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

branch dev: TypeError: __new__() got an unexpected keyword argument 'antialiasing' #994

Closed
zhangwenniu opened this issue Sep 24, 2024 · 8 comments

Comments

@zhangwenniu
Copy link

Hi, when I try to run the dev branch, i got the error:
TypeError: __new__() got an unexpected keyword argument 'antialiasing'
This error occurs in recent days, full error logging are list below:

Optimizing data/output/test9
Output folder: data/output/test9 [24/09 13:06:32]
Tensorboard not available: not logging progress [24/09 13:06:32]
Reading camera 100/100 [24/09 13:06:32]
Loading Training Cameras [24/09 13:06:32]
Loading Test Cameras [24/09 13:06:35]
Number of points at initialisation :  30840 [24/09 13:06:35]
Training progress:   0%|                                                                                                                                          | 0/30000 [00:00<?, ?it/s]Traceback (most recent call last):
  File "train.py", line 252, 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
    render_pkg = render(viewpoint_cam, gaussians, pipe, bg, use_trained_exp=dataset.train_test_exp)
  File "/home/zhangwenniu/github/gaussian-splatting-docker/gaussian_renderer/__init__.py", line 49, in render
    antialiasing=pipe.antialiasing
TypeError: __new__() got an unexpected keyword argument 'antialiasing'
Training progress:   0%|            

I think this problem maybe relate to one recent commit of antialising code updates.
commit b4332aa

@zhangwenniu
Copy link
Author

@alanvinx Hello, I was wondering if there might be a connection between the bug and this commit?

@xuzijian-hik
Copy link

I've met the same error when running the dev branch

@alanvinx
Copy link
Collaborator

Hi, can you please send the commit's tag that you are currently using for the rasterizer? You can see it by running git log inside the submodules/diff-gaussian-rasterization folder.

@xuzijian-hik
Copy link

I've met the same error when running the dev branch

OK I solve it. The reason for this problem is that the author has updated the contents of the diff_gaussian_rasterization, just uninstall it and reinstall the new version.

@zhangwenniu
Copy link
Author

zhangwenniu commented Sep 25, 2024

Thanks for your help. The code has been updated, but the library in the conda environment for gaussian_splatting has not been updated, which is why training is failing.
The solution is

conda activate gaussian_splatting
pip uninstall diff_gaussian_rasterization
pip install submodules/diff-gaussian-rasterization

@nagexiaochengzi
Copy link

Is it downloaded from the main page of this link? Then, I ran python setup.py install and the installation was successful, but I still have this problem "https://github.com/graphdeco-inria/diff-gaussian-rasterization"

@kaixin-bai
Copy link

I cannot solve the problem by reinstalling submodules/diff-gaussian-rasterization.

@iambrc
Copy link

iambrc commented Nov 30, 2024

I cannot solve the problem by reinstalling submodules/diff-gaussian-rasterization.

I solve it. Check if there are two diff_gaussian_rasterization folders in your conda environment : .\envs\3dgs\Lib\site-packages . And only keep diff_gaussian_rasterization-0.0.0-py3.10-win-amd64.egg.

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

6 participants