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 BuildModel()
{
model = new Sequential(new Shape(10));
model.Add(new Dense(dim: 20, activation: new Model.Layers.Activations.ReLU()));
model.Add(new Dense(dim: 20, activation: new Model.Layers.Activations.ReLU()));
model.Add(new Dense(dim: 1));
}
static void Main(string[] args)
{
SaveRateToFileTrainData("USD");
SaveRateToFileTestData("USD");
Global.UseEngine(SiaNet.Backend.ArrayFire.SiaNetBackend.Instance, DeviceType.CUDA, true);
var train = PreparingExchangeRateData.LoadTrain();
var test = PreparingExchangeRateData.LoadTest();
var model = new Sequential();
model.EpochEnd += Model_EpochEnd;
model.Add(new Dense(60, ActType.Sigmoid));
model.Add(new Dense(60, ActType.Sigmoid));
model.Add(new Dense(1, ActType.Linear));
//Compile with Optimizer, Loss and Metric
model.Compile(OptimizerType.SGD, LossType.MeanSquaredError, MetricType.MSE);
// Train for 1000 epoch with batch size of 2
model.Train(train, epochs: 1000, batchSize: 32);
//Create prediction data to evaluate
DataFrame2D predX = new DataFrame2D(2);
predX.Load(0, 0, 0, 1, 1, 0, 1, 1); //Result should be 0, 1, 1, 0
var rawPred = model.Predict(test);
Console.ReadLine();
}
public static void BuildModel()
{
model = new Sequential(new Shape(lookback));
model.Add(new LSTM(dim: 4, returnSequence: true));
model.Add(new LSTM(dim: 4));
model.Add(new Dense(dim: 1));
}
public static void FitMnistSimple()
{
var model = new Sequential();
model.Add(new Dense(512, activation: "relu", inputShape: new int[] { 784 }));
model.Add(new Dropout(0.2));
model.Add(new Dense(512, activation: "relu"));
model.Add(new Dropout(0.2));
model.Add(new Dense(10, activation: "softmax"));
var optimizer = new SGD(lr: 0.01);
model.Compile("categorical_crossentropy", optimizer, new string[] { "accuracy" });
var xtrain = TensorUtils.Deserialize(new FileStream(GetDataPath("datasets/nda_mnist/mnist_xtrain.nda"), FileMode.Open));
var ytrain = TensorUtils.Deserialize(new FileStream(GetDataPath("datasets/nda_mnist/mnist_ytrain.nda"), FileMode.Open));
xtrain = xtrain.Cast(DType.Float32);
xtrain = Ops.Div(null, xtrain, 255f);
ytrain = ytrain.Cast(DType.Float32);
model.Fit(xtrain, ytrain, batchSize: 128, epochs: 20);
var stream = new FileStream("c:/ttt/mnist-simple.model", FileMode.OpenOrCreate, FileAccess.Write);
stream.SetLength(0);
model.Save(stream);
}
private static void BuildMLP(int[] imageDim, int numClasses)
{
model.Add(new Dense(3072, imageDim[0], OptActivations.ReLU));
model.Add(new Dense(2000, OptActivations.ReLU));
model.Add(new Dropout(0.2));
model.Add(new Dense(numClasses));
}
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());
}
// Performs convolutional neural network model training:
// Incorporated parameters include relu and softmax
// Adds fixed preprocessing layers and pooling: could use further development with exposed parameters
private static Sequential ProcessCnnModel(Shape input_shape, NDarray x_train, NDarray y_train, NDarray x_test, NDarray y_test,
int num_classes, string logname, Config config)
{
// Build CNN model
Sequential model = new Sequential();
model.Add(new Conv2D(16, kernel_size: (3, 3).ToTuple(), activation: "relu", input_shape: input_shape));
model.Add(new Conv2D(32, (3, 3).ToTuple(), activation: "relu"));
