public static void performEvaluatorTest(Net network, int[] expectedOutput, params double[] input)
{
var evaluator = new NetEvaluator(network);
var actual = evaluator.Evaluate(DenseMatrix.Build.DenseOfRowArrays(input));
Assert.AreEqual(1, actual.RowCount);
Assert.AreEqual(expectedOutput.Length, actual.ColumnCount);
for (int i = 0; i < expectedOutput.Length; ++i)
{
int actualInt = (int)(Math.Round(actual[0, i]));
Assert.AreEqual(expectedOutput[i], actualInt);
}
}
public CurrentEvaluator(TrainStorageManager tsm)
{
trainStorageManager = tsm;
NetId = trainStorageManager.LoadDefaultNetName();
if (NetId != null)
{
var net = trainStorageManager.LoadNet(NetId);
var settings = trainStorageManager.LoadTrainSettings(NetId);
if (net != null && settings != null)
{
Evaluator = new NetEvaluator(net);
TrainSettings = settings;
}
}
}
public bool SetDefaultNetwork(string netId)
{
var net = trainStorageManager.LoadNet(netId);
var settings = trainStorageManager.LoadTrainSettings(netId);
if (net == null || settings == null)
{
return(false);
}
NetId = netId;
Evaluator = new NetEvaluator(net);
TrainSettings = settings;
trainData = null;
return(trainStorageManager.SaveDefaultNetName(netId));
}
public void TrainNetwork()
{
stopwatch.Reset();
stopwatch.Start();
sendMessage("Loading training settings.");
trainSettings = storageManager.LoadTrainSettings(netId);
if (trainSettings == null)
{
sendMessage("Train settings file was not found.");
return;
}
using (var db = MausrDb.Create()) {
sendMessage("Initializing learning environment.");
trainData = new TrainData();
int inputSize = trainSettings.InputImgSizePx * trainSettings.InputImgSizePx;
int outputSize = db.Symbols.Count();
var layout = new NetLayout(inputSize, trainSettings.HiddenLayersSizes, outputSize);
network = new Net(layout, new SigomidActivationFunc(), new NetCostFunction());
network.SetOutputMap(db.Symbols.Select(s => s.SymbolId).ToArray());
netEvaluator = new NetEvaluator(network);
var optimizer = createOptimizer(trainSettings);
var trainer = new NetTrainer(network, optimizer, trainSettings.RegularizationLambda);
unpackedCoefs = network.Layout.AllocateCoefMatrices();
sendMessage("Preparing inputs and outputs.");
prepareInOut(db);
sendMessage(string.Format("Learning of {0} samples started.", trainInputs.RowCount));
bool converged = trainer.TrainBatch(trainInputs, trainSettings.BatchSize, trainSettings.LearnRounds,
trainOutIds, trainSettings.InitSeed, trainSettings.MinDerivCompMaxMagn, trainIterationCallback, job.CancellationToken);
if (job.CancellationToken.IsCancellationRequested)
{
sendMessage("Training {0}.", job.Canceled ? "canceled" : "stopped");
}
else
{
sendMessage("Training done ({0}converged).", converged ? "" : "not ");
}
if (!job.Canceled)
{
sendMessage("Saving trained data.");
if (!storageManager.SaveNet(netId, network))
{
sendMessage("Failed to save the network.");
}
if (!storageManager.SaveTrainData(netId, trainData))
{
sendMessage("Failed to save training data.");
}
sendMessage("Saving results visualization.");
if (!createAndSaveResultsVis(3, 0.01, 40))
{
sendMessage("Failed visualize results.");
}
}
stopwatch.Stop();
}
sendMessage("All done.");
}