Describe the bug
I just download the origin MipNeRF360 dataset, and use ns-train nerfacto --output-dir "room" colmap --data "/data/Mipnerf360/room" run directly, I find on some scenes it is success like bonsai ,however the room scene failed , and get an error:
Traceback (most recent call last):
File "/miniconda3/envs/nerfstudio/bin/ns-train", line 8, in
sys.exit(entrypoint())
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/nerfstudio/scripts/train.py", line 272, in entrypoint
main(
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/nerfstudio/scripts/train.py", line 257, in main
launch(
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/nerfstudio/scripts/train.py", line 190, in launch
main_func(local_rank=0, world_size=world_size, config=config)
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/nerfstudio/scripts/train.py", line 101, in train_loop
trainer.train()
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/nerfstudio/engine/trainer.py", line 266, in train
loss, loss_dict, metrics_dict = self.train_iteration(step)
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/nerfstudio/utils/profiler.py", line 111, in inner
out = func(*args, **kwargs)
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/nerfstudio/engine/trainer.py", line 502, in train_iteration
_, loss_dict, metrics_dict = self.pipeline.get_train_loss_dict(step=step)
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/nerfstudio/utils/profiler.py", line 111, in inner
out = func(*args, **kwargs)
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/nerfstudio/pipelines/base_pipeline.py", line 298, in get_train_loss_dict
ray_bundle, batch = self.datamanager.next_train(step)
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/nerfstudio/data/datamanagers/parallel_datamanager.py", line 243, in next_train
ray_bundle, batch = next(self.iter_train_raybundles)[0]
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 630, in next
data = self._next_data()
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1344, in _next_data
return self._process_data(data)
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1370, in _process_data
data.reraise()
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/torch/_utils.py", line 706, in reraise
raise exception
IndexError: Caught IndexError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/torch/utils/data/_utils/worker.py", line 309, in _worker_loop
data = fetcher.fetch(index) # type: ignore[possibly-undefined]
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 33, in fetch
data.append(next(self.dataset_iter))
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/nerfstudio/data/utils/dataloaders.py", line 588, in iter
ray_bundle = self.ray_generator(ray_indices)
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/nerfstudio/model_components/ray_generators.py", line 50, in forward
coords = self.image_coords[y, x]
IndexError: index 1037 is out of bounds for dimension 0 with size 1037
Expected behavior
I want to figure out what's wrong, is it a bug of the nerfstudio or my fault?
nerfstudio-project
