search

LightwheelAI / street-gaussians-ns

Unofficial implementation of "Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting", ECCV2024.
Apache License 2.0
326 stars 30 forks source link

preprocessed datasets are missing file points3D_withlidar.txt #53

Open MarcusVH98 opened 2 months ago

MarcusVH98 commented 2 months ago

in waymo_8398516118967750070_3958_000_3978_000/8398516118967750070_3958_000_3978_000/colmap/sparse/0 there is no points3D_withlidar.txt file. The same is true for the three other preprocessed datasets.

This results in the following traceback when trying to train with bash scripts/shells/train.sh waymo_8398516118967750070_3958_000_3978_000/8398516118967750070_3958_000_3978_000 0:

Traceback (most recent call last):
  File "/home/marcus/miniconda3/envs/street-gaussians-ns/bin/sgn-train", line 8, in <module>
    sys.exit(entrypoint())
  File "/home/marcus/miniconda3/envs/street-gaussians-ns/lib/python3.8/site-packages/nerfstudio/scripts/train.py", line 262, in entrypoint
    main(
  File "/home/marcus/miniconda3/envs/street-gaussians-ns/lib/python3.8/site-packages/nerfstudio/scripts/train.py", line 247, in main
    launch(
  File "/home/marcus/miniconda3/envs/street-gaussians-ns/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/marcus/miniconda3/envs/street-gaussians-ns/lib/python3.8/site-packages/nerfstudio/scripts/train.py", line 99, in train_loop
    trainer.setup()
  File "/home/marcus/miniconda3/envs/street-gaussians-ns/lib/python3.8/site-packages/nerfstudio/engine/trainer.py", line 149, in setup
    self.pipeline = self.config.pipeline.setup(
  File "/home/marcus/miniconda3/envs/street-gaussians-ns/lib/python3.8/site-packages/nerfstudio/configs/base_config.py", line 54, in setup
    return self._target(self, **kwargs)
  File "/home/marcus/miniconda3/envs/street-gaussians-ns/lib/python3.8/site-packages/nerfstudio/pipelines/base_pipeline.py", line 254, in __init__
    self.datamanager: DataManager = config.datamanager.setup(
  File "/home/marcus/miniconda3/envs/street-gaussians-ns/lib/python3.8/site-packages/nerfstudio/configs/base_config.py", line 54, in setup
    return self._target(self, **kwargs)
  File "/media/marcus/data/marcus_data/street-gaussians-ns/street_gaussians_ns/data/sgn_datamanager.py", line 100, in __init__
    self.train_dataparser_outputs: DataparserOutputs = self.dataparser.get_dataparser_outputs(split="train")
  File "/home/marcus/miniconda3/envs/street-gaussians-ns/lib/python3.8/site-packages/nerfstudio/data/dataparsers/base_dataparser.py", line 165, in get_dataparser_outputs
    dataparser_outputs = self._generate_dataparser_outputs(split, **kwargs)
  File "/media/marcus/data/marcus_data/street-gaussians-ns/street_gaussians_ns/data/sgn_dataparser.py", line 444, in _generate_dataparser_outputs
    metadata.update(self._load_3D_points(colmap_path, transform_matrix, scale_factor))
  File "/media/marcus/data/marcus_data/street-gaussians-ns/street_gaussians_ns/data/sgn_dataparser.py", line 478, in _load_3D_points
    assert points_filepath.exists()
AssertionError

I got past the error by editing scripts/shells/train.sh argument init_points_filename from points3D_withlidar.txt to points3D.bin, but not sure if that file has lidar information.

Not sure if my change will work, because I get another error TypeError: project_gaussians() missing 1 required positional argument: 'tile_bounds', see issue #52

mingzhuzhang1 commented 1 month ago

Hello, I have encountered the same issue. Have you managed to solve it? How should I go about resolving this problem? TypeError: project_gaussians() missing 1 required positional argument: 'tile_bounds'