private void Forward(TensorOld input, int sampleIndex, int filterIndex)
{
var filterOff = Filters.GetRawOffset(filterIndex, 0, 0, 0);
Parallel.For(0, outRows, row =>
{
var startRow = row * RowStride;
Parallel.For(0, outColumns, col =>
{
var startCol = col * ColumnStride;
var sum = 0d;
for (int i = 0; i < FilterRows; i++)
{
var filterStart = i * filterRowLength;
var inputOff = input.GetRawOffset(sampleIndex, startRow + i, startCol, 0);
for (int j = 0; j < filterRowLength; j++)
{
sum += input.values[inputOff + j] * Filters.values[filterStart + j];
}
}
ForwardOutput.SetValueFast(sum + Bias.values[filterIndex], sampleIndex, row, col, filterIndex);
});
});
}
private void ComputeDerivative()
{
var derData = Derivative.GetRawValues();
var outData = ForwardOutput.GetRawValues();
Parallel.For(0, sampleNumber, sampleIndex =>
{
var outStart = ForwardOutput.GetRawOffset(sampleIndex, 0);
Parallel.For(0, categoryNumber, i =>
{
var derStart = Derivative.GetRawOffset(sampleIndex, i, 0);
for (int j = 0; j < categoryNumber; j++)
{
if (i == j)
{
derData[derStart + j] = outData[(int)(outStart + i)] * (1 - outData[(int)(outStart + j)]);
}
else
{
derData[derStart + j] = -outData[(int)(outStart + i)] * outData[(int)(outStart + j)];
}
}
});
});
}
private void ComputeCrossEntropy(TensorOld y, TensorOld yHat)
{
var foreoutData = ForwardOutput.GetRawValues();
for (int i = 0; i < sampleNumber; i++)
{
//取出一个样本及其对应的Label
y.GetByDim1(i, yBuff);
yHat.GetByDim1(i, yHatBuff);
//计算交叉熵
foreoutData[i] = Functions.CrossEntropy(yBuff, yHatBuff);
}
Array.Copy(y.values, 0, BackwardOutput.values, 0, y.ElementCount);
}
public override double GetLoss(TensorOld y, TensorOld yHat)
{
var outData = ForwardOutput.GetRawValues();
var result = 0d;
for (int i = 0; i < y.shape[0]; i++)
{
//取出一个样本及其对应的Label
y.GetByDim1(i, yBuff);
yHat.GetByDim1(i, yHatBuff);
//计算交叉熵
result += Functions.CrossEntropy(yBuff, yHatBuff);
}
return(result / sampleNumber);
}
private void ComputeCrossEntropy(TensorOld y, TensorOld yHat)
{
var forwardoutData = ForwardOutput.GetRawValues();
var backwardoutData = BackwardOutput.GetRawValues();
for (int i = 0; i < sampleNumber; i++)
{
//取出一个样本及其对应的Label
y.GetByDim1(i, yBuff);
yHat.GetByDim1(i, yHatBuff);
//计算交叉熵
forwardoutData[i] = Functions.CrossEntropy(yBuff, yHatBuff);
//计算损失函数关于输入的导数
Derivatives.CrossEntropy(yBuff, yHatBuff, derBuff);
Array.Copy(derBuff, 0, backwardoutData, i * derBuff.Length, derBuff.Length);
}
}
/// <summary>
/// 获取最近一次Forward的所有样本Loss的平均值。
/// 通过ForwardOutput可以获取每个样本的Loss
/// </summary>
/// <returns>Loss平均值</returns>
public double GetLoss()
{
return(ForwardOutput.Mean());
}
public override double GetAccuracy()
{
return(Math.Sqrt(ForwardOutput.Mean()));
}