I got some problems while training... help!

[jwc-portkeyspac]

(gaussian_splatting) C:\Users\jtoil\gaussian-splatting>python train.py -s data/standard
Optimizing
Output folder: ./output/f63cd780-9 [29/10 22:44:13]
Tensorboard not available: not logging progress [29/10 22:44:13]
Traceback (most recent call last):
  File "C:\Users\jtoil\gaussian-splatting\scene\dataset_readers.py", line 136, in readColmapSceneInfo
    cam_extrinsics = read_extrinsics_binary(cameras_extrinsic_file)
  File "C:\Users\jtoil\gaussian-splatting\scene\colmap_loader.py", line 199, in read_extrinsics_binary
    image_name += current_char.decode("utf-8")
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xc7 in position 0: unexpected end of data

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "train.py", line 219, in <module>
    training(lp.extract(args), op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint, args.debug_from)
  File "train.py", line 35, in training
    scene = Scene(dataset, gaussians)
  File "C:\Users\jtoil\gaussian-splatting\scene\__init__.py", line 44, in __init__
    scene_info = sceneLoadTypeCallbacks["Colmap"](args.source_path, args.images, args.eval)
  File "C:\Users\jtoil\gaussian-splatting\scene\dataset_readers.py", line 141, in readColmapSceneInfo
    cam_extrinsics = read_extrinsics_text(cameras_extrinsic_file)
  File "C:\Users\jtoil\gaussian-splatting\scene\colmap_loader.py", line 249, in read_extrinsics_text
    with open(path, "r") as fid:
FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\jtoil\\gaussian-splatting\\data\\standard\\sparse/0\\images.txt'

after converting by convert python -s, I run the train code and got some problem. What's the problem??

[jaco001]

Paths? convert.py -s [full path here] and if you have colmap instaled you get some pictures in images folder and camera info file. After that train.py -s [full path here] And all should work :) (effects are in the output folder)

[Shichao123123]

(gaussian_splatting) C:\Users\jtoil\gaussian-splatting>python train.py -s data/standard
Optimizing
Output folder: ./output/f63cd780-9 [29/10 22:44:13]
Tensorboard not available: not logging progress [29/10 22:44:13]
Traceback (most recent call last):
  File "C:\Users\jtoil\gaussian-splatting\scene\dataset_readers.py", line 136, in readColmapSceneInfo
    cam_extrinsics = read_extrinsics_binary(cameras_extrinsic_file)
  File "C:\Users\jtoil\gaussian-splatting\scene\colmap_loader.py", line 199, in read_extrinsics_binary
    image_name += current_char.decode("utf-8")
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xc7 in position 0: unexpected end of data

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "train.py", line 219, in <module>
    training(lp.extract(args), op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint, args.debug_from)
  File "train.py", line 35, in training
    scene = Scene(dataset, gaussians)
  File "C:\Users\jtoil\gaussian-splatting\scene\__init__.py", line 44, in __init__
    scene_info = sceneLoadTypeCallbacks["Colmap"](args.source_path, args.images, args.eval)
  File "C:\Users\jtoil\gaussian-splatting\scene\dataset_readers.py", line 141, in readColmapSceneInfo
    cam_extrinsics = read_extrinsics_text(cameras_extrinsic_file)
  File "C:\Users\jtoil\gaussian-splatting\scene\colmap_loader.py", line 249, in read_extrinsics_text
    with open(path, "r") as fid:
FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\jtoil\\gaussian-splatting\\data\\standard\\sparse/0\\images.txt'

after converting by convert python -s, I run the train code and got some problem. What's the problem?? I have the same problem

[kwea123]

'C:\\Users\\jtoil\\gaussian-splatting\\data\\standard\\sparse/0\\images.txt' Is this not some path issue for windows? Like the sparse/0 is linux path format but the rest is windows. Can you try chaging that to sparse\\0, or use os.path.join(..., "sparse", "0", ...) for universal format?

[ferengi82]

had the same problem, rename the images to something like 0001.jpg, 0002.jpg ... and it works