Some question on inplace operation

autograd
1

I have got error message when I tried to run my code as:
"RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation"
However, I can’t find any inplace operation on my code.
Here’s my code:

    def forward(self, sentence, state):
        candidates = state.clone()
        for j in range(self.nslots):
            w_j = self.key_vector_FC[j](Variable(torch.Tensor([1])))
            gate_j = F.sigmoid(state[j] * sentence + state[j] * w_j)
            update = F.relu(self.U(state[j]) + self.V(w_j) + self.W(sentence), inplace=False)
            candidates[j] = candidates[j] + gate_j * update
            norm = candidates[j].norm(p=2, dim=0, keepdim=True)  # .detach()
            candidates[j] = candidates[j].div(norm)  # problem here!
        state = candidates
        return state

I tried to replace the division operation with

state[j] = state[j].div(2)

and the problem solved.
And I tried to use the .detach() method, which makes no efforts.

2

What should be the shape of sentence and state?

3

The second dim of state equals to the first dim of sentence.
For example,
sentence.shape = [5]
state.shape = [10,5]