public void TestGradConditional()
{
var modT = new CondModel("modT", true);
var modF = new CondModel("modF", false);
var psT = modT.GetParameters();
Assert.Equal(4, psT.Length);
var psF = modF.GetParameters();
Assert.Equal(4, psF.Length);
var x = Float32Tensor.RandomN(new long[] { 64, 1000 }, requiresGrad: true);
var y = Float32Tensor.RandomN(new long[] { 64, 10 }, requiresGrad: true);
modT.Train();
var eval = modT.Forward(x);
var loss = MSE(NN.Reduction.Sum);
var output = loss(eval, y);
modT.ZeroGrad();
output.Backward();
var gradCounts = 0;
foreach (var parm in modT.GetParameters())
{
var grad = parm.Grad();
gradCounts += grad.Handle == IntPtr.Zero ? 0 : 1;
}
Assert.Equal(2, gradCounts);
//{ "grad can be implicitly created only for scalar outputs (_make_grads at ..\\..\\torch\\csrc\\autograd\\autograd.cpp:47)\n(no backtrace available)"}
modF.Train();
eval = modF.Forward(x);
output = loss(eval, y);
modF.ZeroGrad();
output.Backward();
gradCounts = 0;
foreach (var parm in modF.GetParameters())
{
var grad = parm.Grad();
gradCounts += grad.Handle == IntPtr.Zero ? 0 : 1;
}
Assert.Equal(3, gradCounts);
}
public void TestGradConditional()
{
var modT = new CondModel(true);
var modF = new CondModel(false);
var x = FloatTensor.RandomN(new long[] { 64, 1000 }, device: "cpu:0");
var y = FloatTensor.RandomN(new long[] { 64, 10 }, device: "cpu:0");
modT.Train();
var eval = modT.Forward(x);
var loss = NN.LossFunction.MSE(NN.Reduction.None);
var output = loss(eval, y);
modT.ZeroGrad();
output.Backward();
var gradCounts = 0;
foreach (var parm in modT.Parameters())
{
var grad = parm.Grad();
gradCounts += grad.Handle == IntPtr.Zero ? 0 : 1;
}
Assert.Equal(2, gradCounts);
modF.Train();
eval = modF.Forward(x);
output = loss(eval, y);
modF.ZeroGrad();
output.Backward();
gradCounts = 0;
foreach (var parm in modF.Parameters())
{
var grad = parm.Grad();
gradCounts += grad.Handle == IntPtr.Zero ? 0 : 1;
}
Assert.Equal(3, gradCounts);
}
