Skip to content

Reference for ultralytics/engine/results.py

Note

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



ultralytics.engine.results.BaseTensor

Bases: SimpleClass

Base tensor class with additional methods for easy manipulation and device handling.

Source code in ultralytics/engine/results.py
class BaseTensor(SimpleClass):
    """Base tensor class with additional methods for easy manipulation and device handling."""

    def __init__(self, data, orig_shape) -> None:
        """
        Initialize BaseTensor with data and original shape.

        Args:
            data (torch.Tensor | np.ndarray): Predictions, such as bboxes, masks and keypoints.
            orig_shape (tuple): Original shape of image.
        """
        assert isinstance(data, (torch.Tensor, np.ndarray))
        self.data = data
        self.orig_shape = orig_shape

    @property
    def shape(self):
        """Return the shape of the data tensor."""
        return self.data.shape

    def cpu(self):
        """Return a copy of the tensor on CPU memory."""
        return self if isinstance(self.data, np.ndarray) else self.__class__(self.data.cpu(), self.orig_shape)

    def numpy(self):
        """Return a copy of the tensor as a numpy array."""
        return self if isinstance(self.data, np.ndarray) else self.__class__(self.data.numpy(), self.orig_shape)

    def cuda(self):
        """Return a copy of the tensor on GPU memory."""
        return self.__class__(torch.as_tensor(self.data).cuda(), self.orig_shape)

    def to(self, *args, **kwargs):
        """Return a copy of the tensor with the specified device and dtype."""
        return self.__class__(torch.as_tensor(self.data).to(*args, **kwargs), self.orig_shape)

    def __len__(self):  # override len(results)
        """Return the length of the data tensor."""
        return len(self.data)

    def __getitem__(self, idx):
        """Return a BaseTensor with the specified index of the data tensor."""
        return self.__class__(self.data[idx], self.orig_shape)

shape property

Return the shape of the data tensor.

__getitem__(idx)

Return a BaseTensor with the specified index of the data tensor.

Source code in ultralytics/engine/results.py
def __getitem__(self, idx):
    """Return a BaseTensor with the specified index of the data tensor."""
    return self.__class__(self.data[idx], self.orig_shape)

__init__(data, orig_shape)

Initialize BaseTensor with data and original shape.

Parameters:

Name Type Description Default
data Tensor | ndarray

Predictions, such as bboxes, masks and keypoints.

required
orig_shape tuple

Original shape of image.

required
Source code in ultralytics/engine/results.py
def __init__(self, data, orig_shape) -> None:
    """
    Initialize BaseTensor with data and original shape.

    Args:
        data (torch.Tensor | np.ndarray): Predictions, such as bboxes, masks and keypoints.
        orig_shape (tuple): Original shape of image.
    """
    assert isinstance(data, (torch.Tensor, np.ndarray))
    self.data = data
    self.orig_shape = orig_shape

__len__()

Return the length of the data tensor.

Source code in ultralytics/engine/results.py
def __len__(self):  # override len(results)
    """Return the length of the data tensor."""
    return len(self.data)

cpu()

Return a copy of the tensor on CPU memory.

Source code in ultralytics/engine/results.py
def cpu(self):
    """Return a copy of the tensor on CPU memory."""
    return self if isinstance(self.data, np.ndarray) else self.__class__(self.data.cpu(), self.orig_shape)

cuda()

Return a copy of the tensor on GPU memory.

Source code in ultralytics/engine/results.py
def cuda(self):
    """Return a copy of the tensor on GPU memory."""
    return self.__class__(torch.as_tensor(self.data).cuda(), self.orig_shape)

numpy()

Return a copy of the tensor as a numpy array.

Source code in ultralytics/engine/results.py
def numpy(self):
    """Return a copy of the tensor as a numpy array."""
    return self if isinstance(self.data, np.ndarray) else self.__class__(self.data.numpy(), self.orig_shape)

to(*args, **kwargs)

Return a copy of the tensor with the specified device and dtype.

Source code in ultralytics/engine/results.py
def to(self, *args, **kwargs):
    """Return a copy of the tensor with the specified device and dtype."""
    return self.__class__(torch.as_tensor(self.data).to(*args, **kwargs), self.orig_shape)



ultralytics.engine.results.Results

Bases: SimpleClass

A class for storing and manipulating inference results.

Attributes:

Name Type Description
orig_img ndarray

Original image as a numpy array.

orig_shape tuple

Original image shape in (height, width) format.

boxes Boxes

Object containing detection bounding boxes.

masks Masks

Object containing detection masks.

probs Probs

Object containing class probabilities for classification tasks.

keypoints Keypoints

Object containing detected keypoints for each object.

speed dict

Dictionary of preprocess, inference, and postprocess speeds (ms/image).

names dict

Dictionary of class names.

path str

Path to the image file.

Methods:

Name Description
update

Updates object attributes with new detection results.

cpu

Returns a copy of the Results object with all tensors on CPU memory.

numpy

Returns a copy of the Results object with all tensors as numpy arrays.

cuda

Returns a copy of the Results object with all tensors on GPU memory.

to

Returns a copy of the Results object with tensors on a specified device and dtype.

new

Returns a new Results object with the same image, path, and names.

plot

Plots detection results on an input image, returning an annotated image.

show

Show annotated results to screen.

save

Save annotated results to file.

verbose

Returns a log string for each task, detailing detections and classifications.

save_txt

Saves detection results to a text file.

save_crop

Saves cropped detection images.

tojson

Converts detection results to JSON format.

Source code in ultralytics/engine/results.py
class Results(SimpleClass):
    """
    A class for storing and manipulating inference results.

    Attributes:
        orig_img (numpy.ndarray): Original image as a numpy array.
        orig_shape (tuple): Original image shape in (height, width) format.
        boxes (Boxes, optional): Object containing detection bounding boxes.
        masks (Masks, optional): Object containing detection masks.
        probs (Probs, optional): Object containing class probabilities for classification tasks.
        keypoints (Keypoints, optional): Object containing detected keypoints for each object.
        speed (dict): Dictionary of preprocess, inference, and postprocess speeds (ms/image).
        names (dict): Dictionary of class names.
        path (str): Path to the image file.

    Methods:
        update(boxes=None, masks=None, probs=None, obb=None): Updates object attributes with new detection results.
        cpu(): Returns a copy of the Results object with all tensors on CPU memory.
        numpy(): Returns a copy of the Results object with all tensors as numpy arrays.
        cuda(): Returns a copy of the Results object with all tensors on GPU memory.
        to(*args, **kwargs): Returns a copy of the Results object with tensors on a specified device and dtype.
        new(): Returns a new Results object with the same image, path, and names.
        plot(...): Plots detection results on an input image, returning an annotated image.
        show(): Show annotated results to screen.
        save(filename): Save annotated results to file.
        verbose(): Returns a log string for each task, detailing detections and classifications.
        save_txt(txt_file, save_conf=False): Saves detection results to a text file.
        save_crop(save_dir, file_name=Path("im.jpg")): Saves cropped detection images.
        tojson(normalize=False): Converts detection results to JSON format.
    """

    def __init__(self, orig_img, path, names, boxes=None, masks=None, probs=None, keypoints=None, obb=None) -> None:
        """
        Initialize the Results class.

