otx.algorithms.detection.adapters.mmdet.models.assigners#
Initial file for mmdetection assigners.
Classes
|
Assign a corresponding gt bbox or background to each bbox. |
- class otx.algorithms.detection.adapters.mmdet.models.assigners.CustomMaxIoUAssigner(pos_iou_thr, neg_iou_thr, min_pos_iou=0.0, gt_max_assign_all=True, ignore_iof_thr=-1, ignore_wrt_candidates=True, match_low_quality=True, gpu_assign_thr=-1, iou_calculator={'type': 'BboxOverlaps2D'})[source]#
Bases:
MaxIoUAssigner
Assign a corresponding gt bbox or background to each bbox.
Each proposals will be assigned with -1, or a semi-positive integer indicating the ground truth index.
-1: negative sample, no assigned gt
semi-positive integer: positive sample, index (0-based) of assigned gt
This CustomMaxIoUAssigner patches assign funtion of mmdet’s MaxIouAssigner so that it can prevent CPU OOM for images whose gt is extremely large
- assign(bboxes, gt_bboxes, gt_bboxes_ignore=None, gt_labels=None)[source]#
Assign gt to bboxes.
This method assign a gt bbox to every bbox (proposal/anchor), each bbox will be assigned with -1, or a semi-positive number. -1 means negative sample, semi-positive number is the index (0-based) of assigned gt. The assignment is done in following steps, the order matters.
Especially CustomMaxIoUAssigner split gt_bboxes tensor into small tensors when gt_bboxes is too large.
assign every bbox to the background
assign proposals whose iou with all gts < neg_iou_thr to 0
for each bbox, if the iou with its nearest gt >= pos_iou_thr, assign it to that bbox
for each gt bbox, assign its nearest proposals (may be more than one) to itself
- Parameters:
bboxes (Tensor) – Bounding boxes to be assigned, shape(n, 4).
gt_bboxes (Tensor) – Groundtruth boxes, shape (k, 4).
gt_bboxes_ignore (Tensor, optional) – Ground truth bboxes that are labelled as ignored, e.g., crowd boxes in COCO.
gt_labels (Tensor, optional) – Label of gt_bboxes, shape (k, ).
- Returns:
The assign result.
- Return type:
AssignResult
Example
>>> self = MaxIoUAssigner(0.5, 0.5) >>> bboxes = torch.Tensor([[0, 0, 10, 10], [10, 10, 20, 20]]) >>> gt_bboxes = torch.Tensor([[0, 0, 10, 9]]) >>> assign_result = self.assign(bboxes, gt_bboxes) >>> expected_gt_inds = torch.LongTensor([1, 0]) >>> assert torch.all(assign_result.gt_inds == expected_gt_inds)