Closed RaemyS closed 5 months ago
I met the same question
I met the same issues....
same problem
Thanks for informing us of this. I found the issue and will update a fix for this later today.
Thanks a lot, I cannot wait to try it again.😁
Just pushed the update. Let me know if you run into any other issues.
seems to work now, thanks for the fix👍
Hi,
I recently started exploring Gaussian Splatting in nerfstudio. I came across your Instruct-GS2GS and wanted to play around with it a bit.
When running ns-train with igs2gs, I get the following error message after loading the pipeline components:
Traceback (most recent call last): File "/home/user/.local/bin/ns-train", line 8, in
sys.exit(entrypoint())
File "/home/user/nerfstudio/nerfstudio/scripts/train.py", line 262, in entrypoint
main(
File "/home/user/nerfstudio/nerfstudio/scripts/train.py", line 247, in main
launch(
File "/home/user/nerfstudio/nerfstudio/scripts/train.py", line 189, in launch
main_func(local_rank=0, world_size=world_size, config=config)
File "/home/user/nerfstudio/nerfstudio/scripts/train.py", line 99, in train_loop
trainer.setup()
File "/home/user/nerfstudio/nerfstudio/engine/trainer.py", line 156, in setup
self.optimizers = self.setup_optimizers()
File "/home/user/nerfstudio/nerfstudio/engine/trainer.py", line 222, in setup_optimizers
return Optimizers(optimizer_config, param_groups)
File "/home/user/nerfstudio/nerfstudio/engine/optimizers.py", line 103, in init
raise RuntimeError(
RuntimeError: Optimizer config for 'means' not found in config file. Make sure you specify an optimizer for each parameter group. Provided configs were: dict_keys(['xyz', 'features_dc', 'features_rest', 'opacity', 'scaling', 'rotation', 'camera_opt'])
With ns-train igs2gs --help I find some blocks for the optimizers (xyz, opacity, ...) but none for "means". Could the problem be due to my setup or is this perhaps a bug?
I work with a locally built Docker container. The code is based on commit 8e0c6875 from last week from the main branch of the nerfstudio repository.
Thank you for having a look at this :)