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 layersmessage 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;}