/// <summary>
/// Loads the standard data from file.
/// </summary>
/// <returns>Collection with datas</returns>
public static TestingCollection LoadStandardData()
{
const int HOW_MANY_NUMBERS_TO_TEST_FROM_FILE = 100;
TestingCollection collection = new TestingCollection(HOW_MANY_NUMBERS_TO_TEST_FROM_FILE);
GiveItemsFromFile itemReturner = new GiveItemsFromFile();
byte[] expectedResultFromFile = itemReturner.GiveArrayOfExpectedResultsToTest();
sbyte[,] trainDataFromFile = itemReturner.GiveArrayOfTestData();
const int SIZE_OF_IMAGE = 28 * 28;
int[] indexes = RandomIndexes.GiveArrayOfRandomDifferentIntegers(HOW_MANY_NUMBERS_TO_TEST_FROM_FILE, 10000);
for (int numberCounter = 0; numberCounter < HOW_MANY_NUMBERS_TO_TEST_FROM_FILE; numberCounter++)
{
int index = indexes[numberCounter];
int expectedResult = expectedResultFromFile[index];
double[] testData = new double[SIZE_OF_IMAGE];
for (int i = 0; i < SIZE_OF_IMAGE; i++)
{
testData[i] = trainDataFromFile[index, i];
}
TestingSet testingSet = new TestingSet();
testingSet.Input = testData;
testingSet.Value = expectedResult;
collection.Values.Add(testingSet);
}
return collection;
}
/// <summary>
/// Loads the standard data from file.
/// </summary>
/// <returns>Collection with datas</returns>
public static TrainingCollection LoadStandardData()
{
const int HOW_MANY_NUMBERS_TO_LEARN_FROM_FILE = 1000;
TrainingCollection collection = new TrainingCollection(HOW_MANY_NUMBERS_TO_LEARN_FROM_FILE);
GiveItemsFromFile itemReturner = new GiveItemsFromFile();
sbyte[,] expectedResultFromFile = itemReturner.GiveArrayOfExpectedResults();
sbyte[,] trainDataFromFile = itemReturner.GiveArrayOfTrainData();
const int NUMBER_OF_RESULTS = 10;
const int SIZE_OF_IMAGE = 28 * 28;
for (int numberCounter = 0; numberCounter < HOW_MANY_NUMBERS_TO_LEARN_FROM_FILE; numberCounter++)
{
double[] expectedResult = new double[NUMBER_OF_RESULTS];
int whatNumber = -1;
for (int i = 0; i < NUMBER_OF_RESULTS; i++)
{
expectedResult[i] = expectedResultFromFile[numberCounter, i];
if (expectedResult[i] == 1)
whatNumber = i;
}
double[] trainData = new double[SIZE_OF_IMAGE];
for (int i = 0; i < SIZE_OF_IMAGE; i++)
{
trainData[i] = trainDataFromFile[numberCounter, i];
}
TrainingSet trainingSet = new TrainingSet();
trainingSet.Input = trainData;
trainingSet.Response = expectedResult;
trainingSet.Value = whatNumber;
collection.Values.Add(trainingSet);
}
return collection;
}
// Test for recognizing digits from ubyte file and recognizing theirs labels
private void TestRecognizingNumbersFromFile()
{
GiveItemsFromFile itemReturner = new GiveItemsFromFile();
sbyte[,] expectedResultFromFile = itemReturner.GiveArrayOfExpectedResults();
sbyte[,] trainDataFromFile = itemReturner.GiveArrayOfTrainData();
const int sizeOfImage = 28 * 28; // heightOfImage * widthOfImage (28 x 28 pixel);
for (int numberCounter = 0; numberCounter < expectedResultFromFile.GetLength(0); numberCounter++)
{
int index = 0;
double[] expectedResult = new double[NUMBER_OF_RESULTS];
for (int i = 0; i < NUMBER_OF_RESULTS; i++)
{
expectedResult[i] = expectedResultFromFile[numberCounter, i];
if (expectedResult[i] == 1)
index = i;
}
double[] trainData = new double[sizeOfImage];
for (int i = 0; i < sizeOfImage; i++)
{
trainData[i] = trainDataFromFile[numberCounter, i];
}
_graphics.Clear(Color.White);
Bitmap bitmap = (Bitmap)_neuralNetworkGUI.GiveImageFromDrawingArea();
for (int w = 0; w < HEIGHTH_FOR_BITMAP; w++)
{
for (int k = 0; k < WIDTH_FOR_BITMAP; k++)
{
if (trainData[w * WIDTH_FOR_BITMAP + k] == 1)
bitmap.SetPixel(k, w, Color.Black);
}
}
_neuralNetworkGUI.RefreshDrawingArea();
_neuralNetworkGUI.SelectNumber(index);
}
}
