public void ComputeTwiceGradientShouldYieldTheSameResult()
{
const int inputWidth = 20;
const int inputHeight = 20;
const int inputDepth = 2;
var layer = new TanhLayer <double>();
layer.Init(inputWidth, inputHeight, inputDepth);
// Forward pass
var input = BuilderInstance <double> .Volume.Random(new Shape(inputWidth, inputHeight, inputDepth));
var output = layer.DoForward(input, true);
// Set output gradients to 1
var outputGradient = BuilderInstance <double> .Volume.SameAs(new double[output.Shape.TotalLength].Populate(1.0), output.Shape);
// Backward pass to retrieve gradients
layer.Backward(outputGradient);
var step1 = ((Volume <double>)layer.InputActivationGradients.Clone()).ToArray();
layer.Backward(outputGradient);
var step2 = ((Volume <double>)layer.InputActivationGradients.Clone()).ToArray();
Assert.IsTrue(step1.SequenceEqual(step2));
}
public dynamic backward(dynamic grid)
{
var dh = h_next_mul.backwardY(grid);
var d_tanh_c = cell_tl.Backward(dh);
//var dc_prev=c_next_mul.backwardY(d_tanh_c);
var d_input_gate = mulin_gate_mul.backward(d_tanh_c);
var d_forget_gate = c_next_mul.backward(d_tanh_c);
var d_cell_memory = mulin_gate_mul.backwardY(d_tanh_c);
var d_output_gate = h_next_mul.backward(grid);// d_tanh_c
var d_ai = input_gate_s.Backward(d_input_gate);
var d_af = forget_gate_s.Backward(d_forget_gate);
var d_ao = output_gate_s.Backward(d_output_gate);
var d_ac = cell_memory_tl.Backward(d_cell_memory);
var temp = Matrix.cat(d_ai, d_af, 1);
var temp2 = Matrix.cat(d_ac, d_ao, 1);
var da = Matrix.cat(temp, temp2, 1);
// var daT=Matrix.T(da);
ihweight = convLayerih.backweight(da);
hhweight = convLayerhh.backweight(da);
return(convLayerih.backward(da));
}
public dynamic backward(dynamic grid)
{
var dy = convLayerhq.backward(grid);
hqW = convLayerhq.backweight(grid);
var DH = dy;
var DZHT = ZHTL.backward(dy);
var dH_tilda = ZHTL.backwardY(dy);
//var Dz1 = ZHTL.backward(DH);
var Dz = ZHL.backward(DZHT);
var DRHS = THL.Backward(dH_tilda);
var DR = RHM.backward(DRHS);//Add 因为加法的梯度等于本身 所以DRHS=DRH
var DHHS = RHM.backwardY(DRHS);
var DRS = RSL.Backward(DR);
var DZS = ZSL.Backward(Dz);
var temp = Matrix.cat(DZS, DRS, 1);
var da = Matrix.cat(temp, DHHS, 1);
ihweight = convLayerih.backweight(da);
hhweight = convLayerhh.backweight(da);
return(convLayerih.backward(da));
}