5 int channels,
int height,
int width,
6 int ksize,
int stride,
int pad,
float* data_im);
10 int channels,
int height,
int width,
11 int ksize,
int stride,
int pad,
float *data_im);
void col2im_gpu(float *data_col, int channels, int height, int width, int ksize, int stride, int pad, float *data_im)
void col2im_cpu(float *data_col, int channels, int height, int width, int ksize, int stride, int pad, float *data_im)