your model. Use Simulink to evaluate the impact of your trained deep learning model on system-level performance.

Get Started

Try Advanced Techniques

Simulate and Generate Synthetic Data

数据的精确模型是至关重要的,MATLAB can generate more data when you don’t have enough of the right scenarios. For example, use synthetic images from gaming engines, such as Unreal Engine^®, to incorporate more edge cases. Use generative adversarial networks (GANs) to create custom simulated images.

Test algorithms before data is available from sensors by generating synthetic data from Simulink, an approach commonly used in automated driving systems.

Get Started

Deep Learning in Simulink(3:45)

Try Advanced Techniques

Integrate with Python-Based Frameworks

It’s not an either/or choice between MATLAB and open source frameworks. MATLAB allows you to access the latest research from anywhere using ONNX import capabilities, and you can also use a library of prebuilt models, including NASNet, SqueezeNet, Inception-v3, and ResNet-101, to get started quickly. The ability to call Python from MATLAB and MATLAB from Python allows you to easily collaborate with colleagues that are using open source.

Get Started

Try Advanced Techniques

Deploy Trained Networks

Deploy your trained model on embedded systems, enterprise systems, FPGA devices, or the cloud. MATLAB supports automatic CUDA^® code generation for the trained network as well as for preprocessing and postprocessing to specifically target the latest NVIDIA GPUs.

th性能问题时,您可以生成代码at leverages optimized libraries from Intel^®, NVIDIA, and ARM^®to create deployable models with high-performance inference speed. For edge deployment you can prototype your network on an FPGA and then generate production-ready HDL to target any device.