public static void Run()
{
//Load train data
NDarray x = np.array(new float[, ] {
{ 0, 0 }, { 0, 1 }, { 1, 0 }, { 1, 1 }
});
NDarray y = np.array(new float[] { 0, 1, 1, 0 });
//Build sequential model
var model = new Sequential();
model.Add(new Dense(32, activation: "relu", input_shape: new Shape(2)));
model.Add(new Dense(64, activation: "relu"));
model.Add(new Dense(1, activation: "sigmoid"));
//Compile and train
model.Compile(optimizer: new Adam(), loss: "binary_crossentropy", metrics: new string[] { "accuracy" });
var history = model.Fit(x, y, batch_size: 2, epochs: 100, verbose: 1);
var logs = history.HistoryLogs;
//Save model and weights
string json = model.ToJson();
File.WriteAllText("model.json", json);
model.SaveWeight("model.h5");
//Load model and weight
var loaded_model = Sequential.ModelFromJson(File.ReadAllText("model.json"));
loaded_model.LoadWeight("model.h5");
}
static void Main(string[] args)
{
//Load train data
NDarray x = np.array(new float[, ] {
{ 0, 0 }, { 0, 1 }, { 1, 0 }, { 1, 1 }
});
NDarray y = np.array(new float[] { 0, 1, 1, 0 });
//Build sequential model
var model = new Sequential();
model.Add(new Dense(32, activation: "relu", input_shape: new Shape(2)));
model.Add(new Dense(64, activation: "relu"));
model.Add(new Dense(1, activation: "sigmoid"));
//Compile and train
model.Compile(optimizer: "sgd", loss: "binary_crossentropy", metrics: new string[] { "accuracy" });
model.Fit(x, y, batch_size: 2, epochs: 1000, verbose: 1);
//Save model and weights
string json = model.ToJson();
File.WriteAllText("model.json", json);
model.SaveWeight("model.h5");
//Load model and weight
var loaded_model = Sequential.ModelFromJson(File.ReadAllText("model.json"));
loaded_model.LoadWeight("model.h5");
var result = loaded_model.Predict(x);
Console.WriteLine("Предсказание для [{0}] = [{1}]", x.ToString(), result.ToString());
}
public static void SmallNetwork(List <Tuple <bool, float[]> > train, List <Tuple <bool, float[]> > test)
{
int vectorSize = train[0].Item2.Length;
//Load train data
var nTrain = ListToNDarrays(train, vectorSize);
var nTest = ListToNDarrays(test, vectorSize);
//Build sequential model
var model = new Sequential();
model.Add(new Dense(8, activation: "relu", input_shape: new Shape(vectorSize)));
model.Add(new Dropout(0.5));
model.Add(new Dense(16, activation: "relu"));
model.Add(new Dropout(0.5));
model.Add(new Dense(1, activation: "sigmoid"));
//Compile and train
//model.Compile(optimizer:"adam", loss:"sparse_categorical_crossentropy", metrics: new string[] { "accuracy" });
model.Compile(optimizer: "adam", loss: "binary_crossentropy", metrics: new string[] { "accuracy" });
model.Fit(
nTrain.Item2,
nTrain.Item1,
batch_size: 8,
epochs: 50,
verbose: 1,
validation_data: new NDarray[] { nTest.Item2, nTest.Item1 });
//Save model and weights
string json = model.ToJson();
File.WriteAllText("./models/sm_model.json", json);
model.SaveWeight("./models/sm_model.h5");
}
public static void Run()
{
//var ((x_train, y_train), (x_test, y_test)) = IMDB.LoadData(num_words: top_words);
var((x_train, y_train), (x_test, y_test)) = LoadDataRussianLanguageToxicComments(
trainCount: train_count, testCount: test_count, numWords: top_words, maxWords: max_words);
//Не нужно массивы дополнять до 500 элементов, т.к. они уже размером в 500 элементов
//x_train = SequenceUtil.PadSequences(x_train, maxlen: max_words);
//x_test = SequenceUtil.PadSequences(x_test, maxlen: max_words);
//Create model
Sequential model = new Sequential();
model.Add(new Embedding(top_words, 32, input_length: max_words));
model.Add(new Conv1D(filters: 32, kernel_size: 3, padding: "same", activation: "relu"));
model.Add(new MaxPooling1D(pool_size: 2));
model.Add(new Flatten());
model.Add(new Dense(250, activation: "relu"));
