Reference for ultralytics/models/rtdetr/val.py

def build_transforms(self, hyp=None):
    """
    Build transformation pipeline for the dataset.

    Args:
        hyp (dict, optional): Hyperparameters for transformations.

    Returns:
        (Compose): Composition of transformation functions.
    """
    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
        hyp.cutmix = hyp.cutmix 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, scale_fill=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

def load_image(self, i, rect_mode=False):
    """
    Load one image from dataset index 'i'.

    Args:
        i (int): Index of the image to load.
        rect_mode (bool, optional): Whether to use rectangular mode for batch inference.

    Returns:
        im (torch.Tensor): The loaded image.
        resized_hw (tuple): Height and width of the resized image with shape (2,).

    Examples:
        Load an image from the dataset
        >>> dataset = RTDETRDataset(img_path="path/to/images")
        >>> image, hw = dataset.load_image(0)
    """
    return super().load_image(i=i, rect_mode=rect_mode)

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, optional): `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`.

    Returns:
        (RTDETRDataset): Dataset configured for RT-DETR validation.
    """
    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: Union[torch.Tensor, List[torch.Tensor], Tuple[torch.Tensor]]
) -> List[Dict[str, torch.Tensor]]:
    """
    Apply Non-maximum suppression to prediction outputs.

    Args:
        preds (torch.Tensor | List | Tuple): Raw predictions from the model. If tensor, should have shape
            (batch_size, num_predictions, num_classes + 4) where last dimension contains bbox coords and class scores.

    Returns:
        (List[Dict[str, torch.Tensor]]): List of dictionaries for each image, each containing:
            - 'bboxes': Tensor of shape (N, 4) with bounding box coordinates
            - 'conf': Tensor of shape (N,) with confidence scores
            - 'cls': Tensor of shape (N,) with class indices
    """
    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, )
        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[score > self.args.conf]

    return [{"bboxes": x[:, :4], "conf": x[:, 4], "cls": x[:, 5]} for x in outputs]