bennyguo / instant-nsr-pl

Neural Surface reconstruction based on Instant-NGP. Efficient and customizable boilerplate for your research projects. Train NeuS in 10min!
MIT License
856 stars 84 forks source link

omegaconf.errors.missingmandatoryvalue: #81

Open anidealeft opened 1 year ago

anidealeft commented 1 year ago

when I try to do testing alone, such error occurs, could you please tell me how to fix the problem?

Traceback (most recent call last): File "launch.py", line 125, in main() File "launch.py", line 52, in main config.exp_dir = config.get('exp_dir') or os.path.join(args.exp_dir, config.name) File "/opt/miniconda3/envs/ngp_pl/lib/python3.8/site-packages/omegaconf/dictconfig.py", line 359, in getattr self._format_and_raise(key=key, value=None, cause=e) File "/opt/miniconda3/envs/ngp_pl/lib/python3.8/site-packages/omegaconf/base.py", line 231, in _format_and_raise format_and_raise( File "/opt/miniconda3/envs/ngp_pl/lib/python3.8/site-packages/omegaconf/_utils.py", line 900, in format_and_raise _raise(ex, cause) File "/opt/miniconda3/envs/ngp_pl/lib/python3.8/site-packages/omegaconf/_utils.py", line 798, in _raise raise ex.with_traceback(sys.exc_info()[2]) # set env var OC_CAUSE=1 for full trace File "/opt/miniconda3/envs/ngp_pl/lib/python3.8/site-packages/omegaconf/dictconfig.py", line 351, in getattr return self._get_impl( File "/opt/miniconda3/envs/ngp_pl/lib/python3.8/site-packages/omegaconf/dictconfig.py", line 451, in _get_impl return self._resolve_with_default( File "/opt/miniconda3/envs/ngp_pl/lib/python3.8/site-packages/omegaconf/basecontainer.py", line 96, in _resolve_with_default raise MissingMandatoryValue("Missing mandatory value: $FULL_KEY") omegaconf.errors.MissingMandatoryValue: Missing mandatory value: name full_key: name object_type=dict

the command I input is as such: python launch.py --config configs/neus-blender.yaml --resume exp/neus-blender-lego/ckpt/epoch=0-step=20000.ckpt --gpu 0 --test

bennyguo commented 1 year ago

If you do not use configs in the experiment directory (e.g., exp/neus-blender-lego/config/parsed.yaml), you still need to specify the scene by dataset.scene=xxx, even if you resume from previous checkpoints :)

anidealeft commented 1 year ago

this makes efforts, thank you for your reply!