public void ProcessSubRegion(InternalArray ar, InternalArray[,] filters, InternalArray ret, int sx, int sy, int ww, int hout, int wout)
{
var hin = ar.Shape[1];
var win = ar.Shape[2];
var c = ar.Shape[0];
int shiftx = padding[0] - kernelSize[0] / 2;
int shifty = padding[1] - kernelSize[1] / 2;
var maxw = Math.Min(wout, (sy + 1) * ww);
var maxh = Math.Min(hout, (sx + 1) * ww);
var starth = sx * ww;
var startw = sy * ww;
for (int i = starth; i < maxh; i++)
{
for (int j = startw; j < maxw; j++)
{
for (int ch = 0; ch < outChannels; ch++)
{
double val = 0;
for (int zz = 0; zz < c; zz++)
{
var kernel = filters[ch, zz];
for (int i1 = 0; i1 < kernelSize[0]; i1++)
{
for (int j1 = 0; j1 < kernelSize[0]; j1++)
{
//var x = i * stride[0] - kernelSize[0] / 2 + i1;
//var y = j * stride[1] - kernelSize[1] / 2 + j1;
//outspace
var xout = (i) * stride[0] - kernelSize[0] / 2 + i1 * dilation[0];
var yout = (j) * stride[1] - kernelSize[1] / 2 + j1 * dilation[1];
//inspace
var xin = xout - shiftx;
var yin = yout - shifty;
if (!ar.WithIn(zz, xin, yin))
{
continue;
}
//var y=jmul+j1
var ii1 = i1 * kernel.Shape[1] + j1;
var ii2 = zz * ar.offsets[0] + xin * ar.offsets[1] + yin;
val += kernel.Get2D(i1, j1) * ar.Get3D(zz, xin, yin);
var ii3 = j + ch * ret.offsets[0] + i * ret.offsets[1];
}
}
}
ret.Set3D(ch, i, j, val);
}
}
}
}
public void ProcessSubRegionOptimized(InternalArray ar, InternalArray[,] filters, InternalArray ret, int sx, int sy, int ww, int hout, int wout)
{
var hin = ar.Shape[1];
var win = ar.Shape[2];
var c = ar.Shape[0];
int shiftx = padding[0] - kernelSize[0] / 2;
int shifty = padding[1] - kernelSize[1] / 2;
var maxw = Math.Min(wout, (sy + 1) * ww);
var maxh = Math.Min(hout, (sx + 1) * ww);
var starth = sx * ww;
var startw = sy * ww;
for (int i = starth; i < maxh; i++)
{
var imul = (i) * stride[0] - kernelSize[0] / 2 - shiftx;
var maxi1 = Math.Min((ar.Shape[1] - imul) / dilation[0], kernelSize[0]);
var mini1 = Math.Max((int)Math.Ceiling(-(double)imul / dilation[0]), 0);
for (int j = startw; j < maxw; j++)
{
var jmul = (j) * stride[1] - kernelSize[1] / 2 - shifty;
var minj1 = Math.Max((int)Math.Ceiling(-(double)jmul / dilation[1]), 0);
var maxj1 = Math.Min((ar.Shape[2] - jmul) / dilation[1], kernelSize[1]);
for (int ch = 0; ch < outChannels; ch++)
{
double val = 0;
for (int zz = 0; zz < c; zz++)
{
var kernel = filters[ch, zz];
var offset1 = zz * ar.offsets[0];
int kindex = 0;
for (int i1 = mini1; i1 < maxi1; i1++)
{
var x = imul + i1 * dilation[0];
for (int j1 = minj1; j1 < maxj1; j1++)
{
var y = jmul + j1 * dilation[1];
var index = offset1 + x * ar.offsets[1] + y;
val += kernel.Data[kindex] * ar.Data[index];
kindex++;
}
}
}
ret.Set3D(ch, i, j, val);
}
}
}
}
internal InternalArray Transpose(int[] v)
{
//3d only!
