public float[] EncodeAudio(string audioFile)
{
Bitmap bitmap = melgram.Convert(audioFile, 48);
TFTensor imageTensor = TensorUtils.GetImageTensor(bitmap, melgram.Width, melgram.Height);
/*
* foreach(TFOperation op in graph.GetEnumerator())
* {
* if (op != null)
* {
* Console.WriteLine(op.Name);
* }
* }*/
var session = new TFSession(graph);
var runner = session.GetRunner();
runner.AddInput(graph["conv2d_1_input"][0], imageTensor);
runner.Fetch(graph["output_node0"][0]);
var output = runner.Run();
// Fetch the results from output:
TFTensor result = output[0];
var rshape = result.Shape;
if (result.NumDims != 2 || rshape[0] != 1)
{
var shape = "";
foreach (var d in rshape)
{
shape += $"{d} ";
}
shape = shape.Trim();
Console.WriteLine($"Error: expected to produce a [1 N] shaped tensor where N is the number of labels, instead it produced one with shape [{shape}]");
Environment.Exit(1);
}
bool jagged = true;
if (jagged)
{
return(((float[][])result.GetValue(jagged: true))[0]);
}
else
{
var val = (float[, ])result.GetValue(jagged: false);
float[] probabilities = new float[val.GetLength(1)];
for (int i = 0; i < val.GetLength(1); i++)
{
probabilities[i] = val[0, i];
}
return(probabilities);
}
}
public double[][] predict(double[][] input)
{
double[] buffer = new double[input.Length * inputDimension];
for (int i = 0; i < input.Length; i++)
{
for (int j = 0; j < inputDimension; j++)
{
buffer[i * inputDimension + j] = input[i][j];
}
}
var inputShape = new TFShape(new long[] { input.Length, inputDimension });
TFTensor tfInput = TFTensor.FromBuffer(inputShape, buffer, 0, input.Length * inputDimension);
TFTensor[] output = session
.GetRunner()
.AddInput("input_node", tfInput)
.Fetch("prediction_node_2")
.Run();
TFTensor theFirstAndOnlyFetchedNode = output[0];
bool jagged = true;
object native_array_representation = theFirstAndOnlyFetchedNode.GetValue(jagged); // when jagged = true, returning expected dimensions of return
double[][] typed = (double[][])native_array_representation; // typing to expected array with expected dimensions
return(typed);
}
static void Main(string[] args)
{
using (TFGraph graph = new TFGraph())
{
graph.Import(File.ReadAllBytes(@"C:\Users\Ben\Desktop\frozen.pb"));
TFSession session = new TFSession(graph);
TFSession.Runner runner = session.GetRunner();
float[] x1 = new float[] { 239, 958, 8, 34, 239 };
float[] x2 = new float[] { 239, 958, 8, 34, 239 };
float[] x3 = new float[] { 239, 958, 8, 34, 239 };
TFTensor x = new TFTensor(new float[][] { x1, x2, x3 });
runner.AddInput(graph["Placeholder"][0], x);
runner.Fetch(graph["add"][0]);
var output = runner.Run();
TFTensor result = output[0];
var v = result.GetValue();
return;
}
}
public override string Execute(string input)
{
var inputdict = JsonConvert.DeserializeObject <Dictionary <string, string> >(input);
float conf = -1.0f;
string strSentence = inputdict["sentence"];
var sentence_node = _graph[_prefix + "/" + "sentence"];
var is_training_node = _graph[_prefix + "/" + "is_training"];
var sm_decision_node = _graph[_prefix + "/" + "sm_decision"];
var runner = _session.GetRunner();
int[][] sentenceTensor = new int[1][];
sentenceTensor[0] = IndexText(strSentence);
TFTensor sentence = new TFTensor(sentenceTensor);
runner.AddInput(sentence_node[0], sentence);
runner.AddInput(is_training_node[0], new TFTensor(false));
runner.Fetch(sm_decision_node[0]);
var output = runner.Run();
// Fetch the results from output:
TFTensor result = output[0];
object o = result.GetValue();
conf = ((float[, ])o)[0, 1];
