Skip to content

Reference for ultralytics/models/rtdetr/val.py

Note

This file is available at https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/rtdetr/val.py. If you spot a problem please help fix it by contributing a Pull Request 🛠️. Thank you 🙏!


ultralytics.models.rtdetr.val.RTDETRDataset 

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

Bases: 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.

Source code in ultralytics/models/rtdetr/val.py 
21
22
23
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 

build_transforms(hyp=None)

Build transformation pipeline for the dataset.

Parameters:

Name Type Description Default
hyp dict

Hyperparameters for transformations.

 None

Returns:

Type Description
Compose

Composition of transformation functions.
Source code in ultralytics/models/rtdetr/val.py 
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
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
        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

load_image 

load_image(i, rect_mode=False)

Loads 1 image from dataset index 'i', returns (im, resized hw).

Source code in ultralytics/models/rtdetr/val.py 
25
26
27
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 

RTDETRValidator(
    dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None
)

Bases: 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.

Examples:

>>> 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.

Source code in ultralytics/models/yolo/detect/val.py 
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=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.
        pbar (Any, optional): Progress bar for displaying progress.
        args (dict, optional): Arguments for the validator.
        _callbacks (list, optional): List of callback functions.
    """
    super().__init__(dataloader, save_dir, pbar, args, _callbacks)
    self.nt_per_class = None
    self.nt_per_image = None
    self.is_coco = False
    self.is_lvis = False
    self.class_map = None
    self.args.task = "detect"
    self.metrics = DetMetrics(save_dir=self.save_dir)
    self.iouv = torch.linspace(0.5, 0.95, 10)  # IoU vector for mAP@0.5:0.95
    self.niou = self.iouv.numel()
    self.lb = []  # for autolabelling
    if self.args.save_hybrid and self.args.task == "detect":
        LOGGER.warning(
            "WARNING ⚠️ 'save_hybrid=True' will append ground truth to predictions for autolabelling.\n"
            "WARNING ⚠️ 'save_hybrid=True' will cause incorrect mAP.\n"
        )

build_dataset 

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

Build an RTDETR Dataset.

Parameters:

Name Type Description Default
img_path str

Path to the folder containing images.

 required
mode str

train mode or val mode, users are able to customize different augmentations for each mode.

 'val'
batch int

Size of batches, this is for rect.

 None

Returns:

Type Description
RTDETRDataset

Dataset configured for RT-DETR validation.
Source code in ultralytics/models/rtdetr/val.py 
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
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`.

    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,
    )

postprocess 

postprocess(preds)

Apply Non-maximum suppression to prediction outputs.

Parameters:

Name Type Description Default
preds List | Tuple | Tensor

Raw predictions from the model.

 required

Returns:

Type Description
List[Tensor]

List of processed predictions for each image in batch.
Source code in ultralytics/models/rtdetr/val.py 
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
def postprocess(self, preds):
    """
    Apply Non-maximum suppression to prediction outputs.

    Args:
        preds (List | Tuple | torch.Tensor): Raw predictions from the model.

    Returns:
        (List[torch.Tensor]): List of processed predictions for each image in batch.
    """
    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



📅 Created 1 year ago ✏️ Updated 6 months ago
jk4e glenn-jocher Burhan-Q Laughing-q