Zum Inhalt springen

Referenz fĂŒr ultralytics/models/nas/val.py

Hinweis

Diese Datei ist verfĂŒgbar unter https://github.com/ultralytics/ ultralytics/blob/main/ ultralytics/models/nas/val .py. Wenn du ein Problem entdeckst, hilf bitte mit, es zu beheben, indem du einen Pull Request đŸ› ïž einreichst. Vielen Dank 🙏!



ultralytics.models.nas.val.NASValidator

Basen: DetectionValidator

Ultralytics YOLO NAS Validator fĂŒr die Objekterkennung.

Erweitert DetectionValidator aus dem Paket Ultralytics models und dient der Nachbearbeitung der Rohvorhersagen die von den YOLO NAS-Modellen erstellt wurden. Es fĂŒhrt eine nicht-maximale UnterdrĂŒckung durch, um ĂŒberlappende Boxen und solche mit niedriger Konfidenz zu entfernen, um schließlich die endgĂŒltigen Entdeckungen zu erhalten.

Attribute:

Name Typ Beschreibung
args Namespace

Namespace containing various configurations for post-processing, such as confidence and IoU.

lb Tensor

Optional tensor fĂŒr Multilabel-NMS.

Beispiel
from ultralytics import NAS

model = NAS('yolo_nas_s')
validator = model.validator
# Assumes that raw_preds are available
final_preds = validator.postprocess(raw_preds)
Hinweis

Diese Klasse wird in der Regel nicht direkt instanziiert, sondern wird intern innerhalb der NAS Klasse.

Quellcode in ultralytics/models/nas/val.py
class NASValidator(DetectionValidator):
    """
    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.
        lb (torch.Tensor): Optional tensor for multilabel NMS.

    Example:
        ```python
        from ultralytics import NAS

        model = NAS('yolo_nas_s')
        validator = model.validator
        # Assumes that raw_preds are available
        final_preds = validator.postprocess(raw_preds)
        ```

    Note:
        This class is generally not instantiated directly but is used internally within the `NAS` class.
    """

    def postprocess(self, preds_in):
        """Apply Non-maximum suppression to prediction outputs."""
        boxes = ops.xyxy2xywh(preds_in[0][0])
        preds = torch.cat((boxes, preds_in[0][1]), -1).permute(0, 2, 1)
        return ops.non_max_suppression(
            preds,
            self.args.conf,
            self.args.iou,
            labels=self.lb,
            multi_label=False,
            agnostic=self.args.single_cls,
            max_det=self.args.max_det,
            max_time_img=0.5,
        )

postprocess(preds_in)

Wende die Nicht-Maximum-UnterdrĂŒckung auf die VorhersageausgĂ€nge an.

Quellcode in ultralytics/models/nas/val.py
def postprocess(self, preds_in):
    """Apply Non-maximum suppression to prediction outputs."""
    boxes = ops.xyxy2xywh(preds_in[0][0])
    preds = torch.cat((boxes, preds_in[0][1]), -1).permute(0, 2, 1)
    return ops.non_max_suppression(
        preds,
        self.args.conf,
        self.args.iou,
        labels=self.lb,
        multi_label=False,
        agnostic=self.args.single_cls,
        max_det=self.args.max_det,
        max_time_img=0.5,
    )





Created 2023-11-12, Updated 2024-06-02
Authors: glenn-jocher (5), Burhan-Q (1)