Overslaan naar inhoud

Referentie voor ultralytics/models/rtdetr/val.py

Opmerking

Dit bestand is beschikbaar op https://github.com/ultralytics/ ultralytics/blob/main/ ultralytics/models/rtdetr/val .py. Als je een probleem ziet, help het dan oplossen door een Pull Request 🛠️ bij te dragen. Bedankt 🙏!



ultralytics.models.rtdetr.val.RTDETRDataset

Basis: YOLODataset

Real-Time DEtection and TRacking (RT-DETR) dataset klasse die de basis YOLODataset klasse uitbreidt.

Deze gespecialiseerde datasetklasse is ontworpen voor gebruik met het RT-DETR objectdetectiemodel en is geoptimaliseerd voor realtime detectie- en volgtaken.

Broncode in ultralytics/models/rtdetr/val.py
class RTDETRDataset(YOLODataset):
    """
    Real-Time DEtection and TRacking (RT-DETR) dataset class extending the base YOLODataset class.

    This specialized dataset class is designed for use with the RT-DETR object detection model and is optimized for
    real-time detection and tracking tasks.
    """

    def __init__(self, *args, data=None, **kwargs):
        """Initialize the RTDETRDataset class by inheriting from the YOLODataset class."""
        super().__init__(*args, data=data, **kwargs)

    # NOTE: add stretch version load_image for RTDETR mosaic
    def load_image(self, i, rect_mode=False):
        """Loads 1 image from dataset index 'i', returns (im, resized hw)."""
        return super().load_image(i=i, rect_mode=rect_mode)

    def build_transforms(self, hyp=None):
        """Temporary, only for evaluation."""
        if self.augment:
            hyp.mosaic = hyp.mosaic if self.augment and not self.rect else 0.0
            hyp.mixup = hyp.mixup if self.augment and not self.rect else 0.0
            transforms = v8_transforms(self, self.imgsz, hyp, stretch=True)
        else:
            # transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), auto=False, scaleFill=True)])
            transforms = Compose([])
        transforms.append(
            Format(
                bbox_format="xywh",
                normalize=True,
                return_mask=self.use_segments,
                return_keypoint=self.use_keypoints,
                batch_idx=True,
                mask_ratio=hyp.mask_ratio,
                mask_overlap=hyp.overlap_mask,
            )
        )
        return transforms

__init__(*args, data=None, **kwargs)

Initialiseer de RTDETRDataset klasse door te erven van de YOLODataset klasse.

Broncode in ultralytics/models/rtdetr/val.py
def __init__(self, *args, data=None, **kwargs):
    """Initialize the RTDETRDataset class by inheriting from the YOLODataset class."""
    super().__init__(*args, data=data, **kwargs)

build_transforms(hyp=None)

Tijdelijk, alleen voor evaluatie.

Broncode in ultralytics/models/rtdetr/val.py
def build_transforms(self, hyp=None):
    """Temporary, only for evaluation."""
    if self.augment:
        hyp.mosaic = hyp.mosaic if self.augment and not self.rect else 0.0
        hyp.mixup = hyp.mixup if self.augment and not self.rect else 0.0
        transforms = v8_transforms(self, self.imgsz, hyp, stretch=True)
    else:
        # transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), auto=False, scaleFill=True)])
        transforms = Compose([])
    transforms.append(
        Format(
            bbox_format="xywh",
            normalize=True,
            return_mask=self.use_segments,
            return_keypoint=self.use_keypoints,
            batch_idx=True,
            mask_ratio=hyp.mask_ratio,
            mask_overlap=hyp.overlap_mask,
        )
    )
    return transforms

load_image(i, rect_mode=False)

Laadt 1 afbeelding uit dataset index 'i', retourneert (im, hw aangepast).

Broncode in ultralytics/models/rtdetr/val.py
def load_image(self, i, rect_mode=False):
    """Loads 1 image from dataset index 'i', returns (im, resized hw)."""
    return super().load_image(i=i, rect_mode=rect_mode)



ultralytics.models.rtdetr.val.RTDETRValidator

Basis: DetectionValidator

RTDETRValidator breidt de klasse DetectionValidator uit om validatiemogelijkheden te bieden die specifiek zijn afgestemd op het RT-DETR (Real-Time DETR) objectdetectiemodel.

De klasse maakt het mogelijk om een RTDETR-specifieke dataset te maken voor validatie, Non-maximum onderdrukking toe te passen voor nabewerking en werkt de evaluatiemetriek dienovereenkomstig bij.

Voorbeeld
from ultralytics.models.rtdetr import RTDETRValidator

args = dict(model='rtdetr-l.pt', data='coco8.yaml')
validator = RTDETRValidator(args=args)
validator()
Opmerking

Raadpleeg de bovenliggende DetectionValidator klasse voor meer details over de attributen en methoden.

Broncode in ultralytics/models/rtdetr/val.py
class RTDETRValidator(DetectionValidator):
    """
    RTDETRValidator extends the DetectionValidator class to provide validation capabilities specifically tailored for
    the RT-DETR (Real-Time DETR) object detection model.

    The class allows building of an RTDETR-specific dataset for validation, applies Non-maximum suppression for
    post-processing, and updates evaluation metrics accordingly.

    Example:
        ```python
        from ultralytics.models.rtdetr import RTDETRValidator

        args = dict(model='rtdetr-l.pt', data='coco8.yaml')
        validator = RTDETRValidator(args=args)
        validator()
        ```

    Note:
        For further details on the attributes and methods, refer to the parent DetectionValidator class.
    """

    def build_dataset(self, img_path, mode="val", batch=None):
        """
        Build an RTDETR Dataset.

