Mmdetection: A little question, why "+1" here?

[lfydegithub]

https://github.com/open-mmlab/mmdetection/blob/482f60fe55c364e50e4fc4b50893a25d8cc261b0/mmdet/core/bbox/assigners/grid_assigner.py#L130

just a question from a fan.

[kellenf]

1.notice in line149 is assigned_gt_inds[pos_inds] - 1
2.notice in class AssignResult:
```python
class AssignResult(util_mixins.NiceRepr):
"""Stores assignments between predicted and truth boxes.

Attributes:
    num_gts (int): the number of truth boxes considered when computing this
        assignment

    gt_inds (LongTensor): for each predicted box indicates the 1-based
        index of the assigned truth box. 0 means unassigned and -1 means
        ignore.

    max_overlaps (FloatTensor): the iou between the predicted box and its
        assigned truth box.

    labels (None | LongTensor): If specified, for each predicted box
        indicates the category label of the assigned truth box.

gt_inds: 0 means unassigned and -1 means ignore. This setting make this code make you confused, help this can help you!

[lfydegithub]

1.notice in line149 is assigned_gt_inds[pos_inds] - 1
2.notice in class AssignResult:

class AssignResult(util_mixins.NiceRepr):
    """Stores assignments between predicted and truth boxes.

    Attributes:
        num_gts (int): the number of truth boxes considered when computing this
            assignment

        gt_inds (LongTensor): for each predicted box indicates the 1-based
            index of the assigned truth box. 0 means unassigned and -1 means
            ignore.

        max_overlaps (FloatTensor): the iou between the predicted box and its
            assigned truth box.

        labels (None | LongTensor): If specified, for each predicted box
            indicates the category label of the assigned truth box.


gt_inds: 0 means unassigned and -1 means ignore. This setting make this code make you confused, help this can help you!

very useful !!!, thank you very much. I should known that...