modularization/src/api/perception_lidar_cnn_segmentation/caffe/layers/log_layer.hpp

#ifndef CAFFE_LOG_LAYER_HPP_
#define CAFFE_LOG_LAYER_HPP_

#include <vector>

#include "caffe/blob.hpp"
#include "caffe/layer.hpp"
#include "caffe/proto/caffe.pb.h"

#include "caffe/layers/neuron_layer.hpp"

namespace caffe {

/**
 * @brief Computes @f$ y = log_{\gamma}(\alpha x + \beta) @f$,
 *        as specified by the scale @f$ \alpha @f$, shift @f$ \beta @f$,
 *        and base @f$ \gamma @f$.
 */
template <typename Dtype>
class LogLayer : public NeuronLayer<Dtype> {
 public:
  /**
   * @param param provides LogParameter log_param,
   *     with LogLayer options:
   *   - scale (\b optional, default 1) the scale @f$ \alpha @f$
   *   - shift (\b optional, default 0) the shift @f$ \beta @f$
   *   - base (\b optional, default -1 for a value of @f$ e \approx 2.718 @f$)
   *         the base @f$ \gamma @f$
   */
  explicit LogLayer(const LayerParameter& param)
      : NeuronLayer<Dtype>(param) {}
  virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);

  virtual inline const char* type() const { return "Log"; }

 protected:
  /**
   * @param bottom input Blob vector (length 1)
   *   -# @f$ (N \times C \times H \times W) @f$
   *      the inputs @f$ x @f$
   * @param top output Blob vector (length 1)
   *   -# @f$ (N \times C \times H \times W) @f$
   *      the computed outputs @f$
   *        y = log_{\gamma}(\alpha x + \beta)
   *      @f$
   */
  virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);
  virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);

  /**
   * @brief Computes the error gradient w.r.t. the exp inputs.
   *
   * @param top output Blob vector (length 1), providing the error gradient with
   *      respect to the outputs
   *   -# @f$ (N \times C \times H \times W) @f$
   *      containing error gradients @f$ \frac{\partial E}{\partial y} @f$
   *      with respect to computed outputs @f$ y @f$
   * @param propagate_down see Layer::Backward.
   * @param bottom input Blob vector (length 1)
   *   -# @f$ (N \times C \times H \times W) @f$
   *      the inputs @f$ x @f$; Backward fills their diff with
   *      gradients @f$
   *        \frac{\partial E}{\partial x} =
   *            \frac{\partial E}{\partial y} y \alpha \log_e(gamma)
   *      @f$ if propagate_down[0]
   */
  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);

  Dtype base_scale_;
  Dtype input_scale_, input_shift_;
  Dtype backward_num_scale_;
};

}  // namespace caffe

#endif  // CAFFE_LOG_LAYER_HPP_