private void saveButton_Clicked(object sender, EventArgs e)
{
if (saveFileDialog1.ShowDialog() == DialogResult.OK)
{
Stream st;
if ((st = saveFileDialog1.OpenFile()) != null)
{
_network.Save(st);
st.Close();
}
}
}
public void SaveNetwork(string filePath)
{
network.Save(filePath);
}
static void Main(string[] args)
{
//Generate the training data
int keySize = 64;
int messageSize = 64;
int trainingSetSize = 100;
List <Triplet> trainingSet = GenerateDESDataset(trainingSetSize, keySize, messageSize);
double[][] inputTraining, outputTraining;
Triplet.Transform2IO(trainingSet, out inputTraining, out outputTraining);
//Generate the test data
List <Triplet> testSet = GenerateDESDataset(trainingSetSize, keySize, messageSize);
double[][] inputTest, outputTest;
Triplet.Transform2IO(testSet, out inputTest, out outputTest);
//Find the right sizes, not sure why I have to do that :-/
int inputSize = trainingSet.First().original.Count() + trainingSet.First().encrypted.Count();
int outputSize = trainingSet.First().key.Count();
//Create a network
var function = new SigmoidFunction(2.0);
//ActivationNetwork network = new ActivationNetwork(function, inputSize, 25, outputSize);
//ParallelResilientBackpropagationLearning teacher = new ParallelResilientBackpropagationLearning(network);
DeepBeliefNetwork network = new DeepBeliefNetwork(inputSize, 10, outputSize);
Accord.Neuro.Learning.DeepNeuralNetworkLearning teacher = new DeepNeuralNetworkLearning(network);
//Train the network
int epoch = 0;
double stopError = 0.1;
int resets = 0;
double minimumErrorReached = double.PositiveInfinity;
while (minimumErrorReached > stopError && resets < 1)
{
network.Randomize();
//teacher.Reset(0.0125);
double errorTrain = double.PositiveInfinity;
for (epoch = 0; epoch < 500000 && errorTrain > stopError; epoch++)
{
errorTrain = teacher.RunEpoch(inputTraining, outputTraining) / (double)trainingSetSize;
//Console.WriteLine("Epoch " + epoch + " = \t" + error);
if (errorTrain < minimumErrorReached)
{
minimumErrorReached = errorTrain;
network.Save("cryptoDESNetwork.mlp");
}
Console.Clear();
Console.WriteLine("Epoch : " + epoch);
Console.WriteLine("Train Set Error : " + errorTrain.ToString("N2"));
double errorTest = teacher.ComputeError(inputTest, outputTest) / (double)inputTest.Count();
Console.WriteLine("Test Set Error : " + errorTest.ToString("N2"));
}
//Console.Write("Reset (" + error+")->");
resets++;
}
Console.WriteLine();
//Compute the reall error
foreach (Triplet tReal in testSet)
{
double[] rIn, rOut, pOut;
byte[] brMsg, brEncrypted, brKey;
tReal.ToBytes(out brMsg, out brEncrypted, out brKey);
tReal.ToIO(out rIn, out rOut);
pOut = network.Compute(rIn);
Triplet tPredicted = new Triplet(rIn, pOut, messageSize);
byte[] bpMsg, bpEncrypted, bpKey;
tPredicted.ToBytes(out bpMsg, out bpEncrypted, out bpKey);
int wrongBytes = 0;
for (int i = 0; i < keySize / 8; i++)
{
if (brKey[i] != bpKey[i])
{
wrongBytes++;
}
}
Console.WriteLine("Wrong bytes = " + wrongBytes);
//Console.WriteLine("REAL = \n" + tReal.GetBytesForm());
//Console.WriteLine("Predicted = \n" + tPredicted.GetBytesForm());
}
Console.ReadKey();
}
public static void Learn(double[][] inputs, double[][] outputs)
{
var n = (int)(count * 0.8);
var testInputs = inputs.Skip(n).ToArray();
var testOutputs = outputs.Skip(n).ToArray();
inputs = inputs.Take(n).ToArray();
outputs = outputs.Take(n).ToArray();
var network = new DeepBeliefNetwork(inputs.First().Length, 10, 10);
new GaussianWeights(network, 0.1).Randomize();
network.UpdateVisibleWeights();
// Setup the learning algorithm.
var teacher = new DeepBeliefNetworkLearning(network)
{
Algorithm = (h, v, i) => new ContrastiveDivergenceLearning(h, v)
{
LearningRate = 0.1,
Momentum = 0.5,
Decay = 0.001,
}
};
// Setup batches of input for learning.
int batchCount = Math.Max(1, inputs.Length / 100);
// Create mini-batches to speed learning.
int[] groups = Classes.Random(inputs.Length, batchCount);
double[][][] batches = inputs.Subgroups(groups);
// Learning data for the specified layer.
double[][][] layerData;
// Unsupervised learning on each hidden layer, except for the output layer.
for (int layerIndex = 0; layerIndex < network.Machines.Count - 1; layerIndex++)
{
teacher.LayerIndex = layerIndex;
layerData = teacher.GetLayerInput(batches);
for (int i = 0; i < 200; i++)
{
double error = teacher.RunEpoch(layerData) / inputs.Length;
if (i % 10 == 0)
{
Console.WriteLine(i + ", Error = " + error);
}
}
}
// Supervised learning on entire network, to provide output classification.
var teacher2 = new BackPropagationLearning(network)
{
LearningRate = 0.1,
Momentum = 0.5
};
// Run supervised learning.
for (int i = 0; i < n; i++)
{
double error = teacher2.RunEpoch(inputs, outputs) / inputs.Length;
if (i % 10 == 0)
{
Console.WriteLine(i + ", Error = " + error);
}
}
// Test the resulting accuracy.
int correct = 0;
for (int i = 0; i < testInputs.Length; i++)
{
double[] outputValues = network.Compute(testInputs[i]);
if (Compare(outputValues, testOutputs[i]))
{
correct++;
}
}
network.Save("deeplearning-countbits.net");
Console.WriteLine("Correct " + correct + "/" + testInputs.Length + ", " + Math.Round(((double)correct / (double)testInputs.Length * 100), 2) + "%");
}
//開始學習
public bool Run()
{
bool IsDone = false;
try
{
FlowDatas db = new FlowDatas();
(double[][] Inputs, double[][] Outputs)
= DeepLearningTools.FlowSampleToLearningData(db.FlowSampleStatistics.Where(c => c.BehaviorNumber != 0).ToArray());
db.Dispose();
//產生DBN網路
DBNetwork = new DeepBeliefNetwork(Inputs.First().Length,
(int)((Inputs.First().Length + Outputs.First().Length) / 1.5),
(int)((Inputs.First().Length + Outputs.First().Length) / 2),
Outputs.First().Length);
//亂數打亂整個網路參數
new GaussianWeights(DBNetwork, 0.1).Randomize();
DBNetwork.UpdateVisibleWeights();
//設定無監督學習組態
DeepBeliefNetworkLearning teacher
= new DeepBeliefNetworkLearning(DBNetwork)
{
Algorithm = (h, v, i) =>
new ContrastiveDivergenceLearning(h, v)
{
LearningRate = 0.01,
Momentum = 0.5,
Decay = 0.001,
}
};
//設置批量輸入學習。
int batchCount1 = Math.Max(1, Inputs.Length / 10);
//創建小批量加速學習。
int[] groups1
= Accord.Statistics.Classes.Random(Inputs.Length, batchCount1);
double[][][] batches = Inputs.Subgroups(groups1);
//學習指定圖層的數據。
double[][][] layerData;
//運行無監督學習。
for (int layerIndex = 0; layerIndex < DBNetwork.Machines.Count - 1; layerIndex++)
{
teacher.LayerIndex = layerIndex;
layerData = teacher.GetLayerInput(batches);
for (int i = 0; i < 200; i++)
{
double error = teacher.RunEpoch(layerData) / Inputs.Length;
if (i % 10 == 0)
{
Console.WriteLine(i + ", Error = " + error);
}
}
}
//對整個網絡進行監督學習，提供輸出分類。
var teacher2 = new ParallelResilientBackpropagationLearning(DBNetwork);
double error1 = double.MaxValue;
//運行監督學習。
for (int i = 0; i < 500; i++)
{
error1 = teacher2.RunEpoch(Inputs, Outputs) / Inputs.Length;
Console.WriteLine(i + ", Error = " + error1);
DBNetwork.Save(Path);
Console.WriteLine("Save Done");
}
DBNetwork.Save(Path);
Console.WriteLine("Save Done");
IsDone = true;
}
catch (Exception ex)
{
Debug.Write(ex.ToString());
}
return(IsDone);
}
private static void Learn(string networkFile, double[][] inputs, double[][] outputs, double trainRate = 0.8)
{
var count = inputs.Length;
var n = (int)(count * trainRate);
var trainedInputs = inputs.Take(n).ToArray();
var trainedOutputs = outputs.Take(n).ToArray();
var testInputs = inputs.Skip(n).ToArray();
var testOutputs = outputs.Skip(n).ToArray();
Console.WriteLine($"trained items: {trainedInputs.Length}, tested items: {testInputs.Length}");
var network = new DeepBeliefNetwork(trainedInputs.First().Length, 10, trainedOutputs.First().Length);
new GaussianWeights(network, 0.1).Randomize();
network.UpdateVisibleWeights();
// Setup the learning algorithm.
var teacher = new DeepBeliefNetworkLearning(network)
{
Algorithm = (h, v, i) => new ContrastiveDivergenceLearning(h, v)
{
LearningRate = 0.1,
Momentum = 0.5,
Decay = 0.001,
}
};
// Setup batches of input for learning.
int batchCount = Math.Max(1, trainedInputs.Length / 100);
// Create mini-batches to speed learning.
int[] groups = Classes.Random(trainedInputs.Length, batchCount);
double[][][] batches = trainedInputs.Subgroups(groups);
// Learning data for the specified layer.
double[][][] layerData;
// Unsupervised learning on each hidden layer, except for the output layer.
for (int layerIndex = 0; layerIndex < network.Machines.Count - 1; layerIndex++)
{
teacher.LayerIndex = layerIndex;
layerData = teacher.GetLayerInput(batches);
for (int i = 0; i < 200; i++)
{
double error = teacher.RunEpoch(layerData) / trainedInputs.Length;
if (i % 10 == 0)
{
Console.WriteLine(i + ", Error = " + error);
}
}
}
// Supervised learning on entire network, to provide output classification.
var teacher2 = new BackPropagationLearning(network)
{
LearningRate = 0.1,
Momentum = 0.5
};
// Run supervised learning.
for (int i = 0; i < Math.Min(2000, n); i++)
{
double error = teacher2.RunEpoch(trainedInputs, trainedOutputs) / trainedInputs.Length;
if (i % 10 == 0)
{
Console.WriteLine(i + ", Error = " + error);
}
}
network.Save(networkFile);
Console.WriteLine($"save network: {networkFile}");
// Test the resulting accuracy.
Test(networkFile, testInputs, testOutputs);
}
/// <summary>
/// DeepBeliefNetworkを保存します。
/// </summary>
/// <param name="network">DeepBeliefNetwork</param>
public void SaveDeepBeliefNetwork(DeepBeliefNetwork network, AiPlayer.Version version)
{
var filePath = string.Format(LearningConfig.LearnerSavePath + @"/{0}_{1}_{2}.bin", DeepBeliefNetworkFileName, DateTime.Now.ToString("yyyyMMddhhmmss"), version.ToString().ToLower());
network.Save(filePath);
}
public void SaveNetwork(String path)
{
network.Save(path);
}
public void SaveNetwork(string name)
{
_network.Save(name);
}