caffe源碼分析--softmax_layer.cpp

caffe源碼分析--softmax_layer.cpp

文件位置為caffe-master/src/caffe/layers/softmax_layer.cpp

這個是一個以前版本的程序，現在的代碼有些不同了，不過可以參考

caffe源碼分析--softmax_layer.cpp

 

// Copyright 2013 Yangqing Jia
//
#include <algorithm>
#include <vector>

#include "caffe/layer.hpp"
#include "caffe/vision_layers.hpp"
#include "caffe/util/math_functions.hpp"

using std::max;

namespace caffe {

/**
 * 建立softmax網絡層
 */
template <typename Dtype>
void SoftmaxLayer<Dtype>::SetUp(const vector<Blob<Dtype>*>& bottom,
      vector<Blob<Dtype>*>* top) {
  CHECK_EQ(bottom.size(), 1) << "Softmax Layer takes a single blob as input.";
  CHECK_EQ(top->size(), 1) << "Softmax Layer takes a single blob as output.";
  //輸出分配空間
  (*top)[0]->Reshape(bottom[0]->num(), bottom[0]->channels(),
      bottom[0]->height(), bottom[0]->width());
  //sum_multiplier_這里都是1，用於輔助計算，可以看作一個行向量，或者行數為1的矩陣
  sum_multiplier_.Reshape(1, bottom[0]->channels(),
      bottom[0]->height(), bottom[0]->width());
  Dtype* multiplier_data = sum_multiplier_.mutable_cpu_data();
  for (int i = 0; i < sum_multiplier_.count(); ++i) {
    multiplier_data[i] = 1.;
  }
  //臨時變量scale_分配空間，大小為num,可以看作一個列向量
  scale_.Reshape(bottom[0]->num(), 1, 1, 1);
}

template <typename Dtype>
void SoftmaxLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
    vector<Blob<Dtype>*>* top) {
  const Dtype* bottom_data = bottom[0]->cpu_data();
  Dtype* top_data = (*top)[0]->mutable_cpu_data();
  Dtype* scale_data = scale_.mutable_cpu_data();
  //把輸出看成是num層，每層dim個元素
  int num = bottom[0]->num();
  int dim = bottom[0]->count() / bottom[0]->num();
  memcpy(top_data, bottom_data, sizeof(Dtype) * bottom[0]->count());
  // we need to subtract the max to avoid numerical issues, compute the exp,
  // and then normalize.
  //找出每一層的最大值
  for (int i = 0; i < num; ++i) {
    scale_data[i] = bottom_data[i*dim];
    for (int j = 0; j < dim; ++j) {
      scale_data[i] = max(scale_data[i], bottom_data[i * dim + j]);
    }
  }
  // subtraction  通過矩陣相乘的方式來計算，有num層的top_data，每層元素減去該層的最大值。太巧妙了
  caffe_cpu_gemm<Dtype>(CblasNoTrans, CblasNoTrans, num, dim, 1, -1.,
    scale_data, sum_multiplier_.cpu_data(), 1., top_data);
  // C = alpha*op( A )*op( B ) + beta*C

  // Perform exponentiation 計算自然對數
  caffe_exp<Dtype>(num * dim, top_data, top_data);
  // sum after exp 每一層各自求和放到scale_data中
  caffe_cpu_gemv<Dtype>(CblasNoTrans, num, dim, 1., top_data,
      sum_multiplier_.cpu_data(), 0., scale_data);
  // Do division 每一層各自除以該層的和
  for (int i = 0; i < num; ++i) {
    caffe_scal<Dtype>(dim, Dtype(1.) / scale_data[i], top_data + i * dim);
  }
}

template <typename Dtype>
Dtype SoftmaxLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
    const bool propagate_down,
    vector<Blob<Dtype>*>* bottom) {
  const Dtype* top_diff = top[0]->cpu_diff();
  const Dtype* top_data = top[0]->cpu_data();
  Dtype* bottom_diff = (*bottom)[0]->mutable_cpu_diff();
  Dtype* scale_data = scale_.mutable_cpu_data();
  int num = top[0]->num();
  int dim = top[0]->count() / top[0]->num();
  memcpy(bottom_diff, top_diff, sizeof(Dtype) * top[0]->count());
  // Compute inner1d(top_diff, top_data) and subtract them from the bottom diff
  for (int i = 0; i < num; ++i) {
    scale_data[i] = caffe_cpu_dot<Dtype>(dim, top_diff + i * dim,
        top_data + i * dim);//每一層，top_diff和top_data計算內積
  }
  // subtraction  每一層bottom_diff的元素減去該層的對應的內積
  caffe_cpu_gemm<Dtype>(CblasNoTrans, CblasNoTrans, num, dim, 1, -1.,
      scale_data, sum_multiplier_.cpu_data(), 1., bottom_diff);
  // elementwise multiplication 元素各自相乘
  caffe_mul<Dtype>(top[0]->count(), bottom_diff, top_data, bottom_diff);
  return Dtype(0);
}


INSTANTIATE_CLASS(SoftmaxLayer);


}  // namespace caffe

 

 

本文作者：linger

本文鏈接：http://blog.csdn.net/lingerlanlan/article/details/32700431