public void AddingRegressionLayerWithoutPrecedingFullConnLayerShouldThrow()
{
var net = new Net();
net.AddLayer(new InputLayer(10, 10, 3));
Assert.Throws(typeof(ArgumentException), () => net.AddLayer(new RegressionLayer(1)));
}
public void BinaryNetSerializerTest()
{
var net = new Net();
net.AddLayer(new InputLayer(5, 5, 3));
var conv = new ConvLayer(2, 2, 16);
net.AddLayer(conv);
var fullycon = new FullyConnLayer(3);
net.AddLayer(fullycon);
net.AddLayer(new SoftmaxLayer(3));
// Serialize (binary)
using (var ms = new MemoryStream())
{
net.SaveBinary(ms);
ms.Position = 0;
// Deserialize (binary)
Net deserialized = SerializationExtensions.LoadBinary(ms) as Net;
// Make sure deserialized is identical to serialized
Assert.IsNotNull(deserialized.Layers);
Assert.AreEqual(net.Layers.Count, deserialized.Layers.Count);
Assert.IsTrue(net.Layers[0] is InputLayer);
var deserializedConv = net.Layers[1] as ConvLayer;
Assert.NotNull(deserializedConv);
Assert.NotNull(deserializedConv.Filters);
Assert.AreEqual(16, deserializedConv.Filters.Count);
for (int i = 0; i < deserializedConv.Filters.Count; i++)
{
for (int k = 0; k < deserializedConv.Filters[i].Length; k++)
{
Assert.AreEqual(conv.Filters[i].Get(k), deserializedConv.Filters[i].Get(k));
Assert.AreEqual(conv.Filters[i].GetGradient(k), deserializedConv.Filters[i].GetGradient(k));
}
}
var deserializedFullyCon = net.Layers[2] as FullyConnLayer;
Assert.NotNull(deserializedFullyCon);
Assert.NotNull(deserializedFullyCon.Filters);
Assert.AreEqual(3, deserializedFullyCon.Filters.Count);
for (int i = 0; i < deserializedFullyCon.Filters.Count; i++)
{
for (int k = 0; k < deserializedFullyCon.Filters[i].Length; k++)
{
Assert.AreEqual(fullycon.Filters[i].Get(k), deserializedFullyCon.Filters[i].Get(k));
Assert.AreEqual(fullycon.Filters[i].GetGradient(k), deserializedFullyCon.Filters[i].GetGradient(k));
}
}
Assert.IsTrue(deserialized.Layers[3] is SoftmaxLayer);
Assert.AreEqual(3, ((SoftmaxLayer)deserialized.Layers[3]).ClassCount);
}
}
public void IncorrectNeuronCountWithRegressionLayer()
{
var net = new Net();
net.AddLayer(new InputLayer(10, 10, 3));
net.AddLayer(new FullyConnLayer(5)); // should be 10
Assert.Throws(typeof(ArgumentException), () => net.AddLayer(new RegressionLayer(10)));
}
public void AddingClassificationLayerWithoutPrecedingFullConnLayerShouldThrow()
{
var net = new Net();
net.AddLayer(new InputLayer(10, 10, 3));
Assert.Throws(typeof(ArgumentException), () => net.AddLayer(new SoftmaxLayer(10)));
Assert.Throws(typeof(ArgumentException), () => net.AddLayer(new SvmLayer(10)));
}
public static Net <float> Build(int width, int height, int batchSize)
{
var net = new Net <float>();
net.AddLayer(new InputLayer(width, height, 1));
// 0.5*((in - 1) * stride + width - in) = pad
// pad = 0.5*(width + in * stride - stride)
// With stride = width = 3, pad = in
net.AddLayer(ConvFromInput(3, width, 1, 64));
net.AddLayer(new ReluLayer());
net.AddLayer(ConvFromInput(3, width, 1, 64));
net.AddLayer(new ReluLayer());
//net.AddLayer(new DropoutLayer(0.3f));
//net.AddLayer(ConvFromInput(3, width, 1, 64));
//net.AddLayer(new ReluLayer());
//net.AddLayer(new DropoutLayer(0.3f));
//net.AddLayer(new ConvLayer(2, 2, 16) { Stride = 1 });
net.AddLayer(ConvFromInput(3, width, 1, 64));
net.AddLayer(new ReluLayer());
//net.AddLayer(new DropoutLayer(0.3f));
//net.AddLayer(new FullyConnLayer(width * height));
//net.AddLayer(new ReluLayer());
net.AddLayer(ConvFromInput(3, width, 1, 1));
//net.AddLayer(new ReluLayer());
net.AddLayer(new RegressionLayer());
return(net);
}
public void JsonNetSerializerTest()
{
var net = new Net();
net.AddLayer(new InputLayer(5, 5, 3));
var conv = new ConvLayer(2, 2, 16);
net.AddLayer(conv);
var fullycon = new FullyConnLayer(3);
net.AddLayer(fullycon);
net.AddLayer(new SoftmaxLayer(3));
// Serialize to json
var json = net.ToJSON();
// Deserialize from json
Net deserialized = SerializationExtensions.FromJSON(json);
