How to update epoch loss in a different way?

1

Currently I update my per epoch loss as such:

for i in range(epoch):
        print('epoch %d:' % i)
        epoch_loss = 0
        model.train()
        for graph1, graph2, target in train_loader:
            pred = torch.squeeze(model(graph1, graph2))
            pred = pred.detach().cpu().numpy()
            target = target.detach().cpu().numpy()
            pred = torch.tensor(pred, requires_grad=True)
            target = torch.LongTensor(target)
            loss = loss_fn(pred, target)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            epoch_loss += loss.detach().item()
        epoch_loss /= (iter + 1)
        print('Epoch {}, loss {:.4f}'.format(epoch, epoch_loss))
        epoch_losses.append(epoch_loss)

However the line

epoch_loss /= (iter + 1)

gives me this error

TypeError: unsupported operand type(s) for +: 'builtin_function_or_method' and 'int'

How do I update the loss in a different way? Why is this giving an error?

2

iter is a Python function defined as:

iter(iterable) -> iterator
iter(callable, sentinel) -> iterator

Get an iterator from an object.  In the first form, the argument must
supply its own iterator, or be a sequence.
In the second form, the callable is called until it returns the sentinel.
Type:      builtin_function_or_method

and I guess you want to divide by i instead?