public void SaveData(string BaseDirectory, string BaseFileName, ManagedArray data)
{
var filename = string.Format("{0}/{1}.txt", BaseDirectory, BaseFileName);
ManagedFile.Save3D(filename, data);
}
public void SaveClassification(string BaseDirectory, string BaseFileName, ManagedArray classification)
{
var filename = string.Format("{0}/{1}.txt", BaseDirectory, BaseFileName);
ManagedFile.Save2D(filename, classification);
}
// Classify data using trained network parameters and count classification errors
public int Classify(ManagedArray test_input, ManagedArray test_output, int classes, int items, int batchsize, ManagedArray classification, bool pool = false)
{
var errors = 0;
var tempx = new ManagedArray(test_input.x, test_input.y, batchsize, false);
var tempy = new ManagedArray(batchsize, classes, false);
var tempclass = new ManagedArray(1, batchsize, false);
ManagedOps.Free(classification);
classification = new ManagedArray(1, items, false);
for (var i = 0; i < items; i += batchsize)
{
// generate batch
ManagedOps.Copy3D(tempx, test_input, 0, 0, i);
ManagedOps.Copy2D(tempy, test_output, i, 0);
// classify
FeedForward(tempx, pool);
// count classifcation errors
errors += Test(tempy, tempclass);
// save classification
ManagedOps.Copy2DOffset(classification, tempclass, i, 0);
}
ManagedOps.Free(tempx, tempy, tempclass);
return(errors);
}
// Update Network Weights based on computed errors
public void BackPropagation(ManagedArray batch)
{
var n = Layers.Count;
var last = n - 1;
var batchz = Layers[last].Activation.z;
// backprop deltas
ManagedOps.Free(OutputDelta, OutputError);
OutputDelta = new ManagedArray(Output, false);
OutputError = new ManagedArray(Output, false);
for (var x = 0; x < Output.Length(); x++)
{
// error
OutputError[x] = Output[x] - batch[x];
// output delta
OutputDelta[x] = OutputError[x] * (Output[x] * (1 - Output[x]));
}
// Loss Function
L = 0.5 * ManagedMatrix.SquareSum(OutputError) / batch.x;
ManagedOps.Free(WeightsTransposed, FeatureVectorDelta);
FeatureVectorDelta = new ManagedArray(FeatureVector, false);
WeightsTransposed = new ManagedArray(Weights, false);
// feature vector delta
ManagedMatrix.Transpose(WeightsTransposed, Weights);
ManagedMatrix.Multiply(FeatureVectorDelta, WeightsTransposed, OutputDelta);
// only conv layers has sigm function
if (Layers[last].Type == LayerTypes.Convolution)
{
for (var x = 0; x < FeatureVectorDelta.Length(); x++)
{
FeatureVectorDelta[x] = FeatureVectorDelta[x] * FeatureVector[x] * (1 - FeatureVector[x]);
}
}
// reshape feature vector deltas into output map style
var MapSize = Layers[last].Activation.x * Layers[last].Activation.y;
var temp1D = new ManagedArray(1, MapSize, false);
var temp2D = new ManagedArray(Layers[last].Activation.x, Layers[last].Activation.y, false);
ManagedOps.Free(Layers[last].Delta);
Layers[last].Delta = new ManagedArray(Layers[last].Activation, false);
for (var j = 0; j < Layers[last].Activation.i; j++)
{
for (var ii = 0; ii < batchz; ii++)
{
ManagedOps.Copy2D(temp1D, FeatureVectorDelta, ii, j * MapSize);
temp1D.Reshape(Layers[last].Activation.x, Layers[last].Activation.y);
ManagedMatrix.Transpose(temp2D, temp1D);
ManagedOps.Copy2D4D(Layers[last].Delta, temp2D, ii, j);
temp1D.Reshape(1, MapSize);
}
}
ManagedOps.Free(temp1D, temp2D);
for (var l = n - 2; l >= 0; l--)
{
var next = l + 1;
if (Layers[l].Type == LayerTypes.Convolution)
{
ManagedOps.Free(Layers[l].Delta);