// Make sure deserialized is identical to serialized
Assert.IsNotNull(deserialized.Layers);
Assert.AreEqual(net.Layers.Count, deserialized.Layers.Count);
Assert.IsTrue(net.Layers[0] is InputLayer);
var deserializedConv = net.Layers[1] as ConvLayer;
Assert.NotNull(deserializedConv);
Assert.NotNull(deserializedConv.Filters);
Assert.AreEqual(16, deserializedConv.Filters.Count);
for (int i = 0; i < deserializedConv.Filters.Count; i++)
{
for (int k = 0; k < deserializedConv.Filters[i].Length; k++)
{
Assert.AreEqual(conv.Filters[i].Get(k), deserializedConv.Filters[i].Get(k));
Assert.AreEqual(conv.Filters[i].GetGradient(k), deserializedConv.Filters[i].GetGradient(k));
}
}
var deserializedFullyCon = net.Layers[2] as FullyConnLayer;
Assert.NotNull(deserializedFullyCon);
Assert.NotNull(deserializedFullyCon.Filters);
Assert.AreEqual(3, deserializedFullyCon.Filters.Count);
for (int i = 0; i < deserializedFullyCon.Filters.Count; i++)
{
for (int k = 0; k < deserializedFullyCon.Filters[i].Length; k++)
{
Assert.AreEqual(fullycon.Filters[i].Get(k), deserializedFullyCon.Filters[i].Get(k));
Assert.AreEqual(fullycon.Filters[i].GetGradient(k), deserializedFullyCon.Filters[i].GetGradient(k));
}
}
Assert.IsTrue(net.Layers[3] is SoftmaxLayer);
Assert.AreEqual(3, ((SoftmaxLayer)net.Layers[3]).ClassCount);
}
public void NetSerialization()
{
var net = new Net <double>();
net.AddLayer(new InputLayer(28, 28, 1));
net.AddLayer(new ConvLayer(5, 5, 8)
{
Stride = 1, Pad = 2, BiasPref = 0.1
});
net.AddLayer(new ReluLayer());
net.AddLayer(new PoolLayer(2, 2)
{
Stride = 2
});
net.AddLayer(new SigmoidLayer());
net.AddLayer(new TanhLayer());
net.AddLayer(new FullyConnLayer(10)
{
BiasPref = 0.2
});
net.AddLayer(new SoftmaxLayer(10));
var json = net.ToJson();
var deserialized = SerializationExtensions.FromJson <double>(json);
}
public void Init()
{
// species a 2-layer neural network with one hidden layer of 20 neurons
Net = new Net <double>();
NetTrainer = new SgdTrainer(Net)
{
LearningRate = 0.02, L2Decay = 0.005
};
// input layer declares size of input. here: 2-D data
// ConvNetJS works on 3-Dimensional volumes (width, height, depth), but if you're not dealing with images
// then the first two dimensions (width, height) will always be kept at size 1
//30 input nodes, one for each 10px of 300px ground to show obstacles as features
Net.AddLayer(new InputLayer(1, 1, TrainerConfig.InputNodesCount));
// declare 20 neurons
Net.AddLayer(new FullyConnLayer(TrainerConfig.HiddenLayerNodesCount));
// declare a ReLU (rectified linear unit non-linearity)
Net.AddLayer(new ReluLayer());
// declare a fully connected layer that will be used by the softmax layer
Net.AddLayer(new FullyConnLayer(2));
// declare the linear classifier on top of the previous hidden layer
Net.AddLayer(new SoftmaxLayer(2));
var batch = 50;
for (var j = 0; j < batch; j++)
{
Train(GenerateTrainData(), true);
}
//var x =
// new Volume(new[] {0.0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0}, new Shape(30));
//var prob = Forward(x);
//// prob is a Volume. Volumes have a property Weights that stores the raw data, and WeightGradients that stores gradients
//Console.WriteLine(prob.Get(0) >= 0.5 ? "Jump" : "Stay"); // prints e.g. 0.50101
//NetTrainer.Train(x, new Volume(new[] { 0.0 }, new Shape(1, 1, 1, 1))); // train the network, specifying that x is class zero
//var prob2 = Net.Forward(x);
//Console.WriteLine("probability that x is class 0: " + prob2.Get(0));
// now prints 0.50374, slightly higher than previous 0.50101: the networks
// weights have been adjusted by the Trainer to give a higher probability to
// the class we trained the network with (zero)
}
// Use this for initialization
void Start()
{
exp = new Experience[experienceSize];
expi = 0;
expn = 0;
t = 0;
r0 = -99f;
// species a 2-layer neural network with one hidden layer of 20 neurons
net = new Net();
// input layer declares size of input. here: 2-D data
// ConvNetSharp works on 3-Dimensional volumes (width, height, depth), but if you're not dealing with images
