我想写我自己的激活函数，但我遇到了一个问题。说矩阵乘法将调用.data。我搜索了，但得到的有用信息很少。任何帮助将不胜感激。错误信息是

Traceback (most recent call last):
      File "defineAutogradFuncion.py", line 126, in <module>
        test = gradcheck(argmin, input, eps=1e-6, atol=1e-4)
      File "/home/zhaosl/.local/lib/python2.7/site-packages/torch/autograd/gradcheck.py", line 154, in gradcheck
        output = func(*inputs)
      File "defineAutogradFuncion.py", line 86, in forward
        output = output.mm(dismap).squeeze(-1)
      File "/home/zhaosl/.local/lib/python2.7/site-packages/torch/autograd/variable.py", line 578, in mm
        output = Variable(self.data.new(self.data.size(0), matrix.data.size(1)))
      File "/home/zhaosl/.local/lib/python2.7/site-packages/torch/tensor.py", line 374, in data
        raise RuntimeError('cannot call .data on a torch.Tensor: did you intend to use autograd.Variable?')
    RuntimeError: cannot call .data on a torch.Tensor: did you intend to use autograd.Variable?

class Softargmin(torch.autograd.Function):
    """
    We can implement our own custom autograd Functions by subclassing
    torch.autograd.Function and implementing the forward and backward passes
    which operate on Tensors.
    """
    @staticmethod
    def forward(self, input):
        """
        In the forward pass we receive a Tensor containing the input and return a
        Tensor containing the output. You can cache arbitrary Tensors for use in the
        backward pass using the save_for_backward method.
        """
        #P = Fun.softmax(-input)
        inputSqueeze = input.squeeze(-1)
        P = Fun.softmax(-inputSqueeze)
        self.save_for_backward(P)

        output = P.permute(0,2,3,1)
        dismap = torch.arange(0,output.size(-1)+1).unsqueeze(1)
        output = output.mm(dismap).squeeze(-1)
       return output
    @staticmethod
    def backward(self, grad_output):
        """
        In the backward pass we receive a Tensor containing the gradient of the loss
        with respect to the output, and we need to compute the gradient of the loss
        with respect to the input.
        """
        P, = self.saved_tensors
        P = P.unsqueeze(-1)
        Pk = torch.squeeze(P,-1).permute(0,2,3,1)
        k = torch.arange(0,Pk.size(-1)+1).unsqueeze(1)
        sumkPk = Pk.mm(k)
        sumkPk = sumkPk.unsqueeze(1).expand(P.size())
        i = torch.arange(0,Pk.size(-1)+1).view(1,-1,1,1,1).expand(P.size())
        grad_output_expand =grad_output.unsqueeze(-1).unsqueeze(1).expand(P.size())
        grad_input = grad_output_expand*P*(sumkPk-i)
        return grad_input