/// <summary>
/// Spatials the maximum pooling forward.
/// </summary>
/// <param name="input">The input.</param>
/// <param name="output">The output.</param>
/// <param name="indices">The indices.</param>
/// <param name="cd">The cd.</param>
/// <param name="ceilMode">if set to <c>true</c> [ceil mode].</param>
/// <exception cref="ArgumentException">input must be a 4D tensor</exception>
/// <exception cref="InvalidOperationException">
/// input image is smaller than kernel size
/// or
/// pad should be smaller than half of the kernel size
/// </exception>
public static void SpatialMaxPoolingForward(NDArray input, NDArray output, NDArray indices, ConvolutionDesc2d cd, bool ceilMode)
{
if (input.DimensionCount != 4)
{
throw new ArgumentException("input must be a 4D tensor");
}
var dimw = 3;
var dimh = 2;
var dimc = 1;
if (input.Shape[dimw] < cd.kW - cd.padW || input.Shape[dimh] < cd.kH - cd.padH)
{
throw new InvalidOperationException("input image is smaller than kernel size");
}
if (cd.padW > cd.kW / 2 || cd.padH > cd.kH / 2)
{
throw new InvalidOperationException("pad should be smaller than half of the kernel size");
}
var nbatch = input.Shape[0];
var nslices = input.Shape[dimc];
var iheight = input.Shape[dimh];
var iwidth = input.Shape[dimw];
long owidth;
long oheight;
if (ceilMode)
{
oheight = (long)(Math.Ceiling((float)(iheight - cd.kH + 2 * cd.padH) / cd.dH)) + 1;
owidth = (long)(Math.Ceiling((float)(iwidth - cd.kW + 2 * cd.padW) / cd.dW)) + 1;
}
else
{
oheight = (long)(Math.Floor((float)(iheight - cd.kH + 2 * cd.padH) / cd.dH)) + 1;
owidth = (long)(Math.Floor((float)(iwidth - cd.kW + 2 * cd.padW) / cd.dW)) + 1;
}
if (cd.padW != 0 || cd.padH != 0)
{
// ensure that the last pooling starts inside the image
if ((oheight - 1) * cd.dH >= iheight + cd.padH)
{
--oheight;
}
if ((owidth - 1) * cd.dW >= iwidth + cd.padW)
{
--owidth;
}
}
using (var inputContig = Ops.AsContiguous(input))
{
for (int i = 0; i < nbatch; ++i)
{
using (var input_i = inputContig.Select(0, i))
using (var output_i = output.Select(0, i))
using (var indices_i = indices.Select(0, i))
{
IntPtr input_iPtr, output_iPtr, indices_iPtr;
using (NativeWrapper.BuildTensorRefPtr(input_i, out input_iPtr))
using (NativeWrapper.BuildTensorRefPtr(output_i, out output_iPtr))
using (NativeWrapper.BuildTensorRefPtr(indices_i, out indices_iPtr))
{
CpuOpsNative.TS_SpatialMaxPooling_updateOutput_frame(input_iPtr, output_iPtr, indices_iPtr,
nslices, iwidth, iheight,
owidth, oheight,
cd.kW, cd.kH, cd.dW, cd.dH, cd.padW, cd.padH);
}
}
}
}
}