        Args:
            orig_img (numpy.ndarray): The original image as a numpy array.
            path (str): The path to the image file.
            names (dict): A dictionary of class names.
            boxes (torch.tensor, optional): A 2D tensor of bounding box coordinates for each detection.
            masks (torch.tensor, optional): A 3D tensor of detection masks, where each mask is a binary image.
            probs (torch.tensor, optional): A 1D tensor of probabilities of each class for classification task.
            keypoints (torch.tensor, optional): A 2D tensor of keypoint coordinates for each detection.
            obb (torch.tensor, optional): A 2D tensor of oriented bounding box coordinates for each detection.
        """
        self.orig_img = orig_img
        self.orig_shape = orig_img.shape[:2]
        self.boxes = Boxes(boxes, self.orig_shape) if boxes is not None else None  # native size boxes
        self.masks = Masks(masks, self.orig_shape) if masks is not None else None  # native size or imgsz masks
        self.probs = Probs(probs) if probs is not None else None
        self.keypoints = Keypoints(keypoints, self.orig_shape) if keypoints is not None else None
        self.obb = OBB(obb, self.orig_shape) if obb is not None else None
        self.speed = {"preprocess": None, "inference": None, "postprocess": None}  # milliseconds per image
        self.names = names
        self.path = path
        self.save_dir = None
        self._keys = "boxes", "masks", "probs", "keypoints", "obb"

    def __getitem__(self, idx):
        """Return a Results object for the specified index."""
        return self._apply("__getitem__", idx)

    def __len__(self):
        """Return the number of detections in the Results object."""
        for k in self._keys:
            v = getattr(self, k)
            if v is not None:
                return len(v)

    def update(self, boxes=None, masks=None, probs=None, obb=None):
        """Update the boxes, masks, and probs attributes of the Results object."""
        if boxes is not None:
            self.boxes = Boxes(ops.clip_boxes(boxes, self.orig_shape), self.orig_shape)
        if masks is not None:
            self.masks = Masks(masks, self.orig_shape)
        if probs is not None:
            self.probs = probs
        if obb is not None:
            self.obb = OBB(obb, self.orig_shape)

    def _apply(self, fn, *args, **kwargs):
        """
        Applies a function to all non-empty attributes and returns a new Results object with modified attributes. This
        function is internally called by methods like .to(), .cuda(), .cpu(), etc.

        Args:
            fn (str): The name of the function to apply.
            *args: Variable length argument list to pass to the function.
            **kwargs: Arbitrary keyword arguments to pass to the function.

        Returns:
            Results: A new Results object with attributes modified by the applied function.
        """
        r = self.new()
        for k in self._keys:
            v = getattr(self, k)
            if v is not None:
                setattr(r, k, getattr(v, fn)(*args, **kwargs))
        return r

    def cpu(self):
        """Return a copy of the Results object with all tensors on CPU memory."""
        return self._apply("cpu")

    def numpy(self):
        """Return a copy of the Results object with all tensors as numpy arrays."""
        return self._apply("numpy")

    def cuda(self):
        """Return a copy of the Results object with all tensors on GPU memory."""
        return self._apply("cuda")

    def to(self, *args, **kwargs):
        """Return a copy of the Results object with tensors on the specified device and dtype."""
        return self._apply("to", *args, **kwargs)

    def new(self):
        """Return a new Results object with the same image, path, and names."""
        return Results(orig_img=self.orig_img, path=self.path, names=self.names)

    def plot(
        self,
        conf=True,
        line_width=None,
        font_size=None,
        font="Arial.ttf",
        pil=False,
        img=None,
        im_gpu=None,
        kpt_radius=5,
        kpt_line=True,
        labels=True,
        boxes=True,
        masks=True,
        probs=True,
        show=False,
        save=False,
        filename=None,
    ):
        """
        Plots the detection results on an input RGB image. Accepts a numpy array (cv2) or a PIL Image.

        Args:
            conf (bool): Whether to plot the detection confidence score.
            line_width (float, optional): The line width of the bounding boxes. If None, it is scaled to the image size.
            font_size (float, optional): The font size of the text. If None, it is scaled to the image size.
            font (str): The font to use for the text.
            pil (bool): Whether to return the image as a PIL Image.
            img (numpy.ndarray): Plot to another image. if not, plot to original image.
            im_gpu (torch.Tensor): Normalized image in gpu with shape (1, 3, 640, 640), for faster mask plotting.
            kpt_radius (int, optional): Radius of the drawn keypoints. Default is 5.
            kpt_line (bool): Whether to draw lines connecting keypoints.
            labels (bool): Whether to plot the label of bounding boxes.
            boxes (bool): Whether to plot the bounding boxes.
            masks (bool): Whether to plot the masks.
            probs (bool): Whether to plot classification probability
            show (bool): Whether to display the annotated image directly.
            save (bool): Whether to save the annotated image to `filename`.
            filename (str): Filename to save image to if save is True.

        Returns:
            (numpy.ndarray): A numpy array of the annotated image.

        Example:
            ```python
            from PIL import Image
            from ultralytics import YOLO

            model = YOLO('yolov8n.pt')
            results = model('bus.jpg')  # results list
            for r in results:
                im_array = r.plot()  # plot a BGR numpy array of predictions
                im = Image.fromarray(im_array[..., ::-1])  # RGB PIL image
                im.show()  # show image
                im.save('results.jpg')  # save image
            ```
        """
        if img is None and isinstance(self.orig_img, torch.Tensor):
            img = (self.orig_img[0].detach().permute(1, 2, 0).contiguous() * 255).to(torch.uint8).cpu().numpy()

        names = self.names
        is_obb = self.obb is not None
        pred_boxes, show_boxes = self.obb if is_obb else self.boxes, boxes
        pred_masks, show_masks = self.masks, masks
        pred_probs, show_probs = self.probs, probs
        annotator = Annotator(
            deepcopy(self.orig_img if img is None else img),
            line_width,
            font_size,
            font,
            pil or (pred_probs is not None and show_probs),  # Classify tasks default to pil=True
            example=names,
        )

        # Plot Segment results
        if pred_masks and show_masks:
            if im_gpu is None:
                img = LetterBox(pred_masks.shape[1:])(image=annotator.result())
                im_gpu = (
                    torch.as_tensor(img, dtype=torch.float16, device=pred_masks.data.device)
                    .permute(2, 0, 1)
                    .flip(0)
                    .contiguous()
                    / 255
                )
            idx = pred_boxes.cls if pred_boxes else range(len(pred_masks))
            annotator.masks(pred_masks.data, colors=[colors(x, True) for x in idx], im_gpu=im_gpu)

        # Plot Detect results
        if pred_boxes is not None and show_boxes:
            for d in reversed(pred_boxes):
                c, conf, id = int(d.cls), float(d.conf) if conf else None, None if d.id is None else int(d.id.item())
                name = ("" if id is None else f"id:{id} ") + names[c]
                label = (f"{name} {conf:.2f}" if conf else name) if labels else None
                box = d.xyxyxyxy.reshape(-1, 4, 2).squeeze() if is_obb else d.xyxy.squeeze()
                annotator.box_label(box, label, color=colors(c, True), rotated=is_obb)

