MATLAB Answers

How to train features that have been extracted by using GoogleNet?

5 views (last 30 days)
sahar alhaddad
sahar alhaddad on 27 Sep 2017
Hello,
I extracted features by using GoogleNet, but I do not know how to train it to create classifier?
Thanks in advance

  6 Comments

Show 3 older comments

Sign in to comment.

Answers (2)

Jatin Waghela
Jatin Waghela on 3 Oct 2017
If I understood you correctly, you would like to transfer learning to retrain GoogLeNet to create a classifier.
Please refer to the below documentation link which gives more information on Pretrained GoogLeNet convolutional neural network:

  7 Comments

Show 4 older comments
rcjr15
rcjr15 on 13 Nov 2017
I am getting error while using the above command. Can someone help me with this? @Jatin Waghela
Sivaramakrishnan Rajaraman
Has anyone tried to extract features from layers other than pool5-drop_7*7_s1? If so what is the syntax?
umit kacar
umit kacar on 7 Mar 2018
https://www.mathworks.com/matlabcentral/answers/379635-error-using-activations-with-googlenet-in-r2017b#answer_302390

Sign in to comment.


michael scheinfeild
michael scheinfeild on 22 Jul 2018
use some layer as the feature . then you can use it for other classifier
net = googlenet;
inputSize = net.Layers(1).InputSize;
imds = imageDatastore(dbpathSave)
augimdsTrain = augmentedImageDatastore(inputSize(1:2),imds );
%%Extract Image Features
layer = 'loss3-classifier';%1000
featuresTrain = activations(net,augimdsTrain,layer,'OutputAs','rows');

  0 Comments

Sign in to comment.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!