#include 

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

namespace caffe {

template 
void ConcatLayer::LayerSetUp(const vector& bottom,
      const vector& top) {
  const ConcatParameter& concat_param = this->layer_param_.concat_param();
  CHECK(!(concat_param.has_axis() && concat_param.has_concat_dim()))
      num_axes();
  const ConcatParameter& concat_param = this->layer_param_.concat_param();
  if (concat_param.has_concat_dim()) {
    concat_axis_ = static_cast(concat_param.concat_dim());
    // Don't allow negative indexing for concat_dim, a uint32 -- almost
    // certainly unintended.
    CHECK_GE(concat_axis_, 0) count();
  for (int i = 1; i < bottom.size(); ++i) {
    CHECK_EQ(num_axes, bottom[i]->num_axes())
        shape(j))
          count();
    top_shape[concat_axis_] += bottom[i]->shape(concat_axis_);
  }
  top[0]->Reshape(top_shape);
  CHECK_EQ(bottom_count_sum, top[0]->count());
  if (bottom.size() == 1) {
    top[0]->ShareData(*bottom[0]);
    top[0]->ShareDiff(*bottom[0]);
  }
}

template 
void ConcatLayer::Forward_cpu(const vector& bottom,
      const vector& top) {
  if (bottom.size() == 1) { return; }
  Dtype* top_data = top[0]->mutable_cpu_data();
  int offset_concat_axis = 0;
  const int top_concat_axis = top[0]->shape(concat_axis_);
  for (int i = 0; i < bottom.size(); ++i) {
    const Dtype* bottom_data = bottom[i]->cpu_data();
    const int bottom_concat_axis = bottom[i]->shape(concat_axis_);
    for (int n = 0; n < num_concats_; ++n) {
      caffe_copy(bottom_concat_axis * concat_input_size_,
          bottom_data + n * bottom_concat_axis * concat_input_size_,
          top_data + (n * top_concat_axis + offset_concat_axis)
              * concat_input_size_);
    }
    offset_concat_axis += bottom_concat_axis;
  }
}

template 
void ConcatLayer::Backward_cpu(const vector& top,
      const vector& propagate_down, const vector& bottom) {
  if (bottom.size() == 1) { return; }
  const Dtype* top_diff = top[0]->cpu_diff();
  int offset_concat_axis = 0;
  const int top_concat_axis = top[0]->shape(concat_axis_);
  for (int i = 0; i < bottom.size(); ++i) {
    const int bottom_concat_axis = bottom[i]->shape(concat_axis_);
    if (propagate_down[i]) {
      Dtype* bottom_diff = bottom[i]->mutable_cpu_diff();
      for (int n = 0; n < num_concats_; ++n) {
        caffe_copy(bottom_concat_axis * concat_input_size_, top_diff +
            (n * top_concat_axis + offset_concat_axis) * concat_input_size_,
            bottom_diff + n * bottom_concat_axis * concat_input_size_);
      }
    }
    offset_concat_axis += bottom_concat_axis;
  }
}

#ifdef CPU_ONLY
STUB_GPU(ConcatLayer);
#endif

INSTANTIATE_CLASS(ConcatLayer);
#ifndef USE_ACL
REGISTER_LAYER_CLASS(Concat);
#endif

}  // namespace caffe