AttributeError: 'Results' object has no attribute 'obb'

[AliMostafaRadwan]

Search before asking

• I have searched the Supervision issues and found no similar bug report.

Bug

i was testing the example provided in the documentation, but i get this error when i run the code, you can see it prints the detection results but still i get this error after it

Error:

0: 256x640 1 person, 2 bicycles, 2 skateboards, 1 potted plant, 64.0ms
Speed: 34.0ms preprocess, 64.0ms inference, 32.1ms postprocess per image at shape (1, 3, 256, 640)
Traceback (most recent call last):
  File "a:\Main\CODE\GUI\GradeVision-QT-material - TESTVERSION\supervis.py", line 8, in <module>
    detections = sv.Detections.from_ultralytics(results)
  File "C:\Users\alimo\miniconda3\envs\guienv\lib\site-packages\supervision\detection\core.py", line 181, in from_ultralytics
    if ultralytics_results.obb is not None:
  File "C:\Users\alimo\miniconda3\envs\guienv\lib\site-packages\ultralytics\utils\__init__.py", line 153, in __getattr__
    raise AttributeError(f"'{name}' object has no attribute '{attr}'. See valid attributes below.\n{self.__doc__}")
AttributeError: 'Results' object has no attribute 'obb'. See valid attributes below.

    A class for storing and manipulating inference results.

    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 (List[List[float]], optional): A list of detected keypoints for each object.

    Attributes:
        orig_img (numpy.ndarray): The original image as a numpy array.
        orig_shape (tuple): The original image shape in (height, width) format.
        boxes (Boxes, optional): A Boxes object containing the detection bounding boxes.
        masks (Masks, optional): A Masks object containing the detection masks.
        probs (Probs, optional): A Probs object containing probabilities of each class for classification task.
        keypoints (Keypoints, optional): A Keypoints object containing detected keypoints for each object.
        speed (dict): A dictionary of preprocess, inference, and postprocess speeds in milliseconds per image.
        names (dict): A dictionary of class names.
        path (str): The path to the image file.
        _keys (tuple): A tuple of attribute names for non-empty attributes.

Environment

python 3.10
supervision==0.18.0
torch==2.1.2+cu118
torchaudio==2.1.2+cu118
torchvision==0.16.2+cu118
ultralytics==8.0.229

Minimal Reproducible Example

import cv2
import supervision as sv
from ultralytics import YOLO

model = YOLO("yolov8s.pt")
image = cv2.imread('image_00\data/0000000047.png')
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)

bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()

labels = [
    model.model.names[class_id]
    for class_id
    in detections.class_id
]

annotated_image = bounding_box_annotator.annotate(
    scene=image, detections=detections)
annotated_image = label_annotator.annotate(
    scene=annotated_image, detections=detections, labels=labels)

Additional

im not running it in a ipynb file

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

[SkalskiP]

@onuralpszr, could you take a look at this?

[onuralpszr]

@AliMostafaRadwan based on model you share you using normal yolov8s not obb one and I made collab for you test it.

https://colab.research.google.com/drive/1yDFFJLohvqAPgg3F4i5E655aobin14OW?usp=sharing

I tried to trigger error but I was unable to trigger it. Also I was make sure it does usable for non obb annotators as well. I tried with small model and obb small model which boths works. Please check out the collab and If possible please share full collab of yours so I can re-test it.

[JhonFrederick]

@AliMostafaRadwan based on model you share you using normal yolov8s not obb one and I made collab for you test it.

https://colab.research.google.com/drive/1yDFFJLohvqAPgg3F4i5E655aobin14OW?usp=sharing

I tried to trigger error but I was unable to trigger it. Also I was make sure it does usable for non obb annotators as well. I tried with small model and obb small model which boths works. Please check out the collab and If possible please share full collab of yours so I can re-test it.

Hi @onuralpszr ,I have the same error but it only occurs when I use stream=True. This error is replicable in the shared colab
Show image:

[onuralpszr]

That is because you giving "generator" and it needs to iterate or we can use "next" and here is how you solve it.

[onuralpszr]

I also notice you are using ultralytics==8.0.229. and obb released in 8.1 so you also need to change that too.

[AliMostafaRadwan]

im testing it now

[AliMostafaRadwan]

I also notice you are using ultralytics==8.0.229. and obb released in 8.1 so you also need to change that too.

yep that was the cause of the error, just updated the package and it works fine now thx

[onuralpszr]

I also notice you are using ultralytics==8.0.229. and obb released in 8.1 so you also need to change that too.

yep that was the cause of the error, just updated the package and it works fine now thx

You are welcome and have fun :))