Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

visible points: 0? #14

Open
zhouilu opened this issue May 14, 2024 · 1 comment
Open

visible points: 0? #14

zhouilu opened this issue May 14, 2024 · 1 comment

Comments

@zhouilu
Copy link

zhouilu commented May 14, 2024

Hi
I am trying to train the model on my custom data, run python3 apps/calibration/read_colmap.py ../../data/xx/sparse/0 --min_views 2 firstly, then got some errors when training, command is python3 apps/train.py --cfg config/example/test/train.yml split train

visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
[LoG] base iteration 1000 done, enable view_correction module
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
visible points: 0
[182999:  32999/550000] 519.0s loss: 0.0529 model Gaussian 4 points
    radius [0.2000~0.2000~0.2000]
    opacity: 0.97, 0 < 0.05, 0 < 0.1,
[LoG]          0 points with weight < 0.10
[LoG]          0 points with weight is non max
[LoG]          1 points with radius < 4.00
[LoG] radii_max_act        4 [38.00000~73.25000+28.19427~107.00000]
[LoG] grad              4 [0.00096~0.00145+0.00035~0.00171]
[LoG] split by grad :        0
[LoG] split by radii:        0
 return f'{name:10s} {data.shape[0]:8d} [{data.min().item():.5f}~{data.float().mean().item():.5f}+{data.float().std().item():.5f}~{data.max().item():.5f}]'
RuntimeError: min(): Expected reduction dim to be specified for input.numel() == 0. Specify the reduction dim with the 'dim' argument.

@chingswy
Copy link
Member

Hi, it seems there might be some issues with your camera parameters and point cloud.

To ensure that the point cloud in the dataset is correctly projected, try the following command:

python3 apps/test_pointcloud.py --cfg config/example/test/dataset.yml split dataset radius 0.01

The output will be directed to the debug/ directory.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants