在C#下使用TensorFlow.NET训练自己的数据集

 private void FillDictionaryLabel(string DirPath)
 {
     string[] str_dir = Directory.GetDirectories(DirPath, "*", SearchOption.TopDirectoryOnly);
     int str_dir_num = str_dir.Length;
     if (str_dir_num > 0)
     {
         Dict_Label = new Dictionary<Int64, string>();
         for (int i = 0; i < str_dir_num; i++)
         {
             string label = (str_dir[i].Replace(DirPath + "\\", "")).Split('\\').First();
             Dict_Label.Add(i, label);
             print(i.ToString() + " : " + label);
         }
         n_classes = Dict_Label.Count;
     }
 }

ArrayFileName_Train = Directory.GetFiles(Name + "\\train", "*.*", SearchOption.AllDirectories);
ArrayLabel_Train = GetLabelArray(ArrayFileName_Train);
​
ArrayFileName_Validation = Directory.GetFiles(Name + "\\validation", "*.*", SearchOption.AllDirectories);
ArrayLabel_Validation = GetLabelArray(ArrayFileName_Validation);
​
ArrayFileName_Test = Directory.GetFiles(Name + "\\test", "*.*", SearchOption.AllDirectories);
ArrayLabel_Test = GetLabelArray(ArrayFileName_Test);

private Int64[] GetLabelArray(string[] FilesArray)
{
    Int64[] ArrayLabel = new Int64[FilesArray.Length];
    for (int i = 0; i < ArrayLabel.Length; i++)
    {
        string[] labels = FilesArray[i].Split('\\');
        string label = labels[labels.Length - 2];
        ArrayLabel[i] = Dict_Label.Single(k => k.Value == label).Key;
    }
    return ArrayLabel;
}

public (string[], Int64[]) ShuffleArray(int count, string[] images, Int64[] labels)
{
    ArrayList mylist = new ArrayList();
    string[] new_images = new string[count];
    Int64[] new_labels = new Int64[count];
    Random r = new Random();
    for (int i = 0; i < count; i++)
    {
        mylist.Add(i);
    }
​
    for (int i = 0; i < count; i++)
    {
        int rand = r.Next(mylist.Count);
        new_images[i] = images[(int)(mylist[rand])];
        new_labels[i] = labels[(int)(mylist[rand])];
        mylist.RemoveAt(rand);
    }
    print("shuffle array list： " + count.ToString());
    return (new_images, new_labels);
}

private void LoadImagesToNDArray()
{
    //Load labels
    y_valid = np.eye(Dict_Label.Count)[new NDArray(ArrayLabel_Validation)];
    y_test = np.eye(Dict_Label.Count)[new NDArray(ArrayLabel_Test)];
    print("Load Labels To NDArray : OK!");

    //Load Images
    x_valid = np.zeros(ArrayFileName_Validation.Length, img_h, img_w, n_channels);
    x_test = np.zeros(ArrayFileName_Test.Length, img_h, img_w, n_channels);
    LoadImage(ArrayFileName_Validation, x_valid, "validation");
    LoadImage(ArrayFileName_Test, x_test, "test");
    print("Load Images To NDArray : OK!");
}
private void LoadImage(string[] a, NDArray b, string c)
{
    for (int i = 0; i < a.Length; i++)
    {
        b[i] = ReadTensorFromImageFile(a[i]);
        Console.Write(".");
    }
    Console.WriteLine();
    Console.WriteLine("Load Images To NDArray: " + c);
}
private NDArray ReadTensorFromImageFile(string file_name)
{
    using (var graph = tf.Graph().as_default())
    {
        var file_reader = tf.read_file(file_name, "file_reader");
        var decodeJpeg = tf.image.decode_jpeg(file_reader, channels: n_channels, name: "DecodeJpeg");
        var cast = tf.cast(decodeJpeg, tf.float32);
        var dims_expander = tf.expand_dims(cast, 0);
        var resize = tf.constant(new int[] { img_h, img_w });
        var bilinear = tf.image.resize_bilinear(dims_expander, resize);
        var sub = tf.subtract(bilinear, new float[] { img_mean });
        var normalized = tf.divide(sub, new float[] { img_std });

        using (var sess = tf.Session(graph))
        {
            return sess.run(normalized);
        }
    }
}

