roi_pooling_layer.cpp

参考：https://blog.csdn.net/lanran2/article/details/60143861/
如果真的以一个10x10的小目标来算的话，来，我们走一走：
（1）首先将10x10的小目标映射到最终的特征图上，将小目标的x1，y1，x2，y2都处以16，不能整除的取整（round 返回四舍五入的整数），边长为10的小目标可能会出现x1=x2或者y1=y2的情况，接下来计算HW，HW的最小值为1，所以小目标的HW肯定是一了。

（2）将一 除以七，嵌套的三个for循环里面，计算hstar，hend，wstar，wend，对该小目标肯定都是0，1，0，1。对应特征图上的一个像素，后面的也都在一个像素内找最大值。

// ------------------------------------------------------------------
// Fast R-CNN
// Copyright (c) 2015 Microsoft
// Licensed under The MIT License [see fast-rcnn/LICENSE for details]
// Written by Ross Girshick
// ------------------------------------------------------------------

#include <cfloat>

#include "caffe/fast_rcnn_layers.hpp"

using std::max;
using std::min;
using std::floor;
using std::ceil;

namespace caffe {

//LayerSetUp 输入参数
template <typename Dtype>
void ROIPoolingLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  ROIPoolingParameter roi_pool_param = this->layer_param_.roi_pooling_param();
  CHECK_GT(roi_pool_param.pooled_h(), 0)
      << "pooled_h must be > 0";
  CHECK_GT(roi_pool_param.pooled_w(), 0)
      << "pooled_w must be > 0";
      //经过pooling后的feature map的高
  pooled_height_ = roi_pool_param.pooled_h();
  //经过pooling之后的 feature map 的宽
  pooled_width_ = roi_pool_param.pooled_w();
  //输入图片与feature map 之间的比值，这个feature map 指的是roi pooling层的输入
  spatial_scale_ = roi_pool_param.spatial_scale();
  LOG(INFO) << "Spatial scale: " << spatial_scale_;
}

//reshape
template <typename Dtype>
void ROIPoolingLayer<Dtype>::Reshape(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
      //bottom[0]指的是输入的feature map
  channels_ = bottom[0]->channels();
  height_ = bottom[0]->height();
  width_ = bottom[0]->width();
  //设置输出的形状NCHW，N=ROI的个数，C=channels_，H=pooled_height_，W=pooled_width_
  top[0]->Reshape(bottom[1]->num(), channels_, pooled_height_,
      pooled_width_);
      //max_idx_的形状与top一致
  max_idx_.Reshape(bottom[1]->num(), channels_, pooled_height_,
      pooled_width_);
}

//forward
template <typename Dtype>
void ROIPoolingLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
      //两部分输入
  const Dtype* bottom_data = bottom[0]->cpu_data();
  const Dtype* bottom_rois = bottom[1]->cpu_data();
  // Number of ROIs
  int num_rois = bottom[1]->num();
  int batch_size = bottom[0]->num();
  int top_count = top[0]->count();
  Dtype* top_data = top[0]->mutable_cpu_data();
  caffe_set(top_count, Dtype(-FLT_MAX), top_data);
  int* argmax_data = max_idx_.mutable_cpu_data();
  caffe_set(top_count, -1, argmax_data);

  // For each ROI R = [batch_index x1 y1 x2 y2]: max pool over R
  for (int n = 0; n < num_rois; ++n) {
    int roi_batch_ind = bottom_rois[0];//roi_batch_ind指的是roi的索引
    //将roi的坐标映射到特征图上，round，取整
    int roi_start_w = round(bottom_rois[1] * spatial_scale_);
    int roi_start_h = round(bottom_rois[2] * spatial_scale_);
    int roi_end_w = round(bottom_rois[3] * spatial_scale_);
    int roi_end_h = round(bottom_rois[4] * spatial_scale_);

    CHECK_GE(roi_batch_ind, 0);
    CHECK_LT(roi_batch_ind, batch_size);
//计算 roi的高和宽，宽和高最小为一
    int roi_height = max(roi_end_h - roi_start_h + 1, 1);
    int roi_width = max(roi_end_w - roi_start_w + 1, 1);
    //将 roi 的高和宽除以pooling之后的超参数高和宽，得到比例。
    const Dtype bin_size_h = static_cast<Dtype>(roi_height)
                             / static_cast<Dtype>(pooled_height_);
    const Dtype bin_size_w = static_cast<Dtype>(roi_width)
                             / static_cast<Dtype>(pooled_width_);

//找到对应 roi 的 feature map ，应该是裁剪下来了，后面循环中用到
//如果input data的batch size为1，那么roi batch ind 等于0
    const Dtype* batch_data = bottom_data + bottom[0]->offset(roi_batch_ind);

    //pooling 的过程是针对每一个channel的，需要循环遍历
    for (int c = 0; c < channels_; ++c) {
      //计算output的每一个值，所以需要遍历一遍output，然后求出所有值
      for (int ph = 0; ph < pooled_height_; ++ph) {
        for (int pw = 0; pw < pooled_width_; ++pw) {
          // Compute pooling region for this output unit:
          //  start (included) = floor(ph * roi_height / pooled_height_)
          //  end (excluded) = ceil((ph + 1) * roi_height / pooled_height_)
          int hstart = static_cast<int>(floor(static_cast<Dtype>(ph)
                                              * bin_size_h));//floor(x)返回不大于x的最大整数值。
          int wstart = static_cast<int>(floor(static_cast<Dtype>(pw)
                                              * bin_size_w));//
          int hend = static_cast<int>(ceil(static_cast<Dtype>(ph + 1)
                                           * bin_size_h));//ceil(x)返回不小于x的最小整数值（然后转换为double型）。
          int wend = static_cast<int>(ceil(static_cast<Dtype>(pw + 1)
                                           * bin_size_w));

          hstart = min(max(hstart + roi_start_h, 0), height_);
          hend = min(max(hend + roi_start_h, 0), height_);
          wstart = min(max(wstart + roi_start_w, 0), width_);
          wend = min(max(wend + roi_start_w, 0), width_);

          bool is_empty = (hend <= hstart) || (wend <= wstart);

          const int pool_index = ph * pooled_width_ + pw;
          if (is_empty) {
            top_data[pool_index] = 0;
            argmax_data[pool_index] = -1;
          }

          for (int h = hstart; h < hend; ++h) {
            for (int w = wstart; w < wend; ++w) {
              const int index = h * width_ + w;
              if (batch_data[index] > top_data[pool_index]) {
                top_data[pool_index] = batch_data[index];
                argmax_data[pool_index] = index;
              }
            }
          }
        }
      }
      // Increment all data pointers by one channel
      batch_data += bottom[0]->offset(0, 1);
      top_data += top[0]->offset(0, 1);
      argmax_data += max_idx_.offset(0, 1);
    }
    // Increment ROI data pointer
    bottom_rois += bottom[1]->offset(1);
  }
}

template <typename Dtype>
void ROIPoolingLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
  NOT_IMPLEMENTED;
}


#ifdef CPU_ONLY
STUB_GPU(ROIPoolingLayer);
#endif

INSTANTIATE_CLASS(ROIPoolingLayer);
REGISTER_LAYER_CLASS(ROIPooling);

}  // namespace caffe