public ParameterSet(PassIndex pass, float blendFactor = 0.7f)
{
Pass = pass;
BlendFactor = blendFactor;
Beta = 0.5f;
Eps = 0.00001f;
IgnoreSingularValue = 0.00001f;
}
/// <summary>
/// Create a Universal style transfer decoder. There are 5 decoders in UST, use index to specify which one to create.
/// </summary>
/// <param name="imageDimension">image dimension for the decoder to work with. Note that it might be different from the decoder input dimemensions</param>
/// <param name="index"></param>
/// <returns></returns>
protected Function CreateDecoders(Vector2Int imageDimension, PassIndex index)
{
Function encoderLayers;
int ind = (int)index + 1; //1 based index for the names
Vector2Int inputDims = imageDimension;
int[] xOffsets = new int[5];
int[] yOffsets = new int[5];
for (int i = 1; i < ind; ++i)
{
var temp = new Vector2Int(Mathf.CeilToInt(inputDims.x / 2.0f), Mathf.CeilToInt(inputDims.y / 2.0f));
if (Mathf.Abs(inputDims.x / 2.0f - temp.x) > 0.00001f)
{
xOffsets[i] = 1;
}
if (Mathf.Abs(inputDims.y / 2.0f - temp.y) > 0.00001f)
{
yOffsets[i] = 1;
}
inputDims = temp;
}
//set the channel number
int inputChannels = 64;
switch (index)
{
case PassIndex.PassOne:
inputChannels = 64;
break;
case PassIndex.PassTwo:
inputChannels = 128;
break;
case PassIndex.PassThree:
inputChannels = 256;
break;
case PassIndex.PassFour:
inputChannels = 512;
break;
case PassIndex.PassFive:
inputChannels = 512;
break;
default:
inputChannels = 64;
break;
}
//input variables
Variable prev = Variable.InputVariable(new int[] { inputDims.x, inputDims.y, inputChannels }, DataType.Float, "input");
//encoderLayers["input"] = prev;
if (ind >= 5)
{
//decoder 5
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 512, 3, 3, device, 1, false, true, "de" + ind + "conv5_1");
prev = CNTKLib.ReLU(prev);
prev = Layers.Upsample2D2(prev, xOffsets[4], yOffsets[4]);
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 512, 3, 3, device, 1, false, true, "de" + ind + "conv4_4");
prev = CNTKLib.ReLU(prev);
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 512, 3, 3, device, 1, false, true, "de" + ind + "conv4_3");
prev = CNTKLib.ReLU(prev);
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 512, 3, 3, device, 1, false, true, "de" + ind + "conv4_2");
prev = CNTKLib.ReLU(prev);
}
if (ind >= 4)
{
//decoder 4
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 256, 3, 3, device, 1, false, true, "de" + ind + "conv4_1");
prev = CNTKLib.ReLU(prev);
prev = Layers.Upsample2D2(prev, xOffsets[3], yOffsets[3]);
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 256, 3, 3, device, 1, false, true, "de" + ind + "conv3_4");
prev = CNTKLib.ReLU(prev);
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 256, 3, 3, device, 1, false, true, "de" + ind + "conv3_3");
prev = CNTKLib.ReLU(prev);
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 256, 3, 3, device, 1, false, true, "de" + ind + "conv3_2");
prev = CNTKLib.ReLU(prev);
}
if (ind >= 3)
{
//decoder 3
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 128, 3, 3, device, 1, false, true, "de" + ind + "conv3_1");
prev = CNTKLib.ReLU(prev);
prev = Layers.Upsample2D2(prev, xOffsets[2], yOffsets[2]);
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 128, 3, 3, device, 1, false, true, "de" + ind + "conv2_2");
prev = CNTKLib.ReLU(prev);
}
if (ind >= 2)
{
//decoder 2
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 64, 3, 3, device, 1, false, true, "de" + ind + "conv2_1");
prev = CNTKLib.ReLU(prev);
prev = Layers.Upsample2D2(prev, xOffsets[1], yOffsets[1]);
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 64, 3, 3, device, 1, false, true, "de" + ind + "conv1_2");
prev = CNTKLib.ReLU(prev);
}
//decoder 1
prev = CNTKLib.Pad(prev, PaddingMode.REFLECTPAD, new SizeTVector(new uint[] { 1, 1, 0 }), new SizeTVector(new uint[] { 1, 1, 0 }));
prev = Layers.Convolution2D(prev, 3, 3, 3, device, 1, false, true, "de" + ind + "conv1_1");
prev = CNTKLib.ReLU(prev, "output");
//encoderLayers["output"] = prev;
encoderLayers = prev;
return(encoderLayers);
}