Layers[l].Delta = new ManagedArray(Layers[l].Activation, false);
var xx = Layers[next].Scale * Layers[next].Activation.x;
var yy = Layers[next].Scale * Layers[next].Activation.y;
var FeatureMap = new ManagedArray(Layers[next].Activation.x, Layers[next].Activation.y, false);
var FeatureMapExpanded = new ManagedArray(xx, yy, false);
var Activation = new ManagedArray(xx, yy, false);
var Delta = new ManagedArray(xx, yy, false);
var Scale = (1.0 / (Layers[next].Scale * Layers[next].Scale));
for (var j = 0; j < Layers[l].Activation.i; j++)
{
for (var z = 0; z < batchz; z++)
{
ManagedOps.Copy4D2D(FeatureMap, Layers[next].Delta, z, j);
ManagedMatrix.Expand(FeatureMap, Layers[next].Scale, Layers[next].Scale, FeatureMapExpanded);
ManagedOps.Copy4D2D(Activation, Layers[l].Activation, z, j);
for (var x = 0; x < Delta.Length(); x++)
{
Delta[x] = Activation[x] * (1 - Activation[x]) * FeatureMapExpanded[x] * Scale;
}
ManagedOps.Copy2D4D(Layers[l].Delta, Delta, z, j);
}
}
ManagedOps.Free(FeatureMap, FeatureMapExpanded, Activation, Delta);
}
else if (Layers[l].Type == LayerTypes.Subsampling)
{
ManagedOps.Free(Layers[l].Delta);
Layers[l].Delta = new ManagedArray(Layers[l].Activation, false);
var Delta = new ManagedArray(Layers[next].Activation.x, Layers[next].Activation.y, batchz);
var FeatureMap = new ManagedArray(Layers[next].KernelSize, Layers[next].KernelSize, false);
var rot180 = new ManagedArray(Layers[next].KernelSize, Layers[next].KernelSize, false);
var z = new ManagedArray(Layers[l].Activation.x, Layers[l].Activation.y, batchz);
var ztemp = new ManagedArray(Layers[l].Activation.x, Layers[l].Activation.y, batchz, false);
for (var i = 0; i < Layers[l].Activation.i; i++)
{
ManagedOps.Set(z, 0.0);
for (var j = 0; j < Layers[next].Activation.i; j++)
{
ManagedOps.Copy4DIJ2D(FeatureMap, Layers[next].FeatureMap, i, j);
ManagedMatrix.Rotate180(rot180, FeatureMap);
ManagedOps.Copy4D3D(Delta, Layers[next].Delta, j);
ManagedConvolution.Full(Delta, rot180, ztemp);
ManagedMatrix.Add(z, ztemp);
}
ManagedOps.Copy3D4D(Layers[l].Delta, z, i);
}
ManagedOps.Free(Delta, FeatureMap, rot180, z, ztemp);
}
}
// calc gradients
for (var l = 1; l < n; l++)
{
var prev = l - 1;
if (Layers[l].Type == LayerTypes.Convolution)
{
ManagedOps.Free(Layers[l].DeltaFeatureMap, Layers[l].DeltaBias);
Layers[l].DeltaFeatureMap = new ManagedArray(Layers[l].FeatureMap, false);
Layers[l].DeltaBias = new ManagedArray(Layers[l].OutputMaps, false);
var FeatureMapDelta = new ManagedArray(Layers[l].FeatureMap.x, Layers[l].FeatureMap.y, Layers[l].FeatureMap.z, false);
// d[j]
var dtemp = new ManagedArray(Layers[l].Activation.x, Layers[l].Activation.y, batchz, false);
// a[i] and flipped
var atemp = new ManagedArray(Layers[prev].Activation.x, Layers[prev].Activation.y, batchz, false);
var ftemp = new ManagedArray(Layers[prev].Activation.x, Layers[prev].Activation.y, batchz, false);
for (var j = 0; j < Layers[l].Activation.i; j++)
{
ManagedOps.Copy4D3D(dtemp, Layers[l].Delta, j);
for (var i = 0; i < Layers[prev].Activation.i; i++)
{
ManagedOps.Copy4D3D(atemp, Layers[prev].Activation, i);
ManagedMatrix.FlipAll(ftemp, atemp);
ManagedConvolution.Valid(ftemp, dtemp, FeatureMapDelta);
ManagedMatrix.Multiply(FeatureMapDelta, 1.0 / batchz);
ManagedOps.Copy2D4DIJ(Layers[l].DeltaFeatureMap, FeatureMapDelta, i, j);
}
Layers[l].DeltaBias[j] = ManagedMatrix.Sum(dtemp) / batchz;
}
ManagedOps.Free(FeatureMapDelta, dtemp, atemp, ftemp);
