Miguel Ángel González Santamarta

Try a threshold below 0.5. Which ultralytics version are you using?

You can try a new version of ultralytics. I have published a new branch ([devel](https://github.com/mgonzs13/yolov8_ros/tree/960a64b2982cd65e02f3211cb865466388bc5d81)) with ultralytics 8.0.149. Btw, I also recommend using Humble [vision_msgs](https://github.com/ros-perception/vision_msgs) package. You can clone the...

I have tried using the device in the predict function and it works well, I may change it in the future. Btw, have you checked https://github.com/ultralytics/ultralytics/issues/3557?

No, I was thinking about the jetpack version since they suggest to update it. Nevertheless, I have changed the use of the device from the model creation to the prediction...

@nypyp, I have changed the ```from torch import cuda``` for a ```import torch``` to use cuda directly from torch. Can you try it?

The last versions of this repo don't support Foxy since it uses lifecycles. You may use an old version. Btw, what about using a docker?

The yolo node is not activating. Can you try to load your model with Ultralytics? ```python from ultralytics import YOLO yolo = YOLO("/home/ws/src/yolo_ros/yolo_bringup/exp21/exp21/weights/best.pt") ```

> from ultralytics import YOLO > yolo = YOLO("/home/ws/src/yolo_ros/yolo_bringup/exp21/exp21/weights/best.pt") You should have used this in a new python file, not in the launch. > TypeError: ERROR ❌️ /home/ws/src/yolo_ros/yolo_bringup/weights/best.pt appears to...

Hi @FHWan, sorry for the lack of documentation. You can peek at the [code here](https://github.com/mgonzs13/yolo_ros/blob/b181d7ac2b2f7946a3d989ed2c69bfd1be68d76b/yolo_ros/yolo_ros/detect_3d_node.py#L225).

Hey @weilinhan, you have to use the markers in rviz2. Then, you will get 3D markers as spheres in the 3D viewer of rviz2.