// then the first two dimensions (width, height) will always be kept at size 1
net.AddLayer(new InputLayer(1, 1, numStates));
// declare 20 neurons, followed by ReLU (rectified linear unit non-linearity)
net.AddLayer(new FullyConnLayer(hiddenNeurons, Activation.Relu));
net.AddLayer(new FullyConnLayer(hiddenNeurons, Activation.Relu));
// declare the linear classifier on top of the previous hidden layer
net.AddLayer(new RegressionLayer(numActions));
double[] weights = { 0.3, -0.5, 0.1, 0.9, 0.6 };
// forward a random data point through the network
var x = new Volume(weights);
var prob = net.Forward(x);
// prob is a Volume. Volumes have a property Weights that stores the raw data, and WeightGradients that stores gradients
Debug.Log("probability that x is class 0: " + prob.Weights[0]); // prints e.g. 0.50101
trainer = new SgdTrainer(net)
{
LearningRate = 0.01, L2Decay = 0.001, Momentum = 0.0, BatchSize = 1
};
//trainer.Train(x, 0); // train the network, specifying that x is class zero
Volume prob2 = net.Forward(x);
Debug.Log("probability that x is class 0: " + prob2.Weights[0]);
// now prints 0.50374, slightly higher than previous 0.50101: the networks
// weights have been adjusted by the Trainer to give a higher probability to
// the class we trained the network with (zero)
}
/// <summary>
/// This sample shows how to serialize and deserialize a ConvNetSharp.Core network
/// 1) Network creation
/// 2) Dummy Training (only use a single data point)
/// 3) Serialization
/// 4) Deserialization
/// </summary>
private static void Main()
{
// 1) Network creation
var net = new Net <double>();
net.AddLayer(new InputLayer(1, 1, 2));
net.AddLayer(new FullyConnLayer(20));
net.AddLayer(new ReluLayer());
net.AddLayer(new FullyConnLayer(10));
net.AddLayer(new SoftmaxLayer(10));
// 2) Dummy Training (only use a single data point)
var x = BuilderInstance.Volume.From(new[] { 0.3, -0.5 }, new Shape(2));
var y = BuilderInstance.Volume.From(new[] { 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 }, new Shape(10));
var count = 0;
var trainer = new SgdTrainer(net)
{
LearningRate = 0.01
};
do
{
trainer.Train(x, y); // train the network, specifying that x is class zero
Console.WriteLine($"Loss: {trainer.Loss}");
count++;
} while (trainer.Loss > 1e-2);
Console.WriteLine($"{count}");
// Forward pass with original network
var prob1 = net.Forward(x);
Console.WriteLine("probability that x is class 0: " + prob1.Get(0));
// 3) Serialization
var json = net.ToJson();
// 4) Deserialization
var deserialized = SerializationExtensions.FromJson <double>(json);
// Forward pass with deserialized network
var prob2 = deserialized.Forward(x);
Console.WriteLine("probability that x is class 0: " + prob2.Get(0)); // This should give exactly the same result as previous network evaluation
Console.ReadLine();
}
public void BuildNetwork(Net <double> net)
{
net.AddLayer(new InputLayer(1, 1, screenDepth));
net.AddLayer(new FullyConnLayer(128));
net.AddLayer(new ReluLayer());
net.AddLayer(new FullyConnLayer(128));
net.AddLayer(new ReluLayer());
net.AddLayer(new FullyConnLayer(16));
net.AddLayer(new ReluLayer());
net.AddLayer(new FullyConnLayer(numAction));
net.AddLayer(new SoftmaxLayer(3));
}
public static Net<T> Build<T>(this LayerBase<T> layer) where T : struct, IEquatable<T>, IFormattable
{
var net = new Net<T>();
net.AddLayer(layer);
return net;
}
public void BiasPrefUpdateWhenAddingReluLayer()
{
var net = new Net();
net.AddLayer(new InputLayer(10, 10, 3));
var dotProduct1 = new FullyConnLayer(5);
net.AddLayer(dotProduct1);
net.AddLayer(new ReluLayer());
var dotProduct2 = new ConvLayer(5, 5, 3);
net.AddLayer(dotProduct2);
net.AddLayer(new ReluLayer());
Assert.AreEqual(0.1, dotProduct1.BiasPref);
Assert.AreEqual(0.1, dotProduct2.BiasPref);
}
public static Network CreateNew()
{
var net = new Net <double>();
net.AddLayer(new InputLayer(256, 256, 3));
// ToDo: Pad ConvLayers?
