Example #1
0
        private static Tensor CalculateY(Tensor w, Tensor x, Tensor b, Kernel kernel, int numberOfFilters, MatrixLayout matrixLayout)
        {
            Tensor y = new Tensor(null,
                                  new Shape(
                                      Shape.BWHC,
                                      x.Shape.GetAxis(Axis.B),
                                      kernel.CalculateOutputWidth(x.Shape.GetAxis(Axis.X)),
                                      kernel.CalculateOutputHeight(x.Shape.GetAxis(Axis.Y)),
                                      x.Shape.GetAxis(Axis.C)));

            for (int ib = 0, iib = y.Shape.GetAxis(Axis.B); ib < iib; ib++)
            {
                for (int ix = 0, xpos = -kernel.PaddingX, iix = y.Shape.GetAxis(Axis.X); ix < iix; ix++, xpos += kernel.StrideX)
                {
                    for (int iy = 0, ypos = -kernel.PaddingY, iiy = y.Shape.GetAxis(Axis.Y); iy < iiy; iy++, ypos += kernel.StrideY)
                    {
                        Tensor  k        = x.CropKernel(ib, xpos, ypos, kernel, false, out int kernelArea);
                        float[] features = FullyConnectedLayerTest.CalculateNeurons(w, k, b, numberOfFilters, matrixLayout);

                        for (int ic = 0, iic = y.Shape.GetAxis(Axis.C); ic < iic; ic++)
                        {
                            y[ib, ix, iy, ic] = features[ic];
                        }
                    }
                }
            }

            return(y);
        }
Example #2
0
        private static Tensor CalculateDW(Tensor w, Tensor x, Tensor y, Kernel kernel, int numberOfFilters, MatrixLayout matrixLayout)
        {
            Tensor dw = new Tensor(null, w.Axes);

            for (int ib = 0, iib = y.Shape.GetAxis(Axis.B); ib < iib; ib++)
            {
                for (int ix = 0, xpos = -kernel.PaddingX, iix = y.Shape.GetAxis(Axis.X); ix < iix; ix++, xpos += kernel.StrideX)
                {
                    for (int iy = 0, ypos = -kernel.PaddingY, iiy = y.Shape.GetAxis(Axis.Y); iy < iiy; iy++, ypos += kernel.StrideY)
                    {
                        Tensor k   = x.CropKernel(ib, xpos, ypos, kernel, false, out int kernelArea);
                        Tensor kdy = y.CropKernel(ib, ix, iy, new Kernel(1, 1, 1, 1), true, out kernelArea);

                        float[] dww = FullyConnectedLayerTest.CalculateDW(k, kdy, matrixLayout);
                        Mathematics.Add(dw.Length, dww, 0, dw.Gradient, 0);
                    }
                }
            }

            return(dw);
        }
Example #3
0
        private static Tensor CalculateDX(Tensor w, Tensor x, Tensor y, Kernel kernel, int numberOfFilters, MatrixLayout matrixLayout)
        {
            Tensor dx = new Tensor(null, x.Axes);

            int xb = Math.Max(-kernel.PaddingX, 0);
            int xe = x.Shape.GetAxis(Axis.X) - 1 - xb;
            int yb = Math.Max(-kernel.PaddingY, 0);
            int ye = x.Shape.GetAxis(Axis.Y) - 1 - yb;

            for (int ib = 0, iib = x.Shape.GetAxis(Axis.B); ib < iib; ib++)
            {
                for (int ix = 0, xpos = -kernel.PaddingX, iix = y.Shape.GetAxis(Axis.X); ix < iix; ix++, xpos += kernel.StrideX)
                {
                    for (int iy = 0, ypos = -kernel.PaddingY, iiy = y.Shape.GetAxis(Axis.Y); iy < iiy; iy++, ypos += kernel.StrideY)
                    {
                        Tensor kdy = y.CropKernel(ib, ix, iy, new Kernel(1, 1, 1, 1), true, out int kernelArea);

