Segmentation fault (code dumped) using PyTorch bindings

[alvaro-budria]

Hi, I was wondering if it is possible to use this library with PyTorch bindings, like the original tinycudann.

I installed the bindings of NeuS2_TCNN as described in tinycudann's repo (building a local clone of NeuS2_TCNN ), and now I am getting a segmentation fault error tracing back to this library. When I run Python with PYTHONFAULTHANDLER=1 I get:

Current thread 0x00007fae68091280 (most recent call first):
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1313 in __setattr__
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/tinycudann-1.6-py3.9-linux-x86_64.egg/tinycudann/modules.py", line 133 in forward
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190 in _call_impl
  File "/home/abudria/NeRF-FSIHR/src/models/texture.py", line 85 in forward
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190 in _call_impl
  File "/home/abudria/NeRF-FSIHR/src/models/DVolSDF.py", line 131 in get_rgb_density
  File "/home/abudria/NeRF-FSIHR/src/models/DVolSDF.py", line 181 in rbg_sigma_fn
  File "/home/abudria/NeRF-FSIHR/src/renderers/renderer_volsdf.py", line 74 in render
  File "/home/abudria/NeRF-FSIHR/src/renderers/renderer_volsdf.py", line 123 in forward
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190 in _call_impl
  File "/home/abudria/NeRF-FSIHR/src/models/DVolSDF.py", line 262 in forward_
  File "/home/abudria/NeRF-FSIHR/src/models/DNeRF.py", line 129 in forward
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190 in _call_impl
  File "/home/abudria/NeRF-FSIHR/src/systems/InstantAvatar.py", line 49 in forward
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190 in _call_impl
  File "/home/abudria/NeRF-FSIHR/src/systems/InstantAvatar.py", line 71 in training_step
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/overrides/base.py", line 79 in forward
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190 in _call_impl
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/nn/parallel/distributed.py", line 1000 in _run_ddp_forward
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/nn/parallel/distributed.py", line 1040 in forward
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1190 in _call_impl
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/strategies/ddp.py", line 352 in training_step
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1704 in _call_strategy_hook
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 407 in _training_step
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 132 in closure
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 146 in __call__
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/plugins/precision/precision_plugin.py", line 138 in _wrap_closure
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/optim/adam.py", line 183 in step
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/optim/optimizer.py", line 23 in _use_grad
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/optim/optimizer.py", line 140 in wrapper
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/torch/optim/lr_scheduler.py", line 68 in wrapper
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/plugins/precision/precision_plugin.py", line 153 in optimizer_step
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/strategies/strategy.py", line 216 in optimizer_step
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/strategies/ddp.py", line 289 in optimizer_step
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/core/optimizer.py", line 168 in step
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/core/module.py", line 1705 in optimizer_step
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1550 in _call_lightning_module_hook
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 358 in _optimizer_step
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 248 in _run_optimization
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 201 in advance
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/loop.py", line 200 in run
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/batch/training_batch_loop.py", line 87 in advance
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/loop.py", line 200 in run
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/epoch/training_epoch_loop.py", line 203 in advance
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/loop.py", line 200 in run
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/fit_loop.py", line 271 in advance
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/loops/loop.py", line 200 in run
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1283 in _run_train
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1252 in _run_stage
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1166 in _run
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 735 in _fit_impl
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/strategies/launchers/subprocess_script.py", line 93 in launch
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 648 in _call_and_handle_interrupt
  File "/home/abudria/miniconda3/envs/neus2/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 696 in fit
  File "/home/abudria/NeRF-FSIHR/src/launch.py", line 154 in main
  File "/home/abudria/NeRF-FSIHR/src/launch.py", line 170 in <module>
Segmentation fault (core dumped)

Many thanks.