net.AddLayer(new ConvLayer(16, 16, 192)
{
Stride = 12
});
net.AddLayer(new ReluLayer());
net.AddLayer(new PoolLayer(6, 6)
{
Stride = 6
});
net.AddLayer(new FullyConnLayer(512));
net.AddLayer(new FullyConnLayer(1));
net.AddLayer(new RegressionLayer());
return(new Network(net));
}
private static void Main()
{
// species a 2-layer neural network with one hidden layer of 20 neurons
var net = new Net <double>();
// input layer declares size of input. here: 2-D data
// ConvNetJS works on 3-Dimensional volumes (width, height, depth), but if you're not dealing with images
// then the first two dimensions (width, height) will always be kept at size 1
net.AddLayer(new InputLayer(1, 1, 2));
// declare 20 neurons
net.AddLayer(new FullyConnLayer(20));
// declare a ReLU (rectified linear unit non-linearity)
net.AddLayer(new ReluLayer());
// declare a fully connected layer that will be used by the softmax layer
net.AddLayer(new FullyConnLayer(10));
// declare the linear classifier on top of the previous hidden layer
net.AddLayer(new SoftmaxLayer(10));
// forward a random data point through the network
var x = BuilderInstance.Volume.From(new[] { 0.3, -0.5 }, new Shape(2));
var prob = net.Forward(x);
// prob is a Volume. Volumes have a property Weights that stores the raw data, and WeightGradients that stores gradients
Console.WriteLine("probability that x is class 0: " + prob.Get(0)); // prints e.g. 0.50101
var trainer = new SgdTrainer(net)
{
LearningRate = 0.01, L2Decay = 0.001
};
trainer.Train(x, BuilderInstance.Volume.From(new[] { 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 }, new Shape(1, 1, 10, 1))); // train the network, specifying that x is class zero
var prob2 = net.Forward(x);
Console.WriteLine("probability that x is class 0: " + prob2.Get(0));
// now prints 0.50374, slightly higher than previous 0.50101: the networks
// weights have been adjusted by the Trainer to give a higher probability to
// the class we trained the network with (zero)
}
public static void Classify2DDemo()
{
var net = new Net <double>();
net.AddLayer(new InputLayer <double>());
net.AddLayer(new FullyConnLayer <double>(6));
net.AddLayer(new TanhLayer <double>());
net.AddLayer(new FullyConnLayer <double>(2));
net.AddLayer(new TanhLayer <double>());
net.AddLayer(new FullyConnLayer <double>(2));
net.AddLayer(new SoftmaxLayer <double>());
// Data
var data = new List <double[]>();
var labels = new List <int>();
data.Add(new[] { -0.4326, 1.1909 });
labels.Add(1);
data.Add(new[] { 3.0, 4.0 });
labels.Add(1);
data.Add(new[] { 0.1253, -0.0376 });
labels.Add(1);
data.Add(new[] { 0.2877, 0.3273 });
labels.Add(1);
data.Add(new[] { -1.1465, 0.1746 });
labels.Add(1);
data.Add(new[] { 1.8133, 1.0139 });
labels.Add(0);
data.Add(new[] { 2.7258, 1.0668 });
labels.Add(0);
data.Add(new[] { 1.4117, 0.5593 });
labels.Add(0);
data.Add(new[] { 4.1832, 0.3044 });
labels.Add(0);
data.Add(new[] { 1.8636, 0.1677 });
labels.Add(0);
data.Add(new[] { 0.5, 3.2 });
labels.Add(1);
data.Add(new[] { 0.8, 3.2 });
labels.Add(1);
data.Add(new[] { 1.0, -2.2 });
labels.Add(1);
var n = labels.Count;
var trainer = new SgdTrainer <double>(net, 0.01);
do
{
Classify2DUpdate(n, data, trainer, labels);
} while (!Console.KeyAvailable);
// Display graph
var vm = new ViewModel <double>(net.Cost);
var app = new Application();
app.Run(new GraphControl {
DataContext = vm
});
}
public Brain(int numInputs, int numActions)
{
CreatedDate = DateTime.Now;
TrainingTime = new TimeSpan();
NumInputs = numInputs;
NumActions = numActions;
// network
var layer1N = (numInputs + numActions) / 2;
Net = new Net();
Net.AddLayer(new InputLayer(1, 1, numInputs));
Net.AddLayer(new FullyConnLayer(layer1N));
Net.AddLayer(new ReluLayer());
Net.AddLayer(new FullyConnLayer(numActions));
Net.AddLayer(new RegressionLayer());
World = GridWorld.StandardState();
}
/// <summary>
/// Creates a layer
/// </summary>
/// <param name="type"> The type. </param>
/// <param name="val1"> The first value.</param>
/// <param name="val2"> The second value.</param>
