search

autonomousvision / gaussian-opacity-fields

Gaussian Opacity Fields: Efficient and Compact Surface Reconstruction in Unbounded Scenes
https://niujinshuchong.github.io/gaussian-opacity-fields/
Other
559 stars 26 forks source link

encounter issues when I train playroom dataset #51

Closed nvslam closed 3 weeks ago

nvslam commented 3 weeks ago

When I try to train on the playroom dataset, I encounter the following issues:

(gof) xxx@xxx:~/Documents/gaussian-opacity-fields$ python train.py -s /home/xxx/Documents/datasets/Playroom/ -m exp_playroom/release -r 2 --use_decoupled_appearance
Optimizing exp_playroom/release
Output folder: exp_playroom/release
Tensorboard not available: not logging progress
Traceback (most recent call last):
  File "train.py", line 374, 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 94, in training
    scene = Scene(dataset, gaussians)
  File "/home/xxx/Documents/gaussian-opacity-fields/scene/__init__.py", line 52, in __init__
    assert False, "Could not recognize scene type!"
AssertionError: Could not recognize scene type!

The structure of playroom is as follows: Playroom ├── images │ ├── model_split_0 │ │ ├── 000 │ │ │ ├── frame0.png │ │ │ └── frame1.png │ │ ├── . │ │ ├── . │ │ ├── . │ │ └── 1249 │ │ ├── frame0.png │ │ └── frame1.png │ ├── model_split_1 │ ├── . │ ├── . │ ├── . │ └── model_split_31 ├── segments └── meta.json