#region BuildGraph
public Graph BuildGraph()
{
    var graph = new Graph().as_default();

    tf_with(tf.name_scope("Input"), delegate
            {
                x = tf.placeholder(tf.float32, shape: (-1, img_h, img_w, n_channels), name: "X");
                y = tf.placeholder(tf.float32, shape: (-1, n_classes), name: "Y");
            });

    var conv1 = conv_layer(x, filter_size1, num_filters1, stride1, name: "conv1");
    var pool1 = max_pool(conv1, ksize: 2, stride: 2, name: "pool1");
    var conv2 = conv_layer(pool1, filter_size2, num_filters2, stride2, name: "conv2");
    var pool2 = max_pool(conv2, ksize: 2, stride: 2, name: "pool2");
    var layer_flat = flatten_layer(pool2);
    var fc1 = fc_layer(layer_flat, h1, "FC1", use_relu: true);
    var output_logits = fc_layer(fc1, n_classes, "OUT", use_relu: false);

    //Some important parameter saved with graph , easy to load later
    var img_h_t = tf.constant(img_h, name: "img_h");
    var img_w_t = tf.constant(img_w, name: "img_w");
    var img_mean_t = tf.constant(img_mean, name: "img_mean");
    var img_std_t = tf.constant(img_std, name: "img_std");
    var channels_t = tf.constant(n_channels, name: "img_channels");

    //learning rate decay
    gloabl_steps = tf.Variable(0, trainable: false);
    learning_rate = tf.Variable(learning_rate_base);

    //create train images graph
    tf_with(tf.variable_scope("LoadImage"), delegate
            {
                decodeJpeg = tf.placeholder(tf.@byte, name: "DecodeJpeg");
                var cast = tf.cast(decodeJpeg, tf.float32);
                var dims_expander = tf.expand_dims(cast, 0);
                var resize = tf.constant(new int[] { img_h, img_w });
                var bilinear = tf.image.resize_bilinear(dims_expander, resize);
                var sub = tf.subtract(bilinear, new float[] { img_mean });
                normalized = tf.divide(sub, new float[] { img_std }, name: "normalized");
            });

    tf_with(tf.variable_scope("Train"), delegate
            {
                tf_with(tf.variable_scope("Loss"), delegate
                        {
                            loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels: y, logits: output_logits), name: "loss");
                        });

                tf_with(tf.variable_scope("Optimizer"), delegate
                        {
                            optimizer = tf.train.AdamOptimizer(learning_rate: learning_rate, name: "Adam-op").minimize(loss, global_step: gloabl_steps);
                        });

                tf_with(tf.variable_scope("Accuracy"), delegate
                        {
                            var correct_prediction = tf.equal(tf.argmax(output_logits, 1), tf.argmax(y, 1), name: "correct_pred");
                            accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name: "accuracy");
                        });

                tf_with(tf.variable_scope("Prediction"), delegate
                        {
                            cls_prediction = tf.argmax(output_logits, axis: 1, name: "predictions");
                            prob = tf.nn.softmax(output_logits, axis: 1, name: "prob");
                        });
            });
    return graph;
}

/// <summary>
/// Create a 2D convolution layer
/// </summary>
/// <param name="x">input from previous layer</param>
/// <param name="filter_size">size of each filter</param>
/// <param name="num_filters">number of filters(or output feature maps)</param>
/// <param name="stride">filter stride</param>
/// <param name="name">layer name</param>
/// <returns>The output array</returns>
private Tensor conv_layer(Tensor x, int filter_size, int num_filters, int stride, string name)
{
    return tf_with(tf.variable_scope(name), delegate
                   {

                       var num_in_channel = x.shape[x.NDims - 1];
                       var shape = new[] { filter_size, filter_size, num_in_channel, num_filters };
                       var W = weight_variable("W", shape);
                       // var tf.summary.histogram("weight", W);
                       var b = bias_variable("b", new