IMLFeatureProvider CreateInput(UIImage image)
{
var pixelBuffer = image.Resize(new CGSize(227, 227)).ToPixelBuffer();
var imageValue = MLFeatureValue.FromPixelBuffer(pixelBuffer);
var inputs = new NSDictionary <NSString, NSObject> (new NSString("image"), imageValue);
return(new MLDictionaryFeatureProvider(inputs, out var error));
}
public MLFeatureValue GetFeatureValue(string featureName)
{
switch (featureName)
{
case "audioSamples":
return(MLFeatureValue.Create(AudioSamples));
default:
return(null);
}
}
private List <Prediction> Classify(MLModel model, UIImage source)
{
if (model == null)
{
throw new ArgumentNullException(nameof(model));
}
if (source == null)
{
throw new ArgumentNullException(nameof(source));
}
var scaled = source.Scale(new CGSize(227, 227));
var pixelBuffer = ToCVPixelBuffer(scaled);
var imageValue = MLFeatureValue.Create(pixelBuffer);
var inputs = new NSDictionary <NSString, NSObject>(new NSString("data"), imageValue);
NSError error, error2;
var inputFp = new MLDictionaryFeatureProvider(inputs, out error);
if (error != null)
{
System.Diagnostics.Debug.WriteLine(error);
throw new InvalidOperationException(error.Description);
}
var outFeatures = model.GetPrediction(inputFp, out error2);
if (error2 != null)
{
System.Diagnostics.Debug.WriteLine(error2);
throw new InvalidOperationException(error2.Description);
}
var predictionsDictionary = outFeatures.GetFeatureValue("loss").DictionaryValue;
var byProbability = new List <Tuple <double, string> >();
foreach (var key in predictionsDictionary.Keys)
{
var description = (string)(NSString)key;
var prob = (double)predictionsDictionary[key];
byProbability.Add(new Tuple <double, string>(prob, description));
}
byProbability.Sort((t1, t2) => t1.Item1.CompareTo(t2.Item1) * -1);
var result = byProbability
.Select(p => new Prediction {
Label = p.Item2, Probability = p.Item1
})
.ToList();
return(result);
}
public MLFeatureValue GetFeatureValue(string featureName)
{
switch (featureName)
{
case "image":
return(MLFeatureValue.Create(Image));
default:
return(null);
}
}
public MLFeatureValue GetFeatureValue(string featureName)
{
switch (featureName)
{
case "output1":
return(MLFeatureValue.Create(Output1));
default:
return(null);
}
}
public MLFeatureValue GetFeatureValue(string featureName)
{
switch (featureName)
{
case "data":
return(MLFeatureValue.Create(Data));
default:
return(null);
}
}
public MLFeatureValue GetFeatureValue(string featureName)
{
if (inputFeatureName.Equals(featureName))
{
return(MLFeatureValue.Create(this.ImagePixelData));
}
else
{
return(MLFeatureValue.Create(0));
}
}
public MLFeatureValue GetFeatureValue(string featureName)
{
switch (featureName)
{
case "confidence":
return(MLFeatureValue.Create(Confidence));
case "coordinates":
return(MLFeatureValue.Create(Coordinates));
default:
return(null);
}
}
public MLFeatureValue GetFeatureValue(string featureName)
{
switch (featureName)
{
case "target":
return(MLFeatureValue.Create(Target));
case "classProbability":
return(MLFeatureValue.Create(ClassProbability));
default:
return(null);
}
}
private IEnumerable <Recognition> Recognize(Stream source)
{
var byProbability = new List <Recognition>();
var image = UIImage.LoadFromData(NSData.FromStream(source));
if (model == null)
{
//ErrorOccurred(this, new EventArgsT<string>(error.ToString()));
return(byProbability);
}
var pixelBuffer = image.Scale(ImageSize).ToCVPixelBuffer();
var imageValue = MLFeatureValue.Create(pixelBuffer);
var inputs = new NSDictionary <NSString, NSObject>(new NSString(INPUT_NAME), imageValue);
var inputFeatureProvider = new MLDictionaryFeatureProvider(inputs, out var error1);
if (error1 != null)
{
//ErrorOccurred(this, new EventArgs<string>(error1.ToString()));
