AI_NVR yolov8 lacks model files

[Captian]

jetson 6.0 GA ，AI_NVR yolov8 lacks model files, only the compose file is used, and the yolov8 model is used to convert to the engine file, and dla cannot be used

[kesong]

I will check it and feedback later. One quick question: why you need run YOLO model on DLA? It is helpful if you can share more details.

[Captian]

We have other models that we need to apply to real-world scenarios, and we want to use dla for inference in order to take full advantage of jetson’s performance, not just the gpu for inference

[kesong]

Please follow here to setup YOVOv8: DeepStream Perception — Metropolis on Jetson documentation 0.1.0 documentation
I can generate the engine file in my side. It will download model and data form github. Please ensure your network works fine.

$ ls yolov8s/
calib.table model_b8_gpu0_int8.engine yolov8s-dependencies

[yingliu]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks