Method forward

semantic_sam/modules/matcher.py:196–219

Performs the matching Params: outputs: This is a dict that contains at least these entries: "pred_logits": Tensor of dim [batch_size, num_queries, num_classes] with the classification logits "pred_masks": Tensor of dim [batch_size, num_queries,

(self, outputs, targets, cost=["cls", "box", "mask"], mode='default', extra={})

    @torch.no_grad()
    def forward(self, outputs, targets, cost=["cls", "box", "mask"], mode='default', extra={}):
        """Performs the matching

        Params:
            outputs: This is a dict that contains at least these entries:
                 "pred_logits": Tensor of dim [batch_size, num_queries, num_classes] with the classification logits
                 "pred_masks": Tensor of dim [batch_size, num_queries, H_pred, W_pred] with the predicted masks

            targets: This is a list of targets (len(targets) = batch_size), where each target is a dict containing:
                 "labels": Tensor of dim [num_target_boxes] (where num_target_boxes is the number of ground-truth
                           objects in the target) containing the class labels
                 "masks": Tensor of dim [num_target_boxes, H_gt, W_gt] containing the target masks

        Returns:
            A list of size batch_size, containing tuples of (index_i, index_j) where:
                - index_i is the indices of the selected predictions (in order)
                - index_j is the indices of the corresponding selected targets (in order)
            For each batch element, it holds:
                len(index_i) = len(index_j) = min(num_queries, num_target_boxes)
        """
        if mode == 'default':
            return self.memory_efficient_forward(outputs, targets, cost)
        else:
            assert False, "Mode {} is not supported.".format(mode)

    def __repr__(self, _repr_indent=4):
        head = "Matcher " + self.__class__.__name__