Dropout caffe源码

GPU和CPU实现的不一样，这里贴的是CPU中的drop out

直接看caffe里面的源码吧：（产生满足伯努利分布的随机数mask，train的时候，data除以p,......

scale_ = 1. / (1. - threshold_);

template <typename Dtype>
void DropoutLayer<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();
  unsigned int* mask = rand_vec_.mutable_cpu_data();
  const int count = bottom[0]->count();
  if (this->phase_ == TRAIN) {
    // Create random numbers
    caffe_rng_bernoulli(count, 1. - threshold_, mask);
    for (int i = 0; i < count; ++i) {
      top_data[i] = bottom_data[i] * mask[i] * scale_;
    }
  } else {
    caffe_copy(bottom[0]->count(), bottom_data, top_data);
  }
}
 
template <typename Dtype>
void DropoutLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
    const vector<bool>& propagate_down,
    const vector<Blob<Dtype>*>& bottom) {
  if (propagate_down[0]) {
    const Dtype* top_diff = top[0]->cpu_diff();
    Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();
    if (this->phase_ == TRAIN) {
      const unsigned int* mask = rand_vec_.cpu_data();
      const int count = bottom[0]->count();
      for (int i = 0; i < count; ++i) {
        bottom_diff[i] = top_diff[i] * mask[i] * scale_;
      }
    } else {
      caffe_copy(top[0]->count(), top_diff, bottom_diff);
    }
  }
}