Caffe中im2col的实现解析

这里，我是将Caffe中im2col的解析过程直接拉了出来，使用C++进行了输出，方便理解。代码如下：

 #include<iostream>

 using namespace std;

 bool is_a_ge_zero_and_a_lt_b(int a,int b)
 {
     if(a>= && a <b) return true;
     return false;
 }

 void im2col_cpu(const float* data_im, const int channels,
     const int height, const int width, const int kernel_h, const int kernel_w,
     const int pad_h, const int pad_w,
     const int stride_h, const int stride_w,
     const int dilation_h, const int dilation_w,
     float* data_col) {
   const int output_h = (height +  * pad_h -
     (dilation_h * (kernel_h - ) + )) / stride_h + ;
   const int output_w = (width +  * pad_w -
     (dilation_w * (kernel_w - ) + )) / stride_w + ;
   const int channel_size = height * width;
   for (int channel = channels; channel--; data_im += channel_size) {
     for (int kernel_row = ; kernel_row < kernel_h; kernel_row++) {
       for (int kernel_col = ; kernel_col < kernel_w; kernel_col++) {
         int input_row = -pad_h + kernel_row * dilation_h;
         for (int output_rows = output_h; output_rows; output_rows--) {
           if (!is_a_ge_zero_and_a_lt_b(input_row, height)) {
             for (int output_cols = output_w; output_cols; output_cols--) {
               *(data_col++) = ;
             }
           } else {
             int input_col = -pad_w + kernel_col * dilation_w;
             for (int output_col = output_w; output_col; output_col--) {
               if (is_a_ge_zero_and_a_lt_b(input_col, width)) {
                 *(data_col++) = data_im[input_row * width + input_col];
               } else {
                 *(data_col++) = ;
               }
               input_col += stride_w;
             }
           }
           input_row += stride_h;
         }
       }
     }
   }
 }

 int main()
 {
      float* data_im;
     int height=;
     int width=;
     int kernel_h=;
     int kernel_w=;
     int pad_h=;
     int pad_w=;
     int stride_h=;
     int stride_w=;
     int dilation_h=;
     int dilation_w=;
     float* data_col;
     int channels =;
     const int output_h = (height +  * pad_h -
     (dilation_h * (kernel_h - ) + )) / stride_h + ;
       const int output_w = (width +  * pad_w -
     (dilation_w * (kernel_w - ) + )) / stride_w + ;
     data_im = new float[channels*height*width];
     data_col = new float[channels*output_h*output_w*kernel_h*kernel_w];

     //init input image data
     for(int m=;m<channels;++m)
     {
       for(int i=;i<height;++i)
       {
         for(int j=;j<width;++j)
         {
           data_im[m*width*height+i*width+j] = m*width*height+ i*width +j;
           cout <<data_im[m*width*height+i*width+j] <<' ';
         }
         cout <<endl;
       }
     }

     im2col_cpu(data_im, channels,
      height,width, kernel_h, kernel_w,
     pad_h, pad_w,
     stride_h, stride_w,
     dilation_h, dilation_w,
      data_col);
     cout <<channels<<endl;
     cout <<output_h<<endl;
     cout <<output_w<<endl;
     cout <<kernel_h<<endl;
     cout <<kernel_w<<endl;
    // cout <<"error"<<endl;
     for(int i=;i<kernel_w*kernel_h*channels;++i)
     {
         for(int j=;j<output_w*output_h;++j)
         {
             cout <<data_col[i*output_w*output_h+j]<<' ';
         }
         cout <<endl;
     }

     return ;
 }

多通道卷积的图像别人已经给过很多了，大家可以搜到的基本都来自于一篇。这里附上一个我自己的理解过程，和程序的输出是完全一致的