public static void TestAttentionReduce()
{
var n = 3;
var b = 4;
var d = 5;
var statesData = new double[n, b, d];
UniformRandomArray(statesData);
var softmaxData = new double[n, b];
UniformRandomArray(softmaxData);
var softmax = Variable <double>(PartialShape.Create(-1, b));
var states = Variable <double>(PartialShape.Create(-1, b, d));
var reduce = new AttentionReduce <double>(softmax, states);
var ctx = Context.GpuContext(0);
var exe = new Executor(ctx, reduce.Output)
{
AssignAllGradient = true
};
exe.Initalize();
var dOutputData = new double[b, d];
UniformRandomArray(dOutputData);
exe.AssignTensor(softmax, softmaxData.AsTensor());
exe.AssignTensor(states, statesData.AsTensor());
exe.Forward();
exe.AssignGradient(reduce.Output, dOutputData.AsTensor(), replace: true);
exe.Backward();
var dSoftmax = exe.GetGradient(reduce.Softmax);
var dStates = exe.GetGradient(reduce.States);
var bump = 1e-6;
var dSoftmaxFd = GradientChecker.FiniteDifferenceGradient(exe, softmax, bump: bump);
AreClose(dSoftmaxFd.ToArray2D(), dSoftmax.ToArray2D(), 1e-7);
var dStatesFd = GradientChecker.FiniteDifferenceGradient(exe, states, bump: bump);
AreClose(dStatesFd.ToArray3D(), dStates.ToArray3D(), 1e-7);
//var dVectorsFdArray = dVectorsFd.Reshape(-1).ToArray();
//var dVectorsBackpropArray = dStates.Reshape(-1).ToArray();
//var err = MaxAbsDiff(dVectorsFdArray, dVectorsBackpropArray);
}
public static void LoopStyle()
{
var inputVar = Variable <double>();
var statesVar = Variable <double>();
var weightVar = Variable <double>();
var loop = new LoopDemo(inputVar, statesVar, weightVar);
var outputVar = loop.Output;
// create executor
var ctx = Context.GpuContext(0);
var exe = new Executor(ctx, outputVar)
{
AssignAllGradient = true
};
exe.Initalize();
// fake forward data
const int steps = 4;
const int n = 5;
var input = new double[n, n];
var states = new double[steps, n, n];
var weight = new double[n, n];
var rng = new Random(42);
UniformRandomArray(input, rng);
UniformRandomArray(states, rng);
UniformRandomArray(weight, rng);
exe.AssignTensor(inputVar, input.AsTensor());
exe.AssignTensor(statesVar, states.AsTensor());
exe.AssignTensor(weightVar, weight.AsTensor());
// run forward
exe.Forward();
var outputTensor = exe.GetTensor(outputVar);
outputTensor.Print();
// fake backward data
var dOutput = new double[n, n];
UniformRandomArray(dOutput, rng);
exe.AssignGradient(outputVar, dOutput.AsTensor(), replace: true);
// run backward
exe.Backward();
// verify gradients
var bump = 1e-7;
var dInputTensor = exe.GetGradient(inputVar);
var dInputTensor_FD = GradientChecker.FiniteDifferenceGradient(exe, inputVar, bump: bump);
//dInputTensor.Print();
//dInputTensor_FD.Print();
AreClose(dInputTensor_FD.ToArray2D(), dInputTensor.ToArray2D(), 1e-7);
var dStatesTensor = exe.GetGradient(statesVar);
var dStatesTensor_FD = GradientChecker.FiniteDifferenceGradient(exe, statesVar, bump: bump);
//dStatesTensor.Reshape(steps, -1).Print();
//dStatesTensor_FD.Reshape(steps, -1).Print();
AreClose(dStatesTensor_FD.ToArray3D(), dStatesTensor.ToArray3D(), 1e-7);
var dWeightTensor = exe.GetGradient(weightVar);
var dWeightTensor_FD = GradientChecker.FiniteDifferenceGradient(exe, weightVar, bump: bump);
//dWeightTensor.Print();
//dWeightTensor_FD.Print();
AreClose(dWeightTensor_FD.ToArray2D(), dWeightTensor.ToArray2D(), 1e-3);
}
public static void UnrollingStyle()
{
// create unrolling graph
const int steps = 4;
var inputVar = Variable <double>();
var stateVars = Enumerable.Range(0, steps).Select(_ => Variable <double>()).ToArray();
var weightVar = Variable <double>();
var outputVar = CreateUnrollingGraph(inputVar, stateVars, weightVar);
// create executor
var ctx = Context.GpuContext(0);
var exe = new Executor(ctx, outputVar)
{
AssignAllGradient = true
};
exe.Initalize();
// fake forward data
const int n = 5;
var input = new double[n, n];
var states = Enumerable.Range(0, steps).Select(_ => new double[n, n]).ToArray();
var weight = new double[n, n];
var rng = new Random(42);
UniformRandomArray(input, rng);
foreach (var state in states)
{
UniformRandomArray(state, rng);
}
UniformRandomArray(weight, rng);
