After installing Jetback, PyTorch, and TorchVision according to the official files, I use Jetson to run Yolov8’s predict, and the following error occurs:
yolo task=detect mode=predict model=yolov8n.pt source=bus.jpg device=0 save=True show=True
Ultralytics YOLOv8.2.16 🚀 Python-3.8.19 torch-2.1.0a0+41361538.nv23.06 CUDA:0 (Orin, 62800MiB)
YOLOv8n summary (fused): 168 layers, 3151904 parameters, 0 gradients, 8.7 GFLOPs
Traceback (most recent call last):
File “/home/jetson/anaconda3/envs/torch38/bin/yolo”, line 8, in
sys.exit(entrypoint())
File “/home/jetson/anaconda3/envs/torch38/lib/python3.8/site-packages/ultralytics/cfg/init.py”, line 583, in entrypoint
getattr(model, mode)(**overrides) # default args from model
File “/home/jetson/anaconda3/envs/torch38/lib/python3.8/site-packages/ultralytics/engine/model.py”, line 453, in predict
return self.predictor.predict_cli(source=source) if is_cli else self.predictor(source=source, stream=stream)
File “/home/jetson/anaconda3/envs/torch38/lib/python3.8/site-packages/ultralytics/engine/predictor.py”, line 177, in predict_cli
for _ in gen: # noqa, running CLI inference without accumulating any outputs (do not modify)
File “/home/jetson/anaconda3/envs/torch38/lib/python3.8/site-packages/torch/utils/_contextlib.py”, line 35, in generator_context
response = gen.send(None)
File “/home/jetson/anaconda3/envs/torch38/lib/python3.8/site-packages/ultralytics/engine/predictor.py”, line 255, in stream_inference
self.results = self.postprocess(preds, im, im0s)
File “/home/jetson/anaconda3/envs/torch38/lib/python3.8/site-packages/ultralytics/models/yolo/detect/predict.py”, line 25, in postprocess
preds = ops.non_max_suppression(
File “/home/jetson/anaconda3/envs/torch38/lib/python3.8/site-packages/ultralytics/utils/ops.py”, line 282, in non_max_suppression
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
File “/home/jetson/.local/lib/python3.8/site-packages/torchvision-0.16.1-py3.8-linux-aarch64.egg/torchvision/ops/boxes.py”, line 41, in nms
return torch.ops.torchvision.nms(boxes, scores, iou_threshold)
File “/home/jetson/anaconda3/envs/torch38/lib/python3.8/site-packages/torch/_ops.py”, line 646, in call
return self._op(*args, **kwargs or {})
RuntimeError: CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
Pls how can this situation be resolved，thanks.