@staticmethod
 def backward(ctx, grad_output):
  ind_lst = ctx.ind_lst
  flag = ctx.flag

  c = grad_output.size(1)
  grad_former_all = grad_output[:, 0:c//3, :, :]
  grad_latter_all = grad_output[:, c//3: c*2//3, :, :]
  grad_swapped_all = grad_output[:, c*2//3:c, :, :]

  spatial_size = ctx.h * ctx.w

  W_mat_all = Variable(ctx.Tensor(ctx.bz, spatial_size, spatial_size).zero_())
  for idx in range(ctx.bz):
   W_mat = W_mat_all.select(0,idx)
   for cnt in range(spatial_size):
    indS = ind_lst[idx][cnt] 

    if flag[cnt] == 1:
     # 这里W_mat是W_mat_all通过select出来的, 他们共享内存.
     W_mat[cnt, indS] = 1

   W_mat_t = W_mat.t()

   grad_swapped_weighted = torch.mm(W_mat_t, grad_swapped_all[idx].view(c//3, -1).t())
   grad_swapped_weighted = grad_swapped_weighted.t().contiguous().view(1, c//3, ctx.h, ctx.w)
   grad_latter_all[idx] = torch.add(grad_latter_all[idx], grad_swapped_weighted.mul(ctx.triple_w))

 @staticmethod
 def backward(ctx, grad_output):
  ind_lst = ctx.ind_lst
  flag = ctx.flag

  c = grad_output.size(1)
  grad_former_all = grad_output[:, 0:c//3, :, :]
  grad_latter_all = grad_output[:, c//3: c*2//3, :, :]
  grad_swapped_all = grad_output[:, c*2//3:c, :, :]

  spatial_size = ctx.h * ctx.w

  W_mat_all = Variable(ctx.Tensor(ctx.bz, spatial_size, spatial_size).zero_())
  for idx in range(ctx.bz):
   # 这里使用clone了
   W_mat = W_mat_all.select(0,idx).clone()
   for cnt in range(spatial_size):
    indS = ind_lst[idx][cnt]

    if flag[cnt] == 1:
     W_mat[cnt, indS] = 1

   W_mat_t = W_mat.t()

   grad_swapped_weighted = torch.mm(W_mat_t, grad_swapped_all[idx].view(c//3, -1).t())
   grad_swapped_weighted = grad_swapped_weighted.t().contiguous().view(1, c//3, ctx.h, ctx.w)

   # 这句话删了不会出错, 加上就吹出错
   grad_latter_all[idx] = torch.add(grad_latter_all[idx], grad_swapped_weighted.mul(ctx.triple_w))

 @staticmethod
 def backward(ctx, grad_output):
  ind_lst = ctx.ind_lst
  flag = ctx.flag

  c = grad_output.size(1)
  grad_former_all = grad_output[:, 0:c//3, :, :]
  # 这两个后面修改值了, 所以也要加clone, 防止它们与grad_output共享内存
  grad_latter_all = grad_output[:, c//3: c*2//3, :, :].clone()
  grad_swapped_all = grad_output[:, c*2//3:c, :, :].clone()

  spatial_size = ctx.h * ctx.w

  W_mat_all = Variable(ctx.Tensor(ctx.bz, spatial_size, spatial_size).zero_())
  for idx in range(ctx.bz):
   W_mat = W_mat_all.select(0,idx).clone()
   for cnt in range(spatial_size):
    indS = ind_lst[idx][cnt]

    if flag[cnt] == 1:
     W_mat[cnt, indS] = 1

   W_mat_t = W_mat.t()

   grad_swapped_weighted = torch.mm(W_mat_t, grad_swapped_all[idx].view(c//3, -1).t())

   grad_swapped_weighted = grad_swapped_weighted.t().contiguous().view(1, c//3, ctx.h, ctx.w)
   grad_latter_all[idx] = torch.add(grad_latter_all[idx], grad_swapped_weighted.mul(ctx.triple_w))

  grad_input = torch.cat([grad_former_all, grad_latter_all], 1)

  return grad_input, None, None, None, None, None, None, None, None, None, None