model.Add(new Dense(1, activation: "sigmoid"));
model.Compile(loss: "binary_crossentropy", optimizer: "adam", metrics: new string[] { "accuracy" });
model.Summary();
// Fit the model
model.Fit(x_train, y_train, validation_data: new NDarray[] { x_test, y_test },
epochs: 2 /*10*/, batch_size: 128, verbose: 2);
// Final evaluation of the model
var scores = model.Evaluate(x_test, y_test, verbose: 0);
Console.WriteLine("Accuracy: " + (scores[1] * 100));
model.Save("model.h5");
File.WriteAllText("model.json", model.ToJson()); //save model
//model.SaveTensorflowJSFormat("./"); //error - Cannot perform runtime binding on a null reference
}
public void Dense_CustomKRegularizerAndKInitParams()
{
NDarray x = np.array(new float[, ] {
{ 1, 0 }, { 1, 1 }, { 1, 0 }, { 1, 1 }
});
NDarray y = np.array(new float[] { 0, 1, 1, 0 });
var model = new Sequential();
model.Add(new Dense(1, activation: "sigmoid", input_shape: new Shape(x.shape[1]), kernel_regularizer: new L1L2(1000, 2000), kernel_initializer: new Constant(100)));
var modelAsJson = JsonConvert.DeserializeObject <dynamic>(model.ToJson());
Assert.AreEqual("Sequential", modelAsJson.class_name.Value);
int i = 0;
while (modelAsJson.config.layers[i].config.kernel_initializer == null && i < 3)
{
i++;
}
Assert.AreEqual(100, modelAsJson.config.layers[i].config.kernel_initializer.config.value.Value);
Assert.AreEqual("Constant", modelAsJson.config.layers[i].config.kernel_initializer.class_name.Value);
Assert.AreEqual("L1L2", modelAsJson.config.layers[i].config.kernel_regularizer.class_name.Value);
Assert.AreEqual(1000, modelAsJson.config.layers[i].config.kernel_regularizer.config.l1.Value);
Assert.AreEqual(2000, modelAsJson.config.layers[i].config.kernel_regularizer.config.l2.Value);
// Compile and train
model.Compile(optimizer: new Adam(lr: 0.001F), loss: "binary_crossentropy", metrics: new string[] { "accuracy" });
model.Fit(x, y, batch_size: x.shape[0], epochs: 100, verbose: 0);
Assert.AreEqual(2, model.GetWeights().Count);
}
public static void Run()
{
//Load IMDb dataset
var((x_train, y_train), (x_test, y_test)) = IMDB.LoadData();
var X = np.concatenate(new NDarray[] { x_train, x_test }, axis: 0);
var Y = np.concatenate(new NDarray[] { y_train, y_test }, axis: 0);
Console.WriteLine("Shape of X: " + X.shape);
Console.WriteLine("Shape of Y: " + Y.shape);
//We can get an idea of the total number of unique words in the dataset.
Console.WriteLine("Number of words: ");
var hstack = np.hstack(new NDarray[] { X });
//var unique = hstack.unique();
//Console.WriteLine(np.unique(np.hstack(new NDarray[] { X })).Item1);
// Load the dataset but only keep the top n words, zero the rest
int top_words = 1000;// 5000;
((x_train, y_train), (x_test, y_test)) = IMDB.LoadData(num_words: top_words);
int max_words = 500;
x_train = SequenceUtil.PadSequences(x_train, maxlen: max_words);
x_test = SequenceUtil.PadSequences(x_test, maxlen: max_words);
//Create model
Sequential model = new Sequential();
model.Add(new Embedding(top_words, 32, input_length: max_words));
model.Add(new Conv1D(filters: 32, kernel_size: 3, padding: "same", activation: "relu"));
model.Add(new MaxPooling1D(pool_size: 2));
model.Add(new Flatten());
model.Add(new Dense(250, activation: "relu"));
model.Add(new Dense(1, activation: "sigmoid"));
model.Compile(loss: "binary_crossentropy", optimizer: "adam", metrics: new string[] { "accuracy" });
model.Summary();
// Fit the model
model.Fit(x_train, y_train, validation_data: new NDarray[] { x_test, y_test },
epochs: 1 /*10*/, batch_size: 128, verbose: 2);
// Final evaluation of the model
var scores = model.Evaluate(x_test, y_test, verbose: 0);
Console.WriteLine("Accuracy: " + (scores[1] * 100));
model.Save("model.h5");
File.WriteAllText("model.json", model.ToJson()); //save model
