recurrent_layer.hpp

#ifndef CAFFE_RECURRENT_LAYER_HPP_
#define CAFFE_RECURRENT_LAYER_HPP_

#include <string>
#include <utility>
#include <vector>

#include "caffe/blob.hpp"
#include "caffe/common.hpp"
#include "caffe/layer.hpp"
#include "caffe/net.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/util/format.hpp"

namespace caffe {

template <typename Dtype> class RecurrentLayer;

template <typename Dtype>
class RecurrentLayer : public Layer<Dtype> {
 public:
  explicit RecurrentLayer(const LayerParameter& param)
      : Layer<Dtype>(param) {}
  virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);
  virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);
  virtual void Reset();

  virtual inline const char* type() const { return "Recurrent"; }
  virtual inline int MinBottomBlobs() const {
    int min_bottoms = 2;
    if (this->layer_param_.recurrent_param().expose_hidden()) {
      vector<string> inputs;
      this->RecurrentInputBlobNames(&inputs);
      min_bottoms += inputs.size();
    }
    return min_bottoms;
  }
  virtual inline int MaxBottomBlobs() const { return MinBottomBlobs() + 1; }
  virtual inline int ExactNumTopBlobs() const {
    int num_tops = 1;
    if (this->layer_param_.recurrent_param().expose_hidden()) {
      vector<string> outputs;
      this->RecurrentOutputBlobNames(&outputs);
      num_tops += outputs.size();
    }
    return num_tops;
  }

  virtual inline bool AllowForceBackward(const int bottom_index) const {
    // Can't propagate to sequence continuation indicators.
    return bottom_index != 1;
  }

 protected:
  virtual void FillUnrolledNet(NetParameter* net_param) const = 0;

  virtual void RecurrentInputBlobNames(vector<string>* names) const = 0;

  virtual void RecurrentInputShapes(vector<BlobShape>* shapes) const = 0;

  virtual void RecurrentOutputBlobNames(vector<string>* names) const = 0;

  virtual void OutputBlobNames(vector<string>* names) const = 0;

  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);
  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);

  shared_ptr<Net<Dtype> > unrolled_net_;

  int N_;

  int T_;

  bool static_input_;

  int last_layer_index_;

  bool expose_hidden_;

  vector<Blob<Dtype>* > recur_input_blobs_;
  vector<Blob<Dtype>* > recur_output_blobs_;
  vector<Blob<Dtype>* > output_blobs_;
  Blob<Dtype>* x_input_blob_;
  Blob<Dtype>* x_static_input_blob_;
  Blob<Dtype>* cont_input_blob_;
};

}  // namespace caffe

#endif  // CAFFE_RECURRENT_LAYER_HPP_