Great god, I need your help. The situation is as follows. Currently, YOLOv5 is being trained on the Ubuntu system Torch 2.0.1 Torchvision 0.15.2, and CUDA 117 version to convert the model best. pt to YOLOv5 Torchscript. I want to deploy it to the ARM platform. Is this idea feasible? Is it supported? If so, where can I download and compile using Libtorch
You could either build PyTorch from source on your ARM platform or use the NGC containers which provide PyTorch builds for ARM with CUDA support.