File Exchange

image thumbnail

Deep Learning ToolboxTM Model for NASNet-Large Network

Pretrained NasNet-Large network model for image classification

23 Downloads

Updated 18 Mar 2020

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.

Usage Example:

% Access the trained model
net = 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 nasnetlarge
label = classify(net, I)

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

To learn more about the network, please visit the documentation page: https://www.mathworks.com/help/deeplearning/ref/nasnetlarge.html

Comments and Ratings (2)

Hassan

atk_dl

Dear DeepLearning Team,

I am using the Matlab R2019b (updated) on Ubuntu, When I train the nasnetlarge network , I get the below error:

"Error using trainNetwork (line 170)
Too many input arguments.

Caused by:
Error using rescale
Too many input arguments."

Do you know what is the problem?

Best,

MATLAB Release Compatibility
Created with R2019a
Compatible with R2019a to R2020a
Platform Compatibility
Windows macOS Linux