RuntimeError: Trying to create tensor with negative dimension

[recordmp3]

Thank you for your wonderful work! Sometimes when I try to decrease the size of bounding box in function ray_marching, I get this error message. I'm sure the camera are all inside the bounding box. Do you have any idea why this happen?

[recordmp3]

this is what I get: File "/home/xxx/projects/nerfstudio4_saved/nerfstudio/model_components/ray_samplers.py", line 422, in forward packed_info, starts, ends = nerfacc.ray_marching( File "/home/xxx/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/home/xxx/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfacc/ray_marching.py", line 171, in ray_marching packed_info, t_starts, t_ends = _C.ray_marching( File "/home/xxx/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfacc/cuda/init.py", line 14, in call_cuda return getattr(_C, name)(*args, **kwargs) RuntimeError: Trying to create tensor with negative dimension -574604142: [-574604142, 1]

[liruilong940607]

what is the parameters you used for ray_marching? It might be the case you are creating too many samples, which causes overflow. Currently the number of samples in each batch has to be smaller than 2,147,483,647 (int32)