TensorFlow.NET机器学习入门【6】采用神经网络处理Fashion-MNIST

"如果一个算法在MNIST上不work，那么它就根本没法用；而如果它在MNIST上work，它在其他数据上也可能不work"。

                                                                                                                                            —— 马克吐温

上一篇文章我们实现了一个MNIST手写数字识别的程序，通过一个简单的两层神经网络，就轻松获得了98%的识别成功率。这个成功率不代表你的网络是有效的，因为MNIST实在是太简单了，我们需要更复杂的数据集来检验网络的有效性！这就有了Fashion-MNIST数据集，它采用10种服装的图片来取代数字0~9，除此之外，其图片大小、数量均和MNIST一致。

上篇文章的代码几乎不用改动，只要改个获取原始图片文件的文件夹名称即可。

程序运行结果识别成功率大约为82%左右。

我们可以对网络进行调整，看能否提高识别率，具体可用的方法：

1、增加网络层

2、增加神经元个数

3、改用其它激活函数

试验结果表明，不管如何调整，识别率始终上不去多少。可见该网络方案已经碰到了瓶颈，如果要大幅度提高识别率必须要采取新的方案了。

下篇文章我们将介绍卷积神经网络（CNN）的应用，通过CNN来处理图像数据将是一个更好、更科学的解决方案。

由于本文代码和上一篇文章的代码高度一致，这里就不再详细说明了。全部代码如下：

 /// <summary>
    /// 采用神经网络处理Fashion-MNIST数据集
    /// </summary>
    public class NN_MultipleClassification_Fashion_MNIST
    {
        private readonly string TrainImagePath = @"D:\Study\Blogs\TF_Net\Asset\fashion_mnist_png\train";
        private readonly string TestImagePath = @"D:\Study\Blogs\TF_Net\Asset\fashion_mnist_png\test";
        private readonly string train_date_path = @"D:\Study\Blogs\TF_Net\Asset\fashion_mnist_png\train_data.bin";
        private readonly string train_label_path = @"D:\Study\Blogs\TF_Net\Asset\fashion_mnist_png\train_label.bin";

        private readonly int img_rows = 28;
        private readonly int img_cols = 28;
        private readonly int num_classes = 10;  // total classes

        public void Run()
        {
            var model = BuildModel();
            model.summary();

            model.compile(optimizer: keras.optimizers.Adam(0.001f),
                loss: keras.losses.SparseCategoricalCrossentropy(),
                metrics: new[] { "accuracy" });

            (NDArray train_x, NDArray train_y) = LoadTrainingData();
            model.fit(train_x, train_y, batch_size: 1024, epochs: 20);

            test(model);
        }

        /// <summary>
        /// 构建网络模型
        /// </summary>
        private Model BuildModel()
        {
            // 网络参数          
            int n_hidden_1 = 128;    // 1st layer number of neurons.     
            int n_hidden_2 = 128;    // 2nd layer number of neurons.                                
            float scale = 1.0f / 255;

            var model = keras.Sequential(new List<ILayer>
            {
                keras.layers.InputLayer((img_rows,img_cols)),
                keras.layers.Flatten(),
                keras.layers.Rescaling(scale),
                keras.layers.Dense(n_hidden_1, activation:keras.activations.Relu),
                keras.layers.Dense(n_hidden_2, activation:keras.activations.Relu),
                keras.layers.Dense(num_classes, activation:keras.activations.Softmax)
            });

            return model;
        }

        /// <summary>
        /// 加载训练数据
        /// </summary>
        /// <param name="total_size"></param>
        private (NDArray, NDArray) LoadTrainingData()
        {
            try
            {
                Console.WriteLine("Load data");
                IFormatter serializer = new BinaryFormatter();
                FileStream loadFile = new FileStream(train_date_path, FileMode.Open, FileAccess.Read);
                float[,,] arrx = serializer.Deserialize(loadFile) as float[,,];

                loadFile = new FileStream(train_label_path, FileMode.Open, FileAccess.Read);
                int[] arry = serializer.Deserialize(loadFile) as int[];
                Console.WriteLine("Load data success");
                return (np.array(arrx), np.array(arry));
            }
            catch (Exception ex)
            {
                Console.WriteLine($"Load data Exception:{ex.Message}");
                return LoadRawData();
            }
        }

        private (NDArray, NDArray) LoadRawData()
        {
            Console.WriteLine("LoadRawData");

            int total_size = 60000;
            float[,,] arrx = new float[total_size, img_rows, img_cols];
            int[] arry = new int[total_size];

            int count = 0;

            DirectoryInfo RootDir = new DirectoryInfo(TrainImagePath);
            foreach (var Dir in RootDir.GetDirectories())
            {
                foreach (var file in Dir.GetFiles("*.png"))
                {
                    Bitmap bmp = (Bitmap)Image.FromFile(file.FullName);
                    if (bmp.Width != img_cols || bmp.Height != img_rows)
                    {
                        continue;
                    }

                    for (int row = 0; row < img_rows; row++)
                        for (int col = 0; col < img_cols; col++)
                        {
                            var pixel = bmp.GetPixel(col, row);
                            int val = (pixel.R + pixel.G + pixel.B) / 3;

                            arrx[count, row, col] = val;
                            arry[count] = int.Parse(Dir.Name);
                        }

                    count++;
                }

                Console.WriteLine($"Load image data count={count}");
            }

            Console.WriteLine("LoadRawData finished");
            //Save Data
            Console.WriteLine("Save data");
            IFormatter serializer = new BinaryFormatter();

            //开始序列化
            FileStream saveFile = new FileStream(train_date_path, FileMode.Create, FileAccess.Write);
            serializer.Serialize(saveFile, arrx);
            saveFile.Close();

            saveFile = new FileStream(train_label_path, FileMode.Create, FileAccess.Write);
            serializer.Serialize(saveFile, arry);
            saveFile.Close();
            Console.WriteLine("Save data finished");

            return (np.array(arrx), np.array(arry));
        }

        /// <summary>
        /// 消费模型
        /// </summary>
        private void test(Model model)
        {
            Random rand = new Random(1);

            DirectoryInfo TestDir = new DirectoryInfo(TestImagePath);
            foreach (var ChildDir in TestDir.GetDirectories())
            {
                Console.WriteLine($"Folder:【{ChildDir.Name}】");
                var Files = ChildDir.GetFiles("*.png");
                for (int i = 0; i < 10; i++)
                {
                    int index = rand.Next(1000);
                    var image = Files[index];

                    var x = LoadImage(image.FullName);
                    var pred_y = model.Apply(x);
                    var result = argmax(pred_y[0].numpy());

                    Console.WriteLine($"FileName:{image.Name}\tPred:{result}");
                }
            }
        }

        private NDArray LoadImage(string filename)
        {
            float[,,] arrx = new float[1, img_rows, img_cols];
            Bitmap bmp = (Bitmap)Image.FromFile(filename);

            for (int row = 0; row < img_rows; row++)
                for (int col = 0; col < img_cols; col++)
                {
                    var pixel = bmp.GetPixel(col, row);
                    int val = (pixel.R + pixel.G + pixel.B) / 3;
                    arrx[0, row, col] = val;
                }

            return np.array(arrx);
        }

        private int argmax(NDArray array)
        {
            var arr = array.reshape(-1);

            float max = 0;
            for (int i = 0; i < 10; i++)
            {
                if (arr[i] > max)
                {
                    max = arr[i];
                }
            }

            for (int i = 0; i < 10; i++)
            {
                if (arr[i] == max)
                {
                    return i;
                }
            }

            return 0;
        }
    }