public static void Load2DV2(string filename, ManagedArray A, char delimiter = ',')
{
if (File.Exists(filename))
{
var temp = new ManagedArray(A.x, A.y);
using (TextReader reader = File.OpenText(filename))
{
for (int y = 0; y < A.y; y++)
{
var line = reader.ReadLine();
if (line != null)
{
var tokens = line.Split(delimiter);
for (int x = 0; x < A.x; x++)
{
temp[x, y] = Convert.ToDouble(tokens[x], ci);
}
}
}
}
ManagedOps.Copy2D(A, temp, 0, 0);
ManagedOps.Free(temp);
}
}
public static void Load2D(string filename, ManagedArray A, char delimiter = ',')
{
if (File.Exists(filename))
{
var temp = new ManagedArray(A.x, A.y);
var lines = File.ReadAllLines(filename);
for (int y = 0; y < A.y; y++)
{
if (y < lines.Length)
{
var tokens = lines[y].Split(delimiter);
for (int x = 0; x < A.x; x++)
{
temp[x, y] = Convert.ToDouble(tokens[x], ci);
}
}
}
ManagedOps.Copy2D(A, temp, 0, 0);
ManagedOps.Free(temp);
}
}
// 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);
}
// Backward propagation
public void BackPropagation(ManagedArray input)
{
var last = Weights.GetLength(0) - 1;
D[0] = ManagedMatrix.Diff(Y, Y_true);
var current = 1;
for (var layer = last - 1; layer >= 0; layer--)
{
var prev = current - 1;
var W = new ManagedArray(Weights[layer + 1].x - 1, Weights[layer + 1].y, false);
var DZ = ManagedMatrix.DSigm(Z[layer]);
D[current] = (new ManagedArray(W.x, D[prev].y, false));
ManagedOps.Copy2D(W, Weights[layer + 1], 1, 0);
ManagedMatrix.Multiply(D[current], D[prev], W);
ManagedMatrix.Product(D[current], DZ);
ManagedOps.Free(W, DZ);
current++;
}
for (var layer = 0; layer < Weights.GetLength(0); layer++)
{
var tD = ManagedMatrix.Transpose(D[Weights.GetLength(0) - layer - 1]);
Deltas[layer] = (new ManagedArray(Weights[layer].x, Weights[layer].y, false));
ManagedMatrix.Multiply(Deltas[layer], tD, X[layer]);
ManagedMatrix.Multiply(Deltas[layer], 1.0 / input.y);
ManagedOps.Free(tD);
}
Cost = 0.0;
L2 = 0.0;
for (var i = 0; i < Y_true.Length(); i++)
{
L2 += 0.5 * (D[0][i] * D[0][i]);
Cost += (-Y_true[i] * Math.Log(Y[i]) - (1 - Y_true[i]) * Math.Log(1 - Y[i]));
}
Cost /= input.y;
L2 /= input.y;
// Cleanup
for (var layer = 0; layer < Weights.GetLength(0); layer++)
{
ManagedOps.Free(D[layer], X[layer], Z[layer]);
}
}
public void Train(ManagedArray input, ManagedArray output, ConvolutionalNeuralNetworkOptions opts)
{
var temp_input = new ManagedArray(input.x, input.y, opts.BatchSize, false);
var temp_output = new ManagedArray(opts.BatchSize, output.y, false);
var index_list = new ManagedIntList(opts.Items);
for (var epoch = 0; epoch < opts.Epochs; epoch++)
{
var start = Profiler.now();
if (opts.Shuffle)
{
ManagedOps.Shuffle(index_list);
}
var rLVal = 0.0;
rL.Clear();
for (var i = 0; i < opts.Items; i += opts.BatchSize)
{
if (opts.Shuffle)
{