/// <param name="val3"> The third value. </param>
internal void CreateLayer(LayerType type, double val1, double val2, double val3)
{
switch (type)
{
case LayerType.InputLayer:
_net?.AddLayer(new InputLayer((int)val1, (int)val2, (int)val3));
break;
case LayerType.FullyConnLayer:
_net?.AddLayer(new FullyConnLayer((int)val1));
break;
case LayerType.ReluLayer:
_net?.AddLayer(new ReluLayer());
break;
case LayerType.SoftmaxLayer:
_net?.AddLayer(new SoftmaxLayer((int)val1));
break;
}
}
public CNN(int[] featureNum, int actionNum, int batchSize = 31)
{
//get channel
_channel = featureNum[0];
_width = featureNum[1];
_height = featureNum[2];
_actionNum = actionNum;
_batchSize = batchSize;
//create cnn neural network
_network = new Net <double>();
_network.AddLayer(new InputLayer <double>(_width, _height, _channel));
_network.AddLayer(new ConvLayer <double>(1, 1, 2)
{
Stride = 1, Pad = 2, BiasPref = 0.1f
});
_network.AddLayer(new ReluLayer <double>());
_network.AddLayer(new PoolLayer <double>(2, 2)
{
Stride = 2
});
_network.AddLayer(new ConvLayer <double>(5, 5, 16)
{
Stride = 1, Pad = 2, BiasPref = 0.1f
});
_network.AddLayer(new ReluLayer <double>());
_network.AddLayer(new PoolLayer <double>(3, 3)
{
Stride = 3
});
_network.AddLayer(new FullyConnLayer <double>(_actionNum));
_network.AddLayer(new SoftmaxLayer <double>(_actionNum));
//create trainer
_trainer = new SgdTrainer <double>(_network)
{
LearningRate = 0.001,
BatchSize = batchSize,
L2Decay = 0.001,
Momentum = 0.9
};
}
private void CreateNetworkForTactile()
{
// Создаем сеть
net = new Net();
net.AddLayer(new InputLayer(inputWidth, inputHeight, inputDepth));
// Ширина и высота рецептивного поля, количество фильтров
net.AddLayer(new ConvLayer(3, 3, 8)
{
// Шаг скольжения свертки
Stride = 1,
// Заполнение краев нулями
Pad = 1
});
net.AddLayer(new ReluLayer());
// Ширина и высота окна уплотнения
net.AddLayer(new PoolLayer(2, 2)
{
// Сдвиг
Stride = 2
});
net.AddLayer(new ConvLayer(3, 3, 16)
{
Stride = 1,
Pad = 1
});
net.AddLayer(new ReluLayer());
net.AddLayer(new PoolLayer(3, 3)
{
Stride = 3
});
net.AddLayer(new FullyConnLayer(names.Length));
net.AddLayer(new SoftmaxLayer(names.Length));
}
public void NetSerializationData()
{
var net = new Net <double>();
net.AddLayer(new InputLayer(28, 28, 1));
net.AddLayer(new ConvLayer(5, 5, 8)
{
Stride = 1, Pad = 2
});
net.AddLayer(new ReluLayer());
net.AddLayer(new PoolLayer(2, 2)
{
Stride = 2
});
net.AddLayer(new ConvLayer(5, 5, 16)
{
Stride = 1, Pad = 2
});
net.AddLayer(new ReluLayer());
net.AddLayer(new PoolLayer(3, 3)
{
Stride = 3
});
net.AddLayer(new FullyConnLayer(10));
net.AddLayer(new SoftmaxLayer(10));
var data = net.GetData();
var layers = data["Layers"] as List <Dictionary <string, object> >;
Assert.IsNotNull(layers);
Assert.AreEqual(net.Layers.Count, layers.Count);
var deserialized = Net <double> .FromData(data);
Assert.AreEqual(net.Layers.Count, deserialized.Layers.Count);
}
private static void Regression1DDemo()
{
var net = new Net();
net.AddLayer(new InputLayer(1, 1, 1));
net.AddLayer(new FullyConnLayer(20));
net.AddLayer(new ReluLayer());
net.AddLayer(new FullyConnLayer(20));
net.AddLayer(new SigmoidLayer());
net.AddLayer(new FullyConnLayer(1));
net.AddLayer(new RegressionLayer());
var trainer = new SgdTrainer(net)
{
LearningRate = 0.01, Momentum = 0.0, BatchSize = 1, L2Decay = 0.001
};
// Function we want to learn
double[] x = { 0.0, 0.5, 1.0 };
double[] y = { 0.0, 0.1, 0.2 };
var n = x.Length;
// Training
do
{
RegressionUpdate(n, x, trainer, y);
} while (!Console.KeyAvailable);
// Testing
var netx = new Volume(1, 1, 1);
for (var ix = 0; ix < n; ix++)
{
netx.Set(0, 0, 0, x[ix]);
var result = net.Forward(netx);
}
}
public void JsonAnotherNetSerilizerTest()
{
var numInputs = 64;
var numActions = 5;
var net = new Net();
net.AddLayer(new InputLayer(1, 1, numInputs));
net.AddLayer(new FullyConnLayer((int)(numInputs * 2.5)));
net.AddLayer(new ReluLayer());
net.AddLayer(new FullyConnLayer((int)(numInputs * 1.5)));
net.AddLayer(new ReluLayer());
