When I train NeRFPlayer by nerfstudio, and there is something wrong with tinycudann

[ZkzMMDC]

Traceback (most recent call last): File "/home/zkz/anaconda3/envs/nerfstudio/bin/ns-train", line 8, in sys.exit(entrypoint()) File "/home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/train.py", line 262, in entrypoint main( File "/home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/train.py", line 247, in main launch( File "/home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/train.py", line 189, in launch main_func(local_rank=0, world_size=world_size, config=config) File "/home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/scripts/train.py", line 99, in train_loop trainer.setup() File "/home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/engine/trainer.py", line 147, in setup self.pipeline = self.config.pipeline.setup( File "/home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/configs/base_config.py", line 54, in setup return self._target(self, **kwargs) File "/home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/pipelines/base_pipeline.py", line 270, in init self._model = config.model.setup( File "/home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/configs/base_config.py", line 54, in setup return self._target(self, **kwargs) File "/home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/nerfstudio/models/base_model.py", line 84, in init self.populate_modules() # populate the modules File "/home/zkz/nerfplayer-nerfstudio-main/nerfplayer/nerfplayer_nerfacto.py", line 99, in populate_modules from nerfplayer.nerfplayer_nerfacto_field import NerfplayerNerfactoField, TemporalHashMLPDensityField File "/home/zkz/nerfplayer-nerfstudio-main/nerfplayer/nerfplayer_nerfacto_field.py", line 27, in import tinycudann as tcnn File "/home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/tinycudann-1.7-py3.8-linux-x86_64.egg/tinycudann/init.py", line 9, in from tinycudann.modules import free_temporary_memory, NetworkWithInputEncoding, Network, Encoding File "/home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/tinycudann-1.7-py3.8-linux-x86_64.egg/tinycudann/modules.py", line 51, in C = importlib.import_module(f"tinycudann_bindings.{cc}_C") File "/home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/importlib/init.py", line 127, in import_module return _bootstrap._gcd_import(name[level:], package, level) ImportError: /home/zkz/anaconda3/envs/nerfstudio/lib/python3.8/site-packages/tinycudann-1.7-py3.8-linux-x86_64.egg/tinycudann_bindings/_89_C.cpython-38-x86_64-linux-gnu.so: undefined symbol: _ZN3c104cuda9SetDeviceEi

My environment is : cuda 11.8 pytorch 2.0.1 python 3.8 RTX4090

[niujinshuchong]

Hi, I never try nerfplayer but it seems like TCNN is not installed properly in your machine. Maybe you could check the official tinycudann repo for guidance.

[haoyuhsu]

@ZkzMMDC Curious do you solve this issue yet?