return(byProbability);
}
var outFeatures = model.GetPrediction(inputFeatureProvider, out var error2);
if (error2 != null)
{
//ErrorOccurred(this, new EventArgs<string>(error2.ToString()));
return(byProbability);
}
var predictionsDictionary = outFeatures.GetFeatureValue(OUTPUT_NAME).DictionaryValue;
foreach (var key in predictionsDictionary.Keys)
{
var description = (string)(NSString)key;
var prob = (double)predictionsDictionary[key];
byProbability.Add(new Recognition
{
Tag = description,
Probability = prob
});
}
//Sort descending
byProbability.Sort((t1, t2) => (t1.Probability.CompareTo(t2.Probability)) * -1);
return(byProbability);
}
public MLFeatureValue GetFeatureValue(string featureName)
{
switch (featureName)
{
case "solarPanels":
return(MLFeatureValue.Create(SolarPanels));
case "greenhouses":
return(MLFeatureValue.Create(Greenhouses));
case "size":
return(MLFeatureValue.Create(Size));
default:
return(MLFeatureValue.Create(0));
}
}
public MLFeatureValue GetFeatureValue(string featureName)
{
switch (featureName)
{
case "image":
return(MLFeatureValue.Create(Image));
case "iouThreshold":
return(MLFeatureValue.Create(IouThreshold));
case "confidenceThreshold":
return(MLFeatureValue.Create(ConfidenceThreshold));
default:
return(null);
}
}
internal void Classify(UIImage source)
{
var model = models[currentModel];
var pixelBuffer = source.Scale(sizeFor[model]).ToCVPixelBuffer();
var imageValue = MLFeatureValue.Create(pixelBuffer);
var inputs = new NSDictionary <NSString, NSObject>(new NSString("image"), imageValue);
NSError error, error2;
var inputFp = new MLDictionaryFeatureProvider(inputs, out error);
if (error != null)
{
ErrorOccurred(this, new EventArgsT <string>(error.ToString()));
return;
}
var outFeatures = model.GetPrediction(inputFp, out error2);
if (error2 != null)
{
ErrorOccurred(this, new EventArgsT <string>(error2.ToString()));
return;
}
var predictionsDictionary = outFeatures.GetFeatureValue("classLabelProbs").DictionaryValue;
var byProbability = new List <Tuple <double, string> >();
foreach (var key in predictionsDictionary.Keys)
{
var description = (string)(NSString)key;
var prob = (double)predictionsDictionary[key];
byProbability.Add(new Tuple <double, string>(prob, description));
}
//Sort descending
byProbability.Sort((t1, t2) => t1.Item1.CompareTo(t2.Item1) * -1);
var prediction = new ImageDescriptionPrediction();
prediction.ModelName = currentModel;
prediction.predictions = byProbability;
PredictionsUpdated(this, new EventArgsT <ImageDescriptionPrediction>(prediction));
}
public async Task <IEnumerable <Recognition> > RecognizeAsync(Stream source, params string[] parameters)
{
var results = new List <Recognition>();
var image = await UIImage.LoadFromData(NSData.FromStream(source)).ResizeImageAsync(INPUT_WIDTH, INPUT_HEIGHT);
await Task.Run(() =>
{
var pixelBuffer = image.Scale(ImageSize).ToCVPixelBuffer();
var imageValue = MLFeatureValue.Create(pixelBuffer);
var inputs = new NSDictionary <NSString, NSObject>(new NSString(INPUT_NAME), imageValue);
var inputFeatureProvider = new MLDictionaryFeatureProvider(inputs, out var error1);
if (error1 != null)
{
throw new ClassifierException(error1.ToString());
}
var outFeatures = model.GetPrediction(inputFeatureProvider, out var error2);
if (error2 != null)
{
throw new ClassifierException(error2.ToString());
}
var predictionsDictionary = outFeatures.GetFeatureValue(OUTPUT_NAME).DictionaryValue;
foreach (var key in predictionsDictionary.Keys)
{
var description = (string)(NSString)key;
var probability = (double)predictionsDictionary[key];
results.Add(new Recognition
{
Tag = description,
Probability = probability
});
}
// Sort descending.
