caffe euclidean loss ignore label

如果需要在Euclidean loss层ignore掉某一类标签，caffe框架里的Euclidean loss层并没有实现这一条件，需要自己根据已有的Euclidean loss层来更改。

1.了解 euclidean loss计算方式

http://blog.csdn.net/seashell_9/article/details/68064294

2.这个版本的Euclidean loss 中的N为全部的标签的个数，并不是去除需忽略标签的标签数。

3.代码

https://github.com/BVLC/caffe/pull/5250/commits/2ba99ef81f87355930891b1b3f14f183a3055806

4. 主要更改代码

euclidean_loss_layer.hpp

#ifndef CAFFE_EUCLIDEAN_LOSS_LAYER_HPP_
#define CAFFE_EUCLIDEAN_LOSS_LAYER_HPP_

#include <vector>

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

#include "caffe/layers/loss_layer.hpp"

namespace caffe {

/**
 * @brief Computes the Euclidean (L2) loss @f$
 *          E = \frac{1}{2N} \sum\limits_{n=1}^N \left| \left| \hat{y}_n - y_n
 *        \right| \right|_2^2 @f$ for real-valued regression tasks.
 *
 * @param bottom input Blob vector (length 2)
 *   -# @f$ (N \times C \times H \times W) @f$
 *      the predictions @f$ \hat{y} \in [-\infty, +\infty]@f$
 *   -# @f$ (N \times C \times H \times W) @f$
 *      the targets @f$ y \in [-\infty, +\infty]@f$
 * @param top output Blob vector (length 1)
 *   -# @f$ (1 \times 1 \times 1 \times 1) @f$
 *      the computed Euclidean loss: @f$ E =
 *          \frac{1}{2n} \sum\limits_{n=1}^N \left| \left| \hat{y}_n - y_n
 *        \right| \right|_2^2 @f$
 *
 * This can be used for least-squares regression tasks.  An InnerProductLayer
 * input to a EuclideanLossLayer exactly formulates a linear least squares
 * regression problem. With non-zero weight decay the problem becomes one of
 * ridge regression -- see src/caffe/test/test_sgd_solver.cpp for a concrete
 * example wherein we check that the gradients computed for a Net with exactly
 * this structure match hand-computed gradient formulas for ridge regression.
 *
 * (Note: Caffe, and SGD in general, is certainly \b not the best way to solve
 * linear least squares problems! We use it only as an instructive example.)
 */
template <typename Dtype>
class EuclideanLossLayer : public LossLayer<Dtype> {
 public:
  explicit EuclideanLossLayer(const LayerParameter& param)
      : LossLayer<Dtype>(param), diff_() {}     
  virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top);

  virtual inline const char* type() const { return "EuclideanLoss"; }
  /**
   * Unlike most loss layers, in the EuclideanLossLayer we can backpropagate
   * to both inputs -- override to return true and always allow force_backward.
   */
  virtual inline bool AllowForceBackward(const int bottom_index) const {
    return true;
  }

 protected:
  /// @copydoc EuclideanLossLayer
  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 Euclidean error gradient w.r.t. the inputs.
   *
   * Unlike other children of LossLayer, EuclideanLossLayer \b can compute
   * gradients with respect to the label inputs bottom[1] (but still only will
   * if propagate_down[1] is set, due to being produced by learnable parameters
   * or if force_backward is set). In fact, this layer is "commutative" -- the
   * result is the same regardless of the order of the two bottoms.
   *
   * @param top output Blob vector (length 1), providing the error gradient with
   *      respect to the outputs
   *   -# @f$ (1 \times 1 \times 1 \times 1) @f$
   *      This Blob's diff will simply contain the loss_weight* @f$ \lambda @f$,
   *      as @f$ \lambda @f$ is the coefficient of this layer's output
   *      @f$\ell_i@f$ in the overall Net loss
   *      @f$ E = \lambda_i \ell_i + \mbox{other loss terms}@f$; hence
   *      @f$ \frac{\partial E}{\partial \ell_i} = \lambda_i @f$.
   *      (*Assuming that this top Blob is not used as a bottom (input) by any
   *      other layer of the Net.)
   * @param propagate_down see Layer::Backward.
   * @param bottom input Blob vector (length 2)
   *   -# @f$ (N \times C \times H \times W) @f$
   *      the predictions @f$\hat{y}@f$; Backward fills their diff with
   *      gradients @f$
   *        \frac{\partial E}{\partial \hat{y}} =
   *            \frac{1}{n} \sum\limits_{n=1}^N (\hat{y}_n - y_n)
   *      @f$ if propagate_down[0]
   *   -# @f$ (N \times C \times H \times W) @f$
   *      the targets @f$y@f$; Backward fills their diff with gradients
   *      @f$ \frac{\partial E}{\partial y} =
   *          \frac{1}{n} \sum\limits_{n=1}^N (y_n - \hat{y}_n)
   *      @f$ if propagate_down[1]
   */
  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);

