Commit b315eb89 authored by Cédric Traizet's avatar Cédric Traizet
Browse files

bug correct : output vector of m_net.evalLayer was not taken from the right layer

parent 4a75d17a
......@@ -365,7 +365,7 @@ AutoencoderModel<TInputValue,NeuronType>::DoPredict(const InputSampleType & valu
shark::Data<shark::RealVector> data = shark::createDataFromRange(features);
data = m_net.evalLayer( m_net.layerMatrices().size()/2 ,data); // features layer for a network containing the encoder and decoder part
data = m_net.evalLayer( m_net.layerMatrices().size()/2-1 ,data); // features layer for a network containing the encoder and decoder part
/*
for (int i=0; i<m_net.size(); i++){ // loop over all autoencoders in m_net
data = m_net[i].encode(data);
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment