我在返回一个列表时遇到问题,这样我就可以将它保存在一个文件中,然后加载它,以便保存权重并再次检索。抱歉这个愚蠢的问题,但我如何从 SaveNetwork 方法调用和保存权重列表,我无法真正掌握我能做些什么来解决这个问题。我知道我还没有创建列表权重的新实例,但是如果我这样做,我将丢失存储在此列表中的当前权重。
public class Neuron
{
private double bias; // Bias value.
private double error; // Sum of error.
private double input; // Sum of inputs.
private double gradient = 5; // Steepness of sigmoid curve.
private double learnRate = 0.01; // Learning rate.
private double output = double.MinValue; // Preset value of neuron.
public List<Weight> weights; // Collection of weights to inputs.
public Neuron() { }
public Neuron(Layer inputs, Random rnd)
{
weights = new List<Weight>();
foreach (Neuron input in inputs)
{
Weight w = new Weight();
w.Input = input;
w.Value = rnd.NextDouble() * 2 - 1;
weights.Add(w);
}
}
public static void SaveNetwork(string path)
{
FileStream FS = new FileStream(path, FileMode.Create);
BinaryFormatter BF = new BinaryFormatter();
BF.Serialize(FS,/* The List in this case is List weights ***/ );
FS.Close();
}
public void LoadNetwork(string path)
{
FileStream FS = new FileStream(path, FileMode.Open);
BinaryFormatter BF = new BinaryFormatter();
weights = (List<Weight>)BF.Deserialize(FS);
FS.Close();
}
对此进行更新——我使用了与下面的代码类似的层次结构,该代码取自 Dynamic Notions 博客,该博客解释了如何创建神经网络。我想要实现的是,在神经网络学会之后,我希望能够保存列表权重,以便在程序停止时我能够加载权重以跳过网络的训练。所以基本上从类网络我想访问这个在神经类中的列表,而不用新方法创建一个新实例,否则我只会得到一个空列表。希望它更清楚,因为我不知道如何更好地解释它......非常感谢
public class Network{
//some variables..
[STAThread]
static void Main()
{
new Network();
}
public Network()
{
LoadPatterns();
Initialise();
Train();
Test();
}
private void Train()
{
double error;
do
{
error = 0;
foreach (Pattern pattern in _patterns)
{
double delta = pattern.Output - Activate(pattern);
AdjustWeights(delta);
error += Math.Pow(delta, 2);
}
Console.WriteLine("Iteration {0}\tError {1:0.000}", _iteration, error);
_iteration++;
if (_iteration > _restartAfter) Initialise();
} while (error > 0.1);
}
private void Test()
{
}
// Must be able to call and save the List<Weight> From here
private double Activate(Pattern pattern)
{
}
private void AdjustWeights(double delta)
{
_output.AdjustWeights(delta);
foreach (Neuron neuron in _hidden)
{
neuron.AdjustWeights(_output.ErrorFeedback(neuron));
}
}
private void Initialise()
{
_inputs = new Layer(_inputDims);
_hidden = new Layer(_hiddenDims, _inputs, _rnd);
_output = new Neuron(_hidden, _rnd);
_iteration = 0;
Console.WriteLine("Network Initialised");
}
private void LoadPatterns()
{
}
}
public class Layer : List<Neuron>
{
public Layer(int size)
{
for (int i = 0; i < size; i++)
base.Add(new Neuron());
}
public Layer(int size, Layer layer, Random rnd)
{
for (int i = 0; i < size; i++)
base.Add(new Neuron(layer, rnd)); //this is where Neuron class is instantiated
}
}
public class Neuron
{
//some other vars
private List<Weight> _weights; // This is the list in question.
public Neuron() { }
public Neuron(Layer inputs, Random rnd)
{
_weights = new List<Weight>();
foreach (Neuron input in inputs)
{
Weight w = new Weight();
w.Input = input;
w.Value = rnd.NextDouble() * 2 - 1;
_weights.Add(w);
}
}
}
public class Weight
{
public Neuron Input;
public double Value;
}