Pretrained GoogLeNet convolutional neural network
GoogLeNet is a pretrained convolutional neural network that is 22 layers deep. You can load a network trained on either the ImageNet  or Places365   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 networks both have an image input size of 224-by-224. For more pretrained networks in MATLAB®, see Pretrained Deep Neural Networks.
You can retrain a GoogLeNet network to perform a new task using transfer learning. When performing transfer learning, the most common approach is to use networks pretrained on the ImageNet data set. If the new task is similar to classifying scenes, then using the network trained on Places-365 can give higher accuracies. For an example showing how to retrain GoogLeNet on a new classification task, see Train Deep Learning Network to Classify New Images
net = googlenet
net = googlenet('Weights',weights)
returns a GoogLeNet network
trained on the ImageNet data set.
net = googlenet
This function requires the Deep Learning Toolbox™ Model for GoogLeNet Network support package. If this support package is not installed, then the function provides a download link.
The network trained on ImageNet requires the Deep Learning Toolbox Model for GoogLeNet Network support package. The network trained on Places365 requires the Deep Learning Toolbox Model for Places365-GoogLeNet Network support package. If the required support package is not installed, then the function provides a download link.
Download and install the Deep Learning Toolbox Model for GoogLeNet Network support package.
googlenet at the command line.
If the Deep Learning
Toolbox Model for GoogLeNet 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
googlenet at the command line. If the required support package is
installed, then the function returns a
ans = DAGNetwork with properties: Layers: [144×1 nnet.cnn.layer.Layer] Connections: [170×2 table]
weights— Source of network parameters
Source of network parameters, specified as
'imagenet', then the
network has weights trained on the ImageNet data set. If
'places365' then the network has weights trained on the
Places365 data set.
 ImageNet. http://www.image-net.org
 Zhou, Bolei, Aditya Khosla, Agata Lapedriza, Antonio Torralba, and Aude Oliva. "Places: An image database for deep scene understanding." arXiv preprint arXiv:1610.02055 (2016).
 Places. http://places2.csail.mit.edu/
 Szegedy, Christian, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. "Going deeper with convolutions." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1-9. 2015.
 BVLC GoogLeNet Model. https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet
For code generation, you can load the network by using the syntax
googlenet or by passing the
googlenet function to
coder.loadDeepLearningNetwork. For example:
For more information, see Load Pretrained Networks for Code Generation (MATLAB Coder).