use in kaggle notebook

Loading model...
Traceback (most recent call last):
File "/kaggle/working/segment-anything/scripts/amg.py", line 238, in
main(args)
File "/kaggle/working/segment-anything/scripts/amg.py", line 198, in main
_ = sam.to(device=args.device)
File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1145, in to
return self._apply(convert)
File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 797, in _apply
module._apply(fn)
File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 797, in _apply
module._apply(fn)
File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 797, in _apply
module._apply(fn)
File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 820, in _apply
param_applied = fn(param)
File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1143, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
File "/opt/conda/lib/python3.10/site-packages/torch/cuda/__init__.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

Start with scripts/amg.py, especially main(args) and the sam.to(device=args.device) call shown in the traceback. Check the Kaggle notebook's PyTorch CUDA availability and device configuration first; done means model loading and inference complete without the CUDA assertion.

Written by the indexing model from the issue text.