search

hugoycj / torch-bakedsdf

An unofficial pytorch implementation of BakedSDF
https://bakedsdf.github.io/
MIT License
187 stars 8 forks source link

Error while building nerfacc #3

Closed aiolosgs closed 1 year ago

aiolosgs commented 1 year ago

I got an error when I train the model using python launch.py --config configs/neus-colmap.yaml --gpu 0 --train:

nvcc fatal   : Value 'c++17' is not defined for option 'std'
ninja: build stopped: subcommand failed.
aiolosgs commented 1 year ago

I got an error when I train the model using python launch.py --config configs/neus-colmap.yaml --gpu 0 --train:

nvcc fatal   : Value 'c++17' is not defined for option 'std'
ninja: build stopped: subcommand failed.

I solved this by upgrade my nvidia-cuda-toolkit. But now i run into another error while training

Traceback (most recent call last):                         | 0/2 [00:00<?, ?it/s]
  File "/home/paul/projects/nerf/torch-bakedsdf/launch.py", line 131, in <module>
    main()
  File "/home/paul/projects/nerf/torch-bakedsdf/launch.py", line 120, in main
    trainer.fit(system, datamodule=dm)
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 608, in fit
    call._call_and_handle_interrupt(
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/trainer/call.py", line 36, in _call_and_handle_interrupt
    return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs)
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/strategies/launchers/subprocess_script.py", line 88, in launch
    return function(*args, **kwargs)
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 650, in _fit_impl
    self._run(model, ckpt_path=self.ckpt_path)
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1112, in _run
    results = self._run_stage()
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1191, in _run_stage
    self._run_train()
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1214, in _run_train
    self.fit_loop.run()
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/loops/loop.py", line 199, in run
    self.advance(*args, **kwargs)
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/loops/fit_loop.py", line 267, in advance
    self._outputs = self.epoch_loop.run(self._data_fetcher)
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/loops/loop.py", line 200, in run
    self.on_advance_end()
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/loops/epoch/training_epoch_loop.py", line 250, in on_advance_end
    self._run_validation()
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/loops/epoch/training_epoch_loop.py", line 308, in _run_validation
    self.val_loop.run()
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/loops/loop.py", line 199, in run
    self.advance(*args, **kwargs)
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/loops/dataloader/evaluation_loop.py", line 152, in advance
    dl_outputs = self.epoch_loop.run(self._data_fetcher, dl_max_batches, kwargs)
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/loops/loop.py", line 199, in run
    self.advance(*args, **kwargs)
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/loops/epoch/evaluation_epoch_loop.py", line 132, in advance
    self._on_evaluation_batch_start(**kwargs)
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/loops/epoch/evaluation_epoch_loop.py", line 262, in _on_evaluation_batch_start
    self.trainer._call_lightning_module_hook(hook_name, *kwargs.values())
  File "/home/paul/anaconda3/envs/bakedsdf/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1356, in _call_lightning_module_hook
    output = fn(*args, **kwargs)
  File "/home/paul/projects/nerf/torch-bakedsdf/systems/base.py", line 61, in on_validation_batch_start
    self.preprocess_data(batch, 'validation')
  File "/home/paul/projects/nerf/torch-bakedsdf/systems/neus.py", line 64, in preprocess_data
    rgb = self.dataset.all_images[index].view(-1, self.dataset.all_images.shape[-1]).to(self.rank)
RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)
hugoycj commented 1 year ago

Sorry to bother you, this bug has been solved in the #1. You could fetch the latest code to solve it