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)];
}
}
});
});
}
//这个方法不会产生多余的临时对象，问题就是不再存储Derivative
//private void ErrorBP(Tensor output, Tensor error, Tensor result, int sampleIndex)
//{
// for (int i = 0; i < categoryNumber; i++)
// {
// var der = 0d;
// for (int j = 0; j < categoryNumber; j++)
// {
// if (i == j)
// der += output[sampleIndex, i] * (1 - output[sampleIndex, j]) * error[sampleIndex, j];
// else
// der += -output[sampleIndex, i] * output[sampleIndex, j] * error[sampleIndex, j];
// }
// result[sampleIndex, i] = der;
// }
//}
private void ErrorBP(TensorOld error)
{
var derData = Derivative.GetRawValues();
var errorData = error.GetRawValues();
var outData = BackwardOutput.GetRawValues();
Parallel.For(0, sampleNumber, sampleIndex =>
{
var errorStart = error.GetRawOffset(sampleIndex, 0);
//这里的两层嵌套执行的并不是严格的矩阵运算，导数应该是：error*jacob，
//因为jacob矩阵是对称的所以使用jacob每行和error相乘的内积，循环写起来方便
Parallel.For(0, categoryNumber, i =>
{
var derStart = Derivative.GetRawOffset(sampleIndex, i, 0);
var sum = 0d;
for (int j = 0; j < categoryNumber; j++)
{
sum += derData[derStart + j] * errorData[errorStart + j];
}
outData[errorStart + i] = sum;
});
});
}
