MATLAB for Deep Learning
Data preparation, design, simulation, and deployment for deep neural networks
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.
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.
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.
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.
Try Advanced Techniques
- Interactively Build Experiments to Fine-Tune and Compare Deep Learning Networks(6:06)
- How to Set Up Your Own Deep Learning Experiments(4:08)
- Interactively Modify a Deep Learning Network for Transfer Learning(还)
- Train Networks on NVIDIA DGX Systems
- Accelerate Development and Training of Deep Learning Networks with NVIDIA GPU Cloud
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.
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.
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.
Try Advanced Techniques
Deep Learning Topics
Signal Processing
Acquire and analyze signals and time-series data.
Computer Vision
Acquire, process, and analyze images and video.
Reinforcement Learning
Define, train, and deploy reinforcement learning policies.
Get Started Fast
Deep Learning Onramp
Get started with deep learning techniques in this free, hands-on tutorial.
Explore Getting Started Resources
Watch a demonstration, explore interactive examples, and access free tutorials.
Get a Free Trial
30 days of exploration at your fingertips.
Explore Deep Learning Toolbox
Have Questions?
Talk to a deep learning expert.