ManagedOps.Copy3D(temp_input, input, 0, 0, i, index_list);
ManagedOps.Copy2D(temp_output, output, i, 0, index_list);
}
else
{
ManagedOps.Copy3D(temp_input, input, 0, 0, i);
ManagedOps.Copy2D(temp_output, output, i, 0);
}
FeedForward(temp_input, opts.Pool);
BackPropagation(temp_output);
ApplyGradients(opts);
if (rL.Count == 0)
{
rL.Add(L);
}
rLVal = 0.99 * rL[rL.Count - 1] + 0.01 * L;
rL.Add(rLVal);
}
Console.WriteLine("epoch {0}/{1} elapsed time is {2} ms - Error: {3}", (epoch + 1).ToString("D", ManagedMatrix.ci), opts.Epochs.ToString("D", ManagedMatrix.ci), Profiler.Elapsed(start).ToString("D", ManagedMatrix.ci), rLVal.ToString("0.000000", ManagedMatrix.ci));
}
ManagedOps.Free(index_list);
ManagedOps.Free(temp_input, temp_output);
}
// Rotate a 2D matrix
public static void Rotate180(ManagedArray dst, ManagedArray src)
{
dst.Resize(src.x, src.y);
var tmp = new ManagedArray(src.x, src.y, false);
ManagedOps.Copy2D(tmp, src, 0, 0);
for (int FlipDim = 0; FlipDim < 2; FlipDim++)
{
Flip(dst, tmp, FlipDim);
ManagedOps.Copy2D(tmp, dst, 0, 0);
}
ManagedOps.Free(tmp);
}
// Backward propagation
public void BackPropagation(ManagedArray training)
{
// add bias column to input layer
var InputBias = new ManagedArray(1, training.y);
ManagedOps.Set(InputBias, 1.0);
// x = cbind(array(1, c(nrow(training_set), 1)), training_set)
var x = ManagedMatrix.CBind(InputBias, training);
// compute intermediate delta values per layer
// d3 = y_k - y_matrix
var D3 = ManagedMatrix.Diff(Yk, Y_output);
// d2 = d3 %*% w_kj[, 2:ncol(w_kj)] * nnet_dsigmoid(z_2)
var sWkj = new ManagedArray(Wkj.x - 1, Wkj.y);
ManagedOps.Copy2D(sWkj, Wkj, 1, 0);
var D2 = new ManagedArray(sWkj.x, D3.y);
ManagedMatrix.Multiply(D2, D3, sWkj);
var DZ2 = ManagedMatrix.DSigm(Z2);
ManagedMatrix.Product(D2, DZ2);
// dWji = (t(d2) %*% x)
// dWkj = (t(d3) % *% a_2)
var tD2 = new ManagedArray(D2.y, D2.x);
var tD3 = new ManagedArray(D3.y, D3.x);
ManagedMatrix.Transpose(tD2, D2);
ManagedMatrix.Transpose(tD3, D3);
DeltaWji = new ManagedArray(Wji.x, Wji.y);
DeltaWkj = new ManagedArray(Wkj.x, Wkj.y);
ManagedMatrix.Multiply(DeltaWji, tD2, x);
ManagedMatrix.Multiply(DeltaWkj, tD3, A2);
// cost = sum(-y_matrix * log(y_k) - (1 - y_matrix) * log(1 - y_k))
Cost = 0.0;
L2 = 0.0;
for (var i = 0; i < Y_output.Length(); i++)
{
L2 += 0.5 * (D3[i] * D3[i]);
Cost += (-Y_output[i] * Math.Log(Yk[i]) - (1 - Y_output[i]) * Math.Log(1 - Yk[i]));
}
// cost = cost / m
// dWji = dWji / m
// dWkj = dWkj / m
Cost /= training.y;
L2 /= training.y;
ManagedMatrix.Multiply(DeltaWji, 1.0 / training.y);
ManagedMatrix.Multiply(DeltaWkj, 1.0 / training.y);
// cleanup
ManagedOps.Free(D2, D3, DZ2, InputBias);
ManagedOps.Free(sWkj, tD2, tD3, x);
// cleanup of arrays allocated in Forward
ManagedOps.Free(A2, Yk, Z2);
}
// 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);
}