static void Main(string[] args)
{
InputLoader loader = new InputLoader();
loader.LoadFile("digits.csv");
Stopwatch sw = new Stopwatch();
var heursiticDetection = new HeuristicDetection(10, 5, quantity:50, numberOfPoints:500);
var hypothesis = new CurrentHypothesis();
foreach (var input in loader.AllElements()) {
///For every new input we extract n points of interest
///And create a feature vector which characterizes the spatial relationship between these features
///For every heuristic we get a dictionary of points of interest
DetectedPoints v = heursiticDetection.getFeatureVector(input.Item1);
///Compare this feature vector agaist each of the other feature vectors we know about
sw.Reset();
sw.Start();
TestResult r = hypothesis.Predict(v);
Debug.Print("Prediction: " + sw.Elapsed.Milliseconds.ToString());
var best= r.BestResult();
if(best != null && best.Item2 != 0){
LogProgress(best.Item1, input.Item2);
}
sw.Reset();
sw.Start();
hypothesis.Train(v, input.Item2, r);
Debug.Print("Training: " + sw.Elapsed.Milliseconds.ToString());
//heursiticDetection.pointsOfInterest.Add(HeuristicDetection.Generate(10, 5, 10));
}
}
static void Main(string[] args)
{
InputLoader loader = new InputLoader();
loader.LoadFile("digits.csv");
Label l;
int i = 0;
DigitRecognizer recognizer = new DigitRecognizer();
Dictionary<string, double> parameters = new Dictionary<string, double>() {
{"NumberOfModels", 100},
{"MaxNumberOfOperations", 100},
{"Width", 28},
{"Height", 28},
};
recognizer.ResetModels(parameters);
while (true) {
i = i % 25000;
if (i == 0) i++;
var a = loader.AccessElement(i, out l);
recognizer.SetContext(a);
recognizer.SetLabel(l);
var output = recognizer.Test();
recognizer.Train();
i++;
}
}
static void Main2(string[] args)
{
double purgeThreshold = .7;
InputLoader loader = new InputLoader();
loader.LoadFile("digits.csv");
StreamProcessor processor = new StreamProcessor(28,28);
//var count = processor.AddContextFeautres();
//Debug.Print(count.ToString() + " context features added.");
processor.GenerateRandomFeatures(1150);
LinkedList<bool> rollingRightWrong = new LinkedList<bool>();
int thresholdIdx = 2;
int correct = 0;
int i = 1;
//for (int i = 1; i < 25000; i++) {
while(true){
i = i % 25000;
//Debug.Print(i.ToString());
Label l;
var a = loader.AccessElement(i, out l);
processor.SetNextFeautreContext(a, l);
var output = processor.Predict();
processor.Train();
var best = output.BestResult();
if (best != null && best.Item2 != 0) {
//Debug.Print(i.ToString() + " " +
// best.Item1.TextRepresentation + " "
// + best.Item2.ToString());
//Debug.Print("Desired: " + processor.DataLabel.TextRepresentation);
bool guessedRight = processor.DataLabel.TextRepresentation == best.Item1.TextRepresentation;
rollingRightWrong.AddLast(guessedRight);
if (guessedRight) {
correct++;
}
if (rollingRightWrong.Count() > 100) {
if (rollingRightWrong.First()) {
correct--;
} rollingRightWrong.RemoveFirst();
}
}
//if(processor.PurgeFeautres(purgeThreshold) > 1000) purgeThreshold+= .01;
if (i % 400 == 0) {
Debug.Print("Idx: " + i.ToString() + " " + ((double)correct / 100).ToString());
processor.PrintUtil(thresholdIdx);
thresholdIdx += 2;
//string output2 = processor.DescribeAllFeatures();
//Debug.Print(output2);
}
i++;
}
//Get the ability to quickly serialize good heuristics for the future
}
static void Main(string[] args)
{
Window window = new Window();
ui = new UI();
ui.LoadNext += new EventHandler(ui_LoadNext);
loader = new InputLoader();
loader.LoadFile("digits.csv");
window.Content = ui;
window.ShowDialog();
}