return(string.Format("{{ conf: {0:N2} }}", conf));
}
/// <summary>
/// Make a prediction for a input image
/// </summary>
/// <param name="image">the input image</param>
/// <returns></returns>
public int Predict(float[,] im)
{
float[] image = TransformArray(im);
//create a runner with the session
var runner = _session.GetRunner();
// create tensor using image
var tensor = TFTensor.FromBuffer(new TFShape(1, 30, 30, 1), image, 0, image.Length);
// set inputput layer
runner.AddInput(_session.Graph[INPUT_NAME][0], tensor);
// set output layer
runner.Fetch(_session.Graph[OUTPUT_NAME][0]);
// run the model
var output = runner.Run();
// Get output tensor
TFTensor result = output[0];
// get result from tensor
var resultArray = result.GetValue() as float[, ];
//return
return(ExtractPrediction(resultArray));
}
private float[] ExtractFeatures(Bitmap candidate)
{
var tensor = ImageUtil.CreateTensorFromBitmap(candidate);
var session = new TFSession(_graph);
var runner = session.GetRunner();
runner.AddInput(_graph["input_2"][0], tensor);
runner.Fetch(_graph["mixed8/concat"][0]);
var output = runner.Run();
TFTensor result = output[0];
var features = (float[, , , ])result.GetValue(jagged: false);
//features shape: [1,4,4,1280]
float[] flattenFeatures = new float[20480];
int n = 0;
for (int k = 0; k < 1280; k++)
{
for (int j = 0; j < 4; j++)
{
for (int i = 0; i < 4; i++)
{
flattenFeatures[n] = features[0, j, i, k];
n++;
}
}
}
return(flattenFeatures);
}
private void button1_Click(object sender, EventArgs e)
{
//int val1=Int32.Parse(textBox1.Text);
//int val2 = Int32.Parse(textBox2.Text);
//var sess = new TFSession();
//var tf = sess.Graph;
//var a = tf.Const(val1);
//var b = tf.Const(val2);
//label1.Text = sess.GetRunner().Run(tf.Add(a, b)).GetValue().ToString();
//sess.CloseSession();
using (var graph = new TFGraph())
{
var file = File.ReadAllBytes(@"..\..\python\tmp\model\output.pb");
graph.Import(file);
var tf = new TFSession(graph);
var runner = tf.GetRunner();
if (img_tensor != null)
{
runner.AddInput(graph["input"][0], img_tensor);
runner.Fetch(graph["output"][0]);
var output = runner.Run();
TFTensor result = output[0];
label1.Text = "Prediction:\n" + ((System.Int64[])result.GetValue())[0].ToString();
}
}
}
public static string Predict(byte[] bytes)
{
var img_tensor = FormatJPEG(bytes);
if (img_tensor != null)
{
var runner = tf.GetRunner();
runner.AddInput(opInput, img_tensor);
runner.Fetch(opDenseDecode);
var output = runner.Run();
TFTensor result = output[0];
StringBuilder stringBuffer = new StringBuilder();
foreach (int s in (System.Int64[, ])result.GetValue())
{
if (s > charset.Count - 1)
{
Console.WriteLine("Current character set do not match the model.");
break;
}
stringBuffer.Append(charset[s]);
}
return(stringBuffer.ToString());
}
Console.WriteLine("Imgage error!");
return(null);
}
public void SetBoolTensor()
{
using (var tensor = new TFTensor(true))
{
tensor.SetValue(false);
Assert.Equal((uint)sizeof(bool), tensor.TensorByteSize.ToUInt32());
Assert.Equal(false, tensor.GetValue());
}
}
public void SetIntTensor()
{
using (var tensor = new TFTensor(123))
{
tensor.SetValue(234);
Assert.Equal((uint)sizeof(int), tensor.TensorByteSize.ToUInt32());
Assert.Equal(234, tensor.GetValue());
}
}
public void SetArrayTensor()
{
using (var tensor = new TFTensor(new [] { 123, 456 }))
{
tensor.SetValue(new [] { 234, 567 });
Assert.Equal((uint)sizeof(int) * 2, tensor.TensorByteSize.ToUInt32());
Assert.Equal(new [] { 234, 567 }, tensor.GetValue());