        Args:
            img_path (str): Path to the folder containing images.
            mode (str): `train` mode or `val` mode, users are able to customize different augmentations for each mode.
            batch (int, optional): Size of batches, this is for `rect`. Defaults to None.
        """
        return RTDETRDataset(
            img_path=img_path,
            imgsz=self.args.imgsz,
            batch_size=batch,
            augment=False,  # no augmentation
            hyp=self.args,
            rect=False,  # no rect
            cache=self.args.cache or None,
            prefix=colorstr(f"{mode}: "),
            data=self.data,
        )

    def postprocess(self, preds):
        """Apply Non-maximum suppression to prediction outputs."""
        if not isinstance(preds, (list, tuple)):  # list for PyTorch inference but list[0] Tensor for export inference
            preds = [preds, None]

        bs, _, nd = preds[0].shape
        bboxes, scores = preds[0].split((4, nd - 4), dim=-1)
        bboxes *= self.args.imgsz
        outputs = [torch.zeros((0, 6), device=bboxes.device)] * bs
        for i, bbox in enumerate(bboxes):  # (300, 4)
            bbox = ops.xywh2xyxy(bbox)
            score, cls = scores[i].max(-1)  # (300, )
            # Do not need threshold for evaluation as only got 300 boxes here
            # idx = score > self.args.conf
            pred = torch.cat([bbox, score[..., None], cls[..., None]], dim=-1)  # filter
            # Sort by confidence to correctly get internal metrics
            pred = pred[score.argsort(descending=True)]
            outputs[i] = pred  # [idx]

        return outputs

    def _prepare_batch(self, si, batch):
        """Prepares a batch for training or inference by applying transformations."""
        idx = batch["batch_idx"] == si
        cls = batch["cls"][idx].squeeze(-1)
        bbox = batch["bboxes"][idx]
        ori_shape = batch["ori_shape"][si]
        imgsz = batch["img"].shape[2:]
        ratio_pad = batch["ratio_pad"][si]
        if len(cls):
            bbox = ops.xywh2xyxy(bbox)  # target boxes
            bbox[..., [0, 2]] *= ori_shape[1]  # native-space pred
            bbox[..., [1, 3]] *= ori_shape[0]  # native-space pred
        return {"cls": cls, "bbox": bbox, "ori_shape": ori_shape, "imgsz": imgsz, "ratio_pad": ratio_pad}

    def _prepare_pred(self, pred, pbatch):
        """Prepares and returns a batch with transformed bounding boxes and class labels."""
        predn = pred.clone()
        predn[..., [0, 2]] *= pbatch["ori_shape"][1] / self.args.imgsz  # native-space pred
        predn[..., [1, 3]] *= pbatch["ori_shape"][0] / self.args.imgsz  # native-space pred
        return predn.float()

build_dataset(img_path, mode='val', batch=None)

Een RTDETR-dataset samenstellen.

Parameters:

Naam Type Beschrijving Standaard
img_path str

Pad naar de map met afbeeldingen.

vereist
mode str

train modus of val modus kunnen gebruikers verschillende augmentaties voor elke modus aanpassen.

'val'
batch int

Grootte van batches, dit is voor rect. Staat standaard op Geen.

None
Broncode in ultralytics/models/rtdetr/val.py
def build_dataset(self, img_path, mode="val", batch=None):
    """
    Build an RTDETR Dataset.

    Args:
        img_path (str): Path to the folder containing images.
        mode (str): `train` mode or `val` mode, users are able to customize different augmentations for each mode.
        batch (int, optional): Size of batches, this is for `rect`. Defaults to None.
    """
    return RTDETRDataset(
        img_path=img_path,
        imgsz=self.args.imgsz,
        batch_size=batch,
        augment=False,  # no augmentation
        hyp=self.args,
        rect=False,  # no rect
        cache=self.args.cache or None,
        prefix=colorstr(f"{mode}: "),
        data=self.data,
    )

postprocess(preds)

Pas niet-maximale onderdrukking toe op voorspellingsuitgangen.

Broncode in ultralytics/models/rtdetr/val.py
def postprocess(self, preds):
    """Apply Non-maximum suppression to prediction outputs."""
    if not isinstance(preds, (list, tuple)):  # list for PyTorch inference but list[0] Tensor for export inference
        preds = [preds, None]

    bs, _, nd = preds[0].shape
    bboxes, scores = preds[0].split((4, nd - 4), dim=-1)
    bboxes *= self.args.imgsz
    outputs = [torch.zeros((0, 6), device=bboxes.device)] * bs
    for i, bbox in enumerate(bboxes):  # (300, 4)
        bbox = ops.xywh2xyxy(bbox)
        score, cls = scores[i].max(-1)  # (300, )
        # Do not need threshold for evaluation as only got 300 boxes here
        # idx = score > self.args.conf
        pred = torch.cat([bbox, score[..., None], cls[..., None]], dim=-1)  # filter
        # Sort by confidence to correctly get internal metrics
        pred = pred[score.argsort(descending=True)]
        outputs[i] = pred  # [idx]

    return outputs





Gemaakt 2023-11-12, bijgewerkt 2024-06-02
Auteurs: glenn-jocher (5), Burhan-Q (1), Laughing-q (1)