An error occurs when I run train.py on Windows

[yinxiaotongji]

Training progress: 0%| | 0/30000 [00:00<?, ?it/s]Traceback (most recent call last):
File "train.py", line 299, in
args.start_checkpoint, args.debug_from, usedepth=args.depth, usedepthReg=args.usedepthReg)
File "train.py", line 123, in training
loss.backward()
File "C:\Users\ZJAF.conda\envs\gs_depth\lib\site-packages\torch_tensor.py", line 489, in backward
self, gradient, retain_graph, create_graph, inputs=inputs
File "C:\Users\ZJAF.conda\envs\gs_depth\lib\site-packages\torch\autograd_init_.py", line 199, in backward
allow_unreachable=True, accumulate_grad=True) # Calls into the C++ engine to run the backward pass
File "C:\Users\ZJAF.conda\envs\gs_depth\lib\site-packages\torch\autograd\function.py", line 267, in apply
return user_fn(self, *args)
File "C:\Users\ZJAF.conda\envs\gs_depth\lib\site-packages\diff_gaussian_rasterization_depth_acc_init_.py", line 144, in backward
grad_means2D, grad_colors_precomp, grad_opacities, grad_means3D, grad_cov3Ds_precomp, grad_sh, grad_scales, grad_rotations = _C.rasterize_gaussians_backward(*args)
TypeError: rasterize_gaussians_backward(): incompatible function arguments. The following argument types are supported:
1. (arg0: at::Tensor, arg1: at::Tensor, arg2: at::Tensor, arg3: at::Tensor, arg4: at::Tensor, arg5: at::Tensor, arg6: float, arg7: at::Tensor, arg8: at::Tensor, arg9: at::Tensor, arg10: float, arg11: float, arg12: at::Tensor, arg13: at::Tensor, arg14: at::Tensor, arg15: at::Tensor, arg16: int, arg17: at::Tensor, arg18: at::Tensor, arg19: int, arg20: at::Tensor, arg21: at::Tensor, arg22: at::Tensor, arg23: bool) -> Tuple[at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor]

when:
python train.py -s ./data/room_new --eval --port 6312 --model_path ./output/method2 --resolution 1 --kshot 5 --seed 3 --depth --usedepthReg

The error mentioned above occurred, and I'm not sure how to resolve it. Thank you for your help.