Error about run train_net.py

[LZL-CS]

Hi, thanks for your wonderful work. When I run train_net.py use the command line, I got the error:

python train_net.py trainer.gpus=1 hydra.run.dir=experiments/npbgpp_scannet datasets=scannet_pretrain datasets.n_point=6e6 system=npbgpp_sphere system.visibility_scale=0.5 trainer.max_epochs=39 dataloader.train_data_mode=each trainer.reload_dataloaders_every_n_epochs=1 In 'config': Could not find 'trainer/project' Config search path: provider=hydra, path=pkg://hydra.conf provider=main, path=file:///public/home/luanzl/WorkSpace/npbgpp/configs provider=schema, path=structured:// Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

By the way, when I try to debug train_net.py on Pycharm IDE in a remote server step-by-step, I got the error:

hydra.errors.MissingConfigException: In 'config': Could not find 'trainer/project' Config search path: provider=hydra, path=pkg://hydra.conf provider=main, path=file:///public/home/luanzl/WorkSpace/npbgpp/configs provider=schema, path=structured://

I think it's due to the config.yaml file error, which is related to trainer: project

May I know how can I resolve these issues? Thanks in advance!

[rakhimovv]

Hello @LZL-CS ! I think your IDE deleted unused imports in train_net.py especially:

from configs import trainer_conf

Without this line the error appears

[LZL-CS]

Thanks for your reply, I will check this.

[LZL-CS]

May I know can npbgpp apply to the outdoor scene such as the KITTI dataset for the novel view synthesis?

[rakhimovv]

Probably. First of all, there is no background modeling in npbg++, so there is no guarantee to have a good image result in picture areas where there is no points, e.g. sky. And second, current software implementation does not support a big amount of points, e.g. larger than 6e6 (on 1080Ti), but it is possible after careful code modification.

[LZL-CS]

Hi @rakhimovv, got it, thanks for your reply.