ffn.hpp

Go to the documentation of this file.

#ifndef MLPACK_METHODS_ANN_FFN_HPP
#define MLPACK_METHODS_ANN_FFN_HPP

#include <mlpack/prereqs.hpp>

#include "visitor/delete_visitor.hpp"
#include "visitor/delta_visitor.hpp"
#include "visitor/output_height_visitor.hpp"
#include "visitor/output_parameter_visitor.hpp"
#include "visitor/output_width_visitor.hpp"
#include "visitor/reset_visitor.hpp"
#include "visitor/weight_size_visitor.hpp"
#include "visitor/copy_visitor.hpp"

#include "init_rules/network_init.hpp"

#include <mlpack/methods/ann/layer/layer_types.hpp>
#include <mlpack/methods/ann/layer/layer.hpp>
#include <mlpack/methods/ann/init_rules/random_init.hpp>
#include <mlpack/core/optimizers/rmsprop/rmsprop.hpp>

namespace mlpack {
namespace ann  {

template<
  typename OutputLayerType = NegativeLogLikelihood<>,
  typename InitializationRuleType = RandomInitialization,
  typename... CustomLayers
>
class FFN
{
 public:
  using NetworkType = FFN<OutputLayerType, InitializationRuleType>;

  FFN(OutputLayerType outputLayer = OutputLayerType(),
      InitializationRuleType initializeRule = InitializationRuleType());

  FFN(const FFN&);

  FFN(FFN&&);

  FFN& operator = (FFN);

  ~FFN();

  template<typename OptimizerType>
  void Train(arma::mat predictors,
             arma::mat responses,
             OptimizerType& optimizer);

  template<typename OptimizerType = mlpack::optimization::RMSProp>
  void Train(arma::mat predictors, arma::mat responses);

  void Predict(arma::mat predictors, arma::mat& results);

  double Evaluate(const arma::mat& parameters);

  double Evaluate(const arma::mat& parameters,
                  const size_t begin,
                  const size_t batchSize,
                  const bool deterministic);

  double Evaluate(const arma::mat& parameters,
                  const size_t begin,
                  const size_t batchSize);

  template<typename GradType>
  double EvaluateWithGradient(const arma::mat& parameters, GradType& gradient);

  template<typename GradType>
  double EvaluateWithGradient(const arma::mat& parameters,
                              const size_t begin,
                              GradType& gradient,
                              const size_t batchSize,
                              const bool deterministic);

  template<typename GradType>
  double EvaluateWithGradient(const arma::mat& parameters,
                              const size_t begin,
                              GradType& gradient,
                              const size_t batchSize);

  void Gradient(const arma::mat& parameters,
                const size_t begin,
                arma::mat& gradient,
                const size_t batchSize);

  void Shuffle();

  /*
   * Add a new module to the model.
   *
   * @param args The layer parameter.
   */
  template <class LayerType, class... Args>
  void Add(Args... args) { network.push_back(new LayerType(args...)); }

  /*
   * Add a new module to the model.
   *
   * @param layer The Layer to be added to the model.
   */
  void Add(LayerTypes<CustomLayers...> layer) { network.push_back(layer); }

  size_t NumFunctions() const { return numFunctions; }

  const arma::mat& Parameters() const { return parameter; }
  arma::mat& Parameters() { return parameter; }

  const arma::mat& Responses() const { return responses; }
  arma::mat& Responses() { return responses; }

  const arma::mat& Predictors() const { return predictors; }
  arma::mat& Predictors() { return predictors; }

  void ResetParameters();

  template<typename Archive>
  void serialize(Archive& ar, const unsigned int /* version */);

  void Forward(arma::mat inputs, arma::mat& results);

  void Forward(arma::mat inputs,
               arma::mat& results,
               const size_t begin,
               const size_t end);

  double Backward(arma::mat targets, arma::mat& gradients);

 private:
  // Helper functions.
  void Forward(arma::mat&& input);

  void ResetData(arma::mat predictors, arma::mat responses);

  void Backward();

  void Gradient(arma::mat&& input);

  void ResetDeterministic();

  void ResetGradients(arma::mat& gradient);

  void Swap(FFN& network);

  OutputLayerType outputLayer;

  InitializationRuleType initializeRule;

  size_t width;

  size_t height;

  bool reset;

  std::vector<LayerTypes<CustomLayers...> > network;

  arma::mat predictors;

  arma::mat responses;

  arma::mat parameter;

  size_t numFunctions;

  arma::mat error;

  arma::mat currentInput;

  DeltaVisitor deltaVisitor;

  OutputParameterVisitor outputParameterVisitor;

  WeightSizeVisitor weightSizeVisitor;

  OutputWidthVisitor outputWidthVisitor;

  OutputHeightVisitor outputHeightVisitor;

  ResetVisitor resetVisitor;

  DeleteVisitor deleteVisitor;

  bool deterministic;

  arma::mat delta;

  arma::mat inputParameter;

  arma::mat outputParameter;

  arma::mat gradient;

  CopyVisitor<CustomLayers...> copyVisitor;
}; // class FFN

} // namespace ann
} // namespace mlpack

namespace boost {
namespace serialization {

template<typename OutputLayerType,
         typename InitializationRuleType,
         typename... CustomLayer>
struct version<
    mlpack::ann::FFN<OutputLayerType, InitializationRuleType, CustomLayer...>>
{
  BOOST_STATIC_CONSTANT(int, value = 1);
};

} // namespace serialization
} // namespace boost

// Include implementation.
#include "ffn_impl.hpp"

#endif