public class Utils{public static NDarray Normalize(string path){var colorMode = Settings.Channels == 3 ? "rgb" : "grayscale";var img = ImageUtil.LoadImg(path, color_mode: colorMode, target_size: (Settings.ImgWidth, Settings.ImgHeight));return ImageUtil.ImageToArray(img) / 255;}}

在此方法中，我们加载具有给定颜色模式（RGB或灰度）的图像，并将其大小调整为给定的宽度和高度。然后，我们返回包含图像的矩阵，其中每个元素都除以255。将每个元素除以255会将它们归一化，因为图像中任何像素的值都在0到255之间，因此通过将它们除以255，我们可以确保新范围是0到1（含）。

public class DataSet{private string _pathToFolder;private string[] _extList;private List<int> _labels;private List<NDarray> _objs;private double _validationSplit;public int NumberClasses { get; set; }public NDarray TrainX { get; set; }public NDarray ValidationX { get; set; }public NDarray TrainY { get; set; }public NDarray ValidationY { get; set; }public DataSet(string pathToFolder, string[] extList, int numberClasses, double validationSplit){_pathToFolder = pathToFolder;_extList = extList;NumberClasses = numberClasses;_labels = new List<int>();_objs = new List<NDarray>();_validationSplit = validationSplit;}public void LoadDataSet(){// Process the list of files found in the directory.string[] fileEntries = Directory.GetFiles(_pathToFolder);foreach (string fileName in fileEntries)if (IsRequiredExtFile(fileName))ProcessFile(fileName);MapToClassRange();GetTrainValidationData();}private bool IsRequiredExtFile(string fileName){foreach (var ext in _extList){if (fileName.Contains("." + ext)){return true;}}return false;}private void MapToClassRange(){HashSet<int> uniqueLabels = _labels.ToHashSet();var uniqueLabelList = uniqueLabels.ToList();uniqueLabelList.Sort();_labels = _labels.Select(x => uniqueLabelList.IndexOf(x)).ToList();}private NDarray OneHotEncoding(List<int> labels){var npLabels = np.array(labels.ToArray()).reshape(-1);return Util.ToCategorical(npLabels, num_classes: NumberClasses);}private void ProcessFile(string path){_objs.Add(Utils.Normalize(path));ProcessLabel(Path.GetFileName(path));}private void ProcessLabel(string filename){_labels.Add(int.Parse(ExtractClassFromFileName(filename)));}private string ExtractClassFromFileName(string filename){return filename.Split('_')[0].Replace("class", "");}private void GetTrainValidationData(){var listIndices = Enumerable.Range(0, _labels.Count).ToList();var toValidate = _objs.Count * _validationSplit;var random = new Random();var xValResult = new List<NDarray>();var yValResult = new List<int>();var xTrainResult = new List<NDarray>();var yTrainResult = new List<int>();// Split validation datafor (var i = 0; i < toValidate; i++){var randomIndex = random.Next(0, listIndices.Count);var indexVal = listIndices[randomIndex];xValResult.Add(_objs[indexVal]);yValResult.Add(_labels[indexVal]);listIndices.RemoveAt(randomIndex);}// Split rest (training data)listIndices.ForEach(indexVal => { xTrainResult.Add(_objs[indexVal]);yTrainResult.Add(_labels[indexVal]);});TrainY = OneHotEncoding(yTrainResult);ValidationY = OneHotEncoding(yValResult);TrainX = np.array(xTrainResult);ValidationX = np.array(xValResult);}}

这是每种方法的说明：

var numberClasses = 60;
var fileExt = new string[] { ".png" };
var dataSetFilePath = @"C:/Users/arnal/Downloads/coin_dataset";
var dataSet = new PreProcessing.DataSet(dataSetFilePath, fileExt, numberClasses, 0.2);
dataSet.LoadDataSet();

现在，我们的数据可以输入到机器学习模型中。在接下来的文章会介绍监督机器学习的基础知识，以及训练和验证阶段包括哪些内容。它是为没有AI经验的读者准备的。