                        Tensor kdx = new Tensor(null, new Shape(Shape.BWHC, 1, kernel.Width, kernel.Height, numberOfFilters));
                        kdx.Set(FullyConnectedLayerTest.CalculateDx(w, kdy, numberOfFilters, matrixLayout));

                        for (int kx = xpos; kx < xpos + kernel.Width; kx++)
                        {
                            for (int ky = ypos; ky < ypos + kernel.Height; ky++)
                            {
                                if (kx.Between(xb, xe) && ky.Between(yb, ye))
                                {
                                    for (int kc = 0; kc < numberOfFilters; kc++)
                                    {
                                        dx.Gradient[x.Shape.Position(ib, kx, ky, kc)] += kdx[0, kx - xpos, ky - ypos, kc];
                                    }
                                }
                            }
                        }
                    }
                }
            }

            return(dx);
        }
Example #4
0
        public void ForwardBackwardTest()
        {
            Shape     shape           = new Shape(new[] { -1, 2, 3, 2 });
            const int NumberOfNeurons = 2;

            foreach (MatrixLayout matrixLayout in Enum.GetValues(typeof(MatrixLayout)).OfType <MatrixLayout>())
            {
                FullyConnectedLayer layer = new FullyConnectedLayer(shape, NumberOfNeurons, matrixLayout, null);
                ////layer.SetLearningMode(true);

                layer.W.Set(new float[]
                {
                    1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12,
                    21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32
                });

                layer.B.Set(new float[] { 1, 2 });

                Tensor xTemp = new Tensor(null, new[] { 1, 12 });
                xTemp.Set(new float[] { 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12 });

                // should be W * x + b
                Tensor expectedTemp = new Tensor(null, new[] { 1, NumberOfNeurons });
                expectedTemp.Set(FullyConnectedLayerTest.CalculateNeurons(layer.W, xTemp, layer.B, NumberOfNeurons, matrixLayout));

                Tensor dyTemp = new Tensor(null, new[] { 1, NumberOfNeurons });
                dyTemp.Set(new float[] { 1, 2 });

                // should be W' * dy
                Tensor expectedDxTemp = new Tensor(null, xTemp.Shape);
                expectedDxTemp.Set(FullyConnectedLayerTest.CalculateDx(layer.W, dyTemp, NumberOfNeurons, matrixLayout));

                Tensor expectedDBTemp = new Tensor(null, layer.B.Shape);
                expectedDBTemp.Set(FullyConnectedLayerTest.CalculateDB(dyTemp));

                // should be sum(x' * dy)
                Tensor expectedDWTemp = new Tensor(null, layer.W.Shape);
                expectedDWTemp.Set(FullyConnectedLayerTest.CalculateDW(xTemp, dyTemp, matrixLayout));

                for (int i = 1; i <= 3; i++)
                {
                    Session session = new Session();

                    layer.W.ClearGradient();
                    layer.B.ClearGradient();

                    Tensor x = session.Tile(xTemp, (int)Axis.B, i);
                    Tensor y = layer.Forward(session, new[] { x })[0];

                    Tensor expected = session.Tile(expectedTemp, (int)Axis.B, i);
                    Helpers.AreTensorsEqual(expected, y);

                    // unroll the graph
                    y.SetGradient(session.Tile(dyTemp, (int)Axis.B, i).Weights);
                    session.Unroll();

                    Tensor expectedDx = session.Tile(expectedDxTemp, (int)Axis.B, i);
                    Helpers.AreArraysEqual(expectedDx.Length, expectedDx.Weights, x.Gradient);

                    // should be dy
                    Tensor expectedDB = session.Multiply(expectedDBTemp, i);
                    Helpers.AreArraysEqual(expectedDB.Length, expectedDB.Weights, layer.B.Gradient);

                    // should be x * dy
                    Tensor expectedDW = session.Multiply(expectedDWTemp, i);
                    Helpers.AreArraysEqual(expectedDW.Length, expectedDW.Weights, layer.W.Gradient);
                }
            }
        }