Scribd
Upload
1K views2 pages

Pretrained ResNet-18 Convolutional Neural Network - MATLAB Resnet18

The document describes the pretrained ResNet-18 convolutional neural network in MATLAB. ResNet-18 is an 18 layer deep network trained on over 1 million images to classify images into 1000 categories. The document provides information on using the pretrained ResNet-18 model to classify new images or retrain the network for a new task.

Uploaded by

sidharth mahotra
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
1K views2 pages

Pretrained ResNet-18 Convolutional Neural Network - MATLAB Resnet18

The document describes the pretrained ResNet-18 convolutional neural network in MATLAB. ResNet-18 is an 18 layer deep network trained on over 1 million images to classify images into 1000 categories. The document provides information on using the pretrained ResNet-18 model to classify new images or retrain the network for a new task.

Uploaded by

sidharth mahotra
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

11/11/2018 Pretrained ResNet-18 convolutional neural network - MATLAB resnet18

resnet18
Pretrained ResNet-18 convolutional neural network

ResNet-18 is a convolutional neural network that is trained on more than a million images from the ImageNet database [1].
The network is 18 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 ResNet-18 model. Follow the steps of Classify Image Using
GoogLeNet and replace GoogLeNet with ResNet-18.

To retrain the network on a new classification task, follow the steps of Train Deep Learning Network to Classify New
Images. Load the ResNet-18 model instead of GoogLeNet and change the names of the layers that you replace to
'fc1000' and 'ClassificationLayer_predictions', respectively.

Syntax

net = resnet18

Description
net = resnet18 returns a pretrained ResNet-18 convolutional neural network. example

This function requires the Deep Learning Toolbox™ Model for ResNet-18 Network support package. If this
support package is not installed, then the function provides a download link.

Examples collapse all

 Download ResNet-18 Support Package

Download and install the Deep Learning Toolbox Model for ResNet-18 Network support package.

Type resnet18 at the command line.

resnet18

If the Deep Learning Toolbox Model for ResNet-18 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 resnet18 at the command line. If the
required support package is installed, then the function returns a DAGNetwork object.

resnet18

ans =

DAGNetwork with properties:

Layers: [72×1 nnet.cnn.layer.Layer]


Connections: [79×2 table]

Output Arguments
collapse all

https://www.mathworks.com/help/deeplearning/ref/resnet18.html?s_tid=doc_ta 1/2
11/11/2018 Pretrained ResNet-18 convolutional neural network - MATLAB resnet18

net — Pretrained ResNet-18 convolutional neural network


 DAGNetwork object

Pretrained ResNet-18 convolutional neural network, returned as a DAGNetwork object.

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

[2] He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Deep residual learning for image recognition." In
Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778. 2016.

See Also
DAGNetwork | alexnet | densenet201 | googlenet | inceptionresnetv2 | layerGraph | plot | resnet101 | resnet50 |
squeezenet | trainNetwork | vgg16 | vgg19

Topics
Deep Learning in MATLAB
Pretrained Convolutional Neural Networks
Classify Image Using GoogLeNet
Train Deep Learning Network to Classify New Images
Train Residual Network for Image Classification

Introduced in R2018a

How useful was this information?

Why did you choose this rating?

https://www.mathworks.com/help/deeplearning/ref/resnet18.html?s_tid=doc_ta 2/2

You might also like