Sometimes, usually after convolution layer, there can be found shapes in form ( width, height, depth) where depth is a number of filters from convolution operation.
I want to reproduce GoogleNet inception module and "squish" (width, height, depth) to (width, height, f(depth)) where f would produce a scalar value.
I know there is CNTKLib.Splice but that is not exactly what I need. I need to get a weighted sum of all values in the column with (x, y) coordinates.
How can that be done in C# API?
edit: added code sample
public static void PrintOutputDims(Function source)
{
var shape = source.Output.Shape;
var sb = new string[shape.Rank];
for (var i = 0; i < shape.Rank; ++i)
{
sb[i] = ($"dim{i}: {shape[i]}");
}
Console.WriteLine(string.Join(", ", sb));
}
static void Main(string[] args)
{
var variable = CNTKLib.InputVariable(NDShape.CreateNDShape(new[] { 100, 100, 20 }), DataType.Float, "source");
PrintOutputDims(variable); // dim0: 100, dim1: 100, dim2: 20
var squished = Squish(variable);
PrintOutputDims(variable); // dim0: 100, dim1: 100, dim2: 1
}
How Squish
function may be implemented?
the answer would be something like this:
public static Function SpatialReduceWeightedSum(this Function source, DeviceDescriptor device)
{
var sourceShape = source.Output.Shape;
if (sourceShape.Rank != 3)
{
throw new ArgumentException("exected rank = 3 but was: " + sourceShape.Rank);
}
var sourceDimensions = sourceShape.Dimensions;
var blocksCount = sourceDimensions[0] * sourceDimensions[1];
var temporaryDimensions = new[]
{
blocksCount,
sourceDimensions[2]
};
var temporatyShape = NDShape.CreateNDShape(temporaryDimensions);
var reshaped = CNTKLib.Reshape(source, temporatyShape);
var initializer = CNTKLib.ConstantInitializer(1d);
var axis0 = new Axis(0);
var axis1 = new Axis(1);
var axisVector = new AxisVector() { axis0 };
var weightedSums = new Variable[blocksCount];
for (var i = 0; i < blocksCount; i++)
{
var beginIndex = new IntVector() { i };
var endIndex = new IntVector() { i + 1 };
var block = CNTKLib.Slice(reshaped, axisVector, beginIndex, endIndex);
var blockShape = NDShape.CreateNDShape(block.Output.Shape.Dimensions.Reverse());
var blockParameters = new Parameter(blockShape, DataType.Float, initializer, device);
var weightedBlock = CNTKLib.Times(block, blockParameters);
weightedSums[i] = CNTKLib.ReduceSum(weightedBlock, axis1);
}
var combined = CNTKLib.Splice(new VariableVector(weightedSums), axis0);
var flatShapeDimensions = new[]
{
sourceDimensions[0],
sourceDimensions[1],
1
};
var flatShape = NDShape.CreateNDShape(flatShapeDimensions);
return CNTKLib.Reshape(combined, flatShape);
}