        # Plot Classify results
        if pred_probs is not None and show_probs:
            text = ",\n".join(f"{names[j] if names else j} {pred_probs.data[j]:.2f}" for j in pred_probs.top5)
            x = round(self.orig_shape[0] * 0.03)
            annotator.text([x, x], text, txt_color=(255, 255, 255))  # TODO: allow setting colors

        # Plot Pose results
        if self.keypoints is not None:
            for k in reversed(self.keypoints.data):
                annotator.kpts(k, self.orig_shape, radius=kpt_radius, kpt_line=kpt_line)

        # Show results
        if show:
            annotator.show(self.path)

        # Save results
        if save:
            annotator.save(filename)

        return annotator.result()

    def show(self, *args, **kwargs):
        """Show annotated results image."""
        self.plot(show=True, *args, **kwargs)

    def save(self, filename=None, *args, **kwargs):
        """Save annotated results image."""
        if not filename:
            filename = f"results_{Path(self.path).name}"
        self.plot(save=True, filename=filename, *args, **kwargs)
        return filename

    def verbose(self):
        """Return log string for each task."""
        log_string = ""
        probs = self.probs
        boxes = self.boxes
        if len(self) == 0:
            return log_string if probs is not None else f"{log_string}(no detections), "
        if probs is not None:
            log_string += f"{', '.join(f'{self.names[j]} {probs.data[j]:.2f}' for j in probs.top5)}, "
        if boxes:
            for c in boxes.cls.unique():
                n = (boxes.cls == c).sum()  # detections per class
                log_string += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "
        return log_string

    def save_txt(self, txt_file, save_conf=False):
        """
        Save predictions into txt file.

        Args:
            txt_file (str): txt file path.
            save_conf (bool): save confidence score or not.
        """
        is_obb = self.obb is not None
        boxes = self.obb if is_obb else self.boxes
        masks = self.masks
        probs = self.probs
        kpts = self.keypoints
        texts = []
        if probs is not None:
            # Classify
            [texts.append(f"{probs.data[j]:.2f} {self.names[j]}") for j in probs.top5]
        elif boxes:
            # Detect/segment/pose
            for j, d in enumerate(boxes):
                c, conf, id = int(d.cls), float(d.conf), None if d.id is None else int(d.id.item())
                line = (c, *(d.xyxyxyxyn.view(-1) if is_obb else d.xywhn.view(-1)))
                if masks:
                    seg = masks[j].xyn[0].copy().reshape(-1)  # reversed mask.xyn, (n,2) to (n*2)
                    line = (c, *seg)
                if kpts is not None:
                    kpt = torch.cat((kpts[j].xyn, kpts[j].conf[..., None]), 2) if kpts[j].has_visible else kpts[j].xyn
                    line += (*kpt.reshape(-1).tolist(),)
                line += (conf,) * save_conf + (() if id is None else (id,))
                texts.append(("%g " * len(line)).rstrip() % line)

        if texts:
            Path(txt_file).parent.mkdir(parents=True, exist_ok=True)  # make directory
            with open(txt_file, "a") as f:
                f.writelines(text + "\n" for text in texts)

    def save_crop(self, save_dir, file_name=Path("im.jpg")):
        """
        Save cropped predictions to `save_dir/cls/file_name.jpg`.

        Args:
            save_dir (str | pathlib.Path): Save path.
            file_name (str | pathlib.Path): File name.
        """
        if self.probs is not None:
            LOGGER.warning("WARNING ⚠️ Classify task do not support `save_crop`.")
            return
        if self.obb is not None:
            LOGGER.warning("WARNING ⚠️ OBB task do not support `save_crop`.")
            return
        for d in self.boxes:
            save_one_box(
                d.xyxy,
                self.orig_img.copy(),
                file=Path(save_dir) / self.names[int(d.cls)] / f"{Path(file_name)}.jpg",
                BGR=True,
            )

    def tojson(self, normalize=False):
        """Convert the object to JSON format."""
        if self.probs is not None:
            LOGGER.warning("Warning: Classify task do not support `tojson` yet.")
            return

        import json

        # Create list of detection dictionaries
        results = []
        data = self.boxes.data.cpu().tolist()
        h, w = self.orig_shape if normalize else (1, 1)
        for i, row in enumerate(data):  # xyxy, track_id if tracking, conf, class_id
            box = {"x1": row[0] / w, "y1": row[1] / h, "x2": row[2] / w, "y2": row[3] / h}
            conf = row[-2]
            class_id = int(row[-1])
            name = self.names[class_id]
            result = {"name": name, "class": class_id, "confidence": conf, "box": box}
            if self.boxes.is_track:
                result["track_id"] = int(row[-3])  # track ID
            if self.masks:
                x, y = self.masks.xy[i][:, 0], self.masks.xy[i][:, 1]  # numpy array
                result["segments"] = {"x": (x / w).tolist(), "y": (y / h).tolist()}
            if self.keypoints is not None:
                x, y, visible = self.keypoints[i].data[0].cpu().unbind(dim=1)  # torch Tensor
                result["keypoints"] = {"x": (x / w).tolist(), "y": (y / h).tolist(), "visible": visible.tolist()}
            results.append(result)

        # Convert detections to JSON
        return json.dumps(results, indent=2)

__getitem__(idx)

Return a Results object for the specified index.

Source code in ultralytics/engine/results.py
def __getitem__(self, idx):
    """Return a Results object for the specified index."""
    return self._apply("__getitem__", idx)

__init__(orig_img, path, names, boxes=None, masks=None, probs=None, keypoints=None, obb=None)

Initialize the Results class.

Parameters:

Name Type Description Default
orig_img ndarray

The original image as a numpy array.

required
path str

The path to the image file.

required
names dict

A dictionary of class names.

required
boxes tensor

A 2D tensor of bounding box coordinates for each detection.

None
masks tensor

A 3D tensor of detection masks, where each mask is a binary image.

None
probs tensor

A 1D tensor of probabilities of each class for classification task.

None
keypoints tensor

A 2D tensor of keypoint coordinates for each detection.

None
obb tensor

A 2D tensor of oriented bounding box coordinates for each detection.

None
Source code in ultralytics/engine/results.py
def __init__(self, orig_img, path, names, boxes=None, masks=None, probs=None, keypoints=None, obb=None) -> None:
    """
    Initialize the Results class.

    Args:
        orig_img (numpy.ndarray): The original image as a numpy array.
        path (str): The path to the image file.
        names (dict): A dictionary of class names.
        boxes (torch.tensor, optional): A 2D tensor of bounding box coordinates for each detection.
        masks (torch.tensor, optional): A 3D tensor of detection masks, where each mask is a binary image.
        probs (torch.tensor, optional): A 1D tensor of probabilities of each class for classification task.
        keypoints (torch.tensor, optional): A 2D tensor of keypoint coordinates for each detection.
        obb (torch.tensor, optional): A 2D tensor of oriented bounding box coordinates for each detection.
    """
    self.orig_img = orig_img
    self.orig_shape = orig_img.shape[:2]
    self.boxes = Boxes(boxes, self.orig_shape) if boxes is not None else None  # native size boxes
    self.masks = Masks(masks, self.orig_shape) if masks is not None else None  # native size or imgsz masks
    self.probs = Probs(probs) if probs is not None else None
    self.keypoints = Keypoints(keypoints, self.orig_shape) if keypoints is not None else None
    self.obb = OBB(obb, self.orig_shape) if obb is not None else None
    self.speed = {"preprocess": None, "inference": None, "postprocess": None}  # milliseconds per image
    self.names = names
    self.path = path
    self.save_dir = None
    self._keys = "boxes", "masks", "probs", "keypoints", "obb"

__len__()

Return the number of detections in the Results object.

