public double TrainContinue(Optimizer optimizer, IDataEnumerator data, int batch)
{
optimizer.network = autoencoder;
if (background.layers.Count != 0)
{
NetworkEnumerator nEm = new NetworkEnumerator(background, data);
double err = optimizer.TrainBatchContinue(nEm, batch, 1).Last();
return(err);
}
else
{
double err = optimizer.TrainBatchContinue(data, batch, 1).Last();
return(err);
}
}
public static KeyValuePair <double, double> Action(Network network, Optimizer optimizer, IDataEnumerator data, IDataEnumerator val, int count, int batch = 32)
{
DateTime start;
start = DateTime.Now;
int layers = network.layers.Count;
for (int i = 0; i < layers - 1; i++)
{
Network background;
Network autoencoder;
if (!network.layers[i].ITrained)
{
continue;
}
background = new Network();
for (int j = 0; j < i; j++)
{
background.layers.Add(network.layers[j]);
}
autoencoder = new Network();
autoencoder.layers.Add(network.layers[i]);
autoencoder.layers.Add(network.layers[i].Mirror);
background.CompileOnlyError();
autoencoder.CompileOnlyError();
NetworkEnumerator nEm = new NetworkEnumerator(background, data);
MirrorEnumerator Mem = new MirrorEnumerator(nEm);
optimizer.network = autoencoder;
double err = optimizer.TrainBatch(Mem, batch, 1).Last();
for (int k = 1; k < count; k++)
{
Console.Write("{0} ", k);
optimizer.TrainBatchContinue(Mem, batch, 1);
if ((DateTime.Now - start).TotalMinutes >= 10)
{
System.IO.File.WriteAllText("autosave_" + i + "_" + k + ".neural", network.SaveJSON());
Console.WriteLine("Save to " + "autosave_" + i + "_" + k + ".neural");
start = DateTime.Now;
}
}
Console.WriteLine("Trained {0} with error {1}", i, (float)err);
}
return(network.GetError(val));
}
public double TrainContinue(Optimizer optimizer, IDataEnumerator data, int batch)
{
NetworkEnumerator nEm = new NetworkEnumerator(background, data);
MirrorEnumerator Mem = new MirrorEnumerator(nEm);
optimizer.network = autoencoder;
double err = optimizer.TrainBatchContinue(Mem, batch, 1).Last();
return(err);
}
public void Learn(int batch, int steps_per_epochs, int epochs = 1)
{
optimizer.Init(batch);
for (int ep = 0; ep < epochs; ep++)
{
var err = optimizer.TrainBatchContinue(train_data, batch, steps_per_epochs);
double err_mean = 0;
for (int i = 0; i < err.Length; i++)
{
err_mean += err[i];
}
err_mean /= err.Length;
Console.WriteLine("Epoch error: {0}", err_mean);
metrics_values["err"] = err_mean;
double[] m_vals = optimizer.network.GetMeanMetrics(train_data, metrics);
for (int i = 0; i < metrics.Count; i++)
{
Console.WriteLine("Epoch {0}: {1}", metrics[i].Name, m_vals[i]);
metrics_values[metrics[i].Name] = m_vals[i];
}
if (val_data != null)
{
var val_err = optimizer.network.GetError(val_data);
Console.WriteLine("Validation error: {0}", val_err.Key);
metrics_values["val_err"] = val_err.Key;
m_vals = optimizer.network.GetMeanMetrics(val_data, metrics);
for (int i = 0; i < metrics.Count; i++)
{
Console.WriteLine("Validation {0}: {1}", metrics[i].Name, m_vals[i]);
metrics_values["val_" + metrics[i].Name] = m_vals[i];
}
}
for (int i = 0; i < callbacks.Count; i++)
{
callbacks[i].Action(this);
}
}
}
public KeyValuePair <double, double> TrainBatch(Optimizer optimizer, IDataEnumerator data, IDataEnumerator val, int count, int batch = 32)
{
DateTime start = DateTime.Now;
NetworkEnumerator nEm = new NetworkEnumerator(background, data);
optimizer.network = autoencoder;
optimizer.TrainBatch(nEm, batch, 1).Last();
for (int k = 1; k < count; k++)
{
optimizer.TrainBatchContinue(nEm, batch, 1);
if ((DateTime.Now - start).TotalMinutes >= 10)
{
System.IO.File.WriteAllText("autosave_" + k + ".neural", network.SaveJSON());
start = DateTime.Now;
}
}
return(autoencoder.GetError(val));
}