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));
}
internal void Classify(UIImage source)
{
var model = models[currentModel];
var pixelBuffer = source.Scale(sizeFor[model]).ToCVPixelBuffer();
var imageValue = MLFeatureValue.FromPixelBuffer(pixelBuffer);
var inputs = new NSDictionary <NSString, NSObject>(new NSString("image"), imageValue);
var inputFp = new MLDictionaryFeatureProvider(inputs, out var error);
if (error != null)
{
ErrorOccurred(this, new EventArgsT <string>(error.ToString()));
return;
}
var outFeatures = model.GetPrediction(inputFp, out var err2);
if (err2 != null)
{
ErrorOccurred(this, new EventArgsT <string>(err2.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));
}