Source code in ultralytics/engine/results.py
def __len__(self):
    """Return the number of detections in the Results object."""
    for k in self._keys:
        v = getattr(self, k)
        if v is not None:
            return len(v)

cpu()

Return a copy of the Results object with all tensors on CPU memory.

Source code in ultralytics/engine/results.py
def cpu(self):
    """Return a copy of the Results object with all tensors on CPU memory."""
    return self._apply("cpu")

cuda()

Return a copy of the Results object with all tensors on GPU memory.

Source code in ultralytics/engine/results.py
def cuda(self):
    """Return a copy of the Results object with all tensors on GPU memory."""
    return self._apply("cuda")

new()

Return a new Results object with the same image, path, and names.

Source code in ultralytics/engine/results.py
def new(self):
    """Return a new Results object with the same image, path, and names."""
    return Results(orig_img=self.orig_img, path=self.path, names=self.names)

numpy()

Return a copy of the Results object with all tensors as numpy arrays.

Source code in ultralytics/engine/results.py
def numpy(self):
    """Return a copy of the Results object with all tensors as numpy arrays."""
    return self._apply("numpy")

plot(conf=True, line_width=None, font_size=None, font='Arial.ttf', pil=False, img=None, im_gpu=None, kpt_radius=5, kpt_line=True, labels=True, boxes=True, masks=True, probs=True, show=False, save=False, filename=None)

Plots the detection results on an input RGB image. Accepts a numpy array (cv2) or a PIL Image.

Parameters:

Name Type Description Default
conf bool

Whether to plot the detection confidence score.

True
line_width float

The line width of the bounding boxes. If None, it is scaled to the image size.

None
font_size float

The font size of the text. If None, it is scaled to the image size.

None
font str

The font to use for the text.

'Arial.ttf'
pil bool

Whether to return the image as a PIL Image.

False
img ndarray

Plot to another image. if not, plot to original image.

None
im_gpu Tensor

Normalized image in gpu with shape (1, 3, 640, 640), for faster mask plotting.

None
kpt_radius int

Radius of the drawn keypoints. Default is 5.

5
kpt_line bool

Whether to draw lines connecting keypoints.

True
labels bool

Whether to plot the label of bounding boxes.

True
boxes bool

Whether to plot the bounding boxes.

True
masks bool

Whether to plot the masks.

True
probs bool

Whether to plot classification probability

True
show bool

Whether to display the annotated image directly.

False
save bool

Whether to save the annotated image to filename.

False
filename str

Filename to save image to if save is True.

None

Returns:

Type Description
ndarray

A numpy array of the annotated image.

Example
from PIL import Image
from ultralytics import YOLO

model = YOLO('yolov8n.pt')
results = model('bus.jpg')  # results list
for r in results:
    im_array = r.plot()  # plot a BGR numpy array of predictions
    im = Image.fromarray(im_array[..., ::-1])  # RGB PIL image
    im.show()  # show image
    im.save('results.jpg')  # save image
Source code in ultralytics/engine/results.py
def plot(
    self,
    conf=True,
    line_width=None,
    font_size=None,
    font="Arial.ttf",
    pil=False,
    img=None,
    im_gpu=None,
    kpt_radius=5,
    kpt_line=True,
    labels=True,
    boxes=True,
    masks=True,
    probs=True,
    show=False,
    save=False,
    filename=None,
):
    """
    Plots the detection results on an input RGB image. Accepts a numpy array (cv2) or a PIL Image.

    Args:
        conf (bool): Whether to plot the detection confidence score.
        line_width (float, optional): The line width of the bounding boxes. If None, it is scaled to the image size.
        font_size (float, optional): The font size of the text. If None, it is scaled to the image size.
        font (str): The font to use for the text.
        pil (bool): Whether to return the image as a PIL Image.
        img (numpy.ndarray): Plot to another image. if not, plot to original image.
        im_gpu (torch.Tensor): Normalized image in gpu with shape (1, 3, 640, 640), for faster mask plotting.
        kpt_radius (int, optional): Radius of the drawn keypoints. Default is 5.
        kpt_line (bool): Whether to draw lines connecting keypoints.
        labels (bool): Whether to plot the label of bounding boxes.
        boxes (bool): Whether to plot the bounding boxes.
        masks (bool): Whether to plot the masks.
        probs (bool): Whether to plot classification probability
        show (bool): Whether to display the annotated image directly.
        save (bool): Whether to save the annotated image to `filename`.
        filename (str): Filename to save image to if save is True.

    Returns:
        (numpy.ndarray): A numpy array of the annotated image.

    Example:
        ```python
        from PIL import Image
        from ultralytics import YOLO

        model = YOLO('yolov8n.pt')
        results = model('bus.jpg')  # results list
        for r in results:
            im_array = r.plot()  # plot a BGR numpy array of predictions
            im = Image.fromarray(im_array[..., ::-1])  # RGB PIL image
            im.show()  # show image
            im.save('results.jpg')  # save image
        ```
    """
    if img is None and isinstance(self.orig_img, torch.Tensor):
        img = (self.orig_img[0].detach().permute(1, 2, 0).contiguous() * 255).to(torch.uint8).cpu().numpy()

    names = self.names
    is_obb = self.obb is not None
    pred_boxes, show_boxes = self.obb if is_obb else self.boxes, boxes
    pred_masks, show_masks = self.masks, masks
    pred_probs, show_probs = self.probs, probs
    annotator = Annotator(
        deepcopy(self.orig_img if img is None else img),
        line_width,
        font_size,
        font,
        pil or (pred_probs is not None and show_probs),  # Classify tasks default to pil=True
        example=names,
    )

    # Plot Segment results
    if pred_masks and show_masks:
        if im_gpu is None:
            img = LetterBox(pred_masks.shape[1:])(image=annotator.result())
            im_gpu = (
                torch.as_tensor(img, dtype=torch.float16, device=pred_masks.data.device)
                .permute(2, 0, 1)
                .flip(0)
                .contiguous()
                / 255
            )
        idx = pred_boxes.cls if pred_boxes else range(len(pred_masks))
        annotator.masks(pred_masks.data, colors=[colors(x, True) for x in idx], im_gpu=im_gpu)

    # Plot Detect results
    if pred_boxes is not None and show_boxes:
        for d in reversed(pred_boxes):
            c, conf, id = int(d.cls), float(d.conf) if conf else None, None if d.id is None else int(d.id.item())
            name = ("" if id is None else f"id:{id} ") + names[c]
            label = (f"{name} {conf:.2f}" if conf else name) if labels else None
            box = d.xyxyxyxy.reshape(-1, 4, 2).squeeze() if is_obb else d.xyxy.squeeze()
            annotator.box_label(box, label, color=colors(c, True), rotated=is_obb)

    # Plot Classify results
    if pred_probs is not None and show_probs:
        text = ",\n".join(f"{names[j] if names else j} {pred_probs.data[j]:.2f}" for j in pred_probs.top5)
        x = round(self.orig_shape[0] * 0.03)
        annotator.text([x, x], text, txt_color=(255, 255, 255))  # TODO: allow setting colors

    # Plot Pose results
    if self.keypoints is not None:
        for k in reversed(self.keypoints.data):
            annotator.kpts(k, self.orig_shape, radius=kpt_radius, kpt_line=kpt_line)

    # Show results
    if show:
        annotator.show(self.path)

    # Save results
    if save:
        annotator.save(filename)

    return annotator.result()

save(filename=None, *args, **kwargs)

Save annotated results image.

