How to add a regression layer at the end of an existing CNN?
2 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Tobias Pahlberg
el 29 de Mayo de 2017
Respondida: Tobias Pahlberg
el 6 de Oct. de 2017
Hi
I have been trying to use transfer learning with a regression layer at the end. However, I end up with NaNs when I try to predict new images with the ConvNet. How should I put together the layers at the end? Like this?
% Load VGG network
net = vgg19;
% Remove last 3 layers.
layersTransfer = net.Layers(1:end-3);
% Add a fully connected layer and a regression layer
layers = [layersTransfer
fullyConnectedLayer(1)
regressionLayer];
% Training options
transferLayerOptions = trainingOptions('sgdm','MiniBatchSize',25,...
'InitialLearnRate',0.001, ...
'MaxEpochs',7, 'Verbose', true);
2 comentarios
Birju Patel
el 20 de Jul. de 2017
What happened during training? Did you see NaNs printed in the training log printed in the command window? If so, it's likely your learning rate is too high.
Respuesta aceptada
Más respuestas (0)
Ver también
Categorías
Más información sobre Image Data Workflows en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!