  Blob<Dtype> diff_;
  bool has_ignore_label_;
  int ignore_label_;
  //int* counts;
};

}  // namespace caffe

#endif  // CAFFE_EUCLIDEAN_LOSS_LAYER_HPP_

euclidean_loss_layer.cpp

#include <vector>

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

namespace caffe {

template <typename Dtype>
void EuclideanLossLayer<Dtype>::Reshape(
  const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
  LossLayer<Dtype>::Reshape(bottom, top);
  CHECK_EQ(bottom[0]->count(1), bottom[1]->count(1))
      << "Inputs must have the same dimension.";
  diff_.ReshapeLike(*bottom[0]);
  
  has_ignore_label_ =
    this->layer_param_.loss_param().has_ignore_label();
  if (has_ignore_label_) {
    ignore_label_ = this->layer_param_.loss_param().ignore_label();
  }  
  
  //int temp_count = bottom[0]->count();
  //counts = &temp_count; 
  
}

template <typename Dtype>
void EuclideanLossLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
    const vector<Blob<Dtype>*>& top) {
  int count = bottom[0]->count();
  caffe_sub(
      count,
      bottom[0]->cpu_data(),
      bottom[1]->cpu_data(),
      diff_.mutable_cpu_data());
      
  
  if (has_ignore_label_) {
    const Dtype* label_data = bottom[1]->cpu_data();
    Dtype* diff__data = diff_.mutable_cpu_data();
    for (int i = 0; i < count; ++i) {
      const int label_value = static_cast<int>(label_data[i]);
      if (label_value == ignore_label_) {
        diff__data[i] = 0;
        //*counts = *counts-1;
      }
    }
  }  

  Dtype dot = caffe_cpu_dot(count, diff_.cpu_data(), diff_.cpu_data());
  Dtype loss = dot / bottom[0]->num() / Dtype(2);
  top[0]->mutable_cpu_data()[0] = loss;
}

template <typename Dtype>
void EuclideanLossLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
    const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
  for (int i = 0; i < 2; ++i) {
    if (propagate_down[i]) {
      const Dtype sign = (i == 0) ? 1 : -1;
      const Dtype alpha = sign * top[0]->cpu_diff()[0] / bottom[0]->num();
      caffe_cpu_axpby(
          bottom[i]->count(),              // count
          alpha,                              // alpha
          diff_.cpu_data(),                   // a
          Dtype(0),                           // beta
          bottom[i]->mutable_cpu_diff());  // b
    }
  }
}

#ifdef CPU_ONLY
STUB_GPU(EuclideanLossLayer);
#endif

INSTANTIATE_CLASS(EuclideanLossLayer);
REGISTER_LAYER_CLASS(EuclideanLoss);

}  // namespace caffe

euclidean_loss_layer.cu

#include <vector>

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

namespace caffe {

template <typename Dtype>
__global__ void EuclideanLossForwardGPU(const int n,
          const Dtype* label_data_, Dtype* diff__data_,
          const int ignore_label_) {
  CUDA_KERNEL_LOOP(index, n) {
    const int label_value = static_cast<int>(label_data_[index]);
    if (label_value == ignore_label_) {
      diff__data_[index] = 0;
      //*counts = *counts - 1;
    }
  }
}


template <typename Dtype>
void EuclideanLossLayer<Dtype>::Forward_gpu(const vector<Blob<Dtype>*>& bottom,
    const vector<Blob<Dtype>*>& top) {
  int count = bottom[0]->count();
  caffe_gpu_sub(
      count,
      bottom[0]->gpu_data(),
      bottom[1]->gpu_data(),
      diff_.mutable_gpu_data());
    
  if (has_ignore_label_) {
    EuclideanLossForwardGPU<Dtype><<<CAFFE_GET_BLOCKS(count),
        CAFFE_CUDA_NUM_THREADS>>>(count, bottom[1]->gpu_data(),
                                  diff_.mutable_gpu_data(),
                                  ignore_label_);
  }  
   
  Dtype dot;
  caffe_gpu_dot(count, diff_.gpu_data(), diff_.gpu_data(), &dot);
  Dtype loss = dot / bottom[0]->num() / Dtype(2);
  top[0]->mutable_cpu_data()[0] = loss;
}

template <typename Dtype>
void EuclideanLossLayer<Dtype>::Backward_gpu(const vector<Blob<Dtype>*>& top,
    const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
  for (int i = 0; i < 2; ++i) {
    if (propagate_down[i]) {
      const Dtype sign = (i == 0) ? 1 : -1;
      const Dtype alpha = sign * top[0]->cpu_diff()[0] / bottom[0]->num();
      caffe_gpu_axpby(
          bottom[i]->count(),              // count
          alpha,                              // alpha
          diff_.gpu_data(),                   // a
          Dtype(0),                           // beta
          bottom[i]->mutable_gpu_diff());  // b
    }
  }
}

INSTANTIATE_LAYER_GPU_FUNCS(EuclideanLossLayer);

}  // namespace caffe