}
}
public void SetLongTensor()
{
using (var tensor = new TFTensor(123L))
{
tensor.SetValue(234L);
Assert.Equal((uint)sizeof(long), tensor.TensorByteSize.ToUInt32());
Assert.Equal(234L, tensor.GetValue());
}
}
public void SetComplexTensor()
{
using (var tensor = new TFTensor(new Complex(1, 2)))
{
tensor.SetValue(new Complex(2, -1));
Assert.Equal((uint)16, tensor.TensorByteSize.ToUInt32());
Assert.Equal(new Complex(2, -1), tensor.GetValue());
}
}
public void SetFloatTensor()
{
using (var tensor = new TFTensor(123.456f))
{
tensor.SetValue(234.567f);
Assert.Equal((uint)sizeof(float), tensor.TensorByteSize.ToUInt32());
Assert.Equal(234.567f, tensor.GetValue());
}
}
public void SetDoubleTensor()
{
using (var tensor = new TFTensor(123.456))
{
tensor.SetValue(234.567);
Assert.Equal((uint)sizeof(double), tensor.TensorByteSize.ToUInt32());
Assert.Equal(234.567, tensor.GetValue());
}
}
public void SetUnsignedShortTensor()
{
using (var tensor = new TFTensor((ushort)123))
{
tensor.SetValue((ushort)234);
Assert.Equal((uint)sizeof(ushort), tensor.TensorByteSize.ToUInt32());
Assert.Equal((ushort)234, tensor.GetValue());
}
}
public void SetSignedByteTensor()
{
using (var tensor = new TFTensor((sbyte)123))
{
tensor.SetValue((sbyte)-123);
Assert.Equal((uint)sizeof(sbyte), tensor.TensorByteSize.ToUInt32());
Assert.Equal((sbyte)-123, tensor.GetValue());
}
}
public void CreateTenso()
{
// Some input matrices
var inp = new float[] { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 96, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 27, 35, 55, 82, 115, 135, 140, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 63, 77, 91, 106, 122, 136, 138, 127, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 112, 103, 95, 107, 121, 131, 131, 111, 90, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 111, 112, 101, 91, 102, 121, 126, 126, 108, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 101, 107, 96, 88, 90, 108, 125, 130, 138, 173, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 102, 98, 88, 91, 96, 101, 120, 138, 146, 185, 243, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 88, 96, 93, 91, 92, 98, 111, 135, 153, 172, 221, 242, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 90, 91, 93, 100, 107, 125, 153, 185, 210, 226, 237, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 126, 131, 140, 163, 188, 206, 216, 223, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 180, 188, 196, 202, 208, 216, 246, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 203, 203, 193, 200, 210, 233, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 227, 232, 222, 216, 231, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 233, 247, 242, 236, 246, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 151, 155, 0, 183, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
Debug.WriteLine("TEST");
for (int i = 0; i < inp.Length; i++)
{
if (inp[i] == 0)
{
inp[i] = 255;
}
// inp[i] = inp[i] / 255;
//Debug.WriteLine(inp[i]);
}
// Debug.WriteLine("len : " + inp.Length);
var tensor = TFTensor.FromBuffer(new TFShape(1, 30, 30, 1), inp, 0, inp.Length);
// Debug.WriteLine("input: " + tensor);
using (var graph = new TFGraph())
{
// Load the model
// graph.Import(File.ReadAllBytes(@"C:\Users\Public\TestFolder\my_model.pb"));
string model_file = Path.Combine(Environment.CurrentDirectory, @"model\gesture_model.pb");
Debug.WriteLine("file path " + model_file);
graph.Import(File.ReadAllBytes(model_file));
using (var session = new TFSession(graph))
