def forward()

in mask_former/modeling/criterion.py [0:0]

• 21 lines of code
• 12 McCabe index (conditional complexity)

    def forward(self, outputs, targets):
        """This performs the loss computation.
        Parameters:
             outputs: dict of tensors, see the output specification of the model for the format
             targets: list of dicts, such that len(targets) == batch_size.
                      The expected keys in each dict depends on the losses applied, see each loss' doc
        """
        outputs_without_aux = {k: v for k, v in outputs.items() if k != "aux_outputs"}

        # Retrieve the matching between the outputs of the last layer and the targets
        indices = self.matcher(outputs_without_aux, targets)

        # Compute the average number of target boxes accross all nodes, for normalization purposes
        num_masks = sum(len(t["labels"]) for t in targets)
        num_masks = torch.as_tensor(
            [num_masks], dtype=torch.float, device=next(iter(outputs.values())).device
        )
        if is_dist_avail_and_initialized():
            torch.distributed.all_reduce(num_masks)
        num_masks = torch.clamp(num_masks / get_world_size(), min=1).item()

        # Compute all the requested losses
        losses = {}
        for loss in self.losses:
            losses.update(self.get_loss(loss, outputs, targets, indices, num_masks))

        # In case of auxiliary losses, we repeat this process with the output of each intermediate layer.
        if "aux_outputs" in outputs:
            for i, aux_outputs in enumerate(outputs["aux_outputs"]):
                indices = self.matcher(aux_outputs, targets)
                for loss in self.losses:
                    l_dict = self.get_loss(loss, aux_outputs, targets, indices, num_masks)
                    l_dict = {k + f"_{i}": v for k, v in l_dict.items()}
                    losses.update(l_dict)

        return losses