private void setupBtmTop(Blob <T> btm, Blob <T> top)
{
m_rgBtm.Clear();
m_rgBtm.Add(btm);
m_rgTop.Clear();
m_rgTop.Add(top);
}
private void addInternal(Blob <T> bottom, Blob <T> top)
{
m_colInternalBottom.Clear();
m_colInternalBottom.Add(bottom);
m_colInternalTop.Clear();
m_colInternalTop.Add(top);
}
/// <summary>
/// Setup the layer.
/// </summary>
/// <param name="colBottom">Specifies the collection of bottom (input) Blobs.</param>
/// <param name="colTop">Specifies the collection of top (output) Blobs.</param>
public override void LayerSetUp(BlobCollection <T> colBottom, BlobCollection <T> colTop)
{
base.LayerSetUp(colBottom, colTop);
// Internal softmax layer.
LayerParameter softmax_param = new LayerParameter(LayerParameter.LayerType.SOFTMAX);
softmax_param.softmax_param.axis = m_param.infogain_loss_param.axis;
softmax_param.loss_weight.Clear();
softmax_param.loss_weight.Add(1);
m_softmaxLayer = new SoftmaxLayer <T>(m_cuda, m_log, softmax_param);
m_colSoftmaxBottomVec.Clear();
m_colSoftmaxBottomVec.Add(colBottom[0]);
m_colSoftmaxTopVec.Clear();
m_colSoftmaxTopVec.Add(m_blobProb);
m_softmaxLayer.Setup(m_colSoftmaxBottomVec, m_colSoftmaxTopVec);
// ignore label.
m_nIgnoreLabel = m_param.loss_param.ignore_label;
// normalization
m_log.CHECK(!m_param.loss_param.normalize, "normalize is drepreciated, use 'normalization'.");
m_normalization = m_param.loss_param.normalization;
// matrix H
if (colBottom.Count < 3)
{
m_log.CHECK(m_param.infogain_loss_param.source != null, "Infogain matrix source must be specified.");
PersistCaffe <T> persist = new PersistCaffe <T>(m_log, true);
BlobProto blobProto = persist.LoadBlobProto(m_param.infogain_loss_param.source, 1);
m_blobInfoGain.FromProto(blobProto);
}
}
/// <summary>
/// Setup the layer.
/// </summary>
/// <param name="colBottom">Specifies the collection of bottom (input) Blobs.</param>
/// <param name="colTop">Specifies the collection of top (output) Blobs.</param>
public override void LayerSetUp(BlobCollection <T> colBottom, BlobCollection <T> colTop)
{
base.LayerSetUp(colBottom, colTop);
m_colSigmoidBottom.Clear();
m_colSigmoidBottom.Add(m_blobSigmoidInput);
m_colSigmoidTop.Clear();
m_colSigmoidTop.Add(m_blobSigmoidOutput);
m_sigmoidLayer.LayerSetUp(m_colSigmoidBottom, m_colSigmoidTop);
}
/// <summary>
/// Setup the layer.
/// </summary>
/// <param name="colBottom">Specifies the collection of bottom (input) Blobs.</param>
/// <param name="colTop">Specifies the collection of top (output) Blobs.</param>
public override void LayerSetUp(BlobCollection <T> colBottom, BlobCollection <T> colTop)
{
base.LayerSetUp(colBottom, colTop);
m_colSigmoidBottomVec.Clear();
m_colSigmoidBottomVec.Add(colBottom[0]);
m_colSigmoidTopVec.Clear();
m_colSigmoidTopVec.Add(m_blobSigmoidOutput);
m_sigmoidLayer.Setup(m_colSigmoidBottomVec, m_colSigmoidTopVec);
m_nIgnoreLabel = m_param.loss_param.ignore_label;
}
/// <summary>
/// Runs the pre-solve which parpares the Solver to start Solving.
/// </summary>
public void PreSolve()
{
BlobCollection <T> colNetParams = m_net.learnable_parameters;
m_colHistory.Clear(true);
// m_colUpdate.Clear(true);
m_colTemp.Clear(true);
for (int i = 0; i < colNetParams.Count; i++)
{
List <int> rgShape = colNetParams[i].shape();
m_colHistory.Add(new Blob <T>(m_cuda, m_log, rgShape, false)); // diff never used
// m_colUpdate.Add(new Blob<T>(m_cuda, m_log, rgShape, false));
m_colTemp.Add(new Blob <T>(m_cuda, m_log, rgShape, false)); // diff never used
}
}
/// <summary>
/// Runs the pre-solve which parpares the Solver to start Solving.
/// </summary>
public void PreSolve()
{
BlobCollection <T> net_params = m_net.learnable_parameters;
m_nN = 0;
for (int i = 0; i < net_params.Count; i++)
{
if (m_net.params_lr[i] != 0)
{
m_nN += net_params[i].count();
}
}
// Nothing to do, all learnable parameters have lr_mult = 0
if (m_nN == 0)
{
return;
}
List <int> rgShape = new List <int>()
{
m_nN
};
m_colBlobHistoryS.Clear();
m_colBlobHistoryY.Clear();
m_rgRhoHistory.Clear();
m_nStart = 0;
m_nEnd = -1;
m_blobGradients = new Blob <T>(m_cuda, m_log, rgShape, false);
m_blobGradients.Name = "gradients";
m_blobGradientsPrev = new Blob <T>(m_cuda, m_log, rgShape, false);
m_blobGradientsPrev.Name = "gradients prev";
m_blobDirection = new Blob <T>(m_cuda, m_log, rgShape, false);
m_blobDirection.Name = "direction";
for (int i = 0; i < m_param.lbgfs_corrections; i++)
{
m_colBlobHistoryS.Add(new Blob <T>(m_cuda, m_log, rgShape, false));
m_colBlobHistoryY.Add(new Blob <T>(m_cuda, m_log, rgShape, false));
m_rgRhoHistory.Add(0);
}
}
