static void Main(string[] args)
{
string directoryPath;
if (args.Length == 0)
{
directoryPath = "..//..//s02170130/ImageNetSample";
}
else
{
directoryPath = args[0];
}
OnnxClassifier.OnnxClassifier onnxModel = new OnnxClassifier.OnnxClassifier();
ThreadClassification task_1 = new ThreadClassification(directoryPath, onnxModel, RecognitionCompletedHandler);
Console.WriteLine("Press any key to stop...");
task_1.Run();
Console.ReadKey(true);
task_1.Stopper();
}
public ClassificationVM()
{
Classes = new ObservableCollection <Tuple <string, int> >();
Result = new ObservableCollection <ResultClassification>();
SelectedResult = new ObservableCollection <ResultClassification>();
onnxModel = new OnnxClassifier.OnnxClassifier();
}
public ThreadClassification(ConcurrentQueue <string> pathImages, OnnxClassifier onnxModel, Action <ResultClassification> handler)
{
Model = onnxModel;
ImageRecognitionCompleted = handler;
PathImages = pathImages;
}
public ThreadClassification(string currentDirectory, OnnxClassifier onnxModel, Action <ResultClassification> handler)
{
Model = onnxModel;
ImageRecognitionCompleted = handler;
PathImages = new ConcurrentQueue <string>(Directory.GetFiles(currentDirectory).Where(s => s.EndsWith(".JPEG") || s.EndsWith(".jpg")));
}
public ClassificationVM()
{
Classes = new ObservableCollection <Tuple <string, int> >();
Result = new ObservableCollection <ResultClassification>();
SelectedResult = new ObservableCollection <RecognitionImage>();
stat = new ObservableCollection <Tuple <int, int> >();
db = new ApplicationContext();
onnxModel = new OnnxClassifier.OnnxClassifier();
}
public ResultClassification PredictModel(string imageFilePath)
{
DenseTensor <float> TensorImage = OnnxClassifier.PreprocImage(imageFilePath);
var inputs = new List <NamedOnnxValue>
{
NamedOnnxValue.CreateFromTensor(session.InputMetadata.Keys.First(), TensorImage)
};
using IDisposableReadOnlyCollection <DisposableNamedOnnxValue> results = session.Run(inputs);
var output = results.First().AsEnumerable <float>().ToArray();
float sum = output.Sum(x => (float)Math.Exp(x));
var softmax = output.Select(x => (float)Math.Exp(x) / sum).ToList();
string cl = LabelMap.Labels[softmax.IndexOf(softmax.Max())];
ResultClassification result = new ResultClassification(imageFilePath, cl, softmax.Max());
return(result);
}
public ResultClassification Post([FromBody] ImageString obj)
{
ResultClassification result;
OnnxClassifier.OnnxClassifier onnxModel;
using (var db = new ApplicationContext())
{
result = db.FindInDataBase(obj);
if (result != null)
{
return(result);
}
onnxModel = new OnnxClassifier.OnnxClassifier();
result = onnxModel.PredictModel(obj.path);
obj.path = result._PathImage;
obj.Probability = result._Probability;
obj.ClassImage = result._ClassImage;
db.AddToDataBase(obj);
}
return(result);
}
