Deep Learning ToolboxTM Model for NASNet-Large Network

Pretrained NasNet-Large network model for image classification

NASNet-Large is a pretrained model that has been trained on a subset of the ImageNet database. This is one of the models from the NASNet architecture family. NASNet architectures were learned from data using a recurrent neural network instead of being fully designed by humans like the other pretrained models.

This model is trained on more than a million images and can classify images into 1000 object categories (e.g. keyboard, mouse, pencil, and many animals).

Opening the nasnetlarge.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 nasnetlarge instead of imagePretrainedNetwork if using a release prior to R2024a.

Usage Example:

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

% See details of the architecture
net.Layers

% 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 NasNet-Large
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')