model.Add(new MaxPooling2D(pool_size: (2, 2).ToTuple()));
model.Add(new Flatten());
Callback[] callbacks = GetCallbacks(config.isEarlyStop, logname);
AddNodes(model, config);
model.Add(new Dense(num_classes, activation: "softmax"));
// Compile with loss, metrics and optimizer
model.Compile(loss: "categorical_crossentropy",
optimizer: new Adam(lr: (float)config.LearnRate, decay: (float)config.LearnDecay), metrics: new[] { "accuracy" });
// Train the model
model.Fit(x_train, y_train, batch_size: config.Batch, epochs: config.Epochs, verbose: 1,
validation_data: new[] { x_test, y_test }, callbacks: callbacks);
return(model);
}
public void sequential_guide_2()
{
var model = new Sequential();
model.Add(new Dense(32, input_dim: 784));
model.Add(new Activation("relu"));
}
public RNN(uint n_inputs, uint n_mem, uint[] shape, IActivation act)
{
n_memory = n_mem;
n_outputs = shape[shape.Length - 1];
mem_stack = new float[n_memory, n_outputs + n_inputs];
flat_mem_stack = Utils.FZerosArray(mem_stack);
activation = act;
//IActivation Tanh = new Tanh();
h_layers = new Sequential();
h_layers.Add(new Layer((uint)(n_inputs + flat_mem_stack.Length), shape[0], Activations.Tanh));
//h_layers[0] = new Layer((uint) (n_inputs + flat_mem_stack.Length), hidden_dim);
for (int i = 1; i < shape.Length; i++)
{
//h_layers[i] = new Layer(hidden_dim, hidden_dim);
h_layers.Add(new Layer(shape[i - 1], shape[i], Activations.Tanh));
}
// Setting the output layer activation to the given activation
Layer lastLayer = (Layer)h_layers.NeuralNetworks[h_layers.NeuralNetworks.Count - 1];
lastLayer.SetActivation(activation);
h_layers.NeuralNetworks[h_layers.CountLayer() - 1] = lastLayer;
this.n_outputs = shape[shape.Length - 1];
}
public static void BuildModel()
{
model = new Sequential(new Shape(trainData.Features.DataShape[0]));
model.Add(new Dense(dim: 20, activation: new SiaNet.Layers.Activations.ReLU()));
model.Add(new Dense(dim: 20, activation: new SiaNet.Layers.Activations.ReLU()));
model.Add(new Dense(dim: trainData.Labels.DataShape[0]));
}
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 void mlp_should_learn_all(
[ValueSource("Backends")] string backend,
[ValueSource("Targets")] float[] y,
[Values(false, true)] bool useBias)
{
KerasSharp.Backends.Current.Switch(backend);
var model = new Sequential();
model.Add(new Dense(5, input_dim: 2,
kernel_initializer: new GlorotUniform(),
bias_initializer: new GlorotUniform(),
use_bias: useBias,
activation: new Sigmoid()));
model.Add(new Dense(1,
kernel_initializer: new GlorotUniform(),
bias_initializer: new GlorotUniform(),
use_bias: useBias,
activation: new Sigmoid()));
model.Compile(loss: new MeanSquareError(), optimizer: new SGD(lr: 1), metrics: new[] { new Accuracy() });
model.fit(x, y, epochs: 1000, batch_size: y.Length);
double[] pred = Matrix.Round(model.predict(x, batch_size: y.Length)[0].To <double[, ]>()).GetColumn(0);
Assert.AreEqual(y, pred);
}
public void sequential_guide_stateful_stacked_lstm()
{
int data_dim = 16;
int timesteps = 8;
int num_classes = 10;
int batch_size = 32;
// Expected input batch shape: (batch_size, timesteps, data_dim)
// Note that we have to provide the full batch_input_shape since the network is stateful.
// the sample of index i in batch k is the follow-up for the sample i in batch k-1.
