#include 
#include 
#include 

#include "caffe/layers/pooling_layer.hpp"
#include "caffe/util/math_functions.hpp"

namespace caffe {

using std::min;
using std::max;

template 
void PoolingLayer::LayerSetUp(const vector& bottom,
      const vector& 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()))
      = 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]);
  }
  // If max pooling, we will initialize the vector index part.
  if (this->layer_param_.pooling_param().pool() ==
      PoolingParameter_PoolMethod_MAX && top.size() == 1) {
    max_idx_.Reshape(bottom[0]->num(), channels_, pooled_height_,
        pooled_width_);
  }
  // If stochastic pooling, we will initialize the random index part.
  if (this->layer_param_.pooling_param().pool() ==
      PoolingParameter_PoolMethod_STOCHASTIC) {
    rand_idx_.Reshape(bottom[0]->num(), channels_, pooled_height_,
      pooled_width_);
  }
}

// TODO(Yangqing): Is there a faster way to do pooling in the channel-first
// case?
template 
void PoolingLayer::Forward_cpu(const vector& bottom,
      const vector& top) {
  const Dtype* bottom_data = bottom[0]->cpu_data();
  Dtype* top_data = top[0]->mutable_cpu_data();
  const int top_count = top[0]->count();
  // We'll output the mask to top[1] if it's of size >1.
  const bool use_top_mask = top.size() > 1;
  int* mask = NULL;  // suppress warnings about uninitalized variables
  Dtype* top_mask = NULL;
  // Different pooling methods. We explicitly do the switch outside the for
  // loop to save time, although this results in more code.
  switch (this->layer_param_.pooling_param().pool()) {
  case PoolingParameter_PoolMethod_MAX:
    // Initialize
    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);
    // The main loop
    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(index);
                  } else {
                    mask[pool_index] = index;
                  }
                }
              }
            }
          }
        }
        // compute offset
        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;
  case PoolingParameter_PoolMethod_AVE:
    for (int i = 0; i < top_count; ++i) {
      top_data[i] = 0;
    }
    // The main loop
    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;
          }
        }
        // compute offset
        bottom_data += bottom[0]->offset(0, 1);
        top_data += top[0]->offset(0, 1);
      }
    }
    break;
  case PoolingParameter_PoolMethod_STOCHASTIC:
    NOT_IMPLEMENTED;
    break;
  default:
    LOG(FATAL) cpu_diff();
  Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();
  // Different pooling methods. We explicitly do the switch outside the for
  // loop to save time, although this results in more codes.
  caffe_set(bottom[0]->count(), Dtype(0), bottom_diff);
  // We'll output the mask to top[1] if it's of size >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()) {
  case PoolingParameter_PoolMethod_MAX:
    // The main loop
    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;
            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;
  case PoolingParameter_PoolMethod_AVE:
    // The main loop
    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) {
                bottom_diff[h * width_ + w] +=
                  top_diff[ph * pooled_width_ + pw] / pool_size;
              }
            }
          }
        }
        // offset
        bottom_diff += bottom[0]->offset(0, 1);
        top_diff += top[0]->offset(0, 1);
      }
    }
    break;
  case PoolingParameter_PoolMethod_STOCHASTIC:
    NOT_IMPLEMENTED;
    break;
  default:
    LOG(FATAL)