How to use the fvcore.nn.smooth_l1_loss function in fvcore

num_foreground = foreground_idxs.sum()

        gt_classes_target = torch.zeros_like(pred_class_logits)
        gt_classes_target[foreground_idxs, gt_classes[foreground_idxs]] = 1

        # logits loss
        loss_cls = sigmoid_focal_loss_jit(
            pred_class_logits[valid_idxs],
            gt_classes_target[valid_idxs],
            alpha=self.focal_loss_alpha,
            gamma=self.focal_loss_gamma,
            reduction="sum",
        ) / max(1, num_foreground)

        # regression loss
        loss_box_reg = smooth_l1_loss(
            pred_anchor_deltas[foreground_idxs],
            gt_anchors_deltas[foreground_idxs],
            beta=self.smooth_l1_loss_beta,
            reduction="sum",
        ) / max(1, num_foreground)

        return {"loss_cls": loss_cls, "loss_box_reg": loss_box_reg}

loss_cls = (
            sigmoid_focal_loss_star_jit(
                pred_logits[gt_valid_inds],
                gt_classes_target[gt_valid_inds],
                alpha=self.focal_loss_alpha,
                gamma=self.focal_loss_gamma,
                reduction="sum",
            )
            / loss_normalizer
        )

        if num_fg == 0:
            loss_box_reg = pred_deltas.sum() * 0
        else:
            loss_box_reg = (
                smooth_l1_loss(pred_deltas[gt_fg_inds], gt_deltas, beta=0.0, reduction="sum")
                / loss_normalizer
            )
        losses = {"loss_cls": loss_cls, "loss_box_reg": loss_box_reg}

        # mask prediction
        if self.mask_on:
            loss_mask = 0
            for lvl in range(self.num_levels):
                cur_level_factor = 2 ** lvl if self.bipyramid_on else 1
                for anc in range(self.num_anchors):
                    cur_gt_mask_inds = gt_mask_inds[lvl][anc]
                    if cur_gt_mask_inds is None:
                        loss_mask += pred_masks[lvl][anc][0, 0, 0, 0] * 0
                    else:
                        cur_mask_size = self.mask_sizes[anc] * cur_level_factor
                        # TODO maybe there are numerical issues when mask sizes are large

gt_anchor_deltas (Tensor): shape (N, box_dim), row i represents ground-truth
            box2box transform targets (dx, dy, dw, dh) or (dx, dy, dw, dh, da) that map anchor i to
            its matched ground-truth box.
        pred_objectness_logits (Tensor): shape (N,), each element is a predicted objectness
            logit.
        pred_anchor_deltas (Tensor): shape (N, box_dim), each row is a predicted box2box
            transform (dx, dy, dw, dh) or (dx, dy, dw, dh, da)
        smooth_l1_beta (float): The transition point between L1 and L2 loss in
            the smooth L1 loss function. When set to 0, the loss becomes L1. When
            set to +inf, the loss becomes constant 0.

    Returns:
        objectness_loss, localization_loss, both unnormalized (summed over samples).
    """
    pos_masks = gt_objectness_logits == 1
    localization_loss = smooth_l1_loss(
        pred_anchor_deltas[pos_masks], gt_anchor_deltas[pos_masks], smooth_l1_beta, reduction="sum"
    )

    valid_masks = gt_objectness_logits >= 0
    objectness_loss = F.binary_cross_entropy_with_logits(
        pred_objectness_logits[valid_masks],
        gt_objectness_logits[valid_masks].to(torch.float32),
        reduction="sum",
    )
    return objectness_loss, localization_loss

# and would produce a nan loss).
        fg_inds = torch.nonzero((self.gt_classes >= 0) & (self.gt_classes < bg_class_ind)).squeeze(
            1
        )
        if cls_agnostic_bbox_reg:
            # pred_proposal_deltas only corresponds to foreground class for agnostic
            gt_class_cols = torch.arange(box_dim, device=device)
        else:
            fg_gt_classes = self.gt_classes[fg_inds]
            # pred_proposal_deltas for class k are located in columns [b * k : b * k + b],
            # where b is the dimension of box representation (4 or 5)
            # Note that compared to Detectron1,
            # we do not perform bounding box regression for background classes.
            gt_class_cols = box_dim * fg_gt_classes[:, None] + torch.arange(box_dim, device=device)

        loss_box_reg = smooth_l1_loss(
            self.pred_proposal_deltas[fg_inds[:, None], gt_class_cols],
            gt_proposal_deltas[fg_inds],
            self.smooth_l1_beta,
            reduction="sum",
        )
        # The loss is normalized using the total number of regions (R), not the number
        # of foreground regions even though the box regression loss is only defined on
        # foreground regions. Why? Because doing so gives equal training influence to
        # each foreground example. To see how, consider two different minibatches:
        #  (1) Contains a single foreground region
        #  (2) Contains 100 foreground regions
        # If we normalize by the number of foreground regions, the single example in
        # minibatch (1) will be given 100 times as much influence as each foreground
        # example in minibatch (2). Normalizing by the total number of regions, R,
        # means that the single example in minibatch (1) and each of the 100 examples
        # in minibatch (2) are given equal influence.