Caffe: Eltwise layer 详解 (pycaffe, 卷积层相加\减等操作)

Caffe: Eltwise layer 详解

1. eltwise_layer的头文件

#ifndef CAFFE_ELTWISE_LAYER_HPP_
#define CAFFE_ELTWISE_LAYER_HPP_

#include <vector>

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

namespace caffe {

/**
 * @brief Compute elementwise operations, such as product and sum,
 *        along multiple input Blobs.
 *
 * TODO(dox): thorough documentation for Forward, Backward, and proto params.
 */
template <typename Dtype>
class EltwiseLayer : public Layer<Dtype> {
 public:
  explicit EltwiseLayer(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 inline const char* type() const { return "Eltwise"; }
  virtual inline int MinBottomBlobs() const { return 2; }
  virtual inline int ExactNumTopBlobs() const { return 1; }

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

  EltwiseParameter_EltwiseOp op_;
  vector<Dtype> coeffs_;
  Blob<int> max_idx_;

  bool stable_prod_grad_;
};

}  // namespace caffe

#endif  // CAFFE_ELTWISE_LAYER_HPP_

2. 参数设置

message EltwiseParameter {
  enum EltwiseOp {
    PROD = 0;
    SUM = 1;
    MAX = 2;
  }
  optional EltwiseOp operation = 1 [default = SUM]; // element-wise operation
  repeated float coeff = 2; // blob-wise coefficient for SUM operation

  // Whether to use an asymptotically slower (for >2 inputs) but stabler method
  // of computing the gradient for the PROD operation. (No effect for SUM op.)
  optional bool stable_prod_grad = 3 [default = true];
}

3. pycaffe设置

用pycaffe设置对应的参数

# operation是0代表的就是乘法
 a = caffe.layers.Eltwise(b, b, name='bxb', operation=0)

也可以写成下面的形式

 a = caffe.layers.Eltwise(b, b, name='bxb',  eltwise_param={'operation': 0})

如果是减法的话,需要在eltwise_param中添加,

 eltwise_param={'operation': 1, 'coeff': 1, 'coeff': -1}

但是在生成caffemodel的时候,会报如下错误

F0429 09:17:02.291570 24088 eltwise_layer.cpp:13] Check failed: this->layer_param().eltwise_param().coeff_size() == 0 || this->layer_param().eltwise_param().coeff_size() == bottom.size() Eltwise Layer takes one coefficient per bottom blob.
*** Check failure stack trace: ***

打开prototxt发现

eltwise_param {
    operation: SUM
    coeff: -1.0
  }

只有一个参数,手动添加一个即可

eltwise_param {
    operation: SUM 
    coeff: 1.0
    coeff: -1.0
  }

当然如果小伙伴们有什么比较好的方法,欢迎在评论区留言!