var model = new Sequential();
model.Add(new LSTM(32, return_sequences: true, stateful: true,
batch_input_shape: new int?[] { batch_size, timesteps, data_dim }));
model.Add(new LSTM(32, return_sequences: true, stateful: true));
model.Add(new LSTM(32, stateful: true));
model.Add(new Dense(10, activation: "softmax"));
model.Compile(loss: "categorical_crossentropy",
optimizer: "rmsprop",
metrics: new[] { "accuracy" });
// Generate dummy training data
double[][][] x_train = null; // Accord.Math.Jagged.Random(1000, timesteps, data_dim); // TODO: Add better method in Accord
int[] y_train = Accord.Math.Vector.Random(1000, min: 0, max: num_classes);
// Generate dummy validation data
double[,,] x_val = null; // Accord.Math.Jagged.Random(1000, timesteps, data_dim); // TODO: Add better method in Accord
int[] y_val = Accord.Math.Vector.Random(1000, min: 0, max: num_classes);
model.fit(x_train, y_train,
batch_size: batch_size, epochs: 5, shuffle: Shuffle.False,
validation_data: new Array[] { x_val, y_val });
}
public static void Main(string[] args)
{
// CreateHostBuilder(args).Build().Run();
//CreateWebHostBuilder(args).Build().Run();
Sequential Seq = new Sequential();
Seq.Add(new Dense(32, activation: "relu", input_shape: new Shape(250, 250, 3)));
Seq.Add(new Dense(64, activation: "relu"));
Seq.Add(new Dense(1, activation: "sigmoid"));
Console.WriteLine(Backend.GetBackend());
var function = Backend.Function(Seq.Layers(0), Seq.Layers(1));
Console.WriteLine(function);
NDarray x = np.array(new float[, ] {
{ 0, 0 }, { 0, 1 }, { 1, 0 }, { 1, 1 }
});
NDarray y = np.array(new float[] { 0, 1, 1, 0 });
var val = (42, 2);
// var data = tf.ones(new TensorShape(new int[] {1, 259, 259, 3}));
var data = Backend.ones();
KerasIterator iter = new KerasIterator(data);
var z = new PyIter(iter.PyObject);
z.MoveNext();
var output = z.Current;
var res = function(data);
Console.WriteLine("function Results:");
Console.WriteLine(res);
}
public void sequential_guide_stacked_lstm()
{
int data_dim = 16;
int timesteps = 8;
int num_classes = 10;
// expected input data shape: (batch_size, timesteps, data_dim)
var model = new Sequential();
model.Add(new LSTM(32, return_sequences: true,
input_shape: new[] { timesteps, data_dim })); // returns a sequence of vectors of dimension 32
model.Add(new LSTM(32, return_sequences: true)); // returns a sequence of vectors of dimension 32
model.Add(new LSTM(32)); // return a single vector of dimension 32
model.Add(new Dense(10, activation: "softmax"));
model.Compile(loss: "categorical_crossentropy",
optimizer: "rmsprop",
metrics: new[] { "accuracy" });
// Generate dummy training data
double[][][] x_train = null; // Accord.Math.Jagged.Random(1000, timesteps, data_dim); // TODO: Add better method in Accord
int[] y_train = Accord.Math.Vector.Random(1000, min: 0, max: num_classes);
// Generate dummy validation data
double[,,] x_val = null; // Accord.Math.Jagged.Random(1000, timesteps, data_dim); // TODO: Add better method in Accord
int[] y_val = Accord.Math.Vector.Random(1000, min: 0, max: num_classes);
model.fit(x_train, y_train,
batch_size: 64, epochs: 5,
validation_data: new Array[] { x_val, y_val });
}
public void sequential_guide_mlp_binary()
{
// Generate dummy data
double[,] x_train = Accord.Math.Matrix.Random(1000, 20);
int[] y_train = Accord.Math.Vector.Random(1000, min: 0, max: 10);
double[,] x_test = Accord.Math.Matrix.Random(1000, 20);
int[] y_test = Accord.Math.Vector.Random(1000, min: 0, max: 10);
var model = new Sequential();
model.Add(new Dense(64, input_dim: 20, activation: "relu"));
model.Add(new Dropout(0.5));
model.Add(new Dense(64, activation: "relu"));
model.Add(new Dropout(0.5));
model.Add(new Dense(1, activation: "sigmoid"));
model.Compile(loss: "binary_crossentropy",
optimizer: "rmsprop",
metrics: new[] { "accuracy" });
model.fit(x_train, y_train,
epochs: 20,
batch_size: 128);
var score = model.evaluate(x_test, y_test, batch_size: 128);
}
public void sequential_guide_mlp_multiclass()
{
// Generate dummy data
double[,] x_train = Accord.Math.Matrix.Random(1000, 20);
int[] y_train = Accord.Math.Vector.Random(1000, min: 0, max: 10);
double[,] x_test = Accord.Math.Matrix.Random(1000, 20);
int[] y_test = Accord.Math.Vector.Random(1000, min: 0, max: 10);
var model = new Sequential();
// Dense(64) is a fully-connected layer with 64 hidden units.
