o V h @s:ddlZddlmZddlmZdgZGdddeZdS)N)DetectionValidator)ops NASValidatorcs eZdZdZfddZZS)ra Ultralytics YOLO NAS Validator for object detection. Extends `DetectionValidator` from the Ultralytics models package and is designed to post-process the raw predictions generated by YOLO NAS models. It performs non-maximum suppression to remove overlapping and low-confidence boxes, ultimately producing the final detections. Attributes: args (Namespace): Namespace containing various configurations for post-processing, such as confidence and IoU thresholds. lb (torch.Tensor): Optional tensor for multilabel NMS. Examples: >>> from ultralytics import NAS >>> model = NAS("yolo_nas_s") >>> validator = model.validator Assumes that raw_preds are available >>> final_preds = validator.postprocess(raw_preds) Notes: This class is generally not instantiated directly but is used internally within the `NAS` class. cs@t|dd}t||ddfdddd}t|S)z4Apply Non-maximum suppression to prediction outputs.r)r xyxy2xywhtorchcatpermutesuper postprocess)selfpreds_inboxespreds __class__N/var/www/vscode/kcb/lib/python3.10/site-packages/ultralytics/models/nas/val.pyr #s" zNASValidator.postprocess)__name__ __module__ __qualname____doc__r __classcell__rrrrr s)r ultralytics.models.yolo.detectrultralytics.utilsr__all__rrrrrs