net.AddLayer(new FullyConnLayer(numActions));
net.AddLayer(new RegressionLayer());
// Serialize to json
var json = net.ToJSON();
// Deserialize from json
var deserialized = SerializationExtensions.FromJSON(json);
var input = new Volume(1, 1, numInputs);
var output1 = net.Forward(input);
var output2 = deserialized.Forward(input);
}
private static void Classify2DDemo()
{
var net = new Net <double>();
net.AddLayer(new InputLayer(1, 1, 2));
net.AddLayer(new FullyConnLayer(6));
net.AddLayer(new TanhLayer());
net.AddLayer(new FullyConnLayer(2));
net.AddLayer(new TanhLayer());
net.AddLayer(new FullyConnLayer(2));
net.AddLayer(new SoftmaxLayer(2));
// Data
var data = new List <double[]>();
var labels = new List <int>();
data.Add(new[] { -0.4326, 1.1909 });
labels.Add(1);
data.Add(new[] { 3.0, 4.0 });
labels.Add(1);
data.Add(new[] { 0.1253, -0.0376 });
labels.Add(1);
data.Add(new[] { 0.2877, 0.3273 });
labels.Add(1);
data.Add(new[] { -1.1465, 0.1746 });
labels.Add(1);
data.Add(new[] { 1.8133, 1.0139 });
labels.Add(0);
data.Add(new[] { 2.7258, 1.0668 });
labels.Add(0);
data.Add(new[] { 1.4117, 0.5593 });
labels.Add(0);
data.Add(new[] { 4.1832, 0.3044 });
labels.Add(0);
data.Add(new[] { 1.8636, 0.1677 });
labels.Add(0);
data.Add(new[] { 0.5, 3.2 });
labels.Add(1);
data.Add(new[] { 0.8, 3.2 });
labels.Add(1);
data.Add(new[] { 1.0, -2.2 });
labels.Add(1);
var n = labels.Count;
var trainer = new SgdTrainer <double>(net)
{
LearningRate = 0.01, L2Decay = 0.001, BatchSize = n
};
// Training
do
{
Classify2DUpdate(n, data, trainer, labels);
} while (!Console.KeyAvailable);
// Testing
var netx = new Volume(new double[2 * n], new Shape(1, 1, 2, n));
for (var ix = 0; ix < n; ix++)
{
netx.Set(0, 0, 0, ix, data[ix][0]);
netx.Set(0, 0, 1, ix, data[ix][1]);
}
var result = net.Forward(netx);
var c = net.GetPrediction();
var accurate = c[0] == labels[0];
}
private static void Main(string[] args)
{
// Load data
var min_count = 10;
var polarity_cutoff = 0.1;
var labels = File.ReadAllLines("../../../../Data/labels.txt");
var reviews = File.ReadAllLines("../../../../Data/reviews.txt");
// Count words
var vocab = new Dictionary <string, int>();
var positive_counts = new Dictionary <string, int>();
var negative_counts = new Dictionary <string, int>();
var pos_neg_ratios = new Dictionary <string, double>();
foreach (var pair in reviews.Zip(labels, (review, label) => new { review, label }))
{
var review = pair.review;
var label = pair.label;
foreach (var word in review.ToLower().Split(' '))
{
vocab.TryGetValue(word, out var count);
vocab[word] = count + 1;
var dico = label == "positive" ? positive_counts : negative_counts;
dico.TryGetValue(word, out count);
dico[word] = count + 1;
var otherDico = label == "positive" ? negative_counts : positive_counts;
otherDico.TryGetValue(word, out count);
otherDico[word] = count; // This is used to set count to 0 words that appear only on one side
}
}
// Compute ratios
foreach (var word in vocab.Keys)
{
if (vocab[word] > 50)
{
var ratio = positive_counts[word] / (negative_counts[word] + 1.0);
if (ratio > 1.0)
{
pos_neg_ratios[word] = Math.Log(ratio);
}
else
{
pos_neg_ratios[word] = -Math.Log(1.0 / (ratio + 0.01));
}
}
else
{
pos_neg_ratios[word] = 0.0;
}
}
var review_vocab = vocab.Where(o => o.Value > min_count && Math.Abs(pos_neg_ratios[o.Key]) > polarity_cutoff).Select(o => o.Key).ToList();
// Create word to index map
var wordToIndex = review_vocab.Select((word, index) => new { word, index }).ToDictionary(o => o.word, o => o.index);
// Build network
var network = new Net <double>();
network.AddLayer(new InputLayer(1, 1, review_vocab.Count));
network.AddLayer(new FullyConnLayer(10));
network.AddLayer(new FullyConnLayer(1));
network.AddLayer(new RegressionLayer());
// Training
var trainer = new SgdTrainer(network)
{
LearningRate = 0.005
};
var input = BuilderInstance.Volume.SameAs(new Shape(1, 1, review_vocab.Count));
var output = BuilderInstance.Volume.SameAs(new Shape(1, 1, 1));
var i = 0;
var correct = 0;
for (var epoch = 0; epoch < 3; epoch++)
{
