src/col2im_kernels.cu
@@ -1,3 +1,7 @@ #include "cuda_runtime.h" #include "curand.h" #include "cublas_v2.h" extern "C" { #include "col2im.h" #include "cuda.h" @@ -42,7 +46,6 @@ int ksize, int stride, int pad, float *data_im){ // We are going to launch channels * height_col * width_col kernels, each // kernel responsible for copying a single-channel grid. pad = pad ? ksize/2 : 0; int height_col = (height + 2 * pad - ksize) / stride + 1; int width_col = (width + 2 * pad - ksize) / stride + 1; int num_kernels = channels * height * width;