Source code in ultralytics/engine/results.py
def save(self, filename=None, *args, **kwargs):
    """Save annotated results image."""
    if not filename:
        filename = f"results_{Path(self.path).name}"
    self.plot(save=True, filename=filename, *args, **kwargs)
    return filename

save_crop(save_dir, file_name=Path('im.jpg'))

Save cropped predictions to save_dir/cls/file_name.jpg.

Parameters:

Name Type Description Default
save_dir str | Path

Save path.

required
file_name str | Path

File name.

Path('im.jpg')
Source code in ultralytics/engine/results.py
def save_crop(self, save_dir, file_name=Path("im.jpg")):
    """
    Save cropped predictions to `save_dir/cls/file_name.jpg`.

    Args:
        save_dir (str | pathlib.Path): Save path.
        file_name (str | pathlib.Path): File name.
    """
    if self.probs is not None:
        LOGGER.warning("WARNING ⚠️ Classify task do not support `save_crop`.")
        return
    if self.obb is not None:
        LOGGER.warning("WARNING ⚠️ OBB task do not support `save_crop`.")
        return
    for d in self.boxes:
        save_one_box(
            d.xyxy,
            self.orig_img.copy(),
            file=Path(save_dir) / self.names[int(d.cls)] / f"{Path(file_name)}.jpg",
            BGR=True,
        )

save_txt(txt_file, save_conf=False)

Save predictions into txt file.

Parameters:

Name Type Description Default
txt_file str

txt file path.

required
save_conf bool

save confidence score or not.

False
Source code in ultralytics/engine/results.py
def save_txt(self, txt_file, save_conf=False):
    """
    Save predictions into txt file.

    Args:
        txt_file (str): txt file path.
        save_conf (bool): save confidence score or not.
    """
    is_obb = self.obb is not None
    boxes = self.obb if is_obb else self.boxes
    masks = self.masks
    probs = self.probs
    kpts = self.keypoints
    texts = []
    if probs is not None:
        # Classify
        [texts.append(f"{probs.data[j]:.2f} {self.names[j]}") for j in probs.top5]
    elif boxes:
        # Detect/segment/pose
        for j, d in enumerate(boxes):
            c, conf, id = int(d.cls), float(d.conf), None if d.id is None else int(d.id.item())
            line = (c, *(d.xyxyxyxyn.view(-1) if is_obb else d.xywhn.view(-1)))
            if masks:
                seg = masks[j].xyn[0].copy().reshape(-1)  # reversed mask.xyn, (n,2) to (n*2)
                line = (c, *seg)
            if kpts is not None:
                kpt = torch.cat((kpts[j].xyn, kpts[j].conf[..., None]), 2) if kpts[j].has_visible else kpts[j].xyn
                line += (*kpt.reshape(-1).tolist(),)
            line += (conf,) * save_conf + (() if id is None else (id,))
            texts.append(("%g " * len(line)).rstrip() % line)

    if texts:
        Path(txt_file).parent.mkdir(parents=True, exist_ok=True)  # make directory
        with open(txt_file, "a") as f:
            f.writelines(text + "\n" for text in texts)

show(*args, **kwargs)

Show annotated results image.

Source code in ultralytics/engine/results.py
def show(self, *args, **kwargs):
    """Show annotated results image."""
    self.plot(show=True, *args, **kwargs)

to(*args, **kwargs)

Return a copy of the Results object with tensors on the specified device and dtype.

Source code in ultralytics/engine/results.py
def to(self, *args, **kwargs):
    """Return a copy of the Results object with tensors on the specified device and dtype."""
    return self._apply("to", *args, **kwargs)

tojson(normalize=False)

Convert the object to JSON format.

Source code in ultralytics/engine/results.py
def tojson(self, normalize=False):
    """Convert the object to JSON format."""
    if self.probs is not None:
        LOGGER.warning("Warning: Classify task do not support `tojson` yet.")
        return

    import json

    # Create list of detection dictionaries
    results = []
    data = self.boxes.data.cpu().tolist()
    h, w = self.orig_shape if normalize else (1, 1)
    for i, row in enumerate(data):  # xyxy, track_id if tracking, conf, class_id
        box = {"x1": row[0] / w, "y1": row[1] / h, "x2": row[2] / w, "y2": row[3] / h}
        conf = row[-2]
        class_id = int(row[-1])
        name = self.names[class_id]
        result = {"name": name, "class": class_id, "confidence": conf, "box": box}
        if self.boxes.is_track:
            result["track_id"] = int(row[-3])  # track ID
        if self.masks:
            x, y = self.masks.xy[i][:, 0], self.masks.xy[i][:, 1]  # numpy array
            result["segments"] = {"x": (x / w).tolist(), "y": (y / h).tolist()}
        if self.keypoints is not None:
            x, y, visible = self.keypoints[i].data[0].cpu().unbind(dim=1)  # torch Tensor
            result["keypoints"] = {"x": (x / w).tolist(), "y": (y / h).tolist(), "visible": visible.tolist()}
        results.append(result)

    # Convert detections to JSON
    return json.dumps(results, indent=2)

update(boxes=None, masks=None, probs=None, obb=None)

Update the boxes, masks, and probs attributes of the Results object.

Source code in ultralytics/engine/results.py
def update(self, boxes=None, masks=None, probs=None, obb=None):
    """Update the boxes, masks, and probs attributes of the Results object."""
    if boxes is not None:
        self.boxes = Boxes(ops.clip_boxes(boxes, self.orig_shape), self.orig_shape)
    if masks is not None:
        self.masks = Masks(masks, self.orig_shape)
    if probs is not None:
        self.probs = probs
    if obb is not None:
        self.obb = OBB(obb, self.orig_shape)

verbose()

Return log string for each task.