Console.WriteLine($"Epoch #{epoch}");
foreach (var pair in reviews.Zip(labels, (review, label) => new { review, label }))
{
var review = pair.review;
var label = pair.label;
FillVolume(input, review, wordToIndex);
output.Set(0, 0, 0, pair.label == "positive" ? 1.0 : 0.0);
var test = network.Forward(input);
if (test > 0.5 && label == "positive" || test < 0.5 && label == "negative")
{
correct++;
}
trainer.Train(input, output);
if (i % 100 == 0)
{
Console.WriteLine($"Accuracy: {Math.Round(correct / (double)i * 100.0, 2)}%");
Console.WriteLine($"{i}/{reviews.Length}");
}
i++;
if (Console.KeyAvailable)
{
break;
}
}
}
// Save Network
File.WriteAllText(@"../../../../Model/sentiment.json", network.ToJson());
}
public void CompareCoreVsFlow()
{
var inputWidth = 28;
var inputHeigth = 28;
var inputDepth = 3;
var batchSize = 20;
#region Flow network
var netFlow = new Net <T>();
netFlow.AddLayer(new InputLayer <T>());
var convLayerFlow1 = new ConvLayer <T>(5, 5, 8)
{
BiasPref = (T)Convert.ChangeType(0.1, typeof(T)), Stride = 1, Pad = 2
};
netFlow.AddLayer(convLayerFlow1);
netFlow.AddLayer(new ReluLayer <T>());
netFlow.AddLayer(new PoolLayer <T>(2, 2)
{
Stride = 2
});
var fullyConnLayerFlow = new FullyConnLayer <T>(10);
netFlow.AddLayer(fullyConnLayerFlow);
netFlow.AddLayer(new SoftmaxLayer <T>());
var trainerFlow = new SgdTrainer <T>(netFlow, (T)Convert.ChangeType(0.01f, typeof(T)))
{
BatchSize = batchSize
};
#endregion
#region Core network
var netCore = new Core.Net <T>();
netCore.AddLayer(new Core.Layers.InputLayer <T>(inputWidth, inputHeigth, inputDepth));
var convLayerCore1 = new Core.Layers.ConvLayer <T>(5, 5, 8)
{
BiasPref = (T)Convert.ChangeType(0.1, typeof(T)), Stride = 1, Pad = 2
};
netCore.AddLayer(convLayerCore1);
netCore.AddLayer(new Core.Layers.ReluLayer <T>());
netCore.AddLayer(new Core.Layers.PoolLayer <T>(2, 2)
{
Stride = 2
});
var fullyConnLayerCore = new Core.Layers.FullyConnLayer <T>(10);
netCore.AddLayer(fullyConnLayerCore);
netCore.AddLayer(new Core.Layers.SoftmaxLayer <T>(10));
var trainerCore = new Core.Training.SgdTrainer <T>(netCore)
{
LearningRate = (T)Convert.ChangeType(0.01f, typeof(T)),
BatchSize = batchSize
};
#endregion
// Same weights
var convfilterCore1 = netFlow.Session.GetVariableByName(netFlow.Op, (convLayerFlow1.Filter as IPersistable <T>).Name);
convfilterCore1.Result = BuilderInstance <T> .Volume.SameAs(convLayerCore1.Filters.ToArray(), convLayerCore1.Filters.Shape);
var fullyfilterCore = netFlow.Session.GetVariableByName(netFlow.Op, (fullyConnLayerFlow.Filter as IPersistable <T>).Name);
fullyfilterCore.Result = BuilderInstance <T> .Volume.SameAs(fullyConnLayerCore.Filters.ToArray(), fullyConnLayerCore.Filters.Shape);
// Create input
var xStorage = new double[inputWidth * inputHeigth * inputDepth * batchSize].Populate(1.0);
var x = NewVolume(xStorage, Volume.Shape.From(inputWidth, inputHeigth, inputDepth, batchSize));
// Create output
var yStorage = new double[10 * batchSize];
var y = NewVolume(yStorage, Volume.Shape.From(1, 1, 10, batchSize));
for (var i = 0; i < batchSize; i++)
{
y.Set(0, 0, i % 10, i, Ops <T> .One);
}
for (var k = 0; k < 10; k++)
{
xStorage = new double[inputWidth * inputHeigth * inputDepth * batchSize].Populate(1.0 + k);
x = NewVolume(xStorage, Volume.Shape.From(inputWidth, inputHeigth, inputDepth, batchSize));
var flowResult = netFlow.Forward(x);
var coreResult = netCore.Forward(x);
var sum1 = BuilderInstance <T> .Volume.SameAs(new Shape(1));
flowResult.DoSum(sum1);
var sum2 = BuilderInstance <T> .Volume.SameAs(new Shape(1));
coreResult.DoSum(sum2);
var diff = Ops <T> .Subtract(sum1.Get(0), sum2.Get(0));
Console.WriteLine(diff);
AssertNumber.AreSequenceEqual(flowResult.ToArray(), coreResult.ToArray(), 1e-6);
trainerCore.Train(x, y);
trainerFlow.Train(x, y);
}
}
public void Start(List <User> userList, int neededUserId, int imageSize, Action <string> infoOutputFunc)
{
// Load data
_userList = userList;
_neededUserId = neededUserId;
_imageSize = imageSize;
_stepCount = 1;
_infoOutputFunc = infoOutputFunc;
// Create network
