How to extract features from different layers in GoogLeNet?

Question

Sivaramakrishnan Rajaraman 2017-11-28

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/369606-how-to-extract-features-from-different-layers-in-googlenet

回答： michael scheinfeild 2018-7-22

采纳的回答： michael scheinfeild

Commonly we extract features using:

net = googlenet()

%Extract features

featureLayer = 'pool5-drop_7x7_s1';

How to extract features from a different layer earlier in the network? I attempting extracting from a different layer but the output of the layer is in 4D. I tried to squeeze it but its not working for those layers. Kindly assist with the syntax for other layers as well.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

michael scheinfeild 2018-7-22

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/369606-how-to-extract-features-from-different-layers-in-googlenet#answer_329803

在 MATLAB Online 中打开

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');