Main Content

Built-In Pretrained Networks

Load built-in pretrained networks and perform transfer learning

Deep Learning Toolbox™ provides several pretrained networks suitable for transfer learning. Transfer learning is the process of taking a pretrained deep learning network and fine-tuning it to learn a new task. Using transfer learning is usually faster and easier than training a network from scratch. You can quickly transfer learned features to a new task using a smaller amount of data. To explore the available pretrained networks, use Deep Network Designer. For more information, see Pretrained Deep Neural Networks.

Apps

Deep Network DesignerDesign, visualize, and train deep learning networks

Functions

expand all

squeezenetSqueezeNet convolutional neural network
googlenetGoogLeNet convolutional neural network
inceptionv3Inception-v3 convolutional neural network
densenet201DenseNet-201 convolutional neural network
mobilenetv2MobileNet-v2 convolutional neural network (Since R2019a)
resnet18ResNet-18 convolutional neural network
resnet50ResNet-50 convolutional neural network
resnet101ResNet-101 convolutional neural network
xceptionXception convolutional neural network (Since R2019a)
inceptionresnetv2Pretrained Inception-ResNet-v2 convolutional neural network
nasnetlargePretrained NASNet-Large convolutional neural network (Since R2019a)
nasnetmobilePretrained NASNet-Mobile convolutional neural network (Since R2019a)
shufflenetPretrained ShuffleNet convolutional neural network (Since R2019a)
darknet19DarkNet-19 convolutional neural network (Since R2020a)
darknet53DarkNet-53 convolutional neural network (Since R2020a)
efficientnetb0EfficientNet-b0 convolutional neural network (Since R2020b)
alexnetAlexNet convolutional neural network
vgg16VGG-16 convolutional neural network
vgg19VGG-19 convolutional neural network

Topics