Examples of ValuesProvider

com.github.neuralnetworks.calculation.ValuesProvider
Provides Matrix instances for the layers of the network. It ensures that the instances are reused.
com.github.neuralnetworks.calculation.memory.ValuesProvider
Something similar to tensor factory

Examples of com.github.neuralnetworks.calculation.memory.ValuesProvider

  cg1.set(0.8f, 0, 1);
  cg1.set(0.4f, 1, 0);
  cg1.set(0.6f, 1, 1);




  ValuesProvider vp = TensorFactory.tensorProvider(rbm, 1, true);
  Matrix visible = vp.get(rbm.getVisibleLayer());
  visible.set(0.35f, 0, 0);
  visible.set(0.9f, 1, 0);


  Set<Layer> calculated = new HashSet<Layer>();
  calculated.add(rbm.getVisibleLayer());
  rbm.getLayerCalculator().calculate(rbm, rbm.getHiddenLayer(), calculated, vp);


  Matrix hidden = vp.get(rbm.getHiddenLayer());
  assertEquals(0.68, hidden.get(0, 0), 0.01);
  assertEquals(0.6637, hidden.get(1, 0), 0.01);
    }

View Full Code Here

Examples of com.github.neuralnetworks.calculation.memory.ValuesProvider

  cg1.set(0.1f, 0, 0);
  cg1.set(0.8f, 1, 0);
  cg1.set(0.4f, 0, 1);
  cg1.set(0.6f, 1, 1);
  
  ValuesProvider vp = TensorFactory.tensorProvider(rbm, 1, true);
  Matrix hidden = vp.get(rbm.getHiddenLayer());
  hidden.set(0.35f, 0, 0);
  hidden.set(0.9f, 1, 0);
  
  Set<Layer> calculated = new HashSet<Layer>();
  calculated.add(rbm.getHiddenLayer());
  rbm.getLayerCalculator().calculate(rbm, rbm.getVisibleLayer(), calculated, vp);
  
  Matrix visible = vp.get(rbm.getVisibleLayer());
  assertEquals(0.68, visible.get(0, 0), 0.01);
  assertEquals(0.6637, visible.get(1, 0), 0.01);
    }

View Full Code Here

Examples of com.github.neuralnetworks.calculation.memory.ValuesProvider


  Matrix cgb1 = rbm.getHiddenBiasConnections().getWeights();
  cgb1.set(-0.4f, 0, 0);
  cgb1.set(0.2f, 1, 0);


  ValuesProvider vp = TensorFactory.tensorProvider(rbm, 1, true);
  Matrix visible = vp.get(rbm.getVisibleLayer());
  visible.set(1f, 0, 0);
  visible.set(0f, 1, 0);
  visible.set(1f, 2, 0);


  Set<Layer> calculated = new HashSet<Layer>();
  calculated.add(rbm.getVisibleLayer());
  rbm.getLayerCalculator().calculate(rbm, rbm.getHiddenLayer(), calculated, vp);


  Matrix hidden = vp.get(rbm.getHiddenLayer());
  assertEquals(0.332, hidden.get(0, 0), 0.001);
  assertEquals(0.525, hidden.get(1, 0), 0.001);
    }

View Full Code Here

Examples of com.github.neuralnetworks.calculation.memory.ValuesProvider


  Matrix cgb1 = rbm.getVisibleBiasConnections().getWeights();
  cgb1.set(-0.4f, 0, 0);
  cgb1.set(0.2f, 1, 0);


  ValuesProvider vp = TensorFactory.tensorProvider(rbm, 1, true);
  Matrix hidden = vp.get(rbm.getHiddenLayer());
  hidden.set(1f, 0, 0);
  hidden.set(0f, 1, 0);
  hidden.set(1f, 2, 0);


  Set<Layer> calculated = new HashSet<Layer>();
  calculated.add(rbm.getHiddenLayer());
  rbm.getLayerCalculator().calculate(rbm, rbm.getVisibleLayer(), calculated, vp);


  Matrix visible = vp.get(rbm.getVisibleLayer());
  assertEquals(0.332, visible.get(0, 0), 0.001);
  assertEquals(0.525, visible.get(1, 0), 0.001);
    }

View Full Code Here

Examples of com.github.neuralnetworks.calculation.memory.ValuesProvider

     * @param miniBatchSize
     * @param useSharedMemory
     * @return Tensor provider based on neural network
     */
    public static ValuesProvider tensorProvider(NeuralNetwork nn, int miniBatchSize, boolean useSharedMemory) {
  ValuesProvider result = new ValuesProvider(useSharedMemory);


  Map<Layer, Set<int[]>> dims = getLayersDimensions(nn, miniBatchSize);


  // create tensors
  List<Layer> layers = new ArrayList<>(dims.keySet());
  for (int i = 0; i < layers.size(); i++) {
      Layer l = layers.get(i);
      for (int[] d : dims.get(l)) {
    result.add(l, true, d);
      }
  }


  return result;
    }

View Full Code Here

Examples of com.github.neuralnetworks.calculation.memory.ValuesProvider

     * @param useSharedMemory
     * @param nns
     * @return Tensor provider based on multiple neural networks - common layers use shared tensors
     */
    public static ValuesProvider tensorProvider(int miniBatchSize, boolean useSharedMemory, NeuralNetwork... nns) {
  ValuesProvider result = new ValuesProvider(useSharedMemory);


  for (NeuralNetwork nn : nns) {
      Map<Layer, Set<int[]>> dims = getLayersDimensions(nn, miniBatchSize);
      
      // create tensors
      List<Layer> layers = new ArrayList<>(dims.keySet());
      for (int i = 0; i < layers.size(); i++) {
    Layer l = layers.get(i);
    for (int[] d : dims.get(l)) {
        if (result.get(l, d) == null) {
      result.add(l, true, d);
        }
    }
      }
  }

View Full Code Here

Examples of com.github.neuralnetworks.calculation.memory.ValuesProvider

     * @return Tensor provider based on neural network
     */
    public static ValuesProvider tensorProvider(ValuesProvider sibling, NeuralNetwork nn) {
  Map<Layer, Set<int[]>> dims = getLayersDimensions(nn, batchSize(sibling));
  
  ValuesProvider result = new ValuesProvider(sibling);


  // create tensors
  List<Layer> layers = new ArrayList<>(dims.keySet());
  for (int i = 0; i < layers.size(); i++) {
      Layer l = layers.get(i);
      for (int[] d : dims.get(l)) {
    result.add(l, true, d);
      }
  }
  
  return result;
    }

View Full Code Here

0 1 2 3 4

TOP

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.