loss_layer.cpp

loss_layer.cpp

#include <algorithm>
#include <vector>

#include "caffe/layers/loss_layer.hpp"

namespace caffe {

template <typename Dtype>
void LossLayer<Dtype>::LayerSetUp(
    const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
  // LossLayers have a non-zero (1) loss by default.
  if (this->layer_param_.loss_weight_size() == 0) {
    this->layer_param_.add_loss_weight(Dtype(1));
  }
}

template <typename Dtype>
void LossLayer<Dtype>::Reshape(
    const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
  CHECK_EQ(bottom[0]->shape(0), bottom[1]->shape(0))
      << "The data and label should have the same first dimension.";
  vector<int> loss_shape(0);  // Loss layers output a scalar; 0 axes.
  top[0]->Reshape(loss_shape);
}

template <typename Dtype>
Dtype LossLayer<Dtype>::GetNormalizer(
    const LossParameter_NormalizationMode normalization_mode,
    const int outer_num, const int inner_num, const int valid_count) {
  Dtype normalizer;
  switch (normalization_mode) {
    case LossParameter_NormalizationMode_FULL:
      normalizer = Dtype(outer_num * inner_num);
      break;
    case LossParameter_NormalizationMode_VALID:
      if (valid_count == -1) {
        normalizer = Dtype(outer_num * inner_num);
      } else {
        normalizer = Dtype(valid_count);
      }
      break;
    case LossParameter_NormalizationMode_BATCH_SIZE:
      normalizer = Dtype(outer_num);
      break;
    case LossParameter_NormalizationMode_NONE:
      normalizer = Dtype(1);
      break;
    default:
      LOG(FATAL) << "Unknown normalization mode: "
          << LossParameter_NormalizationMode_Name(normalization_mode);
  }
  // Some users will have no labels for some examples in order to 'turn off' a
  // particular loss in a multi-task setup. The max prevents NaNs in that case.
  return std::max(Dtype(1.0), normalizer);
}

INSTANTIATE_CLASS(LossLayer);

}  // namespace caffe

loss_layer.hpp

#ifndef CAFFE_LOSS_LAYER_HPP_
#define CAFFE_LOSS_LAYER_HPP_

#include <vector>

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

namespace caffe {

const float kLOG_THRESHOLD = 1e-20;

/**
 * @brief An interface for Layer%s that take two Blob%s as input -- usually
 *        (1) predictions and (2) ground-truth labels -- and output a
 *        singleton Blob representing the loss.
 *
 * LossLayers are typically only capable of backpropagating to their first input
 * -- the predictions.
 */
template <typename Dtype>
class LossLayer : public Layer<Dtype> {
 public:
  explicit LossLayer(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);

  /**
   * Read the normalization mode parameter and compute the normalizer based
   * on the blob size. If normalization_mode is VALID, the count of valid
   * outputs will be read from valid_count, unless it is -1 in which case
   * all outputs are assumed to be valid.
   */
  Dtype GetNormalizer(
      const LossParameter_NormalizationMode normalization_mode,
      const int outer_num, const int inner_num, const int valid_count);

  virtual inline int ExactNumBottomBlobs() const { return 2; }

  /**
   * @brief For convenience and backwards compatibility, instruct the Net to
   *        automatically allocate a single top Blob for LossLayers, into which
   *        they output their singleton loss, (even if the user didn't specify
   *        one in the prototxt, etc.).
   */
  virtual inline bool AutoTopBlobs() const { return true; }
  virtual inline int ExactNumTopBlobs() const { return 1; }
  /**
   * We usually cannot backpropagate to the labels; ignore force_backward for
   * these inputs.
   */
  virtual inline bool AllowForceBackward(const int bottom_index) const {
    return bottom_index != 1;
  }
};

}  // namespace caffe

#endif  // CAFFE_LOSS_LAYER_HPP_

caffe.proto部分源码

// Message that stores parameters shared by loss layers
message LossParameter {
  // If specified, ignore instances with the given label.
  optional int32 ignore_label = 1;
  // How to normalize the loss for loss layers that aggregate across batches,
  // spatial dimensions, or other dimensions.  Currently only implemented in
  // SoftmaxWithLoss and SigmoidCrossEntropyLoss layers.
  enum NormalizationMode {
    // Divide by the number of examples in the batch times spatial dimensions.
    // Outputs that receive the ignore label will NOT be ignored in computing
    // the normalization factor.
    FULL = 0;
    // Divide by the total number of output locations that do not take the
    // ignore_label.  If ignore_label is not set, this behaves like FULL.
    VALID = 1;
    // Divide by the batch size.
    BATCH_SIZE = 2;
    // Do not normalize the loss.
    NONE = 3;
  }
  // For historical reasons, the default normalization for
  // SigmoidCrossEntropyLoss is BATCH_SIZE and *not* VALID.
  optional NormalizationMode normalization = 3 [default = VALID];
  // Deprecated.  Ignored if normalization is specified.  If normalization
  // is not specified, then setting this to false will be equivalent to
  // normalization = BATCH_SIZE to be consistent with previous behavior.
  optional bool normalize = 2;
}