How to extract features from different layers in GoogLeNet?

10 visualizaciones (últimos 30 días)
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.

Respuesta aceptada

michael scheinfeild
michael scheinfeild el 22 de Jul. de 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');

Más respuestas (0)

Categorías

Más información sobre Image Data Workflows en Help Center y File Exchange.

Etiquetas

Community Treasure Hunt

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

Start Hunting!

Translated by