Questions about data formats

[xiaoyaozaixmu]

Hi, I'm very inspired by your code, but I'm currently having some problems, running the main file in the pixelnerf folder keeps showing the following problem：

File "C:\Users\15638\Desktop\Clean-Torch-NeRFs-main\PixelNeRF\main.py", line 49, in
rgb, _, __ = render_rays(net, rays_od, bound=bound, N_samples=N_samples, device=device, ref=ref_dataset)

File "C:\Users\15638\Desktop\Clean-Torch-NeRFs-main\PixelNeRF\Render.py", line 14, in render_rays
f_projection = ref.feature_matching(pts)

File "D:\work\software\anaconda3\envs\pixelnerf\Lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)

File "C:\Users\15638\Desktop\Clean-Torch-NeRFs-main\PixelNeRF\Dataset.py", line 89, in feature_matching
ref_pos = torch.einsum("kij,kbsj->kbsi", self.R_t, (pos - camera_pos).double())

File "D:\work\software\anaconda3\envs\pixelnerf\Lib\site-packages\torch\functional.py", line 402, in einsum
return _VF.einsum(equation, operands) # type: ignore[attr-defined]

RuntimeError: expected scalar type Double but found Float

I made the changes based on the bugs, but the problem is still there，I've tried many methods but failed to solve the problem, please help me to solve it when you see it!