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 Reti neurali profonde preaddestrate.

App

Deep Network DesignerProgetta, visualizza e addestra le reti di Deep Learning

Funzioni

espandi tutto

squeezenetSqueezeNet convolutional neural network
googlenetRete neurale convoluzionale GoogLeNet
inceptionv3Rete neurale convoluzionale Inception-v3
densenet201DenseNet-201 convolutional neural network
mobilenetv2Rete neurale convoluzionale MobileNet-v2 (Da R2019a)
resnet18Rete neurale convoluzionale ResNet-18
resnet50Rete neurale convoluzionale ResNet-50
resnet101Rete neurale convoluzionale ResNet-101
xceptionXception convolutional neural network (Da R2019a)
inceptionresnetv2Rete neurale convoluzionale Inception-ResNet-v2 preaddestrata
nasnetlargePretrained NASNet-Large convolutional neural network (Da R2019a)
nasnetmobilePretrained NASNet-Mobile convolutional neural network (Da R2019a)
shufflenetPretrained ShuffleNet convolutional neural network (Da R2019a)
darknet19DarkNet-19 convolutional neural network (Da R2020a)
darknet53DarkNet-53 convolutional neural network (Da R2020a)
efficientnetb0EfficientNet-b0 convolutional neural network (Da R2020b)
alexnetRete neurale convoluzionale AlexNet
vgg16Rete neurale convoluzionale VGG-16
vgg19Rete neurale convoluzionale VGG-19

Argomenti

Informazioni complementari