public static Function ConvolutionTranspose2D(Variable input, int outFeatureMapCount, int kernelWidth, int kernelHeight, DeviceDescriptor device,
int stride = 1, bool pad = false, bool bias = true, string name = "")
{
int numInputChannels = input.Shape[input.Shape.Rank - 1];
//kernal
var convParams = new Parameter(new int[] { kernelWidth, kernelHeight, numInputChannels, outFeatureMapCount },
DataType.Float, CNTKLib.GlorotUniformInitializer(1, -1, 2), device, name + WeightSuffix);
//deconv
var convFunction = CNTKLib.ConvolutionTranspose(convParams, input, new int[] { stride, stride, numInputChannels }, BoolVector.Repeat(true, 3), new BoolVector(new bool[] { pad, pad, false }));
//bias
if (bias)
{
var b = new Parameter(new int[] { 1, 1, outFeatureMapCount }, DataType.Float, CNTKLib.ConstantInitializer(0), device, name + BiasSuffix);
convFunction = b + convFunction;
}
//name
if (!string.IsNullOrEmpty(name))
{
convFunction.SetName(name);
}
return(convFunction);
}
public QNetworkConvSimple(int inputWidth, int inputHeight, int inputDepth, int actionSize,
int[] filterSizes, int[] filterDepths, int[] strides, bool[] pooling,
int densehiddenLayers, int densehiddenSize, bool denseUseBias, DeviceDescriptor device, float denseInitialWeightScale = 0.01f)
{
Device = device;
StateSize = inputWidth * inputHeight * inputDepth;
ActionSize = actionSize;
InputDimension = new int[3] {
inputWidth, inputHeight, inputDepth
};
//create actor network part
InputState = CNTKLib.InputVariable(InputDimension, DataType.Float);
Debug.Assert(filterSizes.Length == strides.Length && filterDepths.Length == filterSizes.Length, "Length of filterSizes,strides and filterDepth are not the same");
var lastLayer = InputState;
for (int i = 0; i < filterSizes.Length; ++i)
{
//conv layers. Use selu activaion and selu initlaization
lastLayer = Layers.Convolution2D(lastLayer, filterDepths[i],
filterSizes[i], filterSizes[i], device, strides[i], true, true, "QConv_" + i, Mathf.Sqrt((1.0f / (filterSizes[i] * filterSizes[i]))));
lastLayer = new SELUDef().BuildNew(lastLayer, device, "");
//pooling
if (pooling[i])
{
lastLayer = CNTKLib.Pooling(lastLayer, PoolingType.Max, new int[] { 2, 2 }, new int[] { 2, 2 }, BoolVector.Repeat(true, 2), false, true, "pool2");
}
}
lastLayer = CNTKLib.Flatten(lastLayer, new Axis(3), "Flatten");
//dense layers
var inputA = new InputLayerCNTKVar(lastLayer);
var outputA = new OutputLayerDense(actionSize, null, OutputLayerDense.LossFunction.None);
outputA.HasBias = false;
outputA.InitialWeightScale = denseInitialWeightScale;
SequentialNetworkDense qNetwork = new SequentialNetworkDense(inputA, LayerDefineHelper.DenseLayers(densehiddenLayers, densehiddenSize, denseUseBias, NormalizationMethod.None, 0, denseInitialWeightScale, new ReluDef()), outputA, device);
//OutputQs = outputA.GetOutputVariable();
OutputQs = outputA.GetOutputVariable();
}
/// <summary>
/// Create the vgg19 convolutional encoders for UST model
/// </summary>
/// <param name="imageDimension"></param>
/// <returns></returns>
protected Function CreateEncoders(Vector2Int imageDimension)
{
Function encoderLayers;
VariableVector outputs = new VariableVector();
//input variables
Variable prev = Variable.InputVariable(new int[] { imageDimension.x, imageDimension.y, 3 }, DataType.Float, "input");
//encoderLayers["input"] = prev;
//vgg preprocessing
prev = Layers.Convolution2D(prev, 3, 1, 1, device, 1, false, true, "conv0_preprocessing");
//encoderLayers["conv0_preprocessing"] = prev;
//----conv1----
//conv1_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, "conv1_1");
prev = CNTKLib.ReLU(prev, "relu1_1");
//encoderLayers["relu1_1"] = prev;
outputs.Add(prev);
//conv1_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, "conv1_2");
prev = CNTKLib.ReLU(prev, "relu1_2");
//maxpooling 1
prev = CNTKLib.Pooling(prev, PoolingType.Max, new int[] { 2, 2 }, new int[] { 2, 2 }, BoolVector.Repeat(true, 2), false, true, "pool1");
//----conv2----
//conv2_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, 128, 3, 3, device, 1, false, true, "conv2_1");
prev = CNTKLib.ReLU(prev, "relu2_1");
outputs.Add(prev);
// encoderLayers["relu2_1"] = prev;
//conv2_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, "conv2_2");
prev = CNTKLib.ReLU(prev, "relu2_2");
//maxpooling 2
prev = CNTKLib.Pooling(prev, PoolingType.Max, new int[] { 2, 2 }, new int[] { 2, 2 }, BoolVector.Repeat(true, 2), false, true, "pool2");
//----conv3----
//conv3_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, 256, 3, 3, device, 1, false, true, "conv3_1");
prev = CNTKLib.ReLU(prev, "relu3_1");
outputs.Add(prev);
//encoderLayers["relu3_1"] = prev;
//conv3_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, 256, 3, 3, device, 1, false, true, "conv3_2");
prev = CNTKLib.ReLU(prev, "relu3_2");
//conv3_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, "conv3_3");
prev = CNTKLib.ReLU(prev, "relu3_3");
//conv3_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, "conv3_4");
prev = CNTKLib.ReLU(prev, "relu3_4");
//maxpooling 3
prev = CNTKLib.Pooling(prev, PoolingType.Max, new int[] { 2, 2 }, new int[] { 2, 2 }, BoolVector.Repeat(true, 2), false, true, "pool3");
//----conv4----
//conv4_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, 512, 3, 3, device, 1, false, true, "conv4_1");
prev = CNTKLib.ReLU(prev, "relu4_1");
outputs.Add(prev);
//encoderLayers["relu4_1"] = prev;
//conv4_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, 512, 3, 3, device, 1, false, true, "conv4_2");
prev = CNTKLib.ReLU(prev, "relu4_2");
//conv4_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, 512, 3, 3, device, 1, false, true, "conv4_3");
prev = CNTKLib.ReLU(prev, "relu4_3");
//conv4_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, "conv4_4");
prev = CNTKLib.ReLU(prev, "relu4_4");
//maxpooling 4
prev = CNTKLib.Pooling(prev, PoolingType.Max, new int[] { 2, 2 }, new int[] { 2, 2 }, BoolVector.Repeat(true, 2), false, true, "pool4");
//----conv5----
//conv5_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, 512, 3, 3, device, 1, false, true, "conv5_1");
prev = CNTKLib.ReLU(prev, "relu5_1");
outputs.Add(prev);
encoderLayers = CNTKLib.Combine(outputs);
//encoderLayers["relu5_1"] = prev;
return(encoderLayers);
}
