cv2 image as input source

[leberert]

Is there any possibilty for a model input source from OpenCV2 images or ROS2 Images for prediction?

Thanks!

as seen in predictor.py ..

Run prediction on images, videos, directories, globs, YouTube, webcam, streams, etc.
Usage - sources:
    $ yolo task=... mode=predict  model=s.pt --source 0                         # webcam
                                                img.jpg                         # image
                                                vid.mp4                         # video
                                                screen                          # screenshot
                                                path/                           # directory
                                                list.txt                        # list of images
                                                list.streams                    # list of streams
                                                'path/*.jpg'                    # glob
                                                'https://youtu.be/Zgi9g1ksQHc'  # YouTube
                                                'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream

[leberert]

this is implemented in v 8.0.9

[glenn-jocher]

@leberert yes, YOLOv8 supports using OpenCV images as input for predictions. You can pass OpenCV images directly to the model for inference. This functionality is available as of version 8.0.9. For more details on how to use this feature, please refer to the Predictor section in our documentation at https://docs.ultralytics.com. Happy coding! 😊🚀

[AyushExel]

See docs here https://docs.ultralytics.com/predict/