/// <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>
/// The constructor.
/// </summary>
/// <param name="cuda">Specifies the instance of CudaDnn to use.</param>
/// <param name="log">Specifies the output log.</param>
/// <param name="evtCancel">Specifies the cancel event used to abort processing.</param>
/// <param name="strModelType">Specifies the model type: 'vgg19', 'vgg16'</param>
/// <param name="strModel">Specifies the network model to use.</param>
/// <param name="rgWeights">Optionally, specifies the weights to use (or <i>null</i> to ignore).</param>
/// <param name="bCaffeModel">Specifies whether or not the weights are in the caffe (<i>true</i>) or mycaffe (<i>false</i>) format.</param>
/// <param name="solverType">Optionally, specifies the solver type to use (default = LBFGS).</param>
/// <param name="dfLearningRate">Optionally, specifies the solver learning rate (default = 1.0).</param>
public NeuralStyleTransfer(CudaDnn <T> cuda, Log log, CancelEvent evtCancel, string strModelType, string strModel, byte[] rgWeights, bool bCaffeModel, SolverParameter.SolverType solverType = SolverParameter.SolverType.LBFGS, double dfLearningRate = 1.0)
{
m_cuda = cuda;
m_log = log;
m_evtCancel = evtCancel;
m_rgWeights = rgWeights;
m_solverType = solverType;
m_dfLearningRate = dfLearningRate;
if (m_evtCancel != null)
{
m_evtCancel.Reset();
}
RawProto proto = RawProto.Parse(strModel);
m_param = NetParameter.FromProto(proto);
add_input_layer(m_param);
m_rgstrUsedLayers = load_layers(strModelType);
prune(m_param, m_rgstrUsedLayers);
add_gram_layers(m_param);
m_transformationParam = new TransformationParameter();
m_transformationParam.color_order = (bCaffeModel) ? TransformationParameter.COLOR_ORDER.BGR : TransformationParameter.COLOR_ORDER.RGB;
m_transformationParam.scale = 1.0;
m_transformationParam.mean_value = m_rgMeanValues;
m_persist = new PersistCaffe <T>(m_log, false);
}
private BlobProto loadProtoMean(string strFile)
{
try
{
if (!File.Exists(strFile))
{
throw new Exception("Cannot find the file '" + strFile + "'!");
}
byte[] rgBytes;
using (FileStream fs = new FileStream(strFile, FileMode.Open, FileAccess.Read))
{
using (BinaryReader br = new BinaryReader(fs))
{
rgBytes = br.ReadBytes((int)fs.Length);
}
}
PersistCaffe <T> persist = new PersistCaffe <T>(m_log, true);
return(persist.LoadBlobProto(rgBytes, 1));
}
catch (Exception excpt)
{
m_log.FAIL("Loading Proto Image Mean: " + excpt.Message);
return(null);
}
}
/// <summary>
/// The constructor.
/// </summary>
/// <param name="cuda">Specifies the instance of CudaDnn to use.</param>
/// <param name="log">Specifies the output log.</param>
/// <param name="evtCancel">Specifies the cancel event used to abort processing.</param>
/// <param name="rgLayers">Specifies the layers along with their style and content weights.</param>
/// <param name="strModelDesc">Specifies the network model descriptor to use.</param>
/// <param name="rgWeights">Optionally, specifies the weights to use (or <i>null</i> to ignore).</param>
/// <param name="bCaffeModel">Specifies whether or not the weights are in the caffe (<i>true</i>) or mycaffe (<i>false</i>) format.</param>
/// <param name="solverType">Optionally, specifies the solver type to use (default = LBFGS).</param>
/// <param name="dfLearningRate">Optionally, specifies the solver learning rate (default = 1.0).</param>
/// <param name="nMaxImageSize">Optionally, specifies the default maximum image size (default = 840).</param>
/// <param name="nLBFGSCorrections">Optionally, specifies the LBFGS Corrections (only used when using the LBFGS solver, default = 100).</param>
/// <param name="netShare">Optionally, specifies a net to share.</param>
public NeuralStyleTransfer(CudaDnn <T> cuda, Log log, CancelEvent evtCancel, Dictionary <string, Tuple <double, double> > rgLayers, string strModelDesc, byte[] rgWeights, bool bCaffeModel, SolverParameter.SolverType solverType = SolverParameter.SolverType.LBFGS, double dfLearningRate = 1.0, int nMaxImageSize = 840, int nLBFGSCorrections = 100, Net <T> netShare = null)
{
m_log = log;
m_evtCancel = evtCancel;
m_rgWeights = rgWeights;
m_solverType = solverType;
m_dfLearningRate = dfLearningRate;
m_nDefaultMaxImageSize = nMaxImageSize;
m_nLBFGSCorrections = nLBFGSCorrections;
setupNetShare(netShare, cuda);
if (m_evtCancel != null)
{
m_evtCancel.Reset();
}
RawProto proto = RawProto.Parse(strModelDesc);
m_param = NetParameter.FromProto(proto);
Dictionary <string, double> rgStyle = new Dictionary <string, double>();
Dictionary <string, double> rgContent = new Dictionary <string, double>();
foreach (KeyValuePair <string, Tuple <double, double> > kv in rgLayers)
{
if (kv.Value.Item1 != 0)
{
rgStyle.Add(kv.Key, kv.Value.Item1);
}
if (kv.Value.Item2 != 0)
{
rgContent.Add(kv.Key, kv.Value.Item2);
}
}
add_input_layer(m_param);
m_rgstrUsedLayers = load_layers(rgStyle, rgContent);
prune(m_param, m_rgstrUsedLayers);
add_gram_layers(m_param);
m_transformationParam = new TransformationParameter();
m_transformationParam.color_order = (bCaffeModel) ? TransformationParameter.COLOR_ORDER.BGR : TransformationParameter.COLOR_ORDER.RGB;
m_transformationParam.scale = 1.0;
m_transformationParam.mean_value = m_rgMeanValues;
m_persist = new PersistCaffe <T>(m_log, false);
}
