densenet201

Pretrained DenseNet-201 convolutional neural network

DenseNet-201 is a convolutional neural network that is trained on more than a million images from the ImageNet database [1]. The network is 201 layers deep and 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 Convolutional Neural Networks.

You can use classify to classify new images using the DenseNet-201 model. Follow the steps of Classify Image Using GoogLeNet and replace GoogLeNet with DenseNet-201.

To retrain the network on a new classification task, follow the steps of Train Deep Learning Network to Classify New Images and load DenseNet-201 instead of GoogLeNet.

Syntax

net = densenet201

Description

net = densenet201 returns a pretrained DenseNet-201 convolutional neural network.

This function requires the Deep Learning Toolbox™ Model for DenseNet-201 Network support package.

Examples

Load DenseNet-201 Network

Download and install the Deep Learning Toolbox Model for DenseNet-201 Network support package using the Add-On Explorer. You can also download the networks from MathWorks Deep Learning Toolbox Team.

After installing the support package, load the network as a DAGNetwork object using densenet201.

net = densenet201

net = 

  DAGNetwork with properties:

         Layers: [709×1 nnet.cnn.layer.Layer]
    Connections: [806×2 table]

Output Arguments

net — Pretrained DenseNet-201 convolutional neural network

DAGNetwork object

Pretrained DenseNet-201 convolutional neural network, returned as a DAGNetwork object.

References

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

[2] Huang, Gao, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q. Weinberger. "Densely Connected Convolutional Networks." In CVPR, vol. 1, no. 2, p. 3. 2017.