// in the first layer, you must specify the expected input data shape:
// here, 20-dimensional vectors.
model.Add(new Dense(64, activation: "relu", input_dim: 20));
model.Add(new Dropout(0.5));
model.Add(new Dense(64, activation: "relu"));
model.Add(new Dropout(0.5));
model.Add(new Dense(10, activation: "softmax"));
var sgd = new SGD(lr: 0.01, decay: 1e-6, momentum: 0.9, nesterov: true);
model.Compile(loss: "categorical_crossentropy",
optimizer: sgd,
metrics: new[] { "accuracy" });
model.fit(x_train, y_train,
epochs: 20,
batch_size: 128);
var score = model.evaluate(x_test, y_test, batch_size: 128);
}
private static void BuildMLP(int[] imageDim, int numClasses)
{
model.Add(new Dense(dim: 3072, shape: imageDim[0], act: OptActivations.ReLU));
model.Add(new Dense(dim: 2000, act: OptActivations.ReLU));
model.Add(new Dropout(0.2));
model.Add(new Dense(dim: numClasses));
}
static void Main(string[] args)
{
//Setup Engine
Global.UseEngine(SiaNet.Backend.MxNetLib.SiaNetBackend.Instance, DeviceType.CPU);
//Prep Data
var(x, y) = PrepDataset();
x.Head();
DataFrameIter trainSet = new DataFrameIter(x, y);
//Build model with simple fully connected layers
var model = new Sequential();
model.EpochEnd += Model_EpochEnd;
model.Add(new Dense(64, ActType.ReLU));
model.Add(new Dense(1, ActType.Sigmoid));
//Compile with Optimizer, Loss and Metric
model.Compile(OptimizerType.SGD, LossType.MeanSquaredError, MetricType.BinaryAccurary);
// Train for 100 epoch with batch size of 2
model.Train(trainSet, 1000, 2);
//Create prediction data to evaluate
DataFrame2D predX = new DataFrame2D(2);
predX.Load(0, 0, 0, 1); //Result should be 0 and 1
var rawPred = model.Predict(predX);
Console.ReadLine();
}
public static void BuildModel()
{
model = new Sequential();
model.Add(new Dense(dim: 2, shape: 2, act: OptActivations.Sigmoid));
model.Add(new Dense(dim: 2));
model.OnEpochEnd += Model_OnEpochEnd;
}
public static void BuildModel()
{
model = new Sequential();
model.Add(new Dense(dim: 2, shape: 2, act: OptActivations.Sigmoid, weightInitializer: new Model.Initializers.Xavier()));
model.Add(new Dense(dim: 2));
model.OnEpochEnd += Model_OnEpochEnd;
}
private static void createModel()
{
model = new Sequential();
model.Add(new Dense(INPUT_LAYER_SIZE, activation: "sigmoid" /*, input_dim: 1*/)); //relu - better
model.Add(new Dense(ASSOCIATIONS_LAYER_SIZE /* *5 better */, activation: "sigmoid")); // relu - better
model.Add(new Dense(RESULT_LAYER_SIZE, activation: "sigmoid"));
model.Compile(loss: "mean_squared_error" /*binary_crossentropy - better*/, optimizer: new SGD(lr: learningRate), metrics: new string[] { "accuracy" });
}
private static void BuildMLP()
{
model = new Sequential(new Shape(imgDim));
model.Add(new Dense(dim: 200, activation: new SiaNet.Layers.Activations.ReLU()));
model.Add(new Dense(dim: 400, activation: new SiaNet.Layers.Activations.ReLU()));
model.Add(new Dropout(0.2));
model.Add(new Dense(dim: labelDim));
}
public static void Run()
{
// Create
var trainX = new NDArray(new float[] { 0, 0, 0, 1, 1, 0, 1, 1 }).Reshape(4, 2);
var trainY = new NDArray(new float[] { 0, 1, 1, 0 });
var batch_size = 2;
var train_data = new NDArrayIter(trainX, trainY, batch_size);
var val_data = new NDArrayIter(trainX, trainY, batch_size);
var net = new Sequential();
net.Add(new Dense(64, ActivationType.Relu));
net.Add(new Dense(1));
var gpus = TestUtils.ListGpus();
var ctxList = gpus.Count > 0 ? gpus.Select(x => Context.Gpu(x)).ToArray() : new[] { Context.Cpu() };
net.Initialize(new Uniform(), ctxList.ToArray());
var trainer = new Trainer(net.CollectParams(), new Adam());
var epoch = 1000;
