public static void main(String[] args) {
Logging.stopConsoleLogging();
NeuralDataSet trainingSet = new BasicNeuralDataSet(XOR_INPUT, XOR_IDEAL);
BasicNetwork network = EncogUtility.simpleFeedForward(2, 4, 0, 1, false);
ResilientPropagation train = new ResilientPropagation(network, trainingSet);
train.addStrategy(new RequiredImprovementStrategy(5));
System.out.println("Perform initial train.");
EncogUtility.trainToError(train, network, trainingSet, 0.01);
TrainingContinuation cont = train.pause();
System.out.println(
Arrays.toString((double[]) cont.getContents().get(ResilientPropagation.LAST_GRADIENTS)));
System.out.println(
Arrays.toString((double[]) cont.getContents().get(ResilientPropagation.UPDATE_VALUES)));
try {
SerializeObject.save("resume.ser", cont);
cont = (TrainingContinuation) SerializeObject.load("resume.ser");
} catch (Exception ex) {
ex.printStackTrace();
}
System.out.println(
"Now trying a second train, with continue from the first. Should stop after one iteration");
ResilientPropagation train2 = new ResilientPropagation(network, trainingSet);
train2.resume(cont);
EncogUtility.trainToError(train2, network, trainingSet, 0.01);
}
public void recognizer(List<File> files) {
FeatureExtractor fe = new FeatureExtractor();
MLDataSet trainingSet = new BasicMLDataSet();
for (File f : files) {
// System.out.println(f.getAbsolutePath());
List<double[]> data;
try {
data = fe.fileProcessor(f);
MLData mldataIn = new BasicMLData(data.get(0));
double[] out = new double[NUM_OUT];
Integer index = new Integer(Labeler.getLabel(f));
// System.out.println(index+""+data.get(0));
out[index] = 1.;
System.out.println(out.toString());
MLData mldataout = new BasicMLData(out);
trainingSet.add(mldataIn, mldataout);
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
BasicNetwork network = new BasicNetwork();
network.addLayer(new BasicLayer(NUM_IN));
network.addLayer(new BasicLayer(new ActivationSigmoid(), true, 4 * NUM_IN));
// network.addLayer(new BasicLayer(new ActivationSigmoid(), true, 2 * NUM_IN));
network.addLayer(new BasicLayer(new ActivationSigmoid(), false, NUM_OUT));
network.getStructure().finalizeStructure();
network.reset();
// train the neural network
ResilientPropagation train = new ResilientPropagation(network, trainingSet);
System.out.println("Training Set: " + trainingSet.size());
int epoch = 1;
do {
train.iteration();
System.out.println("Epoch:" + epoch + " Error-->" + train.getError());
epoch++;
} while (train.getError() > 0.001);
train.finishTraining();
// test the neural network
System.out.println("Neural Network Results:");
for (MLDataPair pair : trainingSet) {
final MLData output = network.compute(pair.getInput());
System.out.println(
"actual-->" + Labeler.getWord(output) + ", ideal-->" + Labeler.getWord(pair.getIdeal()));
}
Encog.getInstance().shutdown();
}
public static double evaluateMPROP(BasicNetwork network, NeuralDataSet data) {
ResilientPropagation train = new ResilientPropagation(network, data);
train.setNumThreads(0);
long start = System.currentTimeMillis();
System.out.println("Training 20 Iterations with MPROP");
for (int i = 1; i <= 20; i++) {
train.iteration();
System.out.println("Iteration #" + i + " Error:" + train.getError());
}
train.finishTraining();
long stop = System.currentTimeMillis();
double diff = ((double) (stop - start)) / 1000.0;
System.out.println("MPROP Result:" + diff + " seconds.");
System.out.println("Final MPROP error: " + network.calculateError(data));
return diff;
}
/**
* The main method.
*
* @param args No arguments are used.
*/
public static void main(final String args[]) {
// create a neural network, without using a factory
BasicNetwork network = new BasicNetwork();
network.addLayer(new BasicLayer(null, true, 2));
network.addLayer(new BasicLayer(new ActivationSigmoid(), true, 3));
network.addLayer(new BasicLayer(new ActivationSigmoid(), false, 1));
network.getStructure().finalizeStructure();
network.reset();
// create training data
MLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
// train the neural network
final ResilientPropagation train = new ResilientPropagation(network, trainingSet);
int epoch = 1;
do {
train.iteration();
System.out.println("Epoch #" + epoch + " Error:" + train.getError());
epoch++;
} while (train.getError() > 0.01);
train.finishTraining();
// test the neural network
System.out.println("Neural Network Results:");
for (MLDataPair pair : trainingSet) {
final MLData output = network.compute(pair.getInput());
System.out.println(
pair.getInput().getData(0)
+ ","
+ pair.getInput().getData(1)
+ ", actual="
+ output.getData(0)
+ ",ideal="
+ pair.getIdeal().getData(0));
}
Encog.getInstance().shutdown();
}
private void processTrain() throws IOException {
final String strMode = getArg("mode");
final String strMinutes = getArg("minutes");
final String strStrategyError = getArg("strategyerror");
final String strStrategyCycles = getArg("strategycycles");
System.out.println("Training Beginning... Output patterns=" + this.outputCount);
final double strategyError = Double.parseDouble(strStrategyError);
final int strategyCycles = Integer.parseInt(strStrategyCycles);
final ResilientPropagation train = new ResilientPropagation(this.network, this.training);
train.addStrategy(new ResetStrategy(strategyError, strategyCycles));
if (strMode.equalsIgnoreCase("gui")) {
EncogUtility.trainDialog(train, this.network, this.training);
} else {
final int minutes = Integer.parseInt(strMinutes);
EncogUtility.trainConsole(train, this.network, this.training, minutes);
}
System.out.println("Training Stopped...");
}
