Deep Learning ToolboxTM Model for Places365-GoogLeNet Network

Pretrained GoogLeNet network trained on Places365 data set for image classification

Place365GoogLeNet is a pretrained model that has been trained on the Places365 data set and has the same underlying network architecture as GoogLeNet that was trained on the ImageNet data set.

Opening the place365googlenet.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 R2019a and beyond. Use googlenet [net = googlenet(Weights="places365")] instead of imagePretrainedNetwork if using a release prior to R2024a.

Usage Example:

% Access the trained model
[net, classes] = imagePretrainedNetwork("googlenet-places365");

% See details of the architecture
net.Layers

% Read the image to classify
I = imread('test.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-Places365
scores = predict(net, single(I));
label = scores2label(scores, classes)

% Show the image and the classification results
figure
imshow(I)
text(10,20,char(label),'Color','white')