/// <summary>
/// Unflatten the weights, copy the flat network weights to the
/// neural network weight matrixes.
/// </summary>
public void UnflattenWeights()
{
if (flat != null)
{
double[] sourceWeights = flat.Weights;
NetworkCODEC.ArrayToNetwork(sourceWeights, network);
this.flatUpdate = FlatUpdateNeeded.None;
// update context layers
foreach (ILayer layer in this.layers)
{
if (layer is ContextLayer)
{
ContextLayer context = (ContextLayer)layer;
if (context.FlatContextIndex != -1)
{
EngineArray.ArrayCopy(
this.flat.LayerOutput,
context.FlatContextIndex,
context.Context.Data,
0,
context.Context.Count);
}
}
}
}
}
/// <summary>
/// Update the flat network. Either flatten or unflatten as needed.
/// </summary>
public void UpdateFlatNetwork()
{
// if flatUpdate is null, the network was likely just loaded from a serialized file
if (this.flatUpdate == null)
{
FlattenWeights();
this.flatUpdate = FlatUpdateNeeded.None;
}
switch (this.flatUpdate)
{
case FlatUpdateNeeded.Flatten:
FlattenWeights();
break;
case FlatUpdateNeeded.Unflatten:
UnflattenWeights();
break;
case FlatUpdateNeeded.None:
case FlatUpdateNeeded.Never:
return;
}
this.flatUpdate = FlatUpdateNeeded.None;
}
/// <summary>
/// Flatten the weights of a neural network.
/// </summary>
public void FlattenWeights()
{
if (this.flat != null)
{
this.flatUpdate = FlatUpdateNeeded.Flatten;
double[] targetWeights = this.flat.Weights;
double[] sourceWeights = NetworkCODEC.NetworkToArray(this.network);
EngineArray.ArrayCopy(sourceWeights, targetWeights);
this.flatUpdate = FlatUpdateNeeded.None;
// update context layers
foreach (ILayer layer in this.layers)
{
if (layer is ContextLayer)
{
ContextLayer context = (ContextLayer)layer;
if (context.FlatContextIndex != -1)
{
EngineArray.ArrayCopy(
context.Context.Data,
0,
this.flat.LayerOutput,
context.FlatContextIndex,
context.Context.Count);
}
}
}
// handle limited connection networks
if (this.connectionLimited)
{
this.flat.ConnectionLimit = this.connectionLimit;
}
else
{
this.flat.ClearConnectionLimit();
}
}
}
/// <summary>
/// Create the flat neural network.
/// </summary>
public void Flatten()
{
bool isRBF = false;
IDictionary <ILayer, FlatLayer> regular2flat = new Dictionary <ILayer, FlatLayer>();
IDictionary <FlatLayer, ILayer> flat2regular = new Dictionary <FlatLayer, ILayer>();
IList <ObjectPair <ILayer, ILayer> > contexts = new List <ObjectPair <ILayer, ILayer> >();
this.flat = null;
ValidateForFlat val = new ValidateForFlat();
if (val.IsValid(this.network) == null)
{
if (this.layers.Count == 3 &&
this.layers[1] is RadialBasisFunctionLayer)
{
RadialBasisFunctionLayer rbf = (RadialBasisFunctionLayer)this.layers[1];
this.flat = new FlatNetworkRBF(this.network.InputCount,
rbf.NeuronCount, this.network.OutputCount,
rbf.RadialBasisFunction);
FlattenWeights();
this.flatUpdate = FlatUpdateNeeded.None;
return;
}
int flatLayerCount = CountNonContext();
FlatLayer[] flatLayers = new FlatLayer[flatLayerCount];
int index = flatLayers.Length - 1;
foreach (ILayer layer in this.layers)
{
if (layer is ContextLayer)
{
ISynapse inboundSynapse = network.Structure
.FindPreviousSynapseByLayerType(layer,
typeof(BasicLayer));
ISynapse outboundSynapse = network
.Structure
.FindNextSynapseByLayerType(layer, typeof(BasicLayer));
if (inboundSynapse == null)
{
throw new NeuralNetworkError(
"Context layer must be connected to by one BasicLayer.");
}
if (outboundSynapse == null)
{
throw new NeuralNetworkError(
"Context layer must connect to by one BasicLayer.");
}
ILayer inbound = inboundSynapse.FromLayer;
ILayer outbound = outboundSynapse.ToLayer;
contexts
.Add(new ObjectPair <ILayer, ILayer>(inbound, outbound));
}
else
{
double bias = this.FindNextBias(layer);
IActivationFunction activationType;
double[] param = new double[1];
if (layer.ActivationFunction == null)
{
activationType = new ActivationLinear();
