File Exchange

image thumbnail

Deep Learning ToolboxTM Model for Places365-GoogLeNet Network

Pretrained GoogLeNet network trained on Places365 data set for image classification


Updated 16 Sep 2020

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. You can read in the network using

net = googlenet
net = googlenet('Weights',weights)

net = googlenet('Weights',weights) returns a GoogLeNet network trained on either the ImageNet or Places365 data set.

If weights equals 'imagenet', then the network has weights trained on the ImageNet data set. If weights equals 'places365' then the network has weights trained on the Places365 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.

You read the network

Usage Example:

net = googlenet('Weights','places365');
im = imread('test.jpg');
sz = net.Layers(1).InputSize;
im = imresize(im,[sz(1) sz(2)]);
label = classify(net, im)

% Show the image and the classification results

Please visit the documentation page to learn more:

Comments and Ratings (4)


Maria Duarte Rosa

Hi Farrar, this support package requires R2019a.

Farrar Telford

It gives a warning as: The support package is not compatible with your version of MATLAB or operating system.
operatin system is Windows 10.
MATLAB R2018b.

Redha Almahdi

MATLAB Release Compatibility
Created with R2019a
Compatible with R2019a to R2020b
Platform Compatibility
Windows macOS Linux