AssertionError: Torch not compiled with CUDA enabled

[AyshaMK]

python feature_matching_object_detector.py +experiment=object_detector.yaml n_ref_view=15
Global seed set to 12345
/home/ayshabik/miniconda3/envs/onepose/lib/python3.7/site-packages/hydra/_internal/defaults_list.py:251: UserWarning: In 'config.yaml': Defaults list is missing _self_. See https://hydra.cc/docs/upgrades/1.0_to_1.1/default_composition_order for more information
warnings.warn(msg, UserWarning)
0%| | 0/80 [00:00<?, ?it/s]2023-07-23 12:05:47.496 | INFO | main:inference:164 - Run feature matching object detector for: /home/ayshabik/OnePose/data/onepose_datasets/test_data/0408-colorbox-box/colorbox-4
0%| | 0/80 [00:00<?, ?it/s]
Error executing job with overrides: ['+experiment=object_detector.yaml', 'n_ref_view=15']
Traceback (most recent call last):
File "feature_matching_object_detector.py", line 170, in main
globals()cfg.type
File "feature_matching_object_detector.py", line 165, in inference
inference_core(cfg, data_root, seq_dir, sfm_model_dir)
File "/home/ayshabik/miniconda3/envs/onepose/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "feature_matching_object_detector.py", line 124, in inference_core
extractor_model, matching_2D_model = load_2D_matching_model(cfg)
File "feature_matching_object_detector.py", line 95, in load_2D_matching_model
extractor_model = load_extractor_model(cfg, cfg.model.extractor_model_path)
File "feature_matching_object_detector.py", line 79, in load_extractor_model
extractor_model.cuda()
File "/home/ayshabik/miniconda3/envs/onepose/lib/python3.7/site-packages/torch/nn/modules/module.py", line 688, in cuda
return self._apply(lambda t: t.cuda(device))
File "/home/ayshabik/miniconda3/envs/onepose/lib/python3.7/site-packages/torch/nn/modules/module.py", line 578, in _apply
module._apply(fn)
File "/home/ayshabik/miniconda3/envs/onepose/lib/python3.7/site-packages/torch/nn/modules/module.py", line 601, in _apply
param_applied = fn(param)
File "/home/ayshabik/miniconda3/envs/onepose/lib/python3.7/site-packages/torch/nn/modules/module.py", line 688, in
return self._apply(lambda t: t.cuda(device))
File "/home/ayshabik/miniconda3/envs/onepose/lib/python3.7/site-packages/torch/cuda/init.py", line 210, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

System and cuda env details:
Ubuntu 20.4
CUDA Version: 12.0
python=3.7 , pytorch=1.11.0 torchvision=0.12.0 cudatoolkit=11.8

Is there any Dockerfile or docker image available?

pls help