param = new double[1];
param[0] = 1;
}
else
{
activationType = layer.ActivationFunction;
param = layer.ActivationFunction.Params;
}
FlatLayer flatLayer = new FlatLayer(activationType, layer
.NeuronCount, bias, param);
regular2flat[layer] = flatLayer;
flat2regular[flatLayer] = layer;
flatLayers[index--] = flatLayer;
}
}
// now link up the context layers
foreach (ObjectPair <ILayer, ILayer> context in contexts)
{
// link the context layer on the FlatLayer
ILayer layer = context.B;
ISynapse synapse = this.network
.Structure
.FindPreviousSynapseByLayerType(layer, typeof(BasicLayer));
FlatLayer from = regular2flat[context.A];
FlatLayer to = regular2flat[synapse.FromLayer];
to.ContextFedBy = from;
}
this.flat = new FlatNetwork(flatLayers);
// update the context indexes on the non-flat network
for (int i = 0; i < flatLayerCount; i++)
{
FlatLayer fedBy = flatLayers[i].ContextFedBy;
if (fedBy != null)
{
ILayer fedBy2 = flat2regular[flatLayers[i + 1]];
ISynapse synapse = FindPreviousSynapseByLayerType(fedBy2, typeof(ContextLayer));
if (synapse == null)
{
throw new NeuralNetworkError("Can't find parent synapse to context layer.");
}
ContextLayer context = (ContextLayer)synapse.FromLayer;
// find fedby index
int fedByIndex = -1;
for (int j = 0; j < flatLayerCount; j++)
{
if (flatLayers[j] == fedBy)
{
fedByIndex = j;
break;
}
}
if (fedByIndex == -1)
{
throw new NeuralNetworkError("Can't find layer feeding context.");
}
context.FlatContextIndex = this.flat.ContextTargetOffset[fedByIndex];
}
}
// RBF networks will not train every layer
if (isRBF)
{
this.flat.EndTraining = flatLayers.Length - 1;
}
FlattenWeights();
if (this.IsConnectionLimited)
{
}
this.flatUpdate = FlatUpdateNeeded.None;
}
else
{
this.flatUpdate = FlatUpdateNeeded.Never;
}
}
/// <summary>
/// Unflatten the weights, copy the flat network weights to the
/// neural network weight matrixes.
/// </summary>
public void UnflattenWeights()
{
if (flat != null)
{
double[] sourceWeights = flat.Weights;
NetworkCODEC.ArrayToNetwork(sourceWeights, network);
this.flatUpdate = FlatUpdateNeeded.None;
// update context layers
foreach (ILayer layer in this.layers)
{
if (layer is ContextLayer)
{
ContextLayer context = (ContextLayer)layer;
if (context.FlatContextIndex != -1)
{
EngineArray.ArrayCopy(
this.flat.LayerOutput,
context.FlatContextIndex,
context.Context.Data,
0,
context.Context.Count);
}
}
}
}
}
/// <summary>
/// Update the flat network. Either flatten or unflatten as needed.
/// </summary>
public void UpdateFlatNetwork()
{
// if flatUpdate is null, the network was likely just loaded from a serialized file
if (this.flatUpdate == null)
{
FlattenWeights();
this.flatUpdate = FlatUpdateNeeded.None;
}
switch (this.flatUpdate)
{
case FlatUpdateNeeded.Flatten:
FlattenWeights();
break;
case FlatUpdateNeeded.Unflatten:
UnflattenWeights();
break;
case FlatUpdateNeeded.None:
case FlatUpdateNeeded.Never:
return;
}
this.flatUpdate = FlatUpdateNeeded.None;
}
/// <summary>
/// Flatten the weights of a neural network.
/// </summary>
public void FlattenWeights()
{
if (this.flat != null)
{
this.flatUpdate = FlatUpdateNeeded.Flatten;
double[] targetWeights = this.flat.Weights;
double[] sourceWeights = NetworkCODEC.NetworkToArray(this.network);
EngineArray.ArrayCopy(sourceWeights, targetWeights);
this.flatUpdate = FlatUpdateNeeded.None;
// update context layers
foreach( ILayer layer in this.layers )
{
if( layer is ContextLayer )
{
ContextLayer context = (ContextLayer)layer;
if (context.FlatContextIndex != -1)
{
EngineArray.ArrayCopy(
context.Context.Data,
0,
this.flat.LayerOutput,
context.FlatContextIndex,
context.Context.Count);
}
}
}
// handle limited connection networks
if (this.connectionLimited)
{
this.flat.ConnectionLimit = this.connectionLimit;
}
else
{
this.flat.ClearConnectionLimit();
}
}
}
/// <summary>
/// Create the flat neural network.
