Examples of com.github.neuralnetworks.training.DNNLayerTrainer$LayerTrainingFinished

Package com.github.neuralnetworks.training

Examples of com.github.neuralnetworks.training.DNNLayerTrainer$LayerTrainingFinished

com.github.neuralnetworks.training.DNNLayerTrainer
Triggered when a nested neural network has finished training

  TrainingInputProvider trainInputProvider = new IrisInputProvider(150, 1500000, new IrisTargetMultiNeuronOutputConverter(), false, true, false);
  TrainingInputProvider testInputProvider = new IrisInputProvider(1, 150, new IrisTargetMultiNeuronOutputConverter(), false, true, false);
  MultipleNeuronsOutputError error = new MultipleNeuronsOutputError();


  // deep trainer
  DNNLayerTrainer deepTrainer = TrainerFactory.dnnLayerTrainer(sae, map, trainInputProvider, testInputProvider, error);


  // execution mode
  Environment.getInstance().setExecutionMode(EXECUTION_MODE.SEQ);


  // layerwise pre-training
  deepTrainer.train();


  // fine tuning backpropagation
  BackPropagationTrainer<?> bpt = TrainerFactory.backPropagation(sae, trainInputProvider, testInputProvider, new MultipleNeuronsOutputError(), new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f)), 0.01f, 0.5f, 0f, 0f);


  // log data

View Full Code Here

  Map<NeuralNetwork, OneStepTrainer<?>> map = new HashMap<>();
  map.put(firstNN, firstTrainer);
  map.put(lastNN, secondTrainer);


  // deep trainer
  DNNLayerTrainer deepTrainer = TrainerFactory.dnnLayerTrainer(sae, map, trainInputProvider, testInputProvider, null);


  // layerwise pre-training
  deepTrainer.train();


  // fine tuning backpropagation
  BackPropagationTrainer<?> bpt = TrainerFactory.backPropagation(sae, trainInputProvider, testInputProvider, new MultipleNeuronsOutputError(), new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f), 0.5f), 0.02f, 0.7f, 0f, 0f, 0f, 150, 1, 2000);


  // log data

View Full Code Here


  Map<NeuralNetwork, OneStepTrainer<?>> layerTrainers = new HashMap<>();
  layerTrainers.put(firstRBM, firstTrainer);
  layerTrainers.put(secondRBM, secondTrainer);


  DNNLayerTrainer trainer = TrainerFactory.dnnLayerTrainer(dbn, layerTrainers, inputProvider, null, null);
  trainer.train();
  
  assertEquals(0.2 + 0.13203661, cg1.get(0, 0), 0.00001);
  assertEquals(0.4 - 0.22863509,  cg1.get(0, 1), 0.00001);
  assertEquals(-0.5 + 0.12887852, cg1.get(0, 2), 0.00001);
  assertEquals(-0.3 + 0.26158813, cg1.get(1, 0), 0.00001);

View Full Code Here


  Map<NeuralNetwork, OneStepTrainer<?>> layerTrainers = new HashMap<>();
  layerTrainers.put(firstRBM, firstTrainer);
  layerTrainers.put(secondRBM, secondTrainer);
  
  DNNLayerTrainer trainer = TrainerFactory.dnnLayerTrainer(dbn, layerTrainers, inputProvider, null, null);
  trainer.train();
  
  assertEquals(0.2 + 0.13203661, cg1.get(0, 0), 0.00001);
  assertEquals(0.4 - 0.22863509,  cg1.get(0, 1), 0.00001);
  assertEquals(-0.5 + 0.12887852, cg1.get(0, 2), 0.00001);
  assertEquals(-0.3 + 0.26158813, cg1.get(1, 0), 0.00001);

View Full Code Here


  Map<NeuralNetwork, OneStepTrainer<?>> layerTrainers = new HashMap<>();
  layerTrainers.put(firstRBM, firstTrainer);
  layerTrainers.put(secondRBM, secondTrainer);


  DNNLayerTrainer trainer = TrainerFactory.dnnLayerTrainer(dbn, layerTrainers, inputProvider, null, null);
  trainer.train();
  
  assertEquals(0.2 + 0.13203661, cg1.get(0, 0), 0.00001);
  assertEquals(0.4 - 0.22863509,  cg1.get(0, 1), 0.00001);
  assertEquals(-0.5 + 0.12887852, cg1.get(0, 2), 0.00001);
  assertEquals(-0.3 + 0.26158813, cg1.get(1, 0), 0.00001);

View Full Code Here


  Map<NeuralNetwork, OneStepTrainer<?>> layerTrainers = new HashMap<>();
  layerTrainers.put(firstRBM, firstTrainer);
  layerTrainers.put(secondRBM, secondTrainer);


  DNNLayerTrainer trainer = TrainerFactory.dnnLayerTrainer(dbn, layerTrainers, inputProvider, null, null);
  trainer.train();
  
  assertEquals(0.2 + 0.13203661, cg1.get(0, 0), 0.00001);
  assertEquals(0.4 - 0.22863509,  cg1.get(0, 1), 0.00001);
  assertEquals(-0.5 + 0.12887852, cg1.get(0, 2), 0.00001);
  assertEquals(-0.3 + 0.26158813, cg1.get(1, 0), 0.00001);

View Full Code Here

TOP

Related Classes of com.github.neuralnetworks.training.DNNLayerTrainer$LayerTrainingFinished

com.github.neuralnetworks.samples.test.IrisTest

com.github.neuralnetworks.test.DNNTest

com.github.neuralnetworks.training.events.TrainingFinishedEvent

com.github.neuralnetworks.training.events.TrainingStartedEvent

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.