public void Apply(TensorProxy tensorProxy, IEnumerable <int> actionIds, Dictionary <int, float[]> lastActions)
{
var agentIndex = 0;
var memorySize = (int)tensorProxy.shape[tensorProxy.shape.Length - 1];
foreach (int agentId in actionIds)
{
List <float> memory = null;
if (!m_Memories.TryGetValue(agentId, out memory) ||
memory.Count < memorySize * m_MemoriesCount)
{
memory = new List <float>();
memory.AddRange(Enumerable.Repeat(0f, memorySize * m_MemoriesCount));
}
for (var j = 0; j < memorySize; j++)
{
memory[memorySize * m_MemoryIndex + j] = tensorProxy.data[agentIndex, j];
}
m_Memories[agentId] = memory;
agentIndex++;
}
}
/// <summary>
/// Queries the InferenceEngine for the value of a variable in the graph given its name.
/// Only works with int32 Tensors with zero dimensions containing a unique element.
/// If the node was not found or could not be retrieved, the value -1 will be returned.
/// </summary>
/// <param name="name">The name of the Tensor variable</param>
/// <returns>The value of the scalar variable in the model. (-1 if not found)</returns>
private int GetIntScalar(string name)
{
var outputs = new TensorProxy[]
{
new TensorProxy()
{
Name = name,
ValueType = TensorProxy.TensorType.Integer,
Shape = new long[] { },
Data = new Tensor(1, 1)
},
};
try
{
_engine.ExecuteGraph(new TensorProxy[0], outputs);
}
catch (Exception ex)
{
UnityEngine.Debug.LogError($"Failed to execute GetIntScalar()\n{ex}");
return(-1);
}
return((int)outputs[0].Data[0]);
}
public void Generate(TensorProxy tensorProxy, int batchSize, IEnumerable <Agent> agents)
{
TensorUtils.ResizeTensor(tensorProxy, batchSize, m_Allocator);
var memorySize = (int)tensorProxy.shape[tensorProxy.shape.Length - 1];
var agentIndex = 0;
foreach (var agent in agents)
{
var offset = memorySize * m_MemoryIndex;
List <float> memory;
if (agent.Info.done)
{
m_Memories.Remove(agent.Info.id);
}
if (!m_Memories.TryGetValue(agent.Info.id, out memory))
{
for (var j = 0; j < memorySize; j++)
{
tensorProxy.data[agentIndex, j] = 0;
}
agentIndex++;
continue;
}
for (var j = 0; j < memorySize; j++)
{
if (j >= memory.Count)
{
break;
}
tensorProxy.data[agentIndex, j] = memory[j + offset];
}
agentIndex++;
}
}
public void Generate(TensorProxy tensorProxy, int batchSize, IEnumerable <AgentInfoSensorsPair> infos)
{
TensorUtils.ResizeTensor(tensorProxy, batchSize, m_Allocator);
var vecObsSizeT = tensorProxy.shape[tensorProxy.shape.Length - 1];
var agentIndex = 0;
foreach (var info in infos)
{
if (info.agentInfo.done)
{
// If the agent is done, we might have a stale reference to the sensors
// e.g. a dependent object might have been disposed.
// To avoid this, just fill observation with zeroes instead of calling sensor.Write.
TensorUtils.FillTensorBatch(tensorProxy, agentIndex, 0.0f);
}
else
{
var tensorOffset = 0;
// Write each sensor consecutively to the tensor
foreach (var sensorIndex in m_SensorIndices)
{
var sensor = info.sensors[sensorIndex];
m_WriteAdapter.SetTarget(tensorProxy, agentIndex, tensorOffset);
var numWritten = sensor.Write(m_WriteAdapter);
tensorOffset += numWritten;
}
Debug.AssertFormat(
tensorOffset == vecObsSizeT,
"mismatch between vector observation size ({0}) and number of observations written ({1})",
vecObsSizeT, tensorOffset
);
}
agentIndex++;
}
}
public void Generate(TensorProxy tensorProxy, int batchSize, IEnumerable <AgentInfoSensorsPair> infos)
{
tensorProxy.data?.Dispose();
tensorProxy.data = m_Allocator.Alloc(new TensorShape(1, 1));
tensorProxy.data[0] = batchSize;
}
public void Generate(TensorProxy tensorProxy, int batchSize, IEnumerable <AgentInfoSensorsPair> infos)
{
TensorUtils.ResizeTensor(tensorProxy, batchSize, m_Allocator);
TensorUtils.FillTensorWithRandomNormal(tensorProxy, m_RandomNormal);
}
public void Generate(TensorProxy tensorProxy, int batchSize, IEnumerable <AgentInfoSensorsPair> infos)
{
TensorUtils.ResizeTensor(tensorProxy, batchSize, m_Allocator);
}
