Caffe框架源码剖析(6)—池化层PoolingLayer

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/tianrolin/article/details/52584848

    卷积层ConvolutionLayer正向传导的目标层往往是池化层PoolingLayer。池化层通过降采样来降低卷积层输出的特征向量，同时改善结果，不易出现过拟合。最常用的降采样方法有均值采样（取区域平均值作为降采样值）、最大值采样（取区域最大值作为降采样值）和随机采样（取区域内随机一个像素）等。

    PoolingLayer类从Layer基类单一继承而来，没有派生其它子类。具体定义在pooling_layer.hpp中，

template <typename Dtype>
class PoolingLayer : public Layer<Dtype> {
 public:
  explicit PoolingLayer(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);

  virtual inline const char* type() const { return "Pooling"; }
  virtual inline int ExactNumBottomBlobs() const { return 1; }
  virtual inline int MinTopBlobs() const { return 1; }
  // 最大值采样可以额外输出一个Blob，所以MaxTopBlobs返回2
  virtual inline int MaxTopBlobs() const {
    return (this->layer_param_.pooling_param().pool() ==
            PoolingParameter_PoolMethod_MAX) ? 2 : 1;
  }

 protected:
  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);
  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);

  // 卷积区域尺寸
  int kernel_h_, kernel_w_;
  // 卷积平移步幅
  int stride_h_, stride_w_;
  // 图像补齐像素数
  int pad_h_, pad_w_;
  // 通道
  int channels_;
  // 输入图像尺寸
  int height_, width_;
  // 池化后尺寸
  int pooled_height_, pooled_width_;
  // 是否全区域池化（将整幅图像降采样为1x1）
  bool global_pooling_;
  // 随机采样点索引
  Blob<Dtype> rand_idx_;
  // 最大值采样点索引
  Blob<int> max_idx_;
};

具体实现在pooling_layer.cpp中，

template <typename Dtype>
void PoolingLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  PoolingParameter pool_param = this->layer_param_.pooling_param();
  if (pool_param.global_pooling()) {
    CHECK(!(pool_param.has_kernel_size() ||
      pool_param.has_kernel_h() || pool_param.has_kernel_w()))
      << "With Global_pooling: true Filter size cannot specified";
  } else {
    CHECK(!pool_param.has_kernel_size() !=
      !(pool_param.has_kernel_h() && pool_param.has_kernel_w()))
      << "Filter size is kernel_size OR kernel_h and kernel_w; not both";
    CHECK(pool_param.has_kernel_size() ||
      (pool_param.has_kernel_h() && pool_param.has_kernel_w()))
      << "For non-square filters both kernel_h and kernel_w are required.";
  }
  CHECK((!pool_param.has_pad() && pool_param.has_pad_h()
      && pool_param.has_pad_w())
      || (!pool_param.has_pad_h() && !pool_param.has_pad_w()))
      << "pad is pad OR pad_h and pad_w are required.";
  CHECK((!pool_param.has_stride() && pool_param.has_stride_h()
      && pool_param.has_stride_w())
      || (!pool_param.has_stride_h() && !pool_param.has_stride_w()))
      << "Stride is stride OR stride_h and stride_w are required.";
  global_pooling_ = pool_param.global_pooling();
  // 设置卷积区域尺寸
  if (global_pooling_) {
    // 如果全区域池化，则区域尺寸等于输入图像尺寸
    kernel_h_ = bottom[0]->height();
    kernel_w_ = bottom[0]->width();
  } else {
    if (pool_param.has_kernel_size()) {
      kernel_h_ = kernel_w_ = pool_param.kernel_size();
    } else {
      kernel_h_ = pool_param.kernel_h();
      kernel_w_ = pool_param.kernel_w();
    }
  }
  CHECK_GT(kernel_h_, 0) << "Filter dimensions cannot be zero.";
  CHECK_GT(kernel_w_, 0) << "Filter dimensions cannot be zero.";
  // 设置图像补齐像素
  if (!pool_param.has_pad_h()) {
    pad_h_ = pad_w_ = pool_param.pad();
  } else {
    pad_h_ = pool_param.pad_h();
    pad_w_ = pool_param.pad_w();
  }
  // 设置卷积平移步幅
  if (!pool_param.has_stride_h()) {
    stride_h_ = stride_w_ = pool_param.stride();
  } else {
    stride_h_ = pool_param.stride_h();
    stride_w_ = pool_param.stride_w();
  }
  if (global_pooling_) {
    CHECK(pad_h_ == 0 && pad_w_ == 0 && stride_h_ == 1 && stride_w_ == 1)
      << "With Global_pooling: true; only pad = 0 and stride = 1";
  }
  if (pad_h_ != 0 || pad_w_ != 0) {
    CHECK(this->layer_param_.pooling_param().pool()
        == PoolingParameter_PoolMethod_AVE
        || this->layer_param_.pooling_param().pool()
        == PoolingParameter_PoolMethod_MAX)
        << "Padding implemented only for average and max pooling.";
    CHECK_LT(pad_h_, kernel_h_);
    CHECK_LT(pad_w_, kernel_w_);
  }
}