//model.SaveTensorflowJSFormat("./"); //error - Cannot perform runtime binding on a null reference
}
public void SaveFiles()
{
if (model == null || string.IsNullOrEmpty(starttime) || string.IsNullOrEmpty(config.Guid))
{
throw new Exception("Model Save Error");
}
config.StartTime = starttime;
config.Model = model.ToJson();
string filename = Utils.GetFileWithoutExtension(model_dir, starttime);
FileIO.SerializeXml(config, filename + config_ext);
model.SaveWeight(filename + model_ext);
}
private static void train()
{
try
{
Console.WriteLine("Начало тренировки нейросети");
var rows = File.ReadAllLines(FILE_PATH).Skip(1).Take(TRAIN_ROWS_COUNT).ToList();
Console.WriteLine("Заполняем датасет данными");
float[,] inputArray = new float[rows.Count, INPUT_LAYER_SIZE];
float[,] outputArray = new float[rows.Count, RESULT_LAYER_SIZE];
for (int i = 0; i < rows.Count; i++)
{
Console.WriteLine("Итерация {0} из {1}", i + 1, TRAIN_ROWS_COUNT);
var values = rows[i].Split(',');
var correctNumber = byte.Parse(values[0]);
byte[] inputValues = values.Skip(1).Select(x => byte.Parse(x)).ToArray();
for (int j = 0; j < inputValues.Length; j++)
{
inputArray[i, j] = inputValues[j];
}
outputArray[i, correctNumber] = 1;
}
var input = new NDarray(inputArray);
input = input.astype(np.float32);
input /= 255;
var output = new NDarray(outputArray);
Console.WriteLine("Запускаем обучение");
model.Fit(input, output, batch_size: batchSize, epochs: epochs, verbose: 2);
Console.WriteLine("Сохраняем модель");
File.WriteAllText("model.json", model.ToJson());
model.SaveWeight("model.h5");
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
throw;
}
}
public static void Run()
{
//Load train data
NDarray dataset = np.loadtxt(fname: "C:/Project/LSTMCoreApp/pima-indians-diabetes.data.csv", delimiter: ",");
var X = dataset[":,0: 8"];
var Y = dataset[":, 8"];
//Build sequential model
var model = new Sequential();
model.Add(new Dense(12, input_dim: 8, kernel_initializer: "uniform", activation: "relu"));
model.Add(new Dense(8, kernel_initializer: "uniform", activation: "relu"));
model.Add(new Dense(1, activation: "sigmoid"));
//Compile and train
model.Compile(optimizer: "adam", loss: "binary_crossentropy", metrics: new string[] { "accuracy" });
model.Fit(X, Y, batch_size: 10, epochs: 150, verbose: 1);
//Evaluate model
var scores = model.Evaluate(X, Y, verbose: 1);
Console.WriteLine("Accuracy: {0}", scores[1] * 100);
//Save model and weights
string json = model.ToJson();
File.WriteAllText("model.json", json);
model.SaveWeight("model.h5");
Console.WriteLine("Saved model to disk");
//Load model and weight
var loaded_model = Sequential.ModelFromJson(File.ReadAllText("model.json"));
loaded_model.LoadWeight("model.h5");
Console.WriteLine("Loaded model from disk");
loaded_model.Compile(optimizer: "rmsprop", loss: "binary_crossentropy", metrics: new string[] { "accuracy" });
scores = model.Evaluate(X, Y, verbose: 1);
Console.WriteLine("Accuracy: {0}", scores[1] * 100);
}
private (History, Sequential, Dictionary <string, int>) LearnNeuralNetwork(string trainCsvPath, int num_words, int max_news_len, int nb_classes)
{
NDarray x_train = null;
NDarray y_train = null;
var trainCSV = Frame.ReadCsv(trainCsvPath, false, separators: ";");
var trainYFloat = trainCSV.Rows.Select(kvp => { return(kvp.Value.GetAs <float>("Column1")); }).ValuesAll.ToList();
var trainXString = trainCSV.Rows.Select(kvp => { return(kvp.Value.GetAs <string>("Column2")); }).ValuesAll.ToList();
var trainXStringArray = trainXString.ToArray();
//x_train = np.array(new float[,] { { 0, 0 }, { 0, 1 }, { 1, 0 }, { 1, 1 } });
y_train = np.array(trainYFloat.ToArray());
y_train = Util.ToCategorical(y_train, nb_classes);
string[][] tokens = trainXStringArray.Tokenize();
