core.services.model.evaluator.utils.compute_confusion_matrix

compute_confusion_matrix

Functions:

Name	Description
box_iou	Calculate intersection-over-union (IoU) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
compute_full_confusion_matrix	Compute a confusion matrix for object detection with a background class.
compute_confusion_matrix_impl

box_iou(box1, box2, eps=1e-07)

Calculate intersection-over-union (IoU) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. Based on https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py.

Parameters:

Name	Type	Description	Default
box1	Tensor	A tensor of shape (N, 4) representing N bounding boxes.	required
box2	Tensor	A tensor of shape (M, 4) representing M bounding boxes.	required
eps	float	A small value to avoid division by zero. Defaults to 1e-7.	1e-07

Returns:

Type	Description
Tensor	An NxM tensor containing the pairwise IoU values for every element in box1 and box2.

compute_full_confusion_matrix(gt_annotations, pred_annotations, label_map, iou_threshold=0.5)

Compute a confusion matrix for object detection with a background class.

Parameters:

Name	Type	Description	Default
gt_annotations	List[dict]	Ground truth annotations from COCO GT (coco.loadAnns()).	required
pred_annotations	List[dict]	Predicted annotations from COCO Pred (coco.loadAnns()).	required
label_map	dict	Mapping of category indices (as int) to class names.	required
iou_threshold	float	IoU threshold for matching.	0.5

Returns:

Type	Description
ndarray	np.ndarray: Confusion matrix of shape (num_classes+1, num_classes+1) where the last index represents 'background'.

compute_confusion_matrix_impl(coco_gt, coco_pred, label_map, training_labelmap, experiment_logger)