template <typename Dtype>
void PoolingLayer<Dtype>::Reshape(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  CHECK_EQ(4, bottom[0]->num_axes()) << "Input must have 4 axes, "
      << "corresponding to (num, channels, height, width)";
  channels_ = bottom[0]->channels();
  height_ = bottom[0]->height();
  width_ = bottom[0]->width();
  if (global_pooling_) {
    kernel_h_ = bottom[0]->height();
    kernel_w_ = bottom[0]->width();
  }
  // 计算降采样后图像尺寸
  pooled_height_ = static_cast<int>(ceil(static_cast<float>(
      height_ + 2 * pad_h_ - kernel_h_) / stride_h_)) + 1;
  pooled_width_ = static_cast<int>(ceil(static_cast<float>(
      width_ + 2 * pad_w_ - kernel_w_) / stride_w_)) + 1;
  if (pad_h_ || pad_w_) {
    // 如果有图像补齐，则需要确保不发生越界，否则不做最后一个采样点
    if ((pooled_height_ - 1) * stride_h_ >= height_ + pad_h_) {
      --pooled_height_;
    }
    if ((pooled_width_ - 1) * stride_w_ >= width_ + pad_w_) {
      --pooled_width_;
    }
    CHECK_LT((pooled_height_ - 1) * stride_h_, height_ + pad_h_);
    CHECK_LT((pooled_width_ - 1) * stride_w_, width_ + pad_w_);
  }
  top[0]->Reshape(bottom[0]->num(), channels_, pooled_height_,
      pooled_width_);
  if (top.size() > 1) {
    top[1]->ReshapeLike(*top[0]);
  }
  // 如果是最大值采样，则初始化最大值采样点索引
  if (this->layer_param_.pooling_param().pool() ==
      PoolingParameter_PoolMethod_MAX && top.size() == 1) {
    max_idx_.Reshape(bottom[0]->num(), channels_, pooled_height_,
        pooled_width_);
  }
  // 如果是随机采样，则初始化随机采样点索引
  if (this->layer_param_.pooling_param().pool() ==
      PoolingParameter_PoolMethod_STOCHASTIC) {
    rand_idx_.Reshape(bottom[0]->num(), channels_, pooled_height_,
      pooled_width_);
  }
}

// CPU正向传导
// TODO(Yangqing): 池化操作还可以更快吗？
template <typename Dtype>
void PoolingLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  const Dtype* bottom_data = bottom[0]->cpu_data();
  Dtype* top_data = top[0]->mutable_cpu_data();
  const int top_count = top[0]->count();
  // 如果top.size() > 1，则额外输出一个Blob到top[1]
  const bool use_top_mask = top.size() > 1;
  int* mask = NULL;  // suppress warnings about uninitalized variables
  Dtype* top_mask = NULL;
  // switch不同的降采样方法
  // 将swtich放在for循环外用来提高运行速度，虽然这样会增加代码量
  switch (this->layer_param_.pooling_param().pool()) {
  // 最大值采样
  case PoolingParameter_PoolMethod_MAX:
    // 查找区域最大值前，将数组值初始化为-1
    if (use_top_mask) {
      top_mask = top[1]->mutable_cpu_data();
      caffe_set(top_count, Dtype(-1), top_mask);
    } else {
      mask = max_idx_.mutable_cpu_data();
      caffe_set(top_count, -1, mask);
    }
    caffe_set(top_count, Dtype(-FLT_MAX), top_data);
    // 循环遍历区域最大值
    for (int n = 0; n < bottom[0]->num(); ++n) {
      for (int c = 0; c < channels_; ++c) {
        for (int ph = 0; ph < pooled_height_; ++ph) {
          for (int pw = 0; pw < pooled_width_; ++pw) {
            int hstart = ph * stride_h_ - pad_h_;
            int wstart = pw * stride_w_ - pad_w_;
            int hend = min(hstart + kernel_h_, height_);
            int wend = min(wstart + kernel_w_, width_);
            hstart = max(hstart, 0);
            wstart = max(wstart, 0);
            const int pool_index = ph * pooled_width_ + pw;
            for (int h = hstart; h < hend; ++h) {
              for (int w = wstart; w < wend; ++w) {
                const int index = h * width_ + w;
                if (bottom_data[index] > top_data[pool_index]) {
                  top_data[pool_index] = bottom_data[index];
                  if (use_top_mask) {
                    top_mask[pool_index] = static_cast<Dtype>(index);
                  } else {
                    // 位置记录在max_idx_索引中
                    mask[pool_index] = index;
                  }
                }
              }
            }
          }
        }
        // 加上偏移，跳转到下一幅图像
        bottom_data += bottom[0]->offset(0, 1);
        top_data += top[0]->offset(0, 1);
        if (use_top_mask) {
          top_mask += top[0]->offset(0, 1);
        } else {
          mask += top[0]->offset(0, 1);
        }
      }
    }
    break;
  // 平均值采样
  case PoolingParameter_PoolMethod_AVE:
    for (int i = 0; i < top_count; ++i) {
      top_data[i] = 0;
    }
    // 循环遍历计算区域平均值
    for (int n = 0; n < bottom[0]->num(); ++n) {
      for (int c = 0; c < channels_; ++c) {
        for (int ph = 0; ph < pooled_height_; ++ph) {
          for (int pw = 0; pw < pooled_width_; ++pw) {
            int hstart = ph * stride_h_ - pad_h_;
            int wstart = pw * stride_w_ - pad_w_;
            int hend = min(hstart + kernel_h_, height_ + pad_h_);
            int wend = min(wstart + kernel_w_, width_ + pad_w_);
            int pool_size = (hend - hstart) * (wend - wstart);
            hstart = max(hstart, 0);
            wstart = max(wstart, 0);
            hend = min(hend, height_);
            wend = min(wend, width_);
            for (int h = hstart; h < hend; ++h) {
              for (int w = wstart; w < wend; ++w) {
                top_data[ph * pooled_width_ + pw] +=
                    bottom_data[h * width_ + w];
              }
            }
            top_data[ph * pooled_width_ + pw] /= pool_size;
          }
        }
        // 加上偏移，跳转到下一幅图像
        bottom_data += bottom[0]->offset(0, 1);
        top_data += top[0]->offset(0, 1);
      }
    }
    break;
  // 随机采样尚未在CPU端实现
  case PoolingParameter_PoolMethod_STOCHASTIC:
    NOT_IMPLEMENTED;
    break;
  default:
    LOG(FATAL) << "Unknown pooling method.";
  }
}