exe.AssignTensor(inputVar, input.AsTensor());
for (var i = 0; i < steps; ++i)
{
exe.AssignTensor(stateVars[i], states[i].AsTensor());
}
exe.AssignTensor(weightVar, weight.AsTensor());
// run forward
exe.Forward();
var outputTensor = exe.GetTensor(outputVar);
outputTensor.Print();
// fake backward data
var dOutput = new double[n, n];
UniformRandomArray(dOutput, rng);
exe.AssignGradient(outputVar, dOutput.AsTensor(), replace: true);
// run backward
exe.Backward();
// verify gradients
var bump = 1e-7;
var dInputTensor = exe.GetGradient(inputVar);
var dInputTensor_FD = GradientChecker.FiniteDifferenceGradient(exe, inputVar, bump: bump);
//dInputTensor.Print();
//dInputTensor_FD.Print();
AreClose(dInputTensor_FD.ToArray2D(), dInputTensor.ToArray2D(), 1e-7);
for (var i = 0; i < steps; ++i)
{
var stateVar = stateVars[i];
var dStateTensor = exe.GetGradient(stateVar);
var dStateTensor_FD = GradientChecker.FiniteDifferenceGradient(exe, stateVar, bump: bump);
//dStateTensor.Print();
//dStateTensor_FD.Print();
AreClose(dStateTensor_FD.ToArray2D(), dStateTensor.ToArray2D(), 1e-7);
}
var dWeightTensor = exe.GetGradient(weightVar);
var dWeightTensor_FD = GradientChecker.FiniteDifferenceGradient(exe, weightVar, bump: bump);
//dWeightTensor.Print();
//dWeightTensor_FD.Print();
AreClose(dWeightTensor_FD.ToArray2D(), dWeightTensor.ToArray2D(), 1e-3);
}
public static void TestAttention()
{
//var batch = 4;
//var encoderHiddenSize = 5;
//var decoderHiddenSize = 4;
//var attentionDim = 3;
var batch = 10;
var encoderHiddenSize = 20;
var decoderHiddenSize = 25;
var attentionDim = 30;
// (encoderSeqLength, batch, encoderHiddenSize)
var encoderHiddenStates = Variable <double>(PartialShape.Create(-1, batch, encoderHiddenSize));
var decoderHiddenStates = Variable <double>(PartialShape.Create(batch, decoderHiddenSize));
var attention = new Attention <double>(encoderHiddenStates, decoderHiddenStates, attentionDim);
var ctx = Context.GpuContext(0);
var exe = new Executor(ctx, attention.Output)
{
AssignAllGradient = true
};
exe.Initalize();
// encoderSeqLength is flexibly at runtime
var encoderSeqLength = 3;
var dataEncoderHiddenStates = new double[encoderSeqLength, batch, encoderHiddenSize];
UniformRandomArray(dataEncoderHiddenStates);
var dataDecoderHiddenStates = new double[batch, decoderHiddenSize];
UniformRandomArray(dataDecoderHiddenStates);
exe.AssignTensor(encoderHiddenStates, dataEncoderHiddenStates.AsTensor());
exe.AssignTensor(decoderHiddenStates, dataDecoderHiddenStates.AsTensor());
exe.Forward();
var tensorOutput = exe.GetTensor(attention.Output);
//Console.WriteLine(tensorOutput.Shape);
//tensorOutput.Print();
var dataDOutput = new double[batch, encoderHiddenSize];
UniformRandomArray(dataDOutput);
exe.AssignGradient(attention.Output, dataDOutput.AsTensor(), replace: true);
exe.Backward();
var tensorDWh = exe.GetGradient(attention.Wh);
//tensorDWh.Print();
var tensorDWd = exe.GetGradient(attention.Wd);
//tensorDWd.Print();
var tensorDH = exe.GetGradient(attention.EncoderHiddenStates);
//Console.WriteLine(tensorDH.Shape);
//tensorDH.Reshape(-1, encoderHiddenSize).Print();
var tensorDD = exe.GetGradient(attention.DecoderHiddenStates);
//Console.WriteLine(tensorDD.Shape);
//tensorDD.Print();
var bump = 1e-7;
var tensorDWh_fd = GradientChecker.FiniteDifferenceGradient(exe, attention.Wh, bump: bump);
//tensorDWh.Print();
//tensorDWh_fd.Print();
AreClose(tensorDWh.ToArray2D(), tensorDWh_fd.ToArray2D(), 1e-7);
var tensorDWd_fd = GradientChecker.FiniteDifferenceGradient(exe, attention.Wd, bump: bump);
//tensorDWd.Print();
//tensorDWd_fd.Print();
AreClose(tensorDWd.ToArray2D(), tensorDWd_fd.ToArray2D(), 1e-7);
var tensorDH_fd = GradientChecker.FiniteDifferenceGradient(exe, attention.EncoderHiddenStates, bump: bump);
//tensorDH.Reshape(-1, encoderHiddenSize).Print();
//tensorDH_fd.Reshape(-1, encoderHiddenSize).Print();
AreClose(tensorDH.ToArray3D(), tensorDH_fd.ToArray3D(), 1e-7);
var tensorDD_fd = GradientChecker.FiniteDifferenceGradient(exe, attention.DecoderHiddenStates, bump: bump);
//tensorDD.Print();
//tensorDD_fd.Print();
AreClose(tensorDD.ToArray2D(), tensorDD_fd.ToArray2D(), 1e-7);
}
