How to extract features from different layers in GoogLeNet?
4 次查看(过去 30 天)
显示 更早的评论
Sivaramakrishnan Rajaraman
2017-11-28
回答: michael scheinfeild
2018-7-22
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
采纳的回答
michael scheinfeild
2018-7-22
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 个评论
更多回答(0 个)
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!