Method Backward_cpu

src/caffe/layers/prelu_layer.cpp:92–131

template <typename Dtype>
void PReLULayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
    const vector<bool>& propagate_down,
    const vector<Blob<Dtype>*>& bottom) {
  const Dtype* bottom_data = bottom[0]->cpu_data();
  const Dtype* slope_data = this->blobs_[0]->cpu_data();
  const Dtype* top_diff = top[0]->cpu_diff();
  const int count = bottom[0]->count();
  const int dim = bottom[0]->count(2);
  const int channels = bottom[0]->channels();

  // For in-place computation
  if (top[0] == bottom[0]) {
    bottom_data = bottom_memory_.cpu_data();
  }

  // if channel_shared, channel index in the following computation becomes
  // always zero.
  const int div_factor = channel_shared_ ? channels : 1;

  // Propagte to param
  // Since to write bottom diff will affect top diff if top and bottom blobs
  // are identical (in-place computaion), we first compute param backward to
  // keep top_diff unchanged.
  if (this->param_propagate_down_[0]) {
    Dtype* slope_diff = this->blobs_[0]->mutable_cpu_diff();
    for (int i = 0; i < count; ++i) {
      int c = (i / dim) % channels / div_factor;
      slope_diff[c] += top_diff[i] * bottom_data[i] * (bottom_data[i] <= 0);
    }
  }
  // Propagate to bottom
  if (propagate_down[0]) {
    Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();
    for (int i = 0; i < count; ++i) {
      int c = (i / dim) % channels / div_factor;
      bottom_diff[i] = top_diff[i] * ((bottom_data[i] > 0)
          + slope_data[c] * (bottom_data[i] <= 0));
    }
  }
}


#ifdef CPU_ONLY