Miguel Ángel González Santamarta

Hey @kyle-redyeti, can you check your nvcc version (```nvcc --version```)? I was able to compile with CUDA inside a Jetson Orin some time ago, let me check if it is...

Hey @kyle-redyeti, I have updated llama_ros to change LLAMA_CUDA to GGML_CUDA. I have to test that docker image in my Jetson Orin but the last time I tried llama.cpp in...

Hey @kyle-redyeti, I have tested the new llama_ros version within my Jetson Oring using Jetpack 6.0 and nvcc 12.2 and, though it is not as accelerated as in my other...

Hi @ArghyaChatterjee, if you are not getting detections while using 3D and your QoS are correct, you may be having problems with the target frame. By default, the target_frame is...

@ArghyaChatterjee So, the launch is working for you, right? > This looks good. However, a good upgrade will be to add those joint keypoints as lines to visualize an skeleton...

Hi @Ragnar7982, I don't think mixing conda envs and ROS is a good idea. Have you tried to use this repo without conda?

Are you installing torch with pip when not using conda? Dopython-is-python3? Have you tried installing torch with pip3 and not using a conda env?

@Phance have you tried your new model with bare Ultralytics? Your new model architecture with attention may not be supported.

> @mgonzs13 What does it currently support? I don't know if it is supported. Have you tried to load the model directly with Ultralytics to check what errors are raised?...

Hi @goodhsm2000, it seems that YOLOv8 is detecting nothing in your images. You can try reducing the [threshold](https://github.com/mgonzs13/yolov8_ros/blob/b6fb30608764d4f13619e16e10524c5b60bf35e5/yolov8_bringup/launch/yolov8.launch.py#L52). Your objects may be getting bad scores. Have you checked if the...