public void ConstructMultiDimIntArrayTensor()
{
var array = new [, ] {
{ 123, 456 }
};
using (var tensor = new TFTensor(array))
{
Assert.Equal(TFDataType.Int32, tensor.TensorType);
Assert.Equal(array.Rank, tensor.NumDims);
Assert.Equal(array.GetLength(0), tensor.GetTensorDimension(0));
Assert.Equal(array.GetLength(1), tensor.GetTensorDimension(1));
Assert.Equal(new long [] { array.GetLength(0), array.GetLength(1) }, tensor.Shape);
Assert.Equal((uint)sizeof(int) * array.Length, tensor.TensorByteSize.ToUInt32());
Assert.Equal(array, tensor.GetValue());
}
}
public void ConstructDoubleArrayTensor()
{
var array = new [] { 123.456, 234.567 };
using (var tensor = new TFTensor(array))
{
Assert.Equal(TFDataType.Double, tensor.TensorType);
Assert.Equal(array.Rank, tensor.NumDims);
Assert.Equal(array.Length, tensor.GetTensorDimension(0));
Assert.Equal(new long [] { array.Length }, tensor.Shape);
Assert.Equal((uint)sizeof(double) * array.Length, tensor.TensorByteSize.ToUInt32());
Assert.Equal(array, tensor.GetValue());
}
}
public void ConstrucComplexArrayTensor()
{
var array = new [] { new Complex(1, 2), new Complex(2, -1) };
using (var tensor = new TFTensor(array))
{
Assert.Equal(TFDataType.Complex128, tensor.TensorType);
Assert.Equal(array.Rank, tensor.NumDims);
Assert.Equal(array.Length, tensor.GetTensorDimension(0));
Assert.Equal(new long [] { array.Length }, tensor.Shape);
Assert.Equal(16u * array.Length, tensor.TensorByteSize.ToUInt32());
Assert.Equal(array, tensor.GetValue());
}
}
public void ConstructUnsignedShortArrayTensor()
{
var array = new ushort [] { 123, 234 };
using (var tensor = new TFTensor(array))
{
Assert.Equal(TFDataType.UInt16, tensor.TensorType);
Assert.Equal(array.Rank, tensor.NumDims);
Assert.Equal(array.Length, tensor.GetTensorDimension(0));
Assert.Equal(new long [] { array.Length }, tensor.Shape);
Assert.Equal((uint)sizeof(ushort) * array.Length, tensor.TensorByteSize.ToUInt32());
Assert.Equal(array, tensor.GetValue());
}
}
public void ConstructSignedByteArrayTensor()
{
var array = new sbyte [] { 123, -123 };
using (var tensor = new TFTensor(array))
{
Assert.Equal(TFDataType.Int8, tensor.TensorType);
Assert.Equal(array.Rank, tensor.NumDims);
Assert.Equal(array.Length, tensor.GetTensorDimension(0));
Assert.Equal(new long [] { array.Length }, tensor.Shape);
Assert.Equal((uint)sizeof(sbyte) * array.Length, tensor.TensorByteSize.ToUInt32());
Assert.Equal(array, tensor.GetValue());
}
}
public void ConstructBoolArrayTensor()
{
var array = new [] { true, false };
using (var tensor = new TFTensor(array))
{
Assert.Equal(TFDataType.Bool, tensor.TensorType);
Assert.Equal(array.Rank, tensor.NumDims);
Assert.Equal(array.Length, tensor.GetTensorDimension(0));
Assert.Equal(new long [] { array.Length }, tensor.Shape);
Assert.Equal((uint)sizeof(bool) * array.Length, tensor.TensorByteSize.ToUInt32());
Assert.Equal(array, tensor.GetValue());
}
}
static void Main(string[] args)
{
// 整数张量
var tensor = new TFTensor(1);
Console.WriteLine("Value:" + tensor.GetValue());
// 矩阵张量
tensor = new TFTensor(new int[, ]
{
{ 1, 2, 3 },
{ 4, 5, 6 },
});
Console.WriteLine("TensorType: {0}", tensor.TensorType.ToString());
Console.WriteLine("NumDims: " + tensor.NumDims);
Console.WriteLine("Shape", string.Join(",", tensor.Shape));
for (var i = 0; i < tensor.NumDims; i++)
{
var dim = tensor.GetTensorDimension(i);
Console.WriteLine("DimIndex: {0}, Dim: {1}", i, dim);
}
// 创建图
var g = new TFGraph();
// 创建字符串张量
tensor = new TFTensor("Hello, world!".Select(o => (sbyte)o).ToArray());
var hello = g.Const(tensor);
// 创建会话
var sess = new TFSession(g);
// 进行计算
var result = sess.GetRunner().Run(hello).GetValue();
// 输出计算结果
Console.WriteLine(string.Join("", ((sbyte[])result).Select(o => (char)o)));
}
public override IObservable <Pose> Process(IObservable <IplImage> source)
{
return(Observable.Defer(() =>
{
TFSessionOptions options = new TFSessionOptions();
unsafe
{
