caffe研究之layer

Layer是所有层的基类，在Layer的基础上衍生出来的有5种Layers：
data_layer
neuron_layer
loss_layer
common_layer
vision_layer conv_layer 图像卷积，convolusion、pooling、LRN

Layer内部数据主要有两种传递方式，正向传导（Forward）和反向传导（Backward）。Forward和Backward有CPU和GPU两种实现。
Caffe中所有的Layer都要用这两种方法传递数据。

一、data：输入；

data_layer.hpp原始数据的输入层，处于整个网络的最底层，它可以从数据库leveldb、lmdb中读取数据，也可以直接从内存中读取，还可以从hdf5，甚至是原始的图像读入数据。作为网络的最底层，主要实现数据格式的转换。

template <typename Dtype>
void DataLayer<Dtype>::DataLayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  const int batch_size = this->layer_param_.data_param().batch_size();
  // Read a data point, and use it to initialize the top blob.
  Datum& datum = *(reader_.full().peek());

  // Use data_transformer to infer the expected blob shape from datum.
  vector<int> top_shape = this->data_transformer_->InferBlobShape(datum);
  this->transformed_data_.Reshape(top_shape);
  // Reshape top[0] and prefetch_data according to the batch_size.
  top_shape[0] = batch_size;
  top[0]->Reshape(top_shape);
  for (int i = 0; i < this->PREFETCH_COUNT; ++i) {
    this->prefetch_[i].data_.Reshape(top_shape);
  }
  LOG(INFO) << "output data size: " << top[0]->num() << ","
      << top[0]->channels() << "," << top[0]->height() << ","
      << top[0]->width();
  // label
  if (this->output_labels_) {
    vector<int> label_shape(1, batch_size);
    top[1]->Reshape(label_shape);
    for (int i = 0; i < this->PREFETCH_COUNT; ++i) {
      this->prefetch_[i].label_.Reshape(label_shape);
    }
  }
}

二、vision：卷积相关的计算；
conv_layer

#include <vector>

#include "caffe/layers/conv_layer.hpp"

namespace caffe {

template <typename Dtype>
void ConvolutionLayer<Dtype>::compute_output_shape() {
  const int* kernel_shape_data = this->kernel_shape_.cpu_data();
  const int* stride_data = this->stride_.cpu_data();
  const int* pad_data = this->pad_.cpu_data();
  const int* dilation_data = this->dilation_.cpu_data();
  this->output_shape_.clear();
  for (int i = 0; i < this->num_spatial_axes_; ++i) {
    // i + 1 to skip channel axis
    const int input_dim = this->input_shape(i + 1);
    const int kernel_extent = dilation_data[i] * (kernel_shape_data[i] - 1) + 1;
    const int output_dim = (input_dim + 2 * pad_data[i] - kernel_extent)
        / stride_data[i] + 1;
    this->output_shape_.push_back(output_dim);
  }
}

template <typename Dtype>
void ConvolutionLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  const Dtype* weight = this->blobs_[0]->cpu_data();
  for (int i = 0; i < bottom.size(); ++i) {
    const Dtype* bottom_data = bottom[i]->cpu_data();
    Dtype* top_data = top[i]->mutable_cpu_data();
    for (int n = 0; n < this->num_; ++n) {
      this->forward_cpu_gemm(bottom_data + n * this->bottom_dim_, weight,
          top_data + n * this->top_dim_);
      if (this->bias_term_) {
        const Dtype* bias = this->blobs_[1]->cpu_data();
        this->forward_cpu_bias(top_data + n * this->top_dim_, bias);
      }
    }
  }
}

template <typename Dtype>
void ConvolutionLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
  const Dtype* weight = this->blobs_[0]->cpu_data();
  Dtype* weight_diff = this->blobs_[0]->mutable_cpu_diff();
  for (int i = 0; i < top.size(); ++i) {
    const Dtype* top_diff = top[i]->cpu_diff();
    const Dtype* bottom_data = bottom[i]->cpu_data();
    Dtype* bottom_diff = bottom[i]->mutable_cpu_diff();
    // Bias gradient, if necessary.
    if (this->bias_term_ && this->param_propagate_down_[1]) {
      Dtype* bias_diff = this->blobs_[1]->mutable_cpu_diff();
      for (int n = 0; n < this->num_; ++n) {
        this->backward_cpu_bias(bias_diff, top_diff + n * this->top_dim_);
      }
    }
    if (this->param_propagate_down_[0] || propagate_down[i]) {
      for (int n = 0; n < this->num_; ++n) {
        // gradient w.r.t. weight. Note that we will accumulate diffs.
        if (this->param_propagate_down_[0]) {
          this->weight_cpu_gemm(bottom_data + n * this->bottom_dim_,
              top_diff + n * this->top_dim_, weight_diff);
        }
        // gradient w.r.t. bottom data, if necessary.
        if (propagate_down[i]) {
          this->backward_cpu_gemm(top_diff + n * this->top_dim_, weight,
              bottom_diff + n * this->bottom_dim_);
        }
      }
    }
  }
}

#ifdef CPU_ONLY
STUB_GPU(ConvolutionLayer);
#endif

INSTANTIATE_CLASS(ConvolutionLayer);

}  // namespace caffe

三、neuron、common：中间部分的数据计算；
neuron_layer
输入了data后，开始计算，比如常见的sigmoid、tanh等等。这些都计算操作被抽象成了neuron_layers.hpp里面的类NeuronLayer，这个层只负责具体的计算，因此明确定义了输入ExactNumBottomBlobs()和ExactNumTopBlobs()都是常量1,即输入一个blob，输出一个blob。其派生类主要是元素级别的运算（比如Dropout运算，激活函数ReLu，Sigmoid等），运算均为同址计算（in-place computation，返回值覆盖原值而占用新的内存）。

#include <vector>

#include "caffe/layers/neuron_layer.hpp"

namespace caffe {

template <typename Dtype>
void NeuronLayer<Dtype>::Reshape(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  top[0]->ReshapeLike(*bottom[0]);
}

INSTANTIATE_CLASS(NeuronLayer);

}  // namespace caffe

四、loss：计算反向传播的误差
输入2个blob，输出1个blob

#include <vector>

#include "caffe/layers/loss_layer.hpp"

namespace caffe {

template <typename Dtype>
void LossLayer<Dtype>::LayerSetUp(
    const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
  // LossLayers have a non-zero (1) loss by default.
  if (this->layer_param_.loss_weight_size() == 0) {
    this->layer_param_.add_loss_weight(Dtype(1));
  }
}

template <typename Dtype>
void LossLayer<Dtype>::Reshape(
    const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
  CHECK_EQ(bottom[0]->num(), bottom[1]->num())
      << "The data and label should have the same number.";
  vector<int> loss_shape(0);  // Loss layers output a scalar; 0 axes.
  top[0]->Reshape(loss_shape);
}

INSTANTIATE_CLASS(LossLayer);

}  // namespace caffe

Caffe中，Blob，Layer，Net，Solver是最为核心的类，一个Net由多个Layer组成。

参考资料：
http://www.myexception.cn/other/1828071.html
http://www.zhihu.com/question/27982282