How to train features that have been extracted by using GoogleNet?
5 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Hello,
I extracted features by using GoogleNet, but I do not know how to train it to create classifier?
Thanks in advance
6 Kommentare
Antworten (2)
Jatin Waghela
am 3 Okt. 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 Kommentare
Sivaramakrishnan Rajaraman
am 28 Nov. 2017
Has anyone tried to extract features from layers other than pool5-drop_7*7_s1? If so what is the syntax?
umit kacar
am 7 Mär. 2018
https://www.mathworks.com/matlabcentral/answers/379635-error-using-activations-with-googlenet-in-r2017b#answer_302390
michael scheinfeild
am 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 Kommentare
Siehe auch
Kategorien
Mehr zu Classification finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!