deep autoencoder by using (trainAutoencoder and stack) functions

1 次查看（过去 30 天）

ahmad karim 2017-8-22

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/353698-deep-autoencoder-by-using-trainautoencoder-and-stack-functions

Dears, when i implements this below code i take the error thats in the attach? what is the resaon i think its because of the version of matlab or what? my version is 2015 [X,T] = wine_dataset;

hiddenSize = 10; autoenc1 = trainAutoencoder(X,hiddenSize,... 'L2WeightRegularization',0.001,... 'SparsityRegularization',4,... 'SparsityProportion',0.05,... 'DecoderTransferFunction','purelin');

features1 = encode(autoenc1,X);

hiddenSize = 10; autoenc2 = trainAutoencoder(features1,hiddenSize,... 'L2WeightRegularization',0.001,... 'SparsityRegularization',4,... 'SparsityProportion',0.05,... 'DecoderTransferFunction','purelin',... 'ScaleData',false);

features2 = encode(autoenc2,features1);

softnet = trainSoftmaxLayer(features2,T,'LossFunction','crossentropy');

deepnet = stack(autoenc1,autoenc2,softnet);

deepnet = train(deepnet,X,T);

wine_type = deepnet(X);

plotconfusion(T,wine_type);