GoogLeNet is a pretrained model that has been trained on a subset of the ImageNet database which is used in the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC). The model is trained on more than a million images, has 144 layers, and can classify images into 1000 object categories (e.g. keyboard, mouse, pencil, and many animals).
Opening the googlenet.mlpkginstall file from your operating system or from within MATLAB will initiate the installation process for the release you have.
This mlpkginstall file is functional for R2017b and beyond.
% Access the trained model
net = googlenet;
% See details of the architecture
% Read the image to classify
I = imread('peppers.png');
% Adjust size of the image
sz = net.Layers(1).InputSize
I = I(1:sz(1),1:sz(2),1:sz(3));
% Classify the image using GoogLeNet
label = classify(net, I)
% Show the image and the classification results
Hey Shounak Mitra, thank you! I have solved it. The key is to create a copy of googlenet (with data augmentation) with DAGNetwork function.
That's true, you would have to follow some instructions outlined at https://www.mathworks.com/help/nnet/ref/nnet.cnn.layergraph.html?s_tid=doc_ta
For your reference, you can also refer to https://www.mathworks.com/help/nnet/ref/imagedataaugmenter.html?s_tid=srchtitle to know more about the imageDataAugmenter
you cannot manipulate the layers like that. Have you tried going through this
I try to change the inputImageLayer for data augmentation, but occured the error: You cannot set the read-only property 'Layers' of DAGNetwork.
thank you, good tutorial. I have a question. How to implement data augmentation for googlenet?
Kuan, unfortunately, you cannot. you ought to have R2017b version. But you can use another model - AlexNet (https://www.mathworks.com/matlabcentral/fileexchange/59133-neural-network-toolbox-tm--model-for-alexnet-network) with the 17a version.
Hi, can I use it in R2017a version?
Thank you, such a nice tool.
Are you using the R2017b version?
Hello, I try to download it and I get an error message:
The support package is not compatible with your version of MATLAB or operating system
Does not need PCT
The piece of text 'This is for 17b GR' doesn't look appropriate for 'Other Requirements'
Download apps, toolboxes, and other File Exchange content using Add-On Explorer in MATLAB.