前面的基类理解了,这个比较简单了。
conv_layer.cpp:
#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;//计算输出的尺寸
this->output_shape_.push_back(output_dim);
}
}
/*
ConvolutionLayer调用了forward_cpu_gemm,而这个函数内部又调用了math_function里面的caffe_cpu_gemm的通用矩
阵相乘接口,GEMM的全称是General Matrix Matrix Multiply。其基本形式如下:C=alpha∗op(A)∗op(B)+beta∗C,
*/
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();
// num_ = batchsize
for (int n = 0; n < this->num_; ++n) {
// 基类的forward_cpu_gemm函数
// 计算的是top_data[n * this->top_dim_] =
// weights X bottom_data[n * this->bottom_dim_]
// 输入的是一幅图像的数据,对应的是这幅图像卷积之后的位置
this->forward_cpu_gemm(bottom_data + n * this->bottom_dim_, weight,
top_data + n * this->top_dim_);
if (this->bias_term_) {//如果有偏置然后调用带偏置的函数
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) {
//反向传播梯度误差
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();
// //如果有bias项,计算Bias导数
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_);
}
}
//计算weight
if (this->param_propagate_down_[0] || propagate_down[i]) {
for (int n = 0; n < this->num_; ++n) {
// 计算weights权重的梯度
if (this->param_propagate_down_[0]) {
this->weight_cpu_gemm(bottom_data + n * this->bottom_dim_,
top_diff + n * this->top_dim_, weight_diff);
}
//计算botttom数据的梯度,下后传递
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