Source code in ultralytics/engine/results.py
def verbose(self):
    """Return log string for each task."""
    log_string = ""
    probs = self.probs
    boxes = self.boxes
    if len(self) == 0:
        return log_string if probs is not None else f"{log_string}(no detections), "
    if probs is not None:
        log_string += f"{', '.join(f'{self.names[j]} {probs.data[j]:.2f}' for j in probs.top5)}, "
    if boxes:
        for c in boxes.cls.unique():
            n = (boxes.cls == c).sum()  # detections per class
            log_string += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "
    return log_string



ultralytics.engine.results.Boxes

Bases: BaseTensor

Manages detection boxes, providing easy access and manipulation of box coordinates, confidence scores, class identifiers, and optional tracking IDs. Supports multiple formats for box coordinates, including both absolute and normalized forms.

Attributes:

Name Type Description
data Tensor

The raw tensor containing detection boxes and their associated data.

orig_shape tuple

The original image size as a tuple (height, width), used for normalization.

is_track bool

Indicates whether tracking IDs are included in the box data.

Properties

xyxy (torch.Tensor | numpy.ndarray): Boxes in [x1, y1, x2, y2] format. conf (torch.Tensor | numpy.ndarray): Confidence scores for each box. cls (torch.Tensor | numpy.ndarray): Class labels for each box. id (torch.Tensor | numpy.ndarray, optional): Tracking IDs for each box, if available. xywh (torch.Tensor | numpy.ndarray): Boxes in [x, y, width, height] format, calculated on demand. xyxyn (torch.Tensor | numpy.ndarray): Normalized [x1, y1, x2, y2] boxes, relative to orig_shape. xywhn (torch.Tensor | numpy.ndarray): Normalized [x, y, width, height] boxes, relative to orig_shape.

Methods:

Name Description
cpu

Moves the boxes to CPU memory.

numpy

Converts the boxes to a numpy array format.

cuda

Moves the boxes to CUDA (GPU) memory.

to

Moves the boxes to the specified device.

Source code in ultralytics/engine/results.py
class Boxes(BaseTensor):
    """
    Manages detection boxes, providing easy access and manipulation of box coordinates, confidence scores, class
    identifiers, and optional tracking IDs. Supports multiple formats for box coordinates, including both absolute and
    normalized forms.

    Attributes:
        data (torch.Tensor): The raw tensor containing detection boxes and their associated data.
        orig_shape (tuple): The original image size as a tuple (height, width), used for normalization.
        is_track (bool): Indicates whether tracking IDs are included in the box data.

    Properties:
        xyxy (torch.Tensor | numpy.ndarray): Boxes in [x1, y1, x2, y2] format.
        conf (torch.Tensor | numpy.ndarray): Confidence scores for each box.
        cls (torch.Tensor | numpy.ndarray): Class labels for each box.
        id (torch.Tensor | numpy.ndarray, optional): Tracking IDs for each box, if available.
        xywh (torch.Tensor | numpy.ndarray): Boxes in [x, y, width, height] format, calculated on demand.
        xyxyn (torch.Tensor | numpy.ndarray): Normalized [x1, y1, x2, y2] boxes, relative to `orig_shape`.
        xywhn (torch.Tensor | numpy.ndarray): Normalized [x, y, width, height] boxes, relative to `orig_shape`.

    Methods:
        cpu(): Moves the boxes to CPU memory.
        numpy(): Converts the boxes to a numpy array format.
        cuda(): Moves the boxes to CUDA (GPU) memory.
        to(device, dtype=None): Moves the boxes to the specified device.
    """

    def __init__(self, boxes, orig_shape) -> None:
        """
        Initialize the Boxes class.

        Args:
            boxes (torch.Tensor | numpy.ndarray): A tensor or numpy array containing the detection boxes, with
                shape (num_boxes, 6) or (num_boxes, 7). The last two columns contain confidence and class values.
                If present, the third last column contains track IDs.
            orig_shape (tuple): Original image size, in the format (height, width).
        """
        if boxes.ndim == 1:
            boxes = boxes[None, :]
        n = boxes.shape[-1]
        assert n in (6, 7), f"expected 6 or 7 values but got {n}"  # xyxy, track_id, conf, cls
        super().__init__(boxes, orig_shape)
        self.is_track = n == 7
        self.orig_shape = orig_shape

    @property
    def xyxy(self):
        """Return the boxes in xyxy format."""
        return self.data[:, :4]

    @property
    def conf(self):
        """Return the confidence values of the boxes."""
        return self.data[:, -2]

    @property
    def cls(self):
        """Return the class values of the boxes."""
        return self.data[:, -1]

    @property
    def id(self):
        """Return the track IDs of the boxes (if available)."""
        return self.data[:, -3] if self.is_track else None

    @property
    @lru_cache(maxsize=2)  # maxsize 1 should suffice
    def xywh(self):
        """Return the boxes in xywh format."""
        return ops.xyxy2xywh(self.xyxy)

    @property
    @lru_cache(maxsize=2)
    def xyxyn(self):
        """Return the boxes in xyxy format normalized by original image size."""
        xyxy = self.xyxy.clone() if isinstance(self.xyxy, torch.Tensor) else np.copy(self.xyxy)
        xyxy[..., [0, 2]] /= self.orig_shape[1]
        xyxy[..., [1, 3]] /= self.orig_shape[0]
        return xyxy

    @property
    @lru_cache(maxsize=2)
    def xywhn(self):
        """Return the boxes in xywh format normalized by original image size."""
        xywh = ops.xyxy2xywh(self.xyxy)
        xywh[..., [0, 2]] /= self.orig_shape[1]
        xywh[..., [1, 3]] /= self.orig_shape[0]
        return xywh

cls property

Return the class values of the boxes.

conf property

Return the confidence values of the boxes.

id property

Return the track IDs of the boxes (if available).

xywh cached property

Return the boxes in xywh format.

xywhn cached property

Return the boxes in xywh format normalized by original image size.

xyxy property

Return the boxes in xyxy format.

xyxyn cached property

Return the boxes in xyxy format normalized by original image size.

__init__(boxes, orig_shape)

Initialize the Boxes class.

Parameters:

Name Type Description Default
boxes Tensor | ndarray

A tensor or numpy array containing the detection boxes, with shape (num_boxes, 6) or (num_boxes, 7). The last two columns contain confidence and class values. If present, the third last column contains track IDs.

required
orig_shape tuple

Original image size, in the format (height, width).

required
Source code in ultralytics/engine/results.py
def __init__(self, boxes, orig_shape) -> None:
    """
    Initialize the Boxes class.

    Args:
        boxes (torch.Tensor | numpy.ndarray): A tensor or numpy array containing the detection boxes, with
            shape (num_boxes, 6) or (num_boxes, 7). The last two columns contain confidence and class values.
            If present, the third last column contains track IDs.
        orig_shape (tuple): Original image size, in the format (height, width).
    """
    if boxes.ndim == 1:
        boxes = boxes[None, :]
    n = boxes.shape[-1]
    assert n in (6, 7), f"expected 6 or 7 values but got {n}"  # xyxy, track_id, conf, cls
    super().__init__(boxes, orig_shape)
    self.is_track = n == 7
    self.orig_shape = orig_shape



ultralytics.engine.results.Masks

Bases: BaseTensor

A class for storing and manipulating detection masks.

Attributes:

Name Type Description
xy list

A list of segments in pixel coordinates.

xyn list

A list of normalized segments.

