Googlenet
Googlenet卷积神经网络
描述
Googlenet是一个卷积神经网络,深度为22层。您可以在Imagenet上加载经过训练的网络的审计版本[1]或Places365[2][3]data sets. The network trained on ImageNet classifies images into 1000 object categories, such as keyboard, mouse, pencil, and many animals. The network trained on Places365 is similar to the network trained on ImageNet, but classifies images into 365 different place categories, such as field, park, runway, and lobby. These networks have learned different feature representations for a wide range of images. The pretrained networks both have an image input size of 224-by-224. For more pretrained networks in MATLAB®, 看Pretrained Deep Neural Networks。
要使用Googlenet对新图像进行分类,请使用classify
。例如,请参阅Classify Image Using GoogLeNet。
您可以重新训练GoogleNet网络,以使用转移学习执行新任务。在执行传输学习时,最常见的方法是使用在ImageNet数据集上预测的网络。如果新任务类似于分类场景,则使用在Placs-365上训练的网络可以提供更高的精度。有关如何在新的分类任务上重新训练googlenet的示例,请参见Train Deep Learning Network to Classify New Images
返回在ImageNet数据集上训练的Googlenet网络。net
= googlenet
此功能需要深度学习工具箱™模型对于Googlenet网络万博1manbetx支持包。如果未安装此支持万博1manbetx包,则该功能提供了下载链接。
返回在ImageNet或Placs365数据集上训练的Googlenet网络。语法net
= googlenet('Weights',weights
)Googlenet('Weights','imagenet')
(默认)等效于Googlenet
。
在Imagenet上训练的网络需要深度学习工具箱模型对于Googlenet网络万博1manbetx支持包。在Place365上训练的网络需要深度学习工具箱模型for Places365-GoogLeNet Network万博1manbetx支持包。如果the required support package is not installed, then the function provides a download link.
returns the untrained GoogLeNet network architecture. The untrained model does not require the support package.lgraph
= googlenet('Weights','没有任何'
)
例子
输入参数
输出参数
References
[1]成像网。http://www.image-net.org
[2] Zhou,Bolei,Aditya Khosla,Agata Lapedriza,Antonio Torralba和Aude Oliva。“地点:用于深度场景理解的图像数据库。”ARXIV预印ARXIV:1610.02055(2016).
[3]地方。http://places2.csail.mit.edu/
[4] Szegedy, Christian, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. "Going deeper with convolutions." InProceedings of the IEEE conference on computer vision and pattern recognition,,,,pp. 1-9. 2015.
[5]BVLC Googlenet模型。https://github.com/bvlc/caffe/tree/master/models/bvlc_googlenet