Pretrained Deep Learning Models
Take advantage of model architectures developed by the deep learning research community. Popular models offer a robust architecture and skip the need to start from scratch.
Get Pretrained Models
Instead of creating a deep learning model from scratch, get a pretrained model, which you can apply directly or adapt to your task.
MATLAB models
Explore MATLAB Deep Learning Model Hub to access the latest models by category and get tips on choosing a model.
Load most models at the command line. For example:
net = darknet19;
Open-source models
Convert TensorFlow™, PyTorch®, and ONNX™ models to MATLAB networks by using an import function. For example:
net = importTensorFlowNetwork("EfficientNetV2L")
Apply Pretrained Models
Apply pretrained models to image classification, computer vision, audio processing, lidar processing, and other deep learning workflows.
- Find the right pretrained model and apply it directly to your task.
- Perform transfer learning by adapting a pretrained model to a new task or dataset. Updating and retraining a model is faster and easier than creating it from scratch.
- Use a pretrained model as a feature extractor by using the layer activations as features. Then use these features to train another machine learning model, such as a support vector machine (SVM).
- Use a pretrained model as the foundation for another type of model. For example, use a convolutional neural network as a starting point to create an object detection or a semantic segmentation model.
Image classification
For image classification tasks, use a convolutional neural network such as NASNet-Mobile and EfficientNet. The majority of CNNs is trained on the ImageNet database.
Computer vision
Analyze images and videos using object detection (YOLO), semantic/instance segmentation (AdaptSeg/MASK R-CNN), and video classification (SlowFast).
Audio processing
Lidar
Analyze point cloud data using classification (PointNet), object detection (PointPillars), and semantic segmentation (PointSeg).
Natural Language Processing
Tips to Select Models
There are many pretrained models to choose from, and each model has tradeoffs:
Speed
To get started, choose one of the faster models, such as SqueezeNet or GoogLeNet. Then iterate quickly and try different preprocessing and training options.
Accuracy
Once you understand which settings work well, try a more accurate model, such as Inception-v3 or ResNet-50, and see if that improves your results.
Size
When you deploy to edge devices such as Raspberry Pi® or FPGAs, choose a model with a low memory footprint, such as SqueezeNet or MobileNet-v2.
Products
Learn about the products used with deep learning models.
30-Day Free Trial
Get started
