string resultString = ""; // final result string
List <Tuple <string, float> > SendAndReceive(byte[] imageData)
{
var tf_channel = new Channel(ipAddress, Convert.ToInt32(port), ChannelCredentials.Insecure);
var tf_client = new PredictionService.PredictionServiceClient(tf_channel);
try
{
//Create prediction request
var request = new PredictRequest()
{
ModelSpec = new ModelSpec()
{
Name = "inception",
SignatureName = "predict_images"
}
};
var imageTensor = TensorProtoBuilder.TensorProtoFromImage(imageData);
// Add image tensor to request
request.Inputs.Add("images", imageTensor);
// Send request and get response
PredictResponse predictResponse = tf_client.Predict(request);
// Decode response
var classesTensor = predictResponse.Outputs["classes"];
string[] classes = TensorProtoDecoder.TensorProtoToStringArray(classesTensor);
var scoresTensor = predictResponse.Outputs["scores"];
float[] scores = TensorProtoDecoder.TensorProtoToFloatArray(scoresTensor);
List <Tuple <string, float> > predictResult = new List <Tuple <string, float> >();
for (int i = 0; i < classes.Length; i++)
{
predictResult.Add(new Tuple <string, float>(classes[i], scores[i]));
}
return(predictResult);
}
catch (Exception e)
{
if (e is RpcException)
{
RpcException re = (RpcException)e;
Debug.Log(re.Status.Detail);
Debug.Log(re.StatusCode);
}
Debug.Log(e.Message);
throw;
}
}
public async Task recognize(uint[] rgb_image, int height, int width)
{
var request = new PredictRequest()
{
ModelSpec = new ModelSpec()
{
Name = "default"
}
};
request.Inputs.Add("inputs", TensorBuilder.CreateTensorFromImage(rgb_image, height, width, 3));
// Run the prediction
var predictResponse = await client.PredictAsync(request);
//float num_classes= TensorProtoDecoder.TensorProtoToFloat(predictResponse.Outputs["num_classes"]);
int num_detections = (int)TensorProtoDecoder.TensorProtoToFloat(predictResponse.Outputs["num_detections"]);
float[] classes = TensorProtoDecoder.TensorProtoToFloatArray(predictResponse.Outputs["detection_classes"]);
float[] bboxes = TensorProtoDecoder.TensorProtoToFloatArray(predictResponse.Outputs["detection_boxes"]);
float[] scores = TensorProtoDecoder.TensorProtoToFloatArray(predictResponse.Outputs["detection_scores"]);
for (var i = 0; i < num_detections; i++)
{
float[] bbox = new float[4];
Array.Copy(bboxes, i * 4, bbox, 0, 4);
detectedObjects.Add(new Detection
{
boundingBox = bbox,
objectClass = label_list[(int)classes[i]],
confidence = scores[i]
});
}
readyForNextFrame = true;
}
