─░├žeri─če ge├ž

Referans i├žin ultralytics/models/nas/val.py

Not

Bu dosya https://github.com/ultralytics/ultralytics/blob/main/ ultralytics/models/nas/val .py adresinde mevcuttur. Bir sorun tespit ederseniz l├╝tfen bir ├çekme ─░ste─či ­čŤá´ŞĆ ile katk─▒da bulunarak d├╝zeltilmesine yard─▒mc─▒ olun. Te┼čekk├╝rler ­čÖĆ!



ultralytics.models.nas.val.NASValidator

├ťsler: DetectionValidator

Ultralytics YOLO Nesne alg─▒lama i├žin NAS Validator.

Geni┼čletir DetectionValidator Ultralytics modeller paketinden al─▒nm─▒┼čt─▒r ve ham tahminleri sonradan i┼člemek i├žin tasarlanm─▒┼čt─▒r YOLO NAS modelleri taraf─▒ndan olu┼čturulmu┼čtur. ├ťst ├╝ste binen ve d├╝┼č├╝k g├╝venirlikli kutular─▒ kald─▒rmak i├žin maksimum olmayan bast─▒rma ger├žekle┼čtirir, Nihai olarak nihai tespitleri ├╝retir.

Nitelikler:

─░sim Tip A├ž─▒klama
args Namespace

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

lb Tensor

├çok etiketli NMS i├žin iste─če ba─čl─▒ tensor .

├ľrnek
from ultralytics import NAS

model = NAS('yolo_nas_s')
validator = model.validator
# Assumes that raw_preds are available
final_preds = validator.postprocess(raw_preds)
Not

Bu s─▒n─▒f genellikle do─črudan ├Ârneklenmez, ancak dahili olarak NAS S─▒n─▒f.

Kaynak kodu 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)

Tahmin ├ž─▒k─▒┼člar─▒na maksimum olmayan bast─▒rma uygulay─▒n.

Kaynak kodu 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)