Question

我目前正在探索神经网络和机器学习，我在c＃中实现了一个基本的神经网络。现在我想用MNIST数据库测试我的反向传播训练算法。虽然我在阅读文件时遇到了严重问题。

Spoiler代码目前针对性能进行了非常优化。我目前的目标是掌握主题，并在我开始为更快的数据结构抛出数据结构之前获得结构化的视图。

为了训练网络，我想为它提供一个自定义的TrainingSet数据结构：

[Serializable]
public class TrainingSet
{
    public Dictionary<List<double>, List<double>> data = new Dictionary<List<double>, List<double>>();
}

键将是我的输入数据（每个条目784像素（图像），它将表示0到1范围内的灰度值）。值将是我的输出数据（10个条目表示0-9的数字，所有条目都在0，除了1中的exspected一个）

现在我想根据这份合同阅读MNIST数据库。我现在正在进行第二次尝试，受到这篇博文的启发：https://jamesmccaffrey.wordpress.com/2013/11/23/reading-the-mnist-data-set-with-c/。可悲的是，它仍然产生与我第一次尝试以奇怪的模式散射像素相同的废话：

我目前的阅读算法：

    public static TrainingSet GenerateTrainingSet(FileInfo imagesFile, FileInfo labelsFile)
    {
        MnistImageView imageView = new MnistImageView();
        imageView.Show();

        TrainingSet trainingSet = new TrainingSet();

        List<List<double>> labels = new List<List<double>>();
        List<List<double>> images = new List<List<double>>();

        using (BinaryReader brLabels = new BinaryReader(new FileStream(labelsFile.FullName, FileMode.Open)))
        {
            using (BinaryReader brImages = new BinaryReader(new FileStream(imagesFile.FullName, FileMode.Open)))
            {
                int magic1 = brImages.ReadBigInt32(); //Reading as BigEndian
                int numImages = brImages.ReadBigInt32();
                int numRows = brImages.ReadBigInt32();
                int numCols = brImages.ReadBigInt32();

                int magic2 = brLabels.ReadBigInt32();
                int numLabels = brLabels.ReadBigInt32();

                byte[] pixels = new byte[numRows * numCols];

                // each image
                for (int imageCounter = 0; imageCounter < numImages; imageCounter++)
                {
                    List<double> imageInput = new List<double>();
                    List<double> exspectedOutput = new List<double>();

                    for (int i = 0; i < 10; i++) //generate empty exspected output
                        exspectedOutput.Add(0);

                    //read image
                    for (int p = 0; p < pixels.Length; p++)
                    {
                        byte b = brImages.ReadByte();
                        pixels[p] = b;

                        imageInput.Add(b / 255.0f); //scale in 0 to 1 range
                    }

                    //read label
                    byte lbl = brLabels.ReadByte();
                    exspectedOutput[lbl] = 1; //modify exspected output

                    labels.Add(exspectedOutput);
                    images.Add(imageInput);

                    //Debug view showing parsed image.......................
                    Bitmap image = new Bitmap(numCols, numRows);

                    for (int y = 0; y < numRows; y++)
                    {
                        for (int x = 0; x < numCols; x++)
                        {
                            image.SetPixel(x, y, Color.FromArgb(255 - pixels[x * y], 255 - pixels[x * y], 255 - pixels[x * y])); //invert colors to have 0,0,0 be white as specified by mnist
                        }
                    }

                    imageView.SetImage(image);
                    imageView.Refresh();
                    //.......................................................
                }

                brImages.Close();
                brLabels.Close();
            }
        }

        for (int i = 0; i < images.Count; i++)
        {
            trainingSet.data.Add(images[i], labels[i]);
        }

        return trainingSet;
    }

所有图像都会产生如上所示的图案。它从来都不是完全相同的模式，但似乎总是将像素“拉”到右下角。

Answer 1

我就这样做了：

public static class MnistReader
{
    private const string TrainImages = "mnist/train-images.idx3-ubyte";
    private const string TrainLabels = "mnist/train-labels.idx1-ubyte";
    private const string TestImages = "mnist/t10k-images.idx3-ubyte";
    private const string TestLabels = "mnist/t10k-labels.idx1-ubyte";

    public static IEnumerable<Image> ReadTrainingData()
    {
        foreach (var item in Read(TrainImages, TrainLabels))
        {
            yield return item;
        }
    }

    public static IEnumerable<Image> ReadTestData()
    {
        foreach (var item in Read(TestImages, TestLabels))
        {
            yield return item;
        }
    }

    private static IEnumerable<Image> Read(string imagesPath, string labelsPath)
    {
        BinaryReader labels = new BinaryReader(new FileStream(labelsPath, FileMode.Open));
        BinaryReader images = new BinaryReader(new FileStream(imagesPath, FileMode.Open));

        int magicNumber = images.ReadBigInt32();
        int numberOfImages = images.ReadBigInt32();
        int width = images.ReadBigInt32();
        int height = images.ReadBigInt32();

        int magicLabel = labels.ReadBigInt32();
        int numberOfLabels = labels.ReadBigInt32();

        for (int i = 0; i < numberOfImages; i++)
        {
            var bytes = images.ReadBytes(width * height);
            var arr = new byte[height, width];

            arr.ForEach((j,k) => arr[j, k] = bytes[j * height + k]);

            yield return new Image()
            {
                Data = arr,
                Label = labels.ReadByte()
            };
        }
    }
}

Image上课：

public class Image
{
    public byte Label { get; set; }
    public byte[,] Data { get; set; }
}

一些扩展方法：

public static class Extensions
{
    public static int ReadBigInt32(this BinaryReader br)
    {
        var bytes = br.ReadBytes(sizeof(Int32));
        if (BitConverter.IsLittleEndian) Array.Reverse(bytes);
        return BitConverter.ToInt32(bytes, 0);
    }

    public static void ForEach<T>(this T[,] source, Action<int, int> action)
    {
        for (int w = 0; w < source.GetLength(0); w++)
        {
            for (int h = 0; h < source.GetLength(1); h++)
            {
                action(w, h);
            }
        }
    }
}

用法：

foreach (var image in MnistReader.ReadTrainingData())
{
    //use image here     
}

或

foreach (var image in MnistReader.ReadTestData())
{
    //use image here     
}

Answer 2

为什么不使用nuget包：

MNIST.IO只是一个datareader（免责声明：我的包裹）
Accord.DataSets包含用于下载和解析机器学习数据集的类，如MNIST，News20，Iris。该软件包是Accord.NET Framework的一部分。

读MNIST数据库

2 个答案: