xception

Xception convolutional neural network

Since R2019a

• 

×

Syntax

net = xception

net = xception('Weights','imagenet')

lgraph = xception('Weights','none')

Description

Xception is a convolutional neural network that is 71 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^®, see Pretrained Deep Neural Networks.

You can use classify to classify new images using the Xception model. Follow the steps of Classify Image Using GoogLeNet and replace GoogLeNet with Xception.

To retrain the network on a new classification task, follow the steps of Train Deep Learning Network to Classify New Images and load Xception instead of GoogLeNet.

net = xception returns an Xception network trained on the ImageNet data set.

This function requires the Deep Learning Toolbox™ Model for Xception Network support package. If this support package is not installed, then the function provides a download link.

net = xception('Weights','imagenet') returns an Xception network trained on the ImageNet data set. This syntax is equivalent to net = xception.

lgraph = xception('Weights','none') returns the untrained Xception network architecture. The untrained model does not require the support package.

Examples

Download Xception Support Package

Download and install the Deep Learning Toolbox Model for Xception Network support package.

Type xception at the command line.

xception

If the Deep Learning Toolbox Model for Xception Network support 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 click Install. Check that the installation is successful by typing xception at the command line. If the required support package is installed, then the function returns a DAGNetwork object.

xception

ans = 

  DAGNetwork with properties:

         Layers: [171×1 nnet.cnn.layer.Layer]
    Connections: [182×2 table]

Visualize the network using Deep Network Designer.

deepNetworkDesigner(xception)

Explore other pretrained neural networks in Deep Network Designer by clicking New.

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

Output Arguments

net — Pretrained Xception convolutional neural network

DAGNetwork object

Pretrained Xception convolutional neural network, returned as a DAGNetwork object.

lgraph — Untrained Xception convolutional neural network architecture

LayerGraph object

Untrained Xception convolutional neural network architecture, returned as a LayerGraph object.

References

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

[2] Chollet, F., 2017. "Xception: Deep Learning with Depthwise Separable Convolutions." arXiv preprint, pp.1610-02357.

Extended Capabilities

C/C++ Code Generation

Generate C and C++ code using MATLAB® Coder™.

For code generation, you can load the network by using the syntax net = xception or by passing the xception function to coder.loadDeepLearningNetwork (MATLAB Coder). For example: net = coder.loadDeepLearningNetwork('xception')

For more information, see Load Pretrained Networks for Code Generation (MATLAB Coder).

The syntax xception('Weights','none') is not supported for code generation.

GPU Code Generation

Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.

Usage notes and limitations:

• For code generation, you can load the network by using the syntax net = xception or by passing the xception function to coder.loadDeepLearningNetwork (GPU Coder). For example: net = coder.loadDeepLearningNetwork('xception')

  For more information, see Load Pretrained Networks for Code Generation (GPU Coder).

• The syntax xception('Weights','none') is not supported for GPU code generation.

Version History

Introduced in R2019a