File Exchange

image thumbnail

Deep Learning Toolbox Model for GoogLeNet Network

Pretrained GoogLeNet network model for image classification


Updated 20 Mar 2019

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.
Usage Example:
% 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

Comments and Ratings (37)

pei xiang

emma emma

hi ,i'm using Matlab 2019a .Canyou send me a .zip file for this or anything that will be compatible with my current version ?
my email ID:

Jin Huo


Hi can anyone send the alexnet installation zip file to my mail
Thanks in advance

Hi ,
Is there any video describing the Deep Learning Toolbox with an example ?
I have many questions such how many videos I need for deep learning
Thank you .

hi ,i'm currently using Matlab 2016a .Can anyone send me a .zip file for this or anything that will be compatible with my current version ? my email ID:

Hao You

Hi, i'm trying download it, but there is an error message: The support package is not compatible with your version of MATLAB or operating system.
I have installed in my computer Windows 10 and Matlab R2018b. Can you help me?

Fuad Numan

zhenyu tong

feibai zhu

Shayan Goli

Andrew Kim

Hi, I'm using a R2016a, R2017b .I just want to test about deep learning by using matlab. but Unforutnately I cannot receive file related website. I guess security system would block from your website. So I need to get a file which is... googLenet directly. So plz. Could you send me a file? My email address is . Thank you!

thank you help to bring new ai to the world fast transfer learning


hua ye

great works immidiatly no effort



The name of the first and second fully connected layer are 'fc6' & 'fc7' respectively in (Alexnet, VGG16,VGG19). the question is what's the fully connected layer names in googlenet?


Hey Shounak Mitra, thank you! I have solved it. The key is to create a copy of googlenet (with data augmentation) with DAGNetwork function.

Hey Xiao,
That's true, you would have to follow some instructions outlined at

For your reference, you can also refer to 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 ( 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

MATLAB Release Compatibility
Created with R2017b
Compatible with R2017b to R2019a
Platform Compatibility
Windows macOS Linux

Discover Live Editor

Create scripts with code, output, and formatted text in a single executable document.

Learn About Live Editor