7a82079d10379287ba4e6e42e21b5b3ce8f541bc,spotlight/factorization/implicit.py,ImplicitFactorizationModel,fit,#ImplicitFactorizationModel#Any#Any#,102

Before Change

                        user_var
                    )
                else:
                    negative_items = sample_items(
                        self._num_items,
                        len(batch_user),
                        random_state=self._random_state)
                    negative_var = Variable(
                        gpu(torch.from_numpy(negative_items))
                    )
                    negative_prediction = self._net(user_var, negative_var)

                self._optimizer.zero_grad()

                loss = loss_fnc(positive_prediction, negative_prediction)

After Change

            loss_fnc = pointwise_loss
        elif self._loss == "bpr":
            loss_fnc = bpr_loss
        elif self._loss == "hinge":
            loss_fnc = hinge_loss
        else:
            loss_fnc = adaptive_hinge_loss

        for epoch_num in range(self._n_iter):

            users, items = shuffle(user_ids,

Instances