}
}
var FeatureVectorTransposed = new ManagedArray(FeatureVector, false);
ManagedMatrix.Transpose(FeatureVectorTransposed, FeatureVector);
ManagedOps.Free(WeightsDelta, BiasDelta);
WeightsDelta = new ManagedArray(Weights, false);
BiasDelta = new ManagedArray(Bias, false);
ManagedMatrix.Multiply(WeightsDelta, OutputDelta, FeatureVectorTransposed);
ManagedMatrix.Multiply(WeightsDelta, 1.0 / batchz);
ManagedMatrix.Mean(BiasDelta, OutputDelta, 0);
ManagedOps.Free(FeatureVectorTransposed);
}
// Compute Forward Transform on 3D Input
public void FeedForward(ManagedArray batch, bool pool = false)
{
var n = Layers.Count;
var last = n - 1;
var InputMaps = 1;
ManagedOps.Free(Layers[0].Activation);
Layers[0].Activation = new ManagedArray(batch, false);
ManagedOps.Copy4D3D(Layers[0].Activation, batch, 0);
for (var l = 1; l < n; l++)
{
var prev = l - 1;
if (Layers[l].Type == LayerTypes.Convolution)
{
var zx = Layers[prev].Activation.x - Layers[l].KernelSize + 1;
var zy = Layers[prev].Activation.y - Layers[l].KernelSize + 1;
var zz = batch.z;
ManagedOps.Free(Layers[l].Activation);
Layers[l].Activation = new ManagedArray(zx, zy, zz, Layers[l].OutputMaps, 1, false);
var Activation = new ManagedArray(Layers[prev].Activation.x, Layers[prev].Activation.y, batch.z, false);
var FeatureMap = new ManagedArray(Layers[l].KernelSize, Layers[l].KernelSize, false);
// create temp output map
var z = new ManagedArray(zx, zy, zz);
var ztemp = new ManagedArray(zx, zy, zz, false);
// !!below can probably be handled by insane matrix operations
for (var j = 0; j < Layers[l].OutputMaps; j++) // for each output map
{
ManagedOps.Set(z, 0.0);
for (var i = 0; i < InputMaps; i++)
{
// copy Layers
ManagedOps.Copy4D3D(Activation, Layers[prev].Activation, i);
ManagedOps.Copy4DIJ2D(FeatureMap, Layers[l].FeatureMap, i, j);
// convolve with corresponding kernel and add to temp output map
ManagedConvolution.Valid(Activation, FeatureMap, ztemp);
ManagedMatrix.Add(z, ztemp);
}
// add bias, pass through nonlinearity
ManagedMatrix.Add(z, Layers[l].Bias[j]);
var sigm = ManagedMatrix.Sigm(z);
ManagedOps.Copy3D4D(Layers[l].Activation, sigm, j);
ManagedOps.Free(sigm);
}
ManagedOps.Free(Activation, FeatureMap, z, ztemp);
InputMaps = Layers[l].OutputMaps;
}
else if (Layers[l].Type == LayerTypes.Subsampling)
{
// downsample
// generate downsampling kernel
var scale = (double)(Layers[l].Scale * Layers[l].Scale);
var FeatureMap = new ManagedArray(Layers[l].Scale, Layers[l].Scale, false);
ManagedOps.Set(FeatureMap, 1.0 / scale);
ManagedOps.Free(Layers[l].Activation);
Layers[l].Activation = new ManagedArray(Layers[prev].Activation.x / Layers[l].Scale, Layers[prev].Activation.y / Layers[l].Scale, batch.z, InputMaps, 1);
var Activation = new ManagedArray(Layers[prev].Activation.x, Layers[prev].Activation.y, batch.z, false);
var z = new ManagedArray(Layers[prev].Activation.x - Layers[l].Scale + 1, Layers[prev].Activation.y - Layers[l].Scale + 1, batch.z, false);
for (var j = 0; j < InputMaps; j++)
{
// copy Layers
ManagedOps.Copy4D3D(Activation, Layers[prev].Activation, j);
// Subsample
ManagedConvolution.Valid(Activation, FeatureMap, z);
if (pool)
{
ManagedOps.Pool3D4D(Layers[l].Activation, z, j, Layers[l].Scale);
}
else
{
ManagedOps.Copy3D4D(Layers[l].Activation, z, j, Layers[l].Scale);
}
}
ManagedOps.Free(Activation, FeatureMap, z);
}
}
var MapSize = Layers[last].Activation.x * Layers[last].Activation.y;
