RuntimeError: CUDA error: an illegal memory access was encountered

[HandsomeAozai]

trafficstars

(gaussian_splatting) aozai720@aozai720-MS-7E13:~/Research/gaussian-splatting$ python train.py -s Data/train Optimizing Output folder: ./output/f07fb106-0 [22/11 10:59:06] Tensorboard not available: not logging progress [22/11 10:59:06] Reading camera 301/301 [22/11 10:59:06] Loading Training Cameras [22/11 10:59:06] Loading Test Cameras [22/11 10:59:10] Number of points at initialisation : 182686 [22/11 10:59:10] Training progress: 0%| | 0/30000 [00:00<?, ?it/s]Traceback (most recent call last): File "train.py", line 288, in training(lp.extract(args), op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint, args.debug_from) File "train.py", line 116, in training render_pkg = render(viewpoint_cam, gaussians, pipe, bg, use_trained_exp=dataset.train_test_exp, separate_sh=SPARSE_ADAM_AVAILABLE) File "/home/aozai720/Research/gaussian-splatting/gaussian_renderer/init.py", line 119, in render rendered_image = rendered_image.clamp(0, 1) RuntimeError: CUDA error: an illegal memory access was encountered Training progress: 0%| | 0/30000 [00:00<?, ?it/s]

How can I solve my problem?