-
Notifications
You must be signed in to change notification settings - Fork 5
Open
Description
Hi, thank you for open sourcing the great work!
I'm trying to run the train_vq.py
script, but I'm encountering the following error:
$ python train_vq.py --config config.yaml
Traceback (most recