layer.hpp

#ifndef CAFFE_LAYER_H_
#define CAFFE_LAYER_H_
 
#include <algorithm>
#include <string>
#include <vector>
 
#include "caffe/blob.hpp"
#include "caffe/common.hpp"
#include "caffe/layer_factory.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/util/math_functions.hpp"
 
namespace boost { class mutex; }
 
namespace caffe {
 
template <typename Dtype>
class Layer {
 public:
  explicit Layer(const LayerParameter& param)
    : layer_param_(param) {
      // Set phase and copy blobs (if there are any).
      phase_ = param.phase();
      if (layer_param_.blobs_size() > 0) {
        blobs_.resize(layer_param_.blobs_size());
        for (int i = 0; i < layer_param_.blobs_size(); ++i) {
          blobs_[i].reset(new Blob<Dtype>());
          blobs_[i]->FromProto(layer_param_.blobs(i));
        }
      }
    }
  virtual ~Layer() {}
 
  void SetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
    CheckBlobCounts(bottom, top);
    LayerSetUp(bottom, top);
    Reshape(bottom, top);
    SetLossWeights(top);
  }
 
  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) = 0;
 
  inline Dtype Forward(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);
 
  inline void Backward(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down,
      const vector<Blob<Dtype>*>& bottom);
 
  vector<shared_ptr<Blob<Dtype> > >& blobs() {
    return blobs_;
  }
 
  const LayerParameter& layer_param() const { return layer_param_; }
 
  virtual void ToProto(LayerParameter* param, bool write_diff = false);
 
  inline Dtype loss(const int top_index) const {
    return (loss_.size() > top_index) ? loss_[top_index] : Dtype(0);
  }
 
  inline void set_loss(const int top_index, const Dtype value) {
    if (loss_.size() <= top_index) {
      loss_.resize(top_index + 1, Dtype(0));
    }
    loss_[top_index] = value;
  }
 
  virtual inline const char* type() const { return ""; }
 
  virtual inline int ExactNumBottomBlobs() const { return -1; }
  virtual inline int MinBottomBlobs() const { return -1; }
  virtual inline int MaxBottomBlobs() const { return -1; }
  virtual inline int ExactNumTopBlobs() const { return -1; }
  virtual inline int MinTopBlobs() const { return -1; }
  virtual inline int MaxTopBlobs() const { return -1; }
  virtual inline bool EqualNumBottomTopBlobs() const { return false; }
 
  virtual inline bool AutoTopBlobs() const { return false; }
 
  virtual inline bool AllowForceBackward(const int bottom_index) const {
    return true;
  }
 
  inline bool param_propagate_down(const int param_id) {
    return (param_propagate_down_.size() > param_id) ?
        param_propagate_down_[param_id] : false;
  }
  inline void set_param_propagate_down(const int param_id, const bool value) {
    if (param_propagate_down_.size() <= param_id) {
      param_propagate_down_.resize(param_id + 1, true);
    }
    param_propagate_down_[param_id] = value;
  }
 
 
 protected:
  LayerParameter layer_param_;
  Phase phase_;
  vector<shared_ptr<Blob<Dtype> > > blobs_;
  vector<bool> param_propagate_down_;
 
  vector<Dtype> loss_;
 
  virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) = 0;
  virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
    // LOG(WARNING) << "Using CPU code as backup.";
    return Forward_cpu(bottom, top);
  }
 
  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down,
      const vector<Blob<Dtype>*>& bottom) = 0;
  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down,
      const vector<Blob<Dtype>*>& bottom) {
    // LOG(WARNING) << "Using CPU code as backup.";
    Backward_cpu(top, propagate_down, bottom);
  }
 
  virtual void CheckBlobCounts(const vector<Blob<Dtype>*>& bottom,
                               const vector<Blob<Dtype>*>& top) {
    if (ExactNumBottomBlobs() >= 0) {
      CHECK_EQ(ExactNumBottomBlobs(), bottom.size())
          << type() << " Layer takes " << ExactNumBottomBlobs()
          << " bottom blob(s) as input.";
    }
    if (MinBottomBlobs() >= 0) {
      CHECK_LE(MinBottomBlobs(), bottom.size())
          << type() << " Layer takes at least " << MinBottomBlobs()
          << " bottom blob(s) as input.";
    }
    if (MaxBottomBlobs() >= 0) {
      CHECK_GE(MaxBottomBlobs(), bottom.size())
          << type() << " Layer takes at most " << MaxBottomBlobs()
          << " bottom blob(s) as input.";
    }
    if (ExactNumTopBlobs() >= 0) {
      CHECK_EQ(ExactNumTopBlobs(), top.size())
          << type() << " Layer produces " << ExactNumTopBlobs()
          << " top blob(s) as output.";
    }
    if (MinTopBlobs() >= 0) {
      CHECK_LE(MinTopBlobs(), top.size())
          << type() << " Layer produces at least " << MinTopBlobs()
          << " top blob(s) as output.";
    }
    if (MaxTopBlobs() >= 0) {
      CHECK_GE(MaxTopBlobs(), top.size())
          << type() << " Layer produces at most " << MaxTopBlobs()
          << " top blob(s) as output.";
    }
    if (EqualNumBottomTopBlobs()) {
      CHECK_EQ(bottom.size(), top.size())
          << type() << " Layer produces one top blob as output for each "
          << "bottom blob input.";
    }
  }
 
  inline void SetLossWeights(const vector<Blob<Dtype>*>& top) {
    const int num_loss_weights = layer_param_.loss_weight_size();
    if (num_loss_weights) {
      CHECK_EQ(top.size(), num_loss_weights) << "loss_weight must be "
          "unspecified or specified once per top blob.";
      for (int top_id = 0; top_id < top.size(); ++top_id) {
        const Dtype loss_weight = layer_param_.loss_weight(top_id);
        if (loss_weight == Dtype(0)) { continue; }
        this->set_loss(top_id, loss_weight);
        const int count = top[top_id]->count();
        Dtype* loss_multiplier = top[top_id]->mutable_cpu_diff();
        caffe_set(count, loss_weight, loss_multiplier);
      }
    }
  }
 
 private:
  DISABLE_COPY_AND_ASSIGN(Layer);
};  // class Layer
 
// Forward and backward wrappers. You should implement the cpu and
// gpu specific implementations instead, and should not change these
// functions.
template <typename Dtype>
inline Dtype Layer<Dtype>::Forward(const vector<Blob<Dtype>*>& bottom,
    const vector<Blob<Dtype>*>& top) {
  Dtype loss = 0;
  Reshape(bottom, top);
  switch (Caffe::mode()) {
  case Caffe::CPU:
    Forward_cpu(bottom, top);
    for (int top_id = 0; top_id < top.size(); ++top_id) {
      if (!this->loss(top_id)) { continue; }
      const int count = top[top_id]->count();
      const Dtype* data = top[top_id]->cpu_data();
      const Dtype* loss_weights = top[top_id]->cpu_diff();
      loss += caffe_cpu_dot(count, data, loss_weights);
    }
    break;
  case Caffe::GPU:
    Forward_gpu(bottom, top);
#ifndef CPU_ONLY
    for (int top_id = 0; top_id < top.size(); ++top_id) {
      if (!this->loss(top_id)) { continue; }
      const int count = top[top_id]->count();
      const Dtype* data = top[top_id]->gpu_data();
      const Dtype* loss_weights = top[top_id]->gpu_diff();
      Dtype blob_loss = 0;
      caffe_gpu_dot(count, data, loss_weights, &blob_loss);
      loss += blob_loss;
    }
#endif
    break;
  default:
    LOG(FATAL) << "Unknown caffe mode.";
  }
  return loss;
}
 
template <typename Dtype>
inline void Layer<Dtype>::Backward(const vector<Blob<Dtype>*>& top,
    const vector<bool>& propagate_down,
    const vector<Blob<Dtype>*>& bottom) {
  switch (Caffe::mode()) {
  case Caffe::CPU:
    Backward_cpu(top, propagate_down, bottom);
    break;
  case Caffe::GPU:
    Backward_gpu(top, propagate_down, bottom);
    break;
  default:
    LOG(FATAL) << "Unknown caffe mode.";
  }
}
 
// Serialize LayerParameter to protocol buffer
template <typename Dtype>
void Layer<Dtype>::ToProto(LayerParameter* param, bool write_diff) {
  param->Clear();
  param->CopyFrom(layer_param_);
  param->clear_blobs();
  for (int i = 0; i < blobs_.size(); ++i) {
    blobs_[i]->ToProto(param->add_blobs(), write_diff);
  }
}
 
}  // namespace caffe
 
#endif  // CAFFE_LAYER_H_