// CPU反向传导
template <typename Dtype>
void PoolingLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
  if (!propagate_down[0]) {
    return;
  }
  const Dtype* top_diff = top[0]->cpu_diff();
  Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();
  // 和正向传导代码类似，将switch放在for循环外部
  caffe_set(bottom[0]->count(), Dtype(0), bottom_diff);
  // 如果top.size() > 1，则额外输出一个Blob到top[1]
  const bool use_top_mask = top.size() > 1;
  const int* mask = NULL;  // suppress warnings about uninitialized variables
  const Dtype* top_mask = NULL;
  switch (this->layer_param_.pooling_param().pool()) {
  // 最大值采样
  case PoolingParameter_PoolMethod_MAX:
    // 开始循环
    if (use_top_mask) {
      top_mask = top[1]->cpu_data();
    } else {
      mask = max_idx_.cpu_data();
    }
    for (int n = 0; n < top[0]->num(); ++n) {
      for (int c = 0; c < channels_; ++c) {
        for (int ph = 0; ph < pooled_height_; ++ph) {
          for (int pw = 0; pw < pooled_width_; ++pw) {
            const int index = ph * pooled_width_ + pw;
            // 从采样点索引数组中取出反向传导的目的索引
            const int bottom_index =
                use_top_mask ? top_mask[index] : mask[index];
            bottom_diff[bottom_index] += top_diff[index];
          }
        }
        bottom_diff += bottom[0]->offset(0, 1);
        top_diff += top[0]->offset(0, 1);
        if (use_top_mask) {
          top_mask += top[0]->offset(0, 1);
        } else {
          mask += top[0]->offset(0, 1);
        }
      }
    }
    break;
  // 平均值采样
  case PoolingParameter_PoolMethod_AVE:
    // 开始循环
    for (int n = 0; n < top[0]->num(); ++n) {
      for (int c = 0; c < channels_; ++c) {
        for (int ph = 0; ph < pooled_height_; ++ph) {
          for (int pw = 0; pw < pooled_width_; ++pw) {
            int hstart = ph * stride_h_ - pad_h_;
            int wstart = pw * stride_w_ - pad_w_;
            int hend = min(hstart + kernel_h_, height_ + pad_h_);
            int wend = min(wstart + kernel_w_, width_ + pad_w_);
            int pool_size = (hend - hstart) * (wend - wstart);
            hstart = max(hstart, 0);
            wstart = max(wstart, 0);
            hend = min(hend, height_);
            wend = min(wend, width_);
            for (int h = hstart; h < hend; ++h) {
              for (int w = wstart; w < wend; ++w) {
                // 将top偏导平均分配到bottom各点上
                bottom_diff[h * width_ + w] +=
                  top_diff[ph * pooled_width_ + pw] / pool_size;
              }
            }
          }
        }
        // 加上偏移，跳转到下一幅图像
        bottom_diff += bottom[0]->offset(0, 1);
        top_diff += top[0]->offset(0, 1);
      }
    }
    break;
  // 随机采样尚未在CPU端实现
  case PoolingParameter_PoolMethod_STOCHASTIC:
    NOT_IMPLEMENTED;
    break;
  default:
    LOG(FATAL) << "Unknown pooling method.";
  }
}

// 如果CPU_ONLY模式则禁止Forward_gpu和Backward_gpu函数
#ifdef CPU_ONLY
STUB_GPU(PoolingLayer);
#endif