results.Sort((t1, t2) => (t1.Probability.CompareTo(t2.Probability)) * -1);
});
return(results);
}
public ImageClassificationResult RecognizeImage(UIImage imageSource)
{
var pixelBuffer = imageSource.Scale(new CGSize(InputSize, InputSize)).ToCVPixelBuffer();
var imageValue = MLFeatureValue.Create(pixelBuffer);
var inputs = new NSDictionary <NSString, NSObject>(new NSString(InputName), imageValue);
NSError error, error2;
var inputFp = new MLDictionaryFeatureProvider(inputs, out error);
if (error != null)
{
Console.WriteLine("RecognizeImage Error 1: {0}", error);
return(null);
}
var outFeatures = _imageClassifierModel.GetPrediction(inputFp, out error2);
if (error2 != null)
{
Console.WriteLine("RecognizeImage Error 2: {0}", error2);
return(null);
}
var predictionsDictionary = outFeatures.GetFeatureValue(OutputName).DictionaryValue;
var outputs = new List <Tuple <double, string> >();
foreach (var key in predictionsDictionary.Keys)
{
var description = (string)(NSString)key;
var prob = (double)predictionsDictionary[key];
outputs.Add(new Tuple <double, string>(prob, description));
}
var results = outputs
.Select((t1, t2) => new ImageClassificationResult(t1.Item2, t1.Item1))
.ToList();
return(results.OrderByDescending(t => t.Probability).First());
}
public MLFeatureValue GetFeatureValue(string featureName)
{
MLFeatureValue value;
NSError err;
switch (featureName)
{
case "classLabelProbs":
value = MLFeatureValue.Create(ClassLabelProbs, out err);
if (err != null)
{
err.Dispose();
}
return(value);
case "classLabel":
return(MLFeatureValue.Create(ClassLabel));
default:
return(null);
}
}
public MLFeatureValue GetFeatureValue(string featureName)
{
switch (featureName)
{
case "ppi":
return(MLFeatureValue.Create(PPI));
case "eye_blink":
return(MLFeatureValue.Create(Blink));
case "eye_squint":
return(MLFeatureValue.Create(Squint));
case "eye_gaze_inward":
return(MLFeatureValue.Create(GazeIn));
case "eye_gaze_outward":
return(MLFeatureValue.Create(GazeOut));
case "smile":
return(MLFeatureValue.Create(Smile));
case "frown":
return(MLFeatureValue.Create(Frown));
case "head_speed":
return(MLFeatureValue.Create(HeadSpeed));
case "eye_dwelling":
return(MLFeatureValue.Create(EyeDwell));
case "head_tilt":
return(MLFeatureValue.Create(HeadTilt));
default:
return(MLFeatureValue.Create(0)); // default value
}
}
public MLFeatureValue GetFeatureValue(string featureName) => _inputFeatureName.Equals(featureName)
? MLFeatureValue.Create(ImagePixelData)
: MLFeatureValue.Create(0);
public MLFeatureValue GetFeatureValue(string featureName)
{
switch (featureName)
{
case "BrowDownLeft": return(MLFeatureValue.Create(BrowDownLeft));
case "BrowDownRight": return(MLFeatureValue.Create(BrowDownRight));
case "BrowInnerUp": return(MLFeatureValue.Create(BrowInnerUp));
case "BrowOuterUpLeft": return(MLFeatureValue.Create(BrowOuterUpLeft));
case "BrowOuterUpRight": return(MLFeatureValue.Create(BrowOuterUpRight));
case "CheekPuff": return(MLFeatureValue.Create(CheekPuff));
case "CheekSquintLeft": return(MLFeatureValue.Create(CheekSquintLeft));
case "CheekSquintRight": return(MLFeatureValue.Create(CheekSquintRight));
case "EyeBlinkLeft": return(MLFeatureValue.Create(EyeBlinkLeft));
case "EyeBlinkRight": return(MLFeatureValue.Create(EyeBlinkRight));
case "EyeLookDownLeft": return(MLFeatureValue.Create(EyeLookDownLeft));
case "EyeLookDownRight": return(MLFeatureValue.Create(EyeLookDownRight));
case "EyeLookInLeft": return(MLFeatureValue.Create(EyeLookInLeft));
