RuntimeError: Error(s) in loading state_dict for RAVE: #205
Replies: 4 comments 4 replies
-
|
This might be due to the changes from last week. https://github.com/acids-ircam/RAVE/tags |
Beta Was this translation helpful? Give feedback.
-
|
Makes sense. Is this the best place to insert that in the Colab?
I've tried a few variations and still end up with errors, albeit slightly different errors, pasted below. Thanks ——— |
Beta Was this translation helpful? Give feedback.
-
|
Yeah I originally misspelled wasserStein and renamed the file. I'm gonna contact hexorcismos so that he makes the change 🙂 |
Beta Was this translation helpful? Give feedback.
-
|
Thanks, Antoine. I'll wait a day or two for a solution, then? All the best |
Beta Was this translation helpful? Give feedback.
-
|
@caillonantoine Is there something I can edit by hand in the code as a temporary solution, maybe? Thanks |
Beta Was this translation helpful? Give feedback.
-
|
Maybe edit the regularization field to add the typo back (i.e. wassertein) |
Beta Was this translation helpful? Give feedback.
-
|
@christophertrapani try using |
Beta Was this translation helpful? Give feedback.
-
|
Thanks @devstermarts and @caillonantoine! For me, version 2.1.8 and "wassertein" seems to be working for this training started a few weeks ago... |
Beta Was this translation helpful? Give feedback.
-
Training worked well for 7 runs, now this message is appearing since Friday. Any ideas? Thanks
———
Traceback (most recent call last):
File "/content/miniconda/bin/rave", line 8, in
sys.exit(main())
File "/content/miniconda/lib/python3.9/site-packages/scripts/main_cli.py", line 28, in main
app.run(train.main)
File "/content/miniconda/lib/python3.9/site-packages/absl/app.py", line 308, in run
_run_main(main, args)
File "/content/miniconda/lib/python3.9/site-packages/absl/app.py", line 254, in _run_main
sys.exit(main(argv))
File "/content/miniconda/lib/python3.9/site-packages/scripts/train.py", line 160, in main
trainer.fit(model, train, val, ckpt_path=run)
File "/content/miniconda/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 608, in fit
call._call_and_handle_interrupt(
File "/content/miniconda/lib/python3.9/site-packages/pytorch_lightning/trainer/call.py", line 38, in _call_and_handle_interrupt
return trainer_fn(*args, **kwargs)
File "/content/miniconda/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 650, in _fit_impl
self._run(model, ckpt_path=self.ckpt_path)
File "/content/miniconda/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1056, in _run
self._restore_modules_and_callbacks(ckpt_path)
File "/content/miniconda/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1000, in _restore_modules_and_callbacks
self._checkpoint_connector.restore_model()
File "/content/miniconda/lib/python3.9/site-packages/pytorch_lightning/trainer/connectors/checkpoint_connector.py", line 261, in restore_model
self.trainer.strategy.load_model_state_dict(self._loaded_checkpoint)
File "/content/miniconda/lib/python3.9/site-packages/pytorch_lightning/strategies/strategy.py", line 363, in load_model_state_dict
self.lightning_module.load_state_dict(checkpoint["state_dict"])
File "/content/miniconda/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1671, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for RAVE:
Missing key(s) in state_dict: "encoder.encoder.net.0.weight_g", "encoder.encoder.net.0.weight_v", "encoder.encoder.net.1.aligned.branches.0.net.1.weight_g", "encoder.encoder.net.1.aligned.branches.0.net.1.weight_v", "encoder.encoder.net.1.aligned.branches.0.net.3.weight_g".... [etc... many more]
Beta Was this translation helpful? Give feedback.
All reactions