RuntimeError: Could not run ‘torchvision::nms’ with arguments from the ‘CUDA’ backend. ‘torchvision::nms’ is only available for these backends: [CPU, BackendSelect, Named, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, Tracer, Autocast, Batched, VmapMode].
I dont know your scenario but we have a blogpost named “How to Run YoloV5 Real-Time Object Detection on Pytorch with Docker on NVIDIA Jetson Modules” . We have used nvidia docker container for that. You can check it by clicking below link.