byte[] GPUConfig = new byte[] { 0x32, 0x02, 0x20, 0x01 };
fixed(void *ptr = &GPUConfig[0])
{
options.SetConfig(new IntPtr(ptr), GPUConfig.Length);
}
}
var graph = new TFGraph();
var session = new TFSession(graph, options, null);
var bytes = File.ReadAllBytes(ModelFileName);
graph.Import(bytes);
IplImage temp = null;
TFTensor tensor = null;
TFSession.Runner runner = null;
var config = ConfigHelper.PoseConfig(PoseConfigFileName);
return source.Select(input =>
{
var poseScale = 1.0;
const int TensorChannels = 3;
var frameSize = input.Size;
var scaleFactor = ScaleFactor;
if (scaleFactor.HasValue)
{
poseScale = scaleFactor.Value;
frameSize.Width = (int)(frameSize.Width * poseScale);
frameSize.Height = (int)(frameSize.Height * poseScale);
poseScale = 1.0 / poseScale;
}
if (tensor == null || tensor.GetTensorDimension(1) != frameSize.Height || tensor.GetTensorDimension(2) != frameSize.Width)
{
tensor = new TFTensor(
TFDataType.Float,
new long[] { 1, frameSize.Height, frameSize.Width, TensorChannels },
frameSize.Width * frameSize.Height * TensorChannels * sizeof(float));
runner = session.GetRunner();
runner.AddInput(graph["Placeholder"][0], tensor);
runner.Fetch(graph["concat_1"][0]);
}
var frame = input;
if (frameSize != input.Size)
{
if (temp == null || temp.Size != frameSize)
{
temp = new IplImage(frameSize, input.Depth, input.Channels);
}
CV.Resize(input, temp);
frame = temp;
}
using (var image = new IplImage(frameSize, IplDepth.F32, TensorChannels, tensor.Data))
{
CV.Convert(frame, image);
}
// Run the model
var output = runner.Run();
// Fetch the results from output:
var poseTensor = output[0];
var pose = new Mat((int)poseTensor.Shape[0], (int)poseTensor.Shape[1], Depth.F32, 1, poseTensor.Data);
var result = new Pose(input);
var threshold = MinConfidence;
for (int i = 0; i < pose.Rows; i++)
{
BodyPart bodyPart;
bodyPart.Name = config[i];
bodyPart.Confidence = (float)pose.GetReal(i, 2);
if (bodyPart.Confidence < threshold)
{
bodyPart.Position = new Point2f(float.NaN, float.NaN);
}
else
{
bodyPart.Position.X = (float)(pose.GetReal(i, 1) * poseScale);
bodyPart.Position.Y = (float)(pose.GetReal(i, 0) * poseScale);
}
result.Add(bodyPart);
}
return result;
});
}));
}
public override IObservable <Pose> Process(IObservable <IplImage> source)
{
return(Observable.Defer(() =>
{
TFSessionOptions options = new TFSessionOptions();
unsafe
{
byte[] GPUConfig = new byte[] { 0x32, 0x02, 0x20, 0x01 };
fixed(void *ptr = &GPUConfig[0])
{
options.SetConfig(new IntPtr(ptr), GPUConfig.Length);
}
}
var graph = new TFGraph();
var session = new TFSession(graph, options, null);
var bytes = File.ReadAllBytes(ModelFileName);
graph.Import(bytes);
TFTensor tensor = null;
var config = ConfigHelper.PoseConfig(PoseConfigFileName);
return source.Select(input =>
{
if (tensor == null || tensor.GetTensorDimension(1) != input.Height || tensor.GetTensorDimension(2) != input.Width)
{
tensor = new TFTensor(
TFDataType.Float,
new long[] { 1, input.Height, input.Width, 3 },
input.WidthStep * input.Height * 4);
}
using (var image = new IplImage(input.Size, IplDepth.F32, 3, tensor.Data))
{
CV.Convert(input, image);
}
var runner = session.GetRunner();
runner.AddInput(graph["Placeholder"][0], tensor);
runner.Fetch(graph["concat_1"][0]);
// Run the model
var output = runner.Run();
// Fetch the results from output:
var poseTensor = output[0];
var pose = new Mat((int)poseTensor.Shape[0], (int)poseTensor.Shape[1], Depth.F32, 1, poseTensor.Data);
var result = new Pose(input);
var threshold = MinConfidence;
for (int i = 0; i < pose.Rows; i++)
{
BodyPart bodyPart;
bodyPart.Name = config[i];
bodyPart.Confidence = (float)pose.GetReal(i, 2);
if (bodyPart.Confidence < threshold)
{
bodyPart.Position = new Point2f(float.NaN, float.NaN);
}
else
{
bodyPart.Position.X = (float)pose.GetReal(i, 1);
bodyPart.Position.Y = (float)pose.GetReal(i, 0);
}
result.Add(bodyPart);
}
return result;
});
}));
}