discopat.nn_training.torch_detection_utils.coco_eval

Functions

convert_to_xywh(boxes)

create_common_coco_eval(coco_eval, img_ids, ...)

evaluate(imgs)

merge(img_ids, eval_imgs)

Classes

COCOevalIoMean([cocoGt, cocoDt, iouType])

Replace IoU by IoMean.

CocoEvaluator(coco_gt, iou_types)

class discopat.nn_training.torch_detection_utils.coco_eval.COCOevalIoMean(cocoGt=None, cocoDt=None, iouType='segm')[source]

Bases: COCOeval

Replace IoU by IoMean.

computeIoMean(imgId, catId)[source]
computeIoU(imgId, catId)[source]
class discopat.nn_training.torch_detection_utils.coco_eval.CocoEvaluator(coco_gt, iou_types)[source]

Bases: object

accumulate()[source]
prepare(predictions, iou_type)[source]
prepare_for_coco_detection(predictions)[source]
prepare_for_coco_keypoint(predictions)[source]
prepare_for_coco_segmentation(predictions)[source]
summarize()[source]
synchronize_between_processes()[source]
update(predictions)[source]
discopat.nn_training.torch_detection_utils.coco_eval.convert_to_xywh(boxes)[source]
discopat.nn_training.torch_detection_utils.coco_eval.create_common_coco_eval(coco_eval, img_ids, eval_imgs)[source]
discopat.nn_training.torch_detection_utils.coco_eval.evaluate(imgs)[source]
discopat.nn_training.torch_detection_utils.coco_eval.merge(img_ids, eval_imgs)[source]