dla:0 or dla:1 corresponds to the DLA cores

[Adicontrol]

I a using yolov11 and wanted use DLA on jetson orin nx with jetpack 6.1 , but when i am running this following script from ultralytics i am getting follwing error

from ultralytics import YOLO

model = YOLO("yolo11n.pt")

model.export(format="engine", device="dla:0", half=True) # dla:0 or dla:1 corresponds to the DLA cores

trt_model = YOLO("yolo11n.engine")

results = trt_model("https://ultralytics.com/images/bus.jpg")

, then i checked :sudo tegrastats
its showing NVDLA0 off NVDLA1 off , could you help me in that ,

[Ugo1998]

hi, would u reinstall pytorch from https://forums.developer.nvidia.com/t/pytorch-for-jetson/72048
until
import python3
import torch
import torchvision
torch.cuda.is_available()
return true
This may fix ur problem.