hustvl / 4DGaussians

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
https://guanjunwu.github.io/4dgs/
Other
2.11k stars 171 forks source link

FileNotFoundError: [Errno 2] No such file or directory: 'V:\\github_projects\\4DGausssian\\4DGaussians\\data\\hypernerf\\interp_chickchicken\\chickchicken\\points3D_downsample.ply' #91

Closed GYH-skywalker closed 6 months ago

GYH-skywalker commented 7 months ago

when i training with hypernerf dataset i got this error

Traceback (most recent call last):
  File "V:\github_projects\4DGausssian\4DGaussians\train.py", line 429, in <module>
    training(lp.extract(args), hp.extract(args), op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint, args.debug_from, args.expname)
  File "V:\github_projects\4DGausssian\4DGaussians\train.py", line 303, in training
    scene = Scene(dataset, gaussians, load_coarse=None)
  File "V:\github_projects\4DGausssian\4DGaussians\scene\__init__.py", line 56, in __init__
    scene_info = sceneLoadTypeCallbacks["nerfies"](args.source_path, False, args.eval)
  File "V:\github_projects\4DGausssian\4DGaussians\scene\dataset_readers.py", line 386, in readHyperDataInfos
    pcd = fetchPly(ply_path)
  File "V:\github_projects\4DGausssian\4DGaussians\scene\dataset_readers.py", line 125, in fetchPly
    plydata = PlyData.read(path)
  File "D:\Anaconda\envs\Gaussians4D\lib\site-packages\plyfile.py", line 158, in read
    (must_close, stream) = _open_stream(stream, 'read')
  File "D:\Anaconda\envs\Gaussians4D\lib\site-packages\plyfile.py", line 1345, in _open_stream
    return (True, open(stream, read_or_write[0] + 'b'))
FileNotFoundError: [Errno 2] No such file or directory: 'V:\\github_projects\\4DGausssian\\4DGaussians\\data\\hypernerf\\interp_chickchicken\\chickchicken\\points3D_downsample.ply'

I've checked this dir "V:\github_projects\4DGausssian\4DGaussians\data\hypernerf\interp_chickchicken\chickchicken\",and there is not points3D_downsample.ply even though i executed colmap.sh this is my hypernerf dataset directory tree: image

guanjunwu commented 7 months ago

you should downsample point by downsample_point.py