case "EyeLookInRight": return(MLFeatureValue.Create(EyeLookInRight));
case "EyeLookOutLeft": return(MLFeatureValue.Create(EyeLookOutRight));
case "EyeLookOutRight": return(MLFeatureValue.Create(EyeLookOutRight));
case "EyeLookUpLeft": return(MLFeatureValue.Create(EyeLookUpLeft));
case "EyeLookUpRight": return(MLFeatureValue.Create(EyeLookUpRight));
case "EyeSquintLeft": return(MLFeatureValue.Create(EyeSquintLeft));
case "EyeSquintRight": return(MLFeatureValue.Create(EyeSquintRight));
case "EyeWideLeft": return(MLFeatureValue.Create(EyeWideLeft));
case "EyeWideRight": return(MLFeatureValue.Create(EyeWideRight));
case "JawForward": return(MLFeatureValue.Create(JawForward));
case "JawLeft": return(MLFeatureValue.Create(JawLeft));
case "JawOpen": return(MLFeatureValue.Create(JawOpen));
case "JawRight": return(MLFeatureValue.Create(JawRight));
case "MouthClose": return(MLFeatureValue.Create(MouthClose));
case "MouthDimpleLeft": return(MLFeatureValue.Create(MouthDimpleLeft));
case "MouthDimpleRight": return(MLFeatureValue.Create(MouthDimpleRight));
case "MouthFrownLeft": return(MLFeatureValue.Create(MouthFrownLeft));
case "MouthFrownRight": return(MLFeatureValue.Create(MouthFrownRight));
case "MouthFunnel": return(MLFeatureValue.Create(MouthFunnel));
case "MouthLeft": return(MLFeatureValue.Create(MouthLeft));
case "MouthLowerDownLeft": return(MLFeatureValue.Create(MouthLowerDownLeft));
case "MouthLowerDownRight": return(MLFeatureValue.Create(MouthLowerDownRight));
case "MouthPressLeft": return(MLFeatureValue.Create(MouthPressLeft));
case "MouthPressRight": return(MLFeatureValue.Create(MouthPressRight));
case "MouthPucker": return(MLFeatureValue.Create(MouthPucker));
case "MouthRight": return(MLFeatureValue.Create(MouthRight));
case "MouthRollLower": return(MLFeatureValue.Create(MouthRollLower));
case "MouthRollUpper": return(MLFeatureValue.Create(MouthRollUpper));
case "MouthShrugLower": return(MLFeatureValue.Create(MouthShrugLower));
case "MouthShrugUpper": return(MLFeatureValue.Create(MouthShrugUpper));
case "MouthSmileLeft": return(MLFeatureValue.Create(MouthSmileLeft));
case "MouthSmileRight": return(MLFeatureValue.Create(MouthSmileRight));
case "MouthStretchLeft": return(MLFeatureValue.Create(MouthStretchLeft));
case "MouthStretchRight": return(MLFeatureValue.Create(MouthStretchRight));
case "MouthUpperUpLeft": return(MLFeatureValue.Create(MouthUpperUpLeft));
case "MouthUpperUpRight": return(MLFeatureValue.Create(MouthUpperUpRight));
case "NoseSneerLeft": return(MLFeatureValue.Create(NoseSneerLeft));
case "NoseSneerRight": return(MLFeatureValue.Create(NoseSneerRight));
case "M11": return(MLFeatureValue.Create(M11));
case "M12": return(MLFeatureValue.Create(M12));
case "M13": return(MLFeatureValue.Create(M13));
case "M14": return(MLFeatureValue.Create(M14));
case "M21": return(MLFeatureValue.Create(M21));
case "M22": return(MLFeatureValue.Create(M22));
case "M23": return(MLFeatureValue.Create(M23));
case "M24": return(MLFeatureValue.Create(M24));
case "M31": return(MLFeatureValue.Create(M31));
case "M32": return(MLFeatureValue.Create(M32));
case "M33": return(MLFeatureValue.Create(M33));
case "M34": return(MLFeatureValue.Create(M34));
case "qW": return(MLFeatureValue.Create(qW));
case "qX": return(MLFeatureValue.Create(qX));
case "qY": return(MLFeatureValue.Create(qY));
case "qZ": return(MLFeatureValue.Create(qZ));
default:
return(MLFeatureValue.Create(""));
}
}
