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 void Load_model(string name)
{
var loaded_model = Sequential.ModelFromJson(File.ReadAllText("model.json"));
loaded_model.LoadWeight(name);
loaded_model.LoadModel(name);
}
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");
}
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 functional model
var input = new Input(shape: new Keras.Shape(2));
var hidden1 = new Dense(32, activation: "relu").Set(input);
var hidden2 = new Dense(64, activation: "relu").Set(hidden1);
var output = new Dense(1, activation: "sigmoid").Set(hidden2);
var model = new Keras.Models.Model(new Input[] { input }, new BaseLayer[] { output });
//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: 10, verbose: 1);
//var weights = model.GetWeights();
//model.SetWeights(weights);
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");
}
private static void test()
{
Console.WriteLine("Начало тестирования нейросети");
var index = 1;
var rows = File.ReadAllLines(TEST_PATH).Skip(1).Take(TEST_ROWS_COUNT).ToList();
BaseModel loadedModel;
if (model == null)
{
//model = (Sequential)BaseModel.ModelFromJson(File.ReadAllText("model.json")); //не может преобразовать BaseModel в Sequential
loadedModel = Sequential.ModelFromJson(File.ReadAllText("model.json"));
loadedModel.LoadWeight("model.h5");
loadedModel.Compile(loss: "mean_squared_error", optimizer: new SGD(lr: learningRate), metrics: new string[] { "accuracy" });
}
else
{
loadedModel = model;
}
foreach (var row in rows)
{
Console.WriteLine("Итерация {0} из {1}", index++, TEST_ROWS_COUNT);
var values = row.Split(',');
var correctNumber = byte.Parse(values[0]);
float[,] inputArray = new float[1, INPUT_LAYER_SIZE];
byte[] inputValues = values.Skip(1).Select(x => byte.Parse(x)).ToArray();
for (int i = 0; i < inputValues.Length; i++)
{
inputArray[0, i] = inputValues[i];
}
var input = new NDarray(inputArray);
input = input.astype(np.float32);
input /= 255;
float[,] outputArray = new float[1, RESULT_LAYER_SIZE];
outputArray[0, correctNumber] = 1;
var output = new NDarray(outputArray);
var score = loadedModel.Evaluate(input, output, verbose: 0);
Console.WriteLine($"Test loss: {score[0]}");
Console.WriteLine($"Test accuracy: {score[1]}");
var outputActual = loadedModel.Predict(input, verbose: 0);
var x = outputActual.argmax();
calculateStatistics(correctNumber, int.Parse(x.str));
}
}
private void TestNeuralNetwork(string testCsvPath, int nb_classes, Dictionary <string, int> dictionaryLikeIMDB, int max_news_len)
{
NDarray x_test = null;
NDarray y_test = null;
var testCSV = Frame.ReadCsv(testCsvPath, false, separators: ";");
var testYFloat = testCSV.Rows.Select(kvp => { return(kvp.Value.GetAs <float>("Column1")); }).ValuesAll.ToList();
var testXString = testCSV.Rows.Select(kvp => { return(kvp.Value.GetAs <string>("Column2")); }).ValuesAll.ToList();
var testXStringArray = testXString.ToArray();
y_test = np.array(testYFloat.ToArray());
y_test = Util.ToCategorical(y_test, nb_classes);
string[][] tokens_test = testXStringArray.Tokenize();
int[][] bow_test = FrequencyDictionary.Transform(tokens_test, dictionaryLikeIMDB);
//double[][] bow_test = codebook.Transform(tokens_test);
var list_test = new List <NDarray>();
foreach (var item in bow_test)
{
//var newItem = item.Take(100).ToArray();
//var ndarray = np.array(newItem);
var ndarray = np.array(item);
list_test.Add(ndarray);
}
var sequences_test = np.array(list_test);
x_test = SequenceUtil.PadSequences(sequences_test, maxlen: max_news_len);
//Load model and weight
var loaded_model = Sequential.ModelFromJson(File.ReadAllText("model.json"));
loaded_model.LoadWeight("best_model_gru.h5");
loaded_model.Compile(optimizer: "adam", loss: "categorical_crossentropy", metrics: new string[] { "accuracy" });
loaded_model.Summary();
var scores = loaded_model.Evaluate(x_test, y_test, verbose: 0);
Console.WriteLine("Test loss:" + scores[0] * 100);
Console.WriteLine("Test accuracy:" + scores[1] * 100);
}
public bool LoadModel()
{
if (File.Exists(ModelSettingFilename))
{
generatorModel = Sequential.ModelFromJson(File.ReadAllText(ModelSettingFilename));
if (File.Exists(ModelWeightFilename))
{
generatorModel.LoadWeight(ModelWeightFilename);
}
return(true);
}
else
{
return(false);
}
}
public static void Init()
{
try
{
using (Py.GIL())
{
if (model == null)
{
string path = Directory.GetCurrentDirectory();
model = Sequential.ModelFromJson(File.ReadAllText(path + MODEL_PATH));
model.LoadWeight(path + WEIGHTS_PATH);
}
}
}
catch (Exception ex)
{
Console.WriteLine(ex.Message);
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);
}
public void ReadModel(int player_version)
{
model = Sequential.ModelFromJson(File.ReadAllText("player_NN.json"));
model.LoadWeight("version" + player_version.ToString().PadLeft(4, '0') + ".h5");
}
