public void TestEvalBatching()
{
Multinomial m = new Multinomial(2018);
TensorProxy src = new TensorProxy
{
Data = new Tensor(2, 3, new []
{
Mathf.Log(0.1f) - 50, Mathf.Log(0.2f) - 50, Mathf.Log(0.7f) - 50,
Mathf.Log(0.3f) - 25, Mathf.Log(0.4f) - 25, Mathf.Log(0.3f) - 25
}),
ValueType = TensorProxy.TensorType.FloatingPoint
};
TensorProxy dst = new TensorProxy
{
Data = new Tensor(2, 3),
ValueType = TensorProxy.TensorType.FloatingPoint
};
m.Eval(src, dst);
float[] reference = { 2, 2, 2, 0, 1, 0 };
for (var i = 0; i < dst.Data.length; i++)
{
Assert.AreEqual(reference[i], dst.Data[i]);
++i;
}
}
public void TestEvalBatching()
{
Multinomial m = new Multinomial(2018);
Tensor src = new Tensor
{
Data = new float[2, 3]
{
{ Mathf.Log(0.1f) - 50, Mathf.Log(0.2f) - 50, Mathf.Log(0.7f) - 50 },
{ Mathf.Log(0.3f) - 25, Mathf.Log(0.4f) - 25, Mathf.Log(0.3f) - 25 },
},
ValueType = Tensor.TensorType.FloatingPoint
};
Tensor dst = new Tensor
{
Data = new float[2, 3],
ValueType = Tensor.TensorType.FloatingPoint
};
m.Eval(src, dst);
float[] reference = { 2, 2, 2, 0, 1, 0 };
int i = 0;
foreach (var f in dst.Data)
{
Assert.AreEqual(reference[i], f);
++i;
}
}
public void TestEvalP()
{
Multinomial m = new Multinomial(2018);
TensorProxy src = new TensorProxy
{
Data = new Tensor(1, 3, new[] { 0.1f, 0.2f, 0.7f }),
ValueType = TensorProxy.TensorType.FloatingPoint
};
TensorProxy dst = new TensorProxy
{
Data = new Tensor(1, 3),
ValueType = TensorProxy.TensorType.FloatingPoint
};
m.Eval(src, dst);
float[] reference = { 2, 2, 1 };
for (var i = 0; i < dst.Data.length; i++)
{
Assert.AreEqual(reference[i], dst.Data[i]);
++i;
}
}
public void TestEvalP()
{
Multinomial m = new Multinomial(2018);
Tensor src = new Tensor
{
Data = new float[1, 3] {
{ 0.1f, 0.2f, 0.7f }
},
ValueType = Tensor.TensorType.FloatingPoint
};
Tensor dst = new Tensor
{
Data = new float[1, 3],
ValueType = Tensor.TensorType.FloatingPoint
};
m.Eval(src, dst);
float[] reference = { 2, 2, 1 };
int i = 0;
foreach (var f in dst.Data)
{
Assert.AreEqual(reference[i], f);
++i;
}
}
public void Apply(TensorProxy tensorProxy, Dictionary <Agent, AgentInfo> agentInfo)
{
//var tensorDataProbabilities = tensorProxy.Data as float[,];
var batchSize = agentInfo.Keys.Count;
var actions = new float[batchSize, _actionSize.Length];
var startActionIndices = Utilities.CumSum(_actionSize);
for (var actionIndex = 0; actionIndex < _actionSize.Length; actionIndex++)
{
var nBranchAction = _actionSize[actionIndex];
var actionProbs = new TensorProxy()
{
ValueType = TensorProxy.TensorType.FloatingPoint,
Shape = new long[] { batchSize, nBranchAction },
Data = _allocator.Alloc(new TensorShape(batchSize, nBranchAction))
};
for (var batchIndex = 0; batchIndex < batchSize; batchIndex++)
{
for (var branchActionIndex = 0;
branchActionIndex < nBranchAction;
branchActionIndex++)
{
actionProbs.Data[batchIndex, branchActionIndex] =
tensorProxy.Data[batchIndex, startActionIndices[actionIndex] + branchActionIndex];
}
}
var outputTensor = new TensorProxy()
{
ValueType = TensorProxy.TensorType.FloatingPoint,
Shape = new long[] { batchSize, 1 },
Data = _allocator.Alloc(new TensorShape(batchSize, 1))
};
_multinomial.Eval(actionProbs, outputTensor);
for (var ii = 0; ii < batchSize; ii++)
{
actions[ii, actionIndex] = outputTensor.Data[ii, 0];
}
}
var agentIndex = 0;
foreach (var agent in agentInfo.Keys)
{
var action = new float[_actionSize.Length];
for (var j = 0; j < _actionSize.Length; j++)
{
action[j] = actions[agentIndex, j];
}
agent.UpdateVectorAction(action);
agentIndex++;
}
}
public void TestSrcInt()
{
Multinomial m = new Multinomial(2018);
TensorProxy src = new TensorProxy
{
ValueType = TensorProxy.TensorType.Integer
};
Assert.Throws <NotImplementedException>(() => m.Eval(src, null));
}
public void TestSrcDataNull()
{
Multinomial m = new Multinomial(2018);
TensorProxy src = new TensorProxy
{
ValueType = TensorProxy.TensorType.FloatingPoint
};
TensorProxy dst = new TensorProxy
{
ValueType = TensorProxy.TensorType.FloatingPoint
};
Assert.Throws <ArgumentNullException>(() => m.Eval(src, dst));
}
public void TestDstInt()
{
Multinomial m = new Multinomial(2018);
Tensor src = new Tensor
{
ValueType = Tensor.TensorType.FloatingPoint
};
Tensor dst = new Tensor
{
ValueType = Tensor.TensorType.Integer
};
Assert.Throws <ArgumentException>(() => m.Eval(src, dst));
}
public void TestDstDataNull()
{
Multinomial m = new Multinomial(2018);
Tensor src = new Tensor
{
ValueType = Tensor.TensorType.FloatingPoint,
Data = new float[1]
};
Tensor dst = new Tensor
{
ValueType = Tensor.TensorType.FloatingPoint
};
Assert.Throws <ArgumentNullException>(() => m.Eval(src, dst));
}
public void TestUnequalBatchSize()
{
Multinomial m = new Multinomial(2018);
TensorProxy src = new TensorProxy
{
ValueType = TensorProxy.TensorType.FloatingPoint,
Data = new Tensor(1, 1)
};
TensorProxy dst = new TensorProxy
{
ValueType = TensorProxy.TensorType.FloatingPoint,
Data = new Tensor(2, 1)
};
Assert.Throws <ArgumentException>(() => m.Eval(src, dst));
}
public void TestUnequalBatchSize()
{
Multinomial m = new Multinomial(2018);
Tensor src = new Tensor
{
ValueType = Tensor.TensorType.FloatingPoint,
Data = new float[1, 1]
};
Tensor dst = new Tensor
{
ValueType = Tensor.TensorType.FloatingPoint,
Data = new float[2, 1]
};
Assert.Throws <ArgumentException>(() => m.Eval(src, dst));
}