ManagedOps.Free(FeatureVector);
FeatureVector = new ManagedArray(batch.z, MapSize * Layers[last].Activation.i);
var temp1D = new ManagedArray(Layers[last].Activation.y, Layers[last].Activation.x, false);
var temp2D = new ManagedArray(Layers[last].Activation.x, Layers[last].Activation.y, false);
// concatenate all end layer feature maps into vector
for (var j = 0; j < Layers[last].Activation.i; j++)
{
for (var ii = 0; ii < batch.z; ii++)
{
// Use Row-major in flattening the feature map
ManagedOps.Copy4D2D(temp2D, Layers[last].Activation, ii, j);
ManagedMatrix.Transpose(temp1D, temp2D);
temp1D.Reshape(1, MapSize);
ManagedOps.Copy2DOffset(FeatureVector, temp1D, ii, j * MapSize);
}
}
var WeightsFeatureVector = new ManagedArray(FeatureVector.x, Weights.y, false);
ManagedMatrix.Multiply(WeightsFeatureVector, Weights, FeatureVector);
var repmat = new ManagedArray(batch.z, Bias.Length(), false);
ManagedMatrix.Expand(Bias, batch.z, 1, repmat);
ManagedMatrix.Add(WeightsFeatureVector, repmat);
// feedforward into output perceptrons
ManagedOps.Free(Output);
Output = ManagedMatrix.Sigm(WeightsFeatureVector);
ManagedOps.Free(WeightsFeatureVector, repmat, temp1D, temp2D);
}
public void Setup(ManagedArray output, NeuralNetworkOptions opts, bool Reset = true)
{
if (Reset)
{
if (Activations != null && Activations.GetLength(0) > 0)
{
for (var layer = 0; layer < Activations.GetLength(0); layer++)
{
ManagedOps.Free(Activations[layer]);
}
}
if (D != null && D.GetLength(0) > 0)
{
for (var layer = 0; layer < D.GetLength(0); layer++)
{
ManagedOps.Free(D[layer]);
}
}
if (Deltas != null && Deltas.GetLength(0) > 0)
{
for (var layer = 0; layer < Deltas.GetLength(0); layer++)
{
ManagedOps.Free(Deltas[layer]);
}
}
if (X != null && X.GetLength(0) > 0)
{
for (var layer = 0; layer < X.GetLength(0); layer++)
{
ManagedOps.Free(X[layer]);
}
}
if (Z != null && Z.GetLength(0) > 0)
{
for (var layer = 0; layer < Z.GetLength(0); layer++)
{
ManagedOps.Free(Z[layer]);
}
}
if (Weights != null && Weights.GetLength(0) > 0)
{
for (var layer = 0; layer < Weights.GetLength(0); layer++)
{
ManagedOps.Free(Weights[layer]);
}
}
if (Layers.Count > 0)
{
Weights = new ManagedArray[Layers.Count];
for (var layer = 0; layer < Layers.Count; layer++)
{
Weights[layer] = new ManagedArray(Layers[layer].Inputs + 1, Layers[layer].Outputs);
}
}
else
{
Weights = new ManagedArray[opts.HiddenLayers + 1];
Weights[0] = new ManagedArray(opts.Inputs + 1, opts.Nodes);
Layers.Add(new HiddenLayer(opts.Inputs, opts.Nodes));
for (var layer = 1; layer < opts.HiddenLayers; layer++)
{
Weights[layer] = (new ManagedArray(opts.Nodes + 1, opts.Nodes));
Layers.Add(new HiddenLayer(opts.Nodes, opts.Nodes));
}
Weights[opts.HiddenLayers] = (new ManagedArray(opts.Nodes + 1, opts.Categories));
Layers.Add(new HiddenLayer(opts.Nodes, opts.Categories));
}
}
Activations = new ManagedArray[opts.HiddenLayers];
Deltas = new ManagedArray[opts.HiddenLayers + 1];
X = new ManagedArray[opts.HiddenLayers + 1];
D = new ManagedArray[opts.HiddenLayers + 1];
Z = new ManagedArray[opts.HiddenLayers + 1];
SetupLabels(output, opts);
var random = new Random(Guid.NewGuid().GetHashCode());
if (Reset && Weights != null)
{
for (var layer = 0; layer < opts.HiddenLayers + 1; layer++)
{
Rand(Weights[layer], random);
}
}
Cost = 1.0;
L2 = 1.0;
Iterations = 0;
}
public void SetupLabels(ManagedArray output, NeuralNetworkOptions opts)
{
Y_true = Labels(output, opts);
}