Methods:

Name Description
cpu

Returns the masks tensor on CPU memory.

numpy

Returns the masks tensor as a numpy array.

cuda

Returns the masks tensor on GPU memory.

to

Returns the masks tensor with the specified device and dtype.

Source code in ultralytics/engine/results.py
class Masks(BaseTensor):
    """
    A class for storing and manipulating detection masks.

    Attributes:
        xy (list): A list of segments in pixel coordinates.
        xyn (list): A list of normalized segments.

    Methods:
        cpu(): Returns the masks tensor on CPU memory.
        numpy(): Returns the masks tensor as a numpy array.
        cuda(): Returns the masks tensor on GPU memory.
        to(device, dtype): Returns the masks tensor with the specified device and dtype.
    """

    def __init__(self, masks, orig_shape) -> None:
        """Initialize the Masks class with the given masks tensor and original image shape."""
        if masks.ndim == 2:
            masks = masks[None, :]
        super().__init__(masks, orig_shape)

    @property
    @lru_cache(maxsize=1)
    def xyn(self):
        """Return normalized segments."""
        return [
            ops.scale_coords(self.data.shape[1:], x, self.orig_shape, normalize=True)
            for x in ops.masks2segments(self.data)
        ]

    @property
    @lru_cache(maxsize=1)
    def xy(self):
        """Return segments in pixel coordinates."""
        return [
            ops.scale_coords(self.data.shape[1:], x, self.orig_shape, normalize=False)
            for x in ops.masks2segments(self.data)
        ]

xy cached property

Return segments in pixel coordinates.

xyn cached property

Return normalized segments.

__init__(masks, orig_shape)

Initialize the Masks class with the given masks tensor and original image shape.

Source code in ultralytics/engine/results.py
def __init__(self, masks, orig_shape) -> None:
    """Initialize the Masks class with the given masks tensor and original image shape."""
    if masks.ndim == 2:
        masks = masks[None, :]
    super().__init__(masks, orig_shape)



ultralytics.engine.results.Keypoints

Bases: BaseTensor

A class for storing and manipulating detection keypoints.

Attributes:

Name Type Description
xy Tensor

A collection of keypoints containing x, y coordinates for each detection.

xyn Tensor

A normalized version of xy with coordinates in the range [0, 1].

conf Tensor

Confidence values associated with keypoints if available, otherwise None.

Methods:

Name Description
cpu

Returns a copy of the keypoints tensor on CPU memory.

numpy

Returns a copy of the keypoints tensor as a numpy array.

cuda

Returns a copy of the keypoints tensor on GPU memory.

to

Returns a copy of the keypoints tensor with the specified device and dtype.

Source code in ultralytics/engine/results.py
class Keypoints(BaseTensor):
    """
    A class for storing and manipulating detection keypoints.

    Attributes:
        xy (torch.Tensor): A collection of keypoints containing x, y coordinates for each detection.
        xyn (torch.Tensor): A normalized version of xy with coordinates in the range [0, 1].
        conf (torch.Tensor): Confidence values associated with keypoints if available, otherwise None.

    Methods:
        cpu(): Returns a copy of the keypoints tensor on CPU memory.
        numpy(): Returns a copy of the keypoints tensor as a numpy array.
        cuda(): Returns a copy of the keypoints tensor on GPU memory.
        to(device, dtype): Returns a copy of the keypoints tensor with the specified device and dtype.
    """

    @smart_inference_mode()  # avoid keypoints < conf in-place error
    def __init__(self, keypoints, orig_shape) -> None:
        """Initializes the Keypoints object with detection keypoints and original image size."""
        if keypoints.ndim == 2:
            keypoints = keypoints[None, :]
        if keypoints.shape[2] == 3:  # x, y, conf
            mask = keypoints[..., 2] < 0.5  # points with conf < 0.5 (not visible)
            keypoints[..., :2][mask] = 0
        super().__init__(keypoints, orig_shape)
        self.has_visible = self.data.shape[-1] == 3

    @property
    @lru_cache(maxsize=1)
    def xy(self):
        """Returns x, y coordinates of keypoints."""
        return self.data[..., :2]

    @property
    @lru_cache(maxsize=1)
    def xyn(self):
        """Returns normalized x, y coordinates of keypoints."""
        xy = self.xy.clone() if isinstance(self.xy, torch.Tensor) else np.copy(self.xy)
        xy[..., 0] /= self.orig_shape[1]
        xy[..., 1] /= self.orig_shape[0]
        return xy

    @property
    @lru_cache(maxsize=1)
    def conf(self):
        """Returns confidence values of keypoints if available, else None."""
        return self.data[..., 2] if self.has_visible else None

conf cached property

Returns confidence values of keypoints if available, else None.

xy cached property

Returns x, y coordinates of keypoints.

xyn cached property

Returns normalized x, y coordinates of keypoints.

__init__(keypoints, orig_shape)

Initializes the Keypoints object with detection keypoints and original image size.

Source code in ultralytics/engine/results.py
@smart_inference_mode()  # avoid keypoints < conf in-place error
def __init__(self, keypoints, orig_shape) -> None:
    """Initializes the Keypoints object with detection keypoints and original image size."""
    if keypoints.ndim == 2:
        keypoints = keypoints[None, :]
    if keypoints.shape[2] == 3:  # x, y, conf
        mask = keypoints[..., 2] < 0.5  # points with conf < 0.5 (not visible)
        keypoints[..., :2][mask] = 0
    super().__init__(keypoints, orig_shape)
    self.has_visible = self.data.shape[-1] == 3



ultralytics.engine.results.Probs

Bases: BaseTensor

A class for storing and manipulating classification predictions.

Attributes:

Name Type Description
top1 int

Index of the top 1 class.

top5 list[int]

Indices of the top 5 classes.

top1conf Tensor

Confidence of the top 1 class.

top5conf Tensor

Confidences of the top 5 classes.

Methods:

Name Description
cpu

Returns a copy of the probs tensor on CPU memory.

numpy

Returns a copy of the probs tensor as a numpy array.

cuda

Returns a copy of the probs tensor on GPU memory.

to

Returns a copy of the probs tensor with the specified device and dtype.

Source code in ultralytics/engine/results.py
class Probs(BaseTensor):
    """
    A class for storing and manipulating classification predictions.

    Attributes:
        top1 (int): Index of the top 1 class.
        top5 (list[int]): Indices of the top 5 classes.
        top1conf (torch.Tensor): Confidence of the top 1 class.
        top5conf (torch.Tensor): Confidences of the top 5 classes.

    Methods:
        cpu(): Returns a copy of the probs tensor on CPU memory.
        numpy(): Returns a copy of the probs tensor as a numpy array.
        cuda(): Returns a copy of the probs tensor on GPU memory.
        to(): Returns a copy of the probs tensor with the specified device and dtype.
    """

    def __init__(self, probs, orig_shape=None) -> None:
        """Initialize the Probs class with classification probabilities and optional original shape of the image."""
        super().__init__(probs, orig_shape)

    @property
    @lru_cache(maxsize=1)
    def top1(self):
        """Return the index of top 1."""
        return int(self.data.argmax())

    @property
    @lru_cache(maxsize=1)
    def top5(self):
        """Return the indices of top 5."""
        return (-self.data).argsort(0)[:5].tolist()  # this way works with both torch and numpy.

