Main Content

inceptionv3

Inception-v3 convolutional neural network

所有的页面崩溃
  • Inception-v3 network architecture

Syntax

net = inceptionv3
net = inceptionv3('Weights','imagenet')
lgraph = inceptionv3('Weights','none')

Description

Inception-v3 is a convolutional neural network that is 48 layers deep. You can load a pretrained version of the network trained on more than a million images from the ImageNet database[1]. The pretrained network can classify images into 1000 object categories, such as keyboard, mouse, pencil, and many animals. As a result, the network has learned rich feature representations for a wide range of images. The network has an image input size of 299-by-299. For more pretrained networks in MATLAB®, seePretrained Deep Neural Networks.

You can useclassifyto classify new images using the Inception-v3 model. Follow the steps ofClassify Image Using GoogLeNetand replace GoogLeNet with Inception-v3.

To retrain the network on a new classification task, follow the steps ofTrain Deep Learning Network to Classify New Imagesand load Inception-v3 instead of GoogLeNet.

example

net= inceptionv3returns an Inception-v3 network trained on the ImageNet database.

This function requires the Deep Learning Toolbox™ Modelfor Inception-v3 Networksupport package. If this support package is not installed, then the function provides a download link.

net= inceptionv3('Weights','imagenet')returns an Inception-v3 network trained on the ImageNet database. This syntax is equivalent tonet = inceptionv3.

lgraph= inceptionv3('Weights','none')returns the untrained Inception-v3 network architecture. The untrained model does not require the support package.

Examples

collapse all

下来load and install the Deep Learning Toolbox Modelfor Inception-v3 Networksupport package.

Typeinceptionv3at the command line.

inceptionv3

If the Deep Learning Toolbox Modelfor Inception-v3 Networksupport package is not installed, then the function provides a link to the required support package in the Add-On Explorer. To install the support package, click the link, and then clickInstall. Check that the installation is successful by typinginceptionv3at the command line. If the required support package is installed, then the function returns aDAGNetworkobject.

inceptionv3
ans = DAGNetwork with properties: Layers: [316×1 nnet.cnn.layer.Layer] Connections: [350×2 table]

Visualize the network using Deep Network Designer.

deepNetworkDesigner(inceptionv3)

Explore other pretrained networks in Deep Network Designer by clickingNew.

Deep Network Designer start page showing available pretrained networks

If you need to download a network, pause on the desired network and clickInstallto open the Add-On Explorer.

Output Arguments

collapse all

Pretrained Inception-v3 convolutional neural network, returned as aDAGNetworkobject.

Untrained Inception-v3 convolutional neural network architecture, returned as aLayerGraphobject.

References

[1]ImageNet. http://www.image-net.org

[2] Szegedy, Christian, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna. "Rethinking the inception architecture for computer vision." In程序的IEEE承认rence on Computer Vision and Pattern Recognition, pp. 2818-2826. 2016.

Extended Capabilities

Version History

Introduced in R2017b

See Also

|||||||||||

Topics