_net = new Net();
_net.AddLayer(new InputLayer(_imageSize, _imageSize, 1));
_net.AddLayer(new ConvLayer(5, 5, 16)
{
Stride = 1, Pad = 1, Activation = Activation.Relu
});
_net.AddLayer(new PoolLayer(2, 2)
{
Stride = 2
});
_net.AddLayer(new ConvLayer(5, 5, 8)
{
Stride = 1, Pad = 1, Activation = Activation.Relu
});
_net.AddLayer(new PoolLayer(2, 2)
{
Stride = 2
});
_net.AddLayer(new SoftmaxLayer(2));
_trainer = new Trainer(_net)
{
BatchSize = 20,
L2Decay = 0.001,
TrainingMethod = Trainer.Method.Adagrad
};
Stopwatch sw = Stopwatch.StartNew();
do
{
var sample = GenerateTrainingInstance();
if (!Step(sample))
{
break;
}
} while (true);
sw.Stop();
if (_infoOutputFunc != null)
{
_infoOutputFunc(string.Format("\nВремя тренировки: {0} мск", sw.ElapsedMilliseconds));
}
Console.WriteLine(sw.ElapsedMilliseconds / 1000.0);
// Output checking
if (_infoOutputFunc != null)
{
_infoOutputFunc("\n\nId пользователя \t\t Неверный пользователь \t\t Верный пользователь");
}
foreach (User user in _userList.OrderByDescending(i => i.UserId))
{
Random random = new Random();
var signature = user.SignatureList[random.Next(user.SignatureList.Count)];
var x = GetVolume(signature);
var result = _net.Forward(x);
if (_infoOutputFunc != null)
{
_infoOutputFunc(string.Format("{0} \t\t\t {1} \t\t {2}", user.UserId, result.Weights[0], result.Weights[1]));
}
}
}
public void Demo()
{
// Load data
_userList = ReadingManager.ReadData(@"C:\Users\RustamSalakhutdinov\Documents\visual studio 2015\Projects\signatureChecker\data_new");
// Create network
_net = new Net();
_net.AddLayer(new InputLayer(imageSize, imageSize, 1));
_net.AddLayer(new ConvLayer(5, 5, 16)
{
Stride = 1, Pad = 1, Activation = Activation.Relu
});
_net.AddLayer(new PoolLayer(2, 2)
{
Stride = 2
});
_net.AddLayer(new ConvLayer(5, 5, 8)
{
Stride = 1, Pad = 1, Activation = Activation.Relu
});
_net.AddLayer(new PoolLayer(2, 2)
{
Stride = 2
});
_net.AddLayer(new SoftmaxLayer(2));
_trainer = new Trainer(_net)
{
BatchSize = 20,
L2Decay = 0.001,
TrainingMethod = Trainer.Method.Adagrad
};
Stopwatch sw = Stopwatch.StartNew();
do
{
var sample = GenerateTrainingInstance();
if (!Step(sample))
{
break;
}
} while (!Console.KeyAvailable);
sw.Stop();
Console.WriteLine(sw.ElapsedMilliseconds / 1000.0);
foreach (User user in _userList)
{
Random random = new Random();
var signature = user.SignatureList[random.Next(user.SignatureList.Count)];
var x = new Volume(imageSize, imageSize, 1, 0.0);
foreach (var point in signature.SignaturePointList)
{
x.Weights[point.X * imageSize + point.Y] = 1;
}
x = x.Augment(imageSize);
var result = _net.Forward(x);
Console.WriteLine("UserId: {0}. Result: {1} | {2}", user.UserId, result.Weights[0], result.Weights[1]);
}
}
public ConvNetSharpNetwork()
{
network = new Net <double>();
network.AddLayer(new InputLayer(50, 52, 1));
network.AddLayer(new ConvLayer(3, 3, 8)
{
Stride = 1, Pad = 2
});
network.AddLayer(new ReluLayer());
network.AddLayer(new PoolLayer(3, 3)
{
Stride = 2
});
network.AddLayer(new ConvLayer(3, 3, 16)
{
Stride = 1, Pad = 2
});
network.AddLayer(new ReluLayer());
network.AddLayer(new PoolLayer(3, 3)
{
Stride = 2
});
network.AddLayer(new ConvLayer(3, 3, 32)
{
Stride = 1, Pad = 2
});
network.AddLayer(new FullyConnLayer(20));
network.AddLayer(new FullyConnLayer(50));
network.AddLayer(new FullyConnLayer(2));
network.AddLayer(new SoftmaxLayer(2));
trainer = GetTrainerForNetwork(network);
}
private void CreateNetwork()
{
net = new Net <float>();
net.AddLayer(new InputLayer(windowSize, windowSize, 1));
net.AddLayer(new ConvLayer(5, 5, 3)
{
Stride = 1, Pad = 0
}); // 21 x 21
net.AddLayer(new ReluLayer()); // 21 x 21
net.AddLayer(new PoolLayer(2, 2)); // 10 x 10
net.AddLayer(new ConvLayer(5, 5, 3)
{
Stride = 1, Pad = 0
}); // 6 x 6
net.AddLayer(new ReluLayer());
net.AddLayer(new PoolLayer(2, 2));
net.AddLayer(new FullyConnLayer(16));
net.AddLayer(new TanhLayer());
net.AddLayer(new FullyConnLayer(2));
net.AddLayer(new SoftmaxLayer(2));
trainer = new SgdTrainer(net)
{
LearningRate = 0.01f, L2Decay = 0.001f
};
}