    @property
    @lru_cache(maxsize=1)
    def top1conf(self):
        """Return the confidence of top 1."""
        return self.data[self.top1]

    @property
    @lru_cache(maxsize=1)
    def top5conf(self):
        """Return the confidences of top 5."""
        return self.data[self.top5]

top1 cached property

Return the index of top 1.

top1conf cached property

Return the confidence of top 1.

top5 cached property

Return the indices of top 5.

top5conf cached property

Return the confidences of top 5.

__init__(probs, orig_shape=None)

Initialize the Probs class with classification probabilities and optional original shape of the image.

Source code in ultralytics/engine/results.py
def __init__(self, probs, orig_shape=None) -> None:
    """Initialize the Probs class with classification probabilities and optional original shape of the image."""
    super().__init__(probs, orig_shape)



ultralytics.engine.results.OBB

Bases: BaseTensor

A class for storing and manipulating Oriented Bounding Boxes (OBB).

Parameters:

Name Type Description Default
boxes Tensor | ndarray

A tensor or numpy array containing the detection boxes, with shape (num_boxes, 7) or (num_boxes, 8). The last two columns contain confidence and class values. If present, the third last column contains track IDs, and the fifth column from the left contains rotation.

required
orig_shape tuple

Original image size, in the format (height, width).

required

Attributes:

Name Type Description
xywhr Tensor | ndarray

The boxes in [x_center, y_center, width, height, rotation] format.

conf Tensor | ndarray

The confidence values of the boxes.

cls Tensor | ndarray

The class values of the boxes.

id Tensor | ndarray

The track IDs of the boxes (if available).

xyxyxyxyn Tensor | ndarray

The rotated boxes in xyxyxyxy format normalized by orig image size.

xyxyxyxy Tensor | ndarray

The rotated boxes in xyxyxyxy format.

xyxy Tensor | ndarray

The horizontal boxes in xyxyxyxy format.

data Tensor

The raw OBB tensor (alias for boxes).

Methods:

Name Description
cpu

Move the object to CPU memory.

numpy

Convert the object to a numpy array.

cuda

Move the object to CUDA memory.

to

Move the object to the specified device.

Source code in ultralytics/engine/results.py
class OBB(BaseTensor):
    """
    A class for storing and manipulating Oriented Bounding Boxes (OBB).

    Args:
        boxes (torch.Tensor | numpy.ndarray): A tensor or numpy array containing the detection boxes,
            with shape (num_boxes, 7) or (num_boxes, 8). The last two columns contain confidence and class values.
            If present, the third last column contains track IDs, and the fifth column from the left contains rotation.
        orig_shape (tuple): Original image size, in the format (height, width).

    Attributes:
        xywhr (torch.Tensor | numpy.ndarray): The boxes in [x_center, y_center, width, height, rotation] format.
        conf (torch.Tensor | numpy.ndarray): The confidence values of the boxes.
        cls (torch.Tensor | numpy.ndarray): The class values of the boxes.
        id (torch.Tensor | numpy.ndarray): The track IDs of the boxes (if available).
        xyxyxyxyn (torch.Tensor | numpy.ndarray): The rotated boxes in xyxyxyxy format normalized by orig image size.
        xyxyxyxy (torch.Tensor | numpy.ndarray): The rotated boxes in xyxyxyxy format.
        xyxy (torch.Tensor | numpy.ndarray): The horizontal boxes in xyxyxyxy format.
        data (torch.Tensor): The raw OBB tensor (alias for `boxes`).

    Methods:
        cpu(): Move the object to CPU memory.
        numpy(): Convert the object to a numpy array.
        cuda(): Move the object to CUDA memory.
        to(*args, **kwargs): Move the object to the specified device.
    """

    def __init__(self, boxes, orig_shape) -> None:
        """Initialize the Boxes class."""
        if boxes.ndim == 1:
            boxes = boxes[None, :]
        n = boxes.shape[-1]
        assert n in (7, 8), f"expected 7 or 8 values but got {n}"  # xywh, rotation, track_id, conf, cls
        super().__init__(boxes, orig_shape)
        self.is_track = n == 8
        self.orig_shape = orig_shape

    @property
    def xywhr(self):
        """Return the rotated boxes in xywhr format."""
        return self.data[:, :5]

    @property
    def conf(self):
        """Return the confidence values of the boxes."""
        return self.data[:, -2]

    @property
    def cls(self):
        """Return the class values of the boxes."""
        return self.data[:, -1]

    @property
    def id(self):
        """Return the track IDs of the boxes (if available)."""
        return self.data[:, -3] if self.is_track else None

    @property
    @lru_cache(maxsize=2)
    def xyxyxyxy(self):
        """Return the boxes in xyxyxyxy format, (N, 4, 2)."""
        return ops.xywhr2xyxyxyxy(self.xywhr)

    @property
    @lru_cache(maxsize=2)
    def xyxyxyxyn(self):
        """Return the boxes in xyxyxyxy format, (N, 4, 2)."""
        xyxyxyxyn = self.xyxyxyxy.clone() if isinstance(self.xyxyxyxy, torch.Tensor) else np.copy(self.xyxyxyxy)
        xyxyxyxyn[..., 0] /= self.orig_shape[1]
        xyxyxyxyn[..., 1] /= self.orig_shape[0]
        return xyxyxyxyn

    @property
    @lru_cache(maxsize=2)
    def xyxy(self):
        """
        Return the horizontal boxes in xyxy format, (N, 4).

        Accepts both torch and numpy boxes.
        """
        x1 = self.xyxyxyxy[..., 0].min(1).values
        x2 = self.xyxyxyxy[..., 0].max(1).values
        y1 = self.xyxyxyxy[..., 1].min(1).values
        y2 = self.xyxyxyxy[..., 1].max(1).values
        xyxy = [x1, y1, x2, y2]
        return np.stack(xyxy, axis=-1) if isinstance(self.data, np.ndarray) else torch.stack(xyxy, dim=-1)

cls property

Return the class values of the boxes.

conf property

Return the confidence values of the boxes.

id property

Return the track IDs of the boxes (if available).

xywhr property

Return the rotated boxes in xywhr format.

xyxy cached property

Return the horizontal boxes in xyxy format, (N, 4).

Accepts both torch and numpy boxes.

xyxyxyxy cached property

Return the boxes in xyxyxyxy format, (N, 4, 2).

xyxyxyxyn cached property

Return the boxes in xyxyxyxy format, (N, 4, 2).

__init__(boxes, orig_shape)

Initialize the Boxes class.

Source code in ultralytics/engine/results.py
def __init__(self, boxes, orig_shape) -> None:
    """Initialize the Boxes class."""
    if boxes.ndim == 1:
        boxes = boxes[None, :]
    n = boxes.shape[-1]
    assert n in (7, 8), f"expected 7 or 8 values but got {n}"  # xywh, rotation, track_id, conf, cls
    super().__init__(boxes, orig_shape)
    self.is_track = n == 8
    self.orig_shape = orig_shape





Created 2023-11-12, Updated 2024-01-05
Authors: glenn-jocher (4), Laughing-q (1)