{
var runner = session.GetRunner();
//Debug.WriteLine(graph);
runner.AddInput(graph[INPUT_NAME][0], tensor);
runner.Fetch(graph[OUTPUT_NAME][0]);
Debug.WriteLine(System.DateTime.Now);
var output = runner.Run();
TFTensor result = output[0];
var re = result.GetValue() as float[, ];
foreach (float f in re)
{
Debug.WriteLine(f);
}
Debug.WriteLine("o: " + re[0, 1]);
Debug.WriteLine(result);
Debug.WriteLine(System.DateTime.Now);
}
}
}
public void ConstructLongTensor()
{
long value = 123L;
using (var tensor = new TFTensor(value))
{
Assert.Equal(TFDataType.Int64, tensor.TensorType);
Assert.Equal(0, tensor.NumDims);
Assert.Equal(new long [0], tensor.Shape);
Assert.Equal((uint)sizeof(long), tensor.TensorByteSize.ToUInt32());
Assert.Equal(value, tensor.GetValue());
}
}
public void GetArrayValueInPlace(Array array)
{
using (var tensor = new TFTensor(array))
{
var type = array.GetType().GetElementType();
var value = Array.CreateInstance(type, tensor.Shape);
Assert.NotEqual(array, value);
tensor.GetValue(value);
Assert.Equal(array, value);
}
}
public void ConstructComplexTensor()
{
Complex value = new Complex(1, 2);
using (var tensor = new TFTensor(value))
{
Assert.Equal(TFDataType.Complex128, tensor.TensorType);
Assert.Equal(0, tensor.NumDims);
Assert.Equal(new long [0], tensor.Shape);
Assert.Equal(16u, tensor.TensorByteSize.ToUInt32());
Assert.Equal(value, tensor.GetValue());
}
}
public void ConstructFloatTensor()
{
float value = 123.456f;
using (var tensor = new TFTensor(value))
{
Assert.Equal(TFDataType.Float, tensor.TensorType);
Assert.Equal(0, tensor.NumDims);
Assert.Equal(new long [0], tensor.Shape);
Assert.Equal((uint)sizeof(float), tensor.TensorByteSize.ToUInt32());
Assert.Equal(value, tensor.GetValue());
}
}
public void ConstructDoubleTensor()
{
double value = 123.456;
using (var tensor = new TFTensor(value))
{
Assert.Equal(TFDataType.Double, tensor.TensorType);
Assert.Equal(0, tensor.NumDims);
Assert.Equal(new long [0], tensor.Shape);
Assert.Equal((uint)sizeof(double), tensor.TensorByteSize.ToUInt32());
Assert.Equal(value, tensor.GetValue());
}
}
public void ConstructBoolTensor()
{
bool value = true;
using (var tensor = new TFTensor(value))
{
Assert.Equal(TFDataType.Bool, tensor.TensorType);
Assert.Equal(0, tensor.NumDims);
Assert.Equal(new long [0], tensor.Shape);
Assert.Equal((uint)sizeof(bool), tensor.TensorByteSize.ToUInt32());
Assert.Equal(value, tensor.GetValue());
}
}
public void ConstructUnsignedShortTensor()
{
ushort value = 123;
using (var tensor = new TFTensor(value))
{
Assert.Equal(TFDataType.UInt16, tensor.TensorType);
Assert.Equal(0, tensor.NumDims);
Assert.Equal(new long [0], tensor.Shape);
Assert.Equal((uint)sizeof(ushort), tensor.TensorByteSize.ToUInt32());
Assert.Equal(value, tensor.GetValue());
}
}
public void SetMultiDimArrayTensorWithJagged()
{
using (var tensor = new TFTensor(new [, ] {
{ 123, 456 }
}))
{
tensor.SetValue(new [] { new [] { 234, 567 } });
Assert.Equal((uint)sizeof(int) * 2, tensor.TensorByteSize.ToUInt32());
Assert.Equal(new [, ] {
{ 234, 567 }
}, tensor.GetValue());
}
}
public void ConstructSignedByteTensor()
{
sbyte value = 123;
using (var tensor = new TFTensor(value))
{
Assert.Equal(TFDataType.Int8, tensor.TensorType);
Assert.Equal(0, tensor.NumDims);
Assert.Equal(new long [0], tensor.Shape);
Assert.Equal((uint)sizeof(sbyte), tensor.TensorByteSize.ToUInt32());
Assert.Equal(value, 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 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());
}
}