InternalArray ret = new InternalArray(v.Select(z => Shape[z]).ToArray());
for (int i = 0; i < Shape[0]; i++)
{
for (int j = 0; j < Shape[1]; j++)
{
for (int k = 0; k < Shape[2]; k++)
{
var val = Get3D(i, j, k);
var ar1 = new int[] { i, j, k };
ret.Set3D(ar1[v[0]], ar1[v[1]], ar1[v[2]], val);
}
}
}
return(ret);
}
public InternalArray ProcessImage(InternalArray ar)
{
//CalcRegionsHashes(ar);
indexes1.Clear();
indexes2.Clear();
indexes3.Clear();
var hin = ar.Shape[1];
var win = ar.Shape[2];
var c = ar.Shape[0];
var hout = ((hin + 2 * padding[0] - dilation[0] * (kernelSize[0] - 1) - 1) / stride[0]) + 1;
var wout = ((win + 2 * padding[1] - dilation[1] * (kernelSize[1] - 1) - 1) / stride[1]) + 1;
InternalArray ret = new InternalArray(new int[] { outChannels, hout, wout });
InternalArray[,] filters = new InternalArray[outChannels, c];
for (int ch = 0; ch < outChannels; ch++)
{
for (int zz = 0; zz < c; zz++)
{
var kernel = Weight.Get2DImageFrom4DArray(ch, zz);
filters[ch, zz] = kernel;
}
}
int shiftx = padding[0] - kernelSize[0] / 2;
int shifty = padding[1] - kernelSize[1] / 2;
for (int i = 0; i < hout; i++)
{
for (int j = 0; j < wout; j++)
{
for (int ch = 0; ch < outChannels; ch++)
{
double val = 0;
for (int zz = 0; zz < c; zz++)
{
var kernel = filters[ch, zz];
for (int i1 = 0; i1 < kernelSize[0]; i1++)
{
for (int j1 = 0; j1 < kernelSize[0]; j1++)
{
//var x = i * stride[0] - kernelSize[0] / 2 + i1;
//var y = j * stride[1] - kernelSize[1] / 2 + j1;
//outspace
var xout = (i) * stride[0] - kernelSize[0] / 2 + i1 * dilation[0];
var yout = (j) * stride[1] - kernelSize[1] / 2 + j1 * dilation[1];
//inspace
var xin = xout - shiftx;
var yin = yout - shifty;
if (!ar.WithIn(zz, xin, yin))
{
continue;
}
//var y=jmul+j1
var ii1 = i1 * kernel.Shape[1] + j1;
var ii2 = zz * ar.offsets[0] + xin * ar.offsets[1] + yin;
val += kernel.Get2D(i1, j1) * ar.Get3D(zz, xin, yin);
var ii3 = j + ch * ret.offsets[0] + i * ret.offsets[1];
//if (i == 0)
{
/*indexes1.Add(ii1);
* indexes2.Add(ii2);
* indexes3.Add(ii3);*/
}
}
}
}
ret.Set3D(ch, i, j, val);
}
}
}
return(ret);
}
public InternalArray ProcessImageOptimized2(InternalArray ar, int hout, int wout, int c, int hin, int win)
{
InternalArray ret = new InternalArray(new int[] { outChannels, hout, wout });
InternalArray[,] filters = new InternalArray[outChannels, c];
int pos0 = 0;
for (int ch = 0; ch < outChannels; ch++)
{
for (int zz = 0; zz < c; zz++)
{
var kernel = Weight.GetNext2dImageFrom4dArray(ref pos0);
var kernel2 = Weight.Get2DImageFrom4DArray(ch, zz);
filters[ch, zz] = kernel;
}
}
int shiftx = padding[0] - kernelSize[0] / 2;
int shifty = padding[1] - kernelSize[1] / 2;
Parallel.For(0, hout, (i) =>
{
var imul = (i) * stride[0] - kernelSize[0] / 2 - shiftx;
var maxi1 = Math.Min((ar.Shape[1] - imul) / dilation[0], kernelSize[0]);
var mini1 = Math.Max((int)Math.Ceiling(-(double)imul / dilation[0]), 0);
Parallel.For(0, wout, (j) =>
{
var jmul = (j) * stride[1] - kernelSize[1] / 2 - shifty;
var minj1 = Math.Max((int)Math.Ceiling(-(double)jmul / dilation[1]), 0);
var maxj1 = Math.Min((ar.Shape[2] - jmul) / dilation[1], kernelSize[1]);
for (int ch = 0; ch < outChannels; ch++)
{
double val = 0;
for (int zz = 0; zz < c; zz++)
{
var kernel = filters[ch, zz];
var offset1 = zz * ar.offsets[0];
int kindex = 0;
for (int i1 = mini1; i1 < maxi1; i1++)
{
var x = imul + i1 * dilation[0];
for (int j1 = minj1; j1 < maxj1; j1++)
{
var y = jmul + j1 * dilation[1];
var index = offset1 + x * ar.offsets[1] + y;
val += kernel.Data[kindex] * ar.Data[index];
kindex++;
}
}
}
ret.Set3D(ch, i, j, val);
}
});
});
//for (int i = 0; i < hout; i++)
{
}
return(ret);
}