public void Apply(TensorProxy tensorProxy, IEnumerable <int> actionIds, Dictionary <int, float[]> lastActions)
{
//var tensorDataProbabilities = tensorProxy.Data as float[,];
var idActionPairList = actionIds as List <int> ?? actionIds.ToList();
var batchSize = idActionPairList.Count;
var actionValues = new float[batchSize, m_ActionSize.Length];
var startActionIndices = Utilities.CumSum(m_ActionSize);
for (var actionIndex = 0; actionIndex < m_ActionSize.Length; actionIndex++)
{
var nBranchAction = m_ActionSize[actionIndex];
var actionProbs = new TensorProxy()
{
valueType = TensorProxy.TensorType.FloatingPoint,
shape = new long[] { batchSize, nBranchAction },
data = m_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 = m_Allocator.Alloc(new TensorShape(batchSize, 1))
};
Eval(actionProbs, outputTensor, m_Multinomial);
for (var ii = 0; ii < batchSize; ii++)
{
actionValues[ii, actionIndex] = outputTensor.data[ii, 0];
}
actionProbs.data.Dispose();
outputTensor.data.Dispose();
}
var agentIndex = 0;
foreach (int agentId in actionIds)
{
if (lastActions.ContainsKey(agentId))
{
var actionVal = lastActions[agentId];
if (actionVal == null)
{
actionVal = new float[m_ActionSize.Length];
lastActions[agentId] = actionVal;
}
for (var j = 0; j < m_ActionSize.Length; j++)
{
actionVal[j] = actionValues[agentIndex, j];
}
}
agentIndex++;
}
}
private TensorProxy GetOpMetadata(TFOperation op)
{
TFStatus status = new TFStatus();
// Query the shape
long[] shape = null;
var shape_attr = op.GetAttributeMetadata("shape", status);
if (!status.Ok || shape_attr.TotalSize <= 0)
{
Debug.LogWarning($"Operation {op.Name} does not contain shape attribute or it" +
$" doesn't contain valid shape data! Status: {status.StatusMessage}");
}
else
{
if (shape_attr.IsList)
{
throw new NotImplementedException("Querying lists is not implemented yet!");
}
else
{
TFStatus s = new TFStatus();
long[] dims = new long[shape_attr.TotalSize];
TF_OperationGetAttrShape(op.Handle, "shape", dims, (int)shape_attr.TotalSize,
s.Handle);
if (!status.Ok)
{
throw new FormatException("Could not query model for op shape (" + op.Name + ")");
}
else
{
shape = new long[dims.Length];
for (int i = 0; i < shape_attr.TotalSize; ++i)
{
if (dims[i] == -1)
{
// we have to use batchsize 1
shape[i] = 1;
}
else
{
shape[i] = dims[i];
}
}
}
}
}
// Query the data type
TFDataType type_value = new TFDataType();
unsafe
{
TFStatus s = new TFStatus();
TF_OperationGetAttrType(op.Handle, "dtype", &type_value, s.Handle);
if (!s.Ok)
{
Debug.LogWarning("Operation " + op.Name +
": error retrieving dtype, assuming float!");
type_value = TFDataType.Float;
}
}
TensorProxy.TensorType placeholder_type = TensorProxy.TensorType.FloatingPoint;
switch (type_value)
{
case TFDataType.Float:
placeholder_type = TensorProxy.TensorType.FloatingPoint;
break;
case TFDataType.Int32:
placeholder_type = TensorProxy.TensorType.Integer;
break;
default:
Debug.LogWarning("Operation " + op.Name +
" is not a float/integer. Proceed at your own risk!");
break;
}
TensorProxy t = new TensorProxy
{
Data = null,
Name = op.Name,
Shape = shape,
ValueType = placeholder_type
};
return(t);
}
public void Generate(TensorProxy tensorProxy, int batchSize, Dictionary <Agent, AgentInfo> agentInfo)
{
tensorProxy.data?.Dispose();
tensorProxy.data = m_Allocator.Alloc(new TensorShape(1, 1));
tensorProxy.data[0] = batchSize;
}
public void Generate(
TensorProxy tensorProxy, int batchSize, Dictionary <Agent, AgentInfo> agentInfo)
{
TensorUtils.ResizeTensor(tensorProxy, batchSize, m_Allocator);
TensorUtils.FillTensorWithRandomNormal(tensorProxy, m_RandomNormal);
}
public void Generate(TensorProxy tensorProxy, int batchSize, Dictionary <Agent, AgentInfo> agentInfo)
{
TensorUtils.ResizeTensor(tensorProxy, batchSize, m_Allocator);
}
public void Generate(TensorProxy tensorProxy, int batchSize, Dictionary <Agent, AgentInfo> agentInfo)
{
TensorUtils.ResizeTensor(tensorProxy, batchSize, _allocator);
_randomNormal.FillTensor(tensorProxy);
}
