train.py Run failure

[XUJay111]

I first performed convert.py processing on the data set with images to get the pre-processed data set, and then directly trained the processed data set with train.py.Then This error occurred: Parameters antialiasing is not passed correctly.
Then I delete this Parameter in /gaussian-renderer/init.py, The code prompts me to add the include_feature feature
I then add this, too.
Finally, here comes the bug
Optimizing /root/dataset1/output Output folder: /root/dataset1/output [19/02 08:41:08] Reading camera 37/37 [19/02 08:41:09] Loading Training Cameras [19/02 08:41:09] [ INFO ] Encountered quite large input images (>1.6K pixels width), rescaling to 1.6K. If this is not desired, please explicitly specify '--resolution/-r' as 1 [19/02 08:41:09] Loading Test Cameras [19/02 08:41:25] Number of points at initialisation : 41656 [19/02 08:41:25] Training progress: 0%| | 0/30000 [00:00<?, ?it/s]Traceback (most recent call last): File "/root/gaussian-splatting/train.py", line 282, in <module> 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 "/root/gaussian-splatting/train.py", line 111, in training render_pkg = render(viewpoint_cam, gaussians, pipe, bg, use_trained_exp=dataset.train_test_exp, separate_sh=SPARSE_ADAM_AVAILABLE) File "/root/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%|

[XUJay111]

I think my CUDA and torch have no problem