/// </summary>
public void Flatten()
{
bool isRBF = false;
IDictionary<ILayer, FlatLayer> regular2flat = new Dictionary<ILayer, FlatLayer>();
IDictionary<FlatLayer, ILayer> flat2regular = new Dictionary<FlatLayer, ILayer>();
IList<ObjectPair<ILayer, ILayer>> contexts = new List<ObjectPair<ILayer, ILayer>>();
this.flat = null;
ValidateForFlat val = new ValidateForFlat();
if (val.IsValid(this.network) == null)
{
if (this.layers.Count == 3
&& this.layers[1] is RadialBasisFunctionLayer)
{
RadialBasisFunctionLayer rbf = (RadialBasisFunctionLayer)this.layers[1];
this.flat = new FlatNetworkRBF(this.network.InputCount,
rbf.NeuronCount, this.network.OutputCount,
rbf.RadialBasisFunction);
FlattenWeights();
this.flatUpdate = FlatUpdateNeeded.None;
return;
}
int flatLayerCount = CountNonContext();
FlatLayer[] flatLayers = new FlatLayer[flatLayerCount];
int index = flatLayers.Length - 1;
foreach (ILayer layer in this.layers)
{
if (layer is ContextLayer)
{
ISynapse inboundSynapse = network.Structure
.FindPreviousSynapseByLayerType(layer,
typeof(BasicLayer));
ISynapse outboundSynapse = network
.Structure
.FindNextSynapseByLayerType(layer, typeof(BasicLayer));
if (inboundSynapse == null)
throw new NeuralNetworkError(
"Context layer must be connected to by one BasicLayer.");
if (outboundSynapse == null)
throw new NeuralNetworkError(
"Context layer must connect to by one BasicLayer.");
ILayer inbound = inboundSynapse.FromLayer;
ILayer outbound = outboundSynapse.ToLayer;
contexts
.Add(new ObjectPair<ILayer, ILayer>(inbound, outbound));
}
else
{
double bias = this.FindNextBias(layer);
IActivationFunction activationType;
double[] param = new double[1];
if (layer.ActivationFunction == null)
{
activationType = new ActivationLinear();
param = new double[1];
param[0] = 1;
}
else
{
activationType = layer.ActivationFunction;
param = layer.ActivationFunction.Params;
}
FlatLayer flatLayer = new FlatLayer(activationType, layer
.NeuronCount, bias, param);
regular2flat[layer] = flatLayer;
flat2regular[flatLayer] = layer;
flatLayers[index--] = flatLayer;
}
}
// now link up the context layers
foreach (ObjectPair<ILayer, ILayer> context in contexts)
{
// link the context layer on the FlatLayer
ILayer layer = context.B;
ISynapse synapse = this.network
.Structure
.FindPreviousSynapseByLayerType(layer, typeof(BasicLayer));
FlatLayer from = regular2flat[context.A];
FlatLayer to = regular2flat[synapse.FromLayer];
to.ContextFedBy = from;
}
this.flat = new FlatNetwork(flatLayers);
// update the context indexes on the non-flat network
for (int i = 0; i < flatLayerCount; i++)
{
FlatLayer fedBy = flatLayers[i].ContextFedBy;
if (fedBy != null)
{
ILayer fedBy2 = flat2regular[flatLayers[i + 1]];
ISynapse synapse = FindPreviousSynapseByLayerType(fedBy2, typeof(ContextLayer));
if (synapse == null)
throw new NeuralNetworkError("Can't find parent synapse to context layer.");
ContextLayer context = (ContextLayer)synapse.FromLayer;
// find fedby index
int fedByIndex = -1;
for(int j=0;j<flatLayerCount;j++)
{
if( flatLayers[j]==fedBy )
{
fedByIndex = j;
break;
}
}
if (fedByIndex == -1)
throw new NeuralNetworkError("Can't find layer feeding context.");
context.FlatContextIndex = this.flat.ContextTargetOffset[fedByIndex];
}
}
// RBF networks will not train every layer
if (isRBF)
{
this.flat.EndTraining = flatLayers.Length - 1;
}
FlattenWeights();
if (this.IsConnectionLimited)
{
}
this.flatUpdate = FlatUpdateNeeded.None;
}
else
this.flatUpdate = FlatUpdateNeeded.Never;
}
