liangzimei / Weighted_Softmax_Loss

Weighted Softmax Loss Layer for Caffe

Weighted_Softmax_Loss

Weighted Softmax Loss Layer for Caffe

Usage:

（1）caffe.proto文件修改以下部分，增加pos_mult（指定某类的权重乘子）和pos_cid（指定的某类的类别编号）两个参数：

// Message that stores parameters used by SoftmaxLayer, SoftmaxWithLossLayer
message SoftmaxParameter {
  enum Engine {
    DEFAULT = 0;
    CAFFE = 1;
    CUDNN = 2;
  }
  optional Engine engine = 1 [default = DEFAULT];

  // The axis along which to perform the softmax -- may be negative to index
  // from the end (e.g., -1 for the last axis).
  // Any other axes will be evaluated as independent softmaxes.
  optional int32 axis = 2 [default = 1];
  optional float pos_mult = 3 [default = 1];
  optional int32 pos_cid = 4 [default = 1];
}

（2）include\caffe\loss_layers.hpp，增加以下部分：

/**
 * @brief A weighted version of SoftmaxWithLossLayer.
 *
 * TODO: Add description. Add the formulation in math.
 */
template <typename Dtype>
class WeightedSoftmaxWithLossLayer : public LossLayer<Dtype> {
 public:
   /**
    * @param param provides LossParameter loss_param, with options:
    *  - ignore_label (optional)
    *    Specify a label value that should be ignored when computing the loss.
    *  - normalize (optional, default true)
    *    If true, the loss is normalized by the number of (nonignored) labels
    *    present; otherwise the loss is simply summed over spatial locations.
    */
  explicit WeightedSoftmaxWithLossLayer(const LayerParameter& param)
      : LossLayer<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 "WeightedSoftmaxWithLoss"; }
  virtual inline int ExactNumBottomBlobs() const { return -1; }
  virtual inline int MinBottomBlobs() const { return 1; }
  virtual inline int MaxBottomBlobs() const { return 2; }
  virtual inline int ExactNumTopBlobs() const { return -1; }
  virtual inline int MinTopBlobs() const { return 1; }
  virtual inline int MaxTopBlobs() const { return 2; }

 protected:
  /// @copydoc WeightedSoftmaxWithLossLayer
  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 softmax loss error gradient w.r.t. the predictions.
   *
   * Gradients cannot be computed with respect to the label inputs (bottom[1]),
   * so this method ignores bottom[1] and requires !propagate_down[1], crashing
   * if propagate_down[1] is set.
   *
   * @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$.
   *      (*Assuming that this top Blob is not used as a bottom (input) by any
   *      other layer of the Net.)
   * @param propagate_down see Layer::Backward.
   *      propagate_down[1] must be false as we can't compute gradients with
   *      respect to the labels.
   * @param bottom input Blob vector (length 2)
   *   -# @f$ (N \times C \times H \times W) @f$
   *      the predictions @f$ x @f$; Backward computes diff
   *      @f$ \frac{\partial E}{\partial x} @f$
   *   -# @f$ (N \times 1 \times 1 \times 1) @f$
   *      the labels -- ignored as we can't compute their error gradients
   */
  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);


  /// The internal SoftmaxLayer used to map predictions to a distribution.
  shared_ptr<Layer<Dtype> > softmax_layer_;
  /// prob stores the output probability predictions from the SoftmaxLayer.
  Blob<Dtype> prob_;
  /// bottom vector holder used in call to the underlying SoftmaxLayer::Forward
  vector<Blob<Dtype>*> softmax_bottom_vec_;
  /// top vector holder used in call to the underlying SoftmaxLayer::Forward
  vector<Blob<Dtype>*> softmax_top_vec_;
  /// Whether to ignore instances with a certain label.
  bool has_ignore_label_;
  /// The label indicating that an instance should be ignored.
  int ignore_label_;
  /// Whether to normalize the loss by the total number of values present
  /// (otherwise just by the batch size).
  bool normalize_;
  int softmax_axis_, outer_num_, inner_num_;

  float pos_mult_;
  int pos_cid_;
};

（3）在src\caffe\layers文件夹中增加weighted_softmax_loss_layer.cpp和weighted_softmax_loss_layer.cu两个文件

（4）在训练的prototxt文件中，按照下面方法使用（比如指定从0数起的第1类，权重加强，乘子为2.0）：

layer {
  name: "loss"
  type: "WeightedSoftmaxWithLoss"
  bottom: "fc_end"
  bottom: "label"
  top: "loss"
  softmax_param {
    pos_cid: 1
    pos_mult: 2.0
  }
}