Caffe 學習：Eltwise層

Caffe 學習：Eltwise層

　　Eltwise層的操作有三個：product（點乘）， sum（相加減） 和 max（取大值），其中sum是默認操作。

      1. PROD：按元素乘積
      2. SUM：按元素求和（默認）
      3. MAX：保存元素大者

      該層還定義了 coeff 參數，該參數只對SUM操作起作用。

最後，caffe還設定了stable_prod_grad #[default = true ] 來選擇是否漸進較慢的梯度計算方法，該方法只適用於PROD操作，對SUM操作無效。
更多細節參見下面的源碼。

eltwise_layer 源碼

#include <cfloat>
#include <vector>

#include "caffe/layers/eltwise_layer.hpp"
#include "caffe/util/math_functions.hpp"

namespace caffe {

template <typename Dtype>
void EltwiseLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  CHECK(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(!(this->layer_param().eltwise_param().operation()
      == EltwiseParameter_EltwiseOp_PROD
      && this->layer_param().eltwise_param().coeff_size())) <<
      "Eltwise layer only takes coefficients for summation.";
  op_ = this->layer_param_.eltwise_param().operation();
  // Blob-wise coefficients for the elementwise operation.
  coeffs_ = vector<Dtype>(bottom.size(), 1);
  if (this->layer_param().eltwise_param().coeff_size()) {
    for (int i = 0; i < bottom.size(); ++i) {
      coeffs_[i] = this->layer_param().eltwise_param().coeff(i);
    }
  }
  stable_prod_grad_ = this->layer_param_.eltwise_param().stable_prod_grad();
}

template <typename Dtype>
void EltwiseLayer<Dtype>::Reshape(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  for (int i = 1; i < bottom.size(); ++i) {
    CHECK(bottom[i]->shape() == bottom[0]->shape());
  }
  top[0]->ReshapeLike(*bottom[0]);
  // If max operation, we will initialize the vector index part.
  if (this->layer_param_.eltwise_param().operation() ==
      EltwiseParameter_EltwiseOp_MAX && top.size() == 1) {
    max_idx_.Reshape(bottom[0]->shape());
  }
}

template <typename Dtype>
void EltwiseLayer<Dtype>::Forward_cpu(
    const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
  int* mask = NULL;
  const Dtype* bottom_data_a = NULL;
  const Dtype* bottom_data_b = NULL;
  const int count = top[0]->count();
  Dtype* top_data = top[0]->mutable_cpu_data();
  switch (op_) {                         //choose different operations according to op_
  case EltwiseParameter_EltwiseOp_PROD:  //PROD,按位乘
    caffe_mul(count, bottom[0]->cpu_data(), bottom[1]->cpu_data(), top_data);
    for (int i = 2; i < bottom.size(); ++i) {
      caffe_mul(count, top_data, bottom[i]->cpu_data(), top_data);
    }
    break;
  case EltwiseParameter_EltwiseOp_SUM: //SUM 按位和，這裏有coffs_爲係數，可以通過指定某一輸入的係數來完成按位加和按位減
    caffe_set(count, Dtype(0), top_data);
    // TODO(shelhamer) does BLAS optimize to sum for coeff = 1?
    for (int i = 0; i < bottom.size(); ++i) {
      caffe_axpy(count, coeffs_[i], bottom[i]->cpu_data(), top_data);
    }
    break;
  case EltwiseParameter_EltwiseOp_MAX: //按位取大數
    // Initialize
    mask = max_idx_.mutable_cpu_data();
    caffe_set(count, -1, mask);
    caffe_set(count, Dtype(-FLT_MAX), top_data);
    // bottom 0 & 1
    bottom_data_a = bottom[0]->cpu_data();
    bottom_data_b = bottom[1]->cpu_data();
    for (int idx = 0; idx < count; ++idx) {
      if (bottom_data_a[idx] > bottom_data_b[idx]) {
        top_data[idx] = bottom_data_a[idx];  // maxval
        mask[idx] = 0;  // maxid
      } else {
        top_data[idx] = bottom_data_b[idx];  // maxval
        mask[idx] = 1;  // maxid
      }
    }
    // bottom 2++
    for (int blob_idx = 2; blob_idx < bottom.size(); ++blob_idx) {
      bottom_data_b = bottom[blob_idx]->cpu_data();
      for (int idx = 0; idx < count; ++idx) {
        if (bottom_data_b[idx] > top_data[idx]) {
          top_data[idx] = bottom_data_b[idx];  // maxval
          mask[idx] = blob_idx;  // maxid
        }
      }
    }
    break;
  default:
    LOG(FATAL) << "Unknown elementwise operation.";
  }
}

template <typename Dtype>
void EltwiseLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
    const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
  const int* mask = NULL;
  const int count = top[0]->count();
  const Dtype* top_data = top[0]->cpu_data();
  const Dtype* top_diff = top[0]->cpu_diff();
  for (int i = 0; i < bottom.size(); ++i) {
    if (propagate_down[i]) {
      const Dtype* bottom_data = bottom[i]->cpu_data();
      Dtype* bottom_diff = bottom[i]->mutable_cpu_diff();
      switch (op_) {
      case EltwiseParameter_EltwiseOp_PROD:
        if (stable_prod_grad_) {
          bool initialized = false;
          for (int j = 0; j < bottom.size(); ++j) {
            if (i == j) { continue; }
            if (!initialized) {
              caffe_copy(count, bottom[j]->cpu_data(), bottom_diff);
              initialized = true;
            } else {
              caffe_mul(count, bottom[j]->cpu_data(), bottom_diff,
                        bottom_diff);
            }
          }
        } else {
          caffe_div(count, top_data, bottom_data, bottom_diff);
        }
        caffe_mul(count, bottom_diff, top_diff, bottom_diff);
        break;
      case EltwiseParameter_EltwiseOp_SUM:
        if (coeffs_[i] == Dtype(1)) {
          caffe_copy(count, top_diff, bottom_diff);
        } else {
          caffe_cpu_scale(count, coeffs_[i], top_diff, bottom_diff);
        }
        break;
      case EltwiseParameter_EltwiseOp_MAX:
        mask = max_idx_.cpu_data();
        for (int index = 0; index < count; ++index) {
          Dtype gradient = 0;
          if (mask[index] == i) {
            gradient += top_diff[index];
          }
          bottom_diff[index] = gradient;
        }
        break;
      default:
        LOG(FATAL) << "Unknown elementwise operation.";
      }
    }
  }
}

#ifdef CPU_ONLY
STUB_GPU(EltwiseLayer);
#endif

INSTANTIATE_CLASS(EltwiseLayer);
REGISTER_LAYER_CLASS(Eltwise);

}  // namespace caffe

　　假設輸入（bottom）爲A和B，如果要實現element_wise的A+B，即A和B的對應元素相加，prototxt文件如下：

layer 
{
  name: "eltwise_layer"
  type: "Eltwise"
  bottom: "A"
  bottom: "B"
  top: "diff"
  eltwise_param {
    operation: SUM
  }
}​

　　如果實現A-B，則prototxt爲：

layer 
{
  name: "eltwise_layer"
  type: "Eltwise"
  bottom: "A"
  bottom: "B"
  top: "diff"
  eltwise_param {
    operation: SUM
    coeff: 1
    coeff: -1
  }
}​

　　其中A和B的係數（coefficient）都要給出！

轉載鏈接：http://blog.csdn.net/m0_37407756/article/details/72556750