2 FOR loops, having RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation

[Lening_Li]

Hi, I think I have found the problem. After I use the backward, I use the network’s forward to get some other values.

@Lening_Li

            loss.backward()

            # check if the weights are updated
            a = list(self.value.model.parameters())[0].clone()
            optimizer.zero_grad()
            optimizer.step()
            b = list(self.value.model.parameters())[0].clone()
            print("Weights Updated: ", not torch.equal(a.data, b.data))

            # compute the expectation of h of g
            e_v = self.e_vio(trajs) # I used forward of the model
> ```

Which may cause the weights to change (I am not sure). Basically, my steps are the following:

1. backwork, updates the weights
2. forward, may change the weights (not sure)
   Is there a way to avoid this?
   Thanks,