resnet101

Pretrained ResNet-101 convolutional neural network

ResNet-101 is a convolutional neural network that is trained on more than a million images from the ImageNet database [1]. The network is 101 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-101 model. Follow the steps of Classify Image Using GoogLeNet and replace GoogLeNet with ResNet-101.

To retrain the network on a new classification task, follow the steps of Train Deep Learning Network to Classify New Images. Load the ResNet-101 model instead of GoogLeNet and change the names of the layers that you replace to 'fc1000' and 'ClassificationLayer_predictions', respectively.

Syntax

net = resnet101

Description

net = resnet101 returns a pretrained ResNet-101 network.

This function requires the Deep Learning Toolbox™ Model for ResNet-101 Network support package. If this support package is not installed, then the function provides a download link.

Examples

Download ResNet-101 Support Package

Download and install the Deep Learning Toolbox Model for ResNet-101 Network support package.

Type resnet101 at the command line.

resnet101

If the Deep Learning Toolbox Model for ResNet-101 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 resnet101 at the command line. If the required support package is installed, then the function returns a DAGNetwork object.

resnet101

ans = 

  DAGNetwork with properties:

         Layers: [347×1 nnet.cnn.layer.Layer]
    Connections: [379×2 table]

Output Arguments

net — Pretrained ResNet-101 convolutional neural network

DAGNetwork object

Pretrained ResNet-101 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.

[3] https://github.com/KaimingHe/deep-residual-networks

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 = resnet101 or by passing the resnet101 function to coder.loadDeepLearningNetwork. For example: net = coder.loadDeepLearningNetwork('resnet101')

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