Pretrained ShuffleNet convolutional neural network

ShuffleNet is a convolutional neural network that is trained on more than a million images from the ImageNet database [1]. The 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 224-by-224. For more pretrained networks in MATLAB®, see Pretrained Deep Neural Networks.

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

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


net = shufflenet



net = shufflenet returns a pretrained ShuffleNet convolutional neural network.

This function requires the Deep Learning Toolbox™ Model for ShuffleNet Network support package.


collapse all

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

Open the Add-On Explorer in MATLAB and search for ShuffleNet. Select the Deep Learning Toolbox Model for ShuffleNet Network support package. Download and install the support package by clicking Install. You can also download the network from MathWorks Deep Learning Toolbox Team.

Check that the installation is successful by typing shufflenet at the command line. If the required support package is installed, then the function returns a DAGNetwork object.

ans = 

  DAGNetwork with properties:

         Layers: [173×1 nnet.cnn.layer.Layer]
    Connections: [188×2 table]

You can use transfer learning to retrain the network to classify a new set of images.

Open the example Train Deep Learning Network to Classify New Images. The original example uses the GoogLeNet pretrained network. To perform transfer learning using a different network, load your desired pretrained network and follow the steps in the example.

Load the ShuffleNet network instead of GoogLeNet.

net = shufflenet

Follow the remaining steps in the example to retrain your network. You must replace the last learnable layer and the classification layer in your network with new layers for training. The example shows you how to find which layers to replace.

Output Arguments

collapse all

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


[1] ImageNet.

[2] Zhang, Xiangyu, Xinyu Zhou, Mengxiao Lin, and Jian Sun. "ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices." arXiv preprint arXiv: 1707.01083v2 (2017).

Introduced in R2019a