public static MnistModel ReadImage(string path, bool normalize, bool trainAsEncoder)
{
var bitmap = new Bitmap(path);
var fileName = path.Substring(path.LastIndexOfAny(FileSeparators) + 1);
var label = int.Parse(fileName[0].ToString());
var values = new DenseVector(bitmap.Height * bitmap.Width);
for (var i = 0; i < bitmap.Height; i++)
{
for (var j = 0; j < bitmap.Width; j++)
{
{
var color = bitmap.GetPixel(j, i);
var gray = (int)(color.R * 0.3 + color.G * 0.59 + color.B * 0.11);
values[j + i * bitmap.Width] = 1 - gray / 255.0;
}
}
}
if (normalize)
{
var max = values.Maximum();
max /= 2;
values.MapInplace(v => v - max);
}
//values.CoerceZero(0.005);
//values.MapInplace(v => v > 0.995 ? 1 : v);
Vector solution;
if (trainAsEncoder)
{
solution = values;
}
else
{
solution = new DenseVector(10)
{
[label] = 1.0
};
}
var image = new MnistModel
{
Width = bitmap.Width,
Height = bitmap.Height,
Values = values,
FileName = fileName,
Label = label,
ExpectedSolution = solution
};
return(image);
}
public static string Dump(MnistModel image)
{
var sb = new StringBuilder();
sb.Append(Print(image.Values, image.Width));
sb.AppendLine($"Filename - {image.FileName}");
sb.AppendLine($"Label - {image.Label}");
sb.AppendLine($"Width - {image.Width}");
sb.Append($"Height - {image.Height}");
return(sb.ToString());
}
public static MnistModel[] ReadAll(string pathToDirectory, bool normalize, bool trainAsEncoder)
{
var directoryInfo = new DirectoryInfo(pathToDirectory);
var files = directoryInfo.GetFiles("*.png");
var count = files.Length;
var models = new MnistModel[count];
for (var i = 0; i < files.Length; i++)
{
models[i] = ReadImage(files[i].FullName, normalize, trainAsEncoder);
}
return(models);
}
