ResNet-50 convolutional neural network
ResNet-50 is a convolutional neural network that is 50 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 224-by-224. For more pretrained networks in MATLAB®, seePretrained Deep Neural Networks.
You can useclassify
to classify new images using the ResNet-50 model. Follow the steps ofClassify Image Using GoogLeNetand replace GoogLeNet with ResNet-50.
To retrain the network on a new classification task, follow the steps ofTrain Deep Learning Network to Classify New Imagesand load ResNet-50 instead of GoogLeNet.
Tip
To create an untrained residual network suitable for image classification tasks, useresnetLayers
.
returns a ResNet-50 network trained on the ImageNet data set.net
= resnet50
This function requires the Deep Learning Toolbox™ Modelfor ResNet-50 Networksupport package. If this support package is not installed, then the function provides a download link.
returns a ResNet-50 network trained on the ImageNet data set. This syntax is equivalent tonet
= resnet50('Weights','imagenet'
)net = resnet50
.
returns the untrained ResNet-50 network architecture. The untrained model does not require the support package.lgraph
= resnet50('Weights','none'
)
[1]ImageNet. http://www.image-net.org
[2] He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Deep residual learning for image recognition." InProceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778. 2016.
Deep Network Designer|resnetLayers
|vgg16
|vgg19
|googlenet
|trainNetwork
|layerGraph
|DAGNetwork
|resnet18
|resnet101
|densenet201
|inceptionresnetv2
|squeezenet