Reference for ultralytics/models/nas/val.py

Bases: DetectionValidator

              flowchart TD
              ultralytics.models.nas.val.NASValidator[NASValidator]
              ultralytics.models.yolo.detect.val.DetectionValidator[DetectionValidator]
              ultralytics.engine.validator.BaseValidator[BaseValidator]

                              ultralytics.models.yolo.detect.val.DetectionValidator --> ultralytics.models.nas.val.NASValidator
                                ultralytics.engine.validator.BaseValidator --> ultralytics.models.yolo.detect.val.DetectionValidator
                



              click ultralytics.models.nas.val.NASValidator href "" "ultralytics.models.nas.val.NASValidator"
              click ultralytics.models.yolo.detect.val.DetectionValidator href "" "ultralytics.models.yolo.detect.val.DetectionValidator"
              click ultralytics.engine.validator.BaseValidator href "" "ultralytics.engine.validator.BaseValidator"
            

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:

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)

45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61

def __init__(self, dataloader=None, save_dir=None, args=None, _callbacks=None) -> None:
    """Initialize detection validator with necessary variables and settings.

    Args:
        dataloader (torch.utils.data.DataLoader, optional): Dataloader to use for validation.
        save_dir (Path, optional): Directory to save results.
        args (dict[str, Any], optional): Arguments for the validator.
        _callbacks (list[Any], optional): List of callback functions.
    """
    super().__init__(dataloader, save_dir, args, _callbacks)
    self.is_coco = False
    self.is_lvis = False
    self.class_map = None
    self.args.task = "detect"
    self.iouv = torch.linspace(0.5, 0.95, 10)  # IoU vector for mAP@0.5:0.95
    self.niou = self.iouv.numel()
    self.metrics = DetMetrics()

postprocess(preds_in)

34
35
36
37
38

def postprocess(self, preds_in):
    """Apply Non-maximum suppression to prediction outputs."""
    boxes = ops.xyxy2xywh(preds_in[0][0])  # Convert bounding box format from xyxy to xywh
    preds = torch.cat((boxes, preds_in[0][1]), -1).permute(0, 2, 1)  # Concatenate boxes with scores and permute
    return super().postprocess(preds)