var metric = new BinaryAccuracy();
var binary_crossentropy = new LogisticLoss();
float lossVal = 0;
for (var iter = 0; iter < epoch; iter++)
{
train_data.Reset();
lossVal = 0;
while (!train_data.End())
{
var batch = train_data.Next();
var data = Utils.SplitAndLoad(batch.Data[0], ctxList);
var label = Utils.SplitAndLoad(batch.Label[0], ctxList);
NDArrayList outputs = null;
using (var ag = Autograd.Record())
{
outputs = Enumerable.Zip(data, label, (x, y) =>
{
var z = net.Call(x);
NDArray loss = binary_crossentropy.Call(z, y);
loss.Backward();
lossVal += loss.Mean();
return(z);
}).ToList();
}
metric.Update(label, outputs.ToArray());
trainer.Step(batch.Data[0].Shape[0]);
}
var(name, acc) = metric.Get();
metric.Reset();
Console.WriteLine($"Loss: {lossVal}");
Console.WriteLine($"Training acc at epoch {iter}: {name}={acc * 100}%");
}
}
private static Sequential BuildFCModel()
{
Sequential model = new Sequential();
model.Add(new Dense(dim: 784, activation: ActType.ReLU));
model.Add(new Dense(dim: 10, activation: ActType.Softmax));
return(model);
}
public void TrainXOR()
{
try {
//Load train data
float[,] testX = new float[, ] {
{ 0, 1 },
};
float[,] x = new float[, ] {
{ 0, 0 }, { 0, 1 }, { 1, 0 }, { 1, 1 }
};
float[] y = 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(32, activation: "relu"));
model.Add(new Dropout(0.1d));
model.Add(new Dense(1, activation: "sigmoid"));
//Compile and train
var optimizer = new Adam();
model.Compile(optimizer: optimizer, loss: "mse", metrics: new string[] { "accuracy" });
model.Fit(x, y, batch_size: 2, epochs: 1000, verbose: 1);
float[] predicts;
predicts = model.Predict(x).GetData <float>();
predicts = model.PredictOnBatch(x).GetData <float>();
predicts = model.Predict(x).GetData <float>();
predicts = model.PredictOnBatch(x).GetData <float>();
predicts = model.Predict(x).GetData <float>();
predicts = model.PredictOnBatch(x).GetData <float>();
Stopwatch watch = new Stopwatch();
watch.Restart();
for (int i = 0; i < 5; ++i)
{
predicts = model.PredictOnBatch(testX).GetData <float>();
}
watch.Stop();
string batchMs = watch.GetElapsedMilliseconds().ToString();
watch.Restart();
for (int i = 0; i < 5; ++i)
{
predicts = model.Predict(testX).GetData <float>();
}
watch.Stop();
//MainWindow.Instance.Dispatcher.BeginInvoke(new Action(() => {
// MainWindow.Instance.DebugTextBox.Text = batchMs + " / " + watch.GetElapsedMilliseconds().ToString();
//}));
} catch (Exception ex) {
//MainWindow.Instance.Dispatcher.BeginInvoke(new Action(() => {
// MainWindow.Instance.DebugTextBox.Text = ex.ToString();
//}));
}
}
public static void BuildModel()
{
model = new Sequential();
model.Add(new Reshape(targetshape: Shape.Create(1, train.XFrame.Shape[1]), shape: Shape.Create(lookback)));
model.Add(new LSTM(dim: 5, shape: Shape.Create(1, train.XFrame.Shape[1])));
model.Add(new Dense(dim: 1));
model.OnEpochEnd += Model_OnEpochEnd;
model.OnTrainingEnd += Model_OnTrainingEnd;
}
public static void BuildModel()
{
model = new Sequential();
model.Add(new Dense(dim: 20, shape: 13, act: OptActivations.LeakyReLU));
model.Add(new Dense(dim: 13, act: OptActivations.LeakyReLU));
model.Add(new Dropout(rate: 0.2));
model.Add(new Dense(dim: 1, act: OptActivations.LeakyReLU));
model.OnEpochEnd += Model_OnEpochEnd;
model.OnTrainingEnd += Model_OnTrainingEnd;
}
public static void BuildModel()
{
model = new Sequential();
model.Add(new LSTM(dim: 4, shape: Shape.Create(lookback), returnSequence: true));
model.Add(new LSTM(dim: 4, shape: Shape.Create(lookback)));
model.Add(new Dense(dim: 1));
model.OnEpochEnd += Model_OnEpochEnd;
model.OnTrainingEnd += Model_OnTrainingEnd;
}