var dictionaryLikeIMDB = FrequencyDictionary.Learn(tokens);
var bow = FrequencyDictionary.Transform(tokens, dictionaryLikeIMDB);
// Create a new TF-IDF with options:
/*var codebook = new Accord.MachineLearning.TFIDF()
* {
* Tf = TermFrequency.Log,
* Idf = InverseDocumentFrequency.Default
* };
*
* codebook.Learn(tokens);
*
* double[][] bow = codebook.Transform(tokens);*/
var list = new List <NDarray>();
foreach (var item in bow)
{
//var newItem = item.Take(max_news_len).ToArray();
//var ndarray = np.array(newItem);
var ndarray = np.array(item);
list.Add(ndarray);
}
var sequences = np.array(list);
//x_train = SequenceUtil.PadSequences(sequences, maxlen: max_news_len, dtype: "double");
x_train = SequenceUtil.PadSequences(sequences, maxlen: max_news_len);
var model = new Sequential();
model.Add(new Embedding(num_words, 32, null, null, null, null, false, max_news_len));
model.Add(new GRU(138));//16
model.Add(new Dense(12, activation: "softmax"));
model.Compile(optimizer: "adam", loss: "categorical_crossentropy", metrics: new string[] { "accuracy" });
model.Summary();
var model_gru_save_path = "best_model_gru.h5";
var checkpoint_callback_gru = new ModelCheckpoint(
model_gru_save_path,
"val_accuracy",
1,
true
);
var callbacks = new List <Callback>()
{
checkpoint_callback_gru
};
float validation_split = (float)0.1;
var history_gru = model.Fit(x_train,
y_train,
batch_size: 128,
epochs: 10,
validation_split: validation_split,
callbacks: callbacks.ToArray());
//Save model and weights
string json = model.ToJson();
File.WriteAllText("model.json", json);
return(history_gru, model, dictionaryLikeIMDB);
}
//https://github.com/SciSharp/Keras.NET#mnist-cnn-example
//Python example taken from: https://keras.io/examples/mnist_cnn/
static void Main(string[] args)
{
int batch_size = 128;
int num_classes = 10;
int epochs = 12;
// input image dimensions
int img_rows = 28, img_cols = 28;
Shape input_shape = null;
// the data, split between train and test sets
var((x_train, y_train), (x_test, y_test)) = MNIST.LoadData();
if (Backend.ImageDataFormat() == "channels_first")
{
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols);
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols);
input_shape = (1, img_rows, img_cols);
}
else
{
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1);
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1);
input_shape = (img_rows, img_cols, 1);
}
x_train = x_train.astype(np.float32);
x_test = x_test.astype(np.float32);
x_train /= 255;
x_test /= 255;
Console.WriteLine($"x_train shape: {x_train.shape}");
Console.WriteLine($"{x_train.shape[0]} train samples");
Console.WriteLine($"{x_test.shape[0]} test samples");
// convert class vectors to binary class matrices
y_train = Util.ToCategorical(y_train, num_classes);
y_test = Util.ToCategorical(y_test, num_classes);
// Build CNN model
var model = new Sequential();
model.Add(new Conv2D(32, kernel_size: (3, 3).ToTuple(),
activation: "relu",
input_shape: input_shape));
model.Add(new Conv2D(64, (3, 3).ToTuple(), activation: "relu"));
model.Add(new MaxPooling2D(pool_size: (2, 2).ToTuple()));
model.Add(new Dropout(0.25));
model.Add(new Flatten());
model.Add(new Dense(128, activation: "relu"));
model.Add(new Dropout(0.5));
model.Add(new Dense(num_classes, activation: "softmax"));
model.Compile(loss: "categorical_crossentropy",
optimizer: new Adadelta(), metrics: new string[] { "accuracy" });
File.WriteAllText("model.json", model.ToJson()); //save model
model.Fit(x_train, y_train,
batch_size: batch_size,
epochs: epochs,
verbose: 1,
validation_data: new NDarray[] { x_test, y_test });
var score = model.Evaluate(x_test, y_test, verbose: 0);
Console.WriteLine($"Test loss: {score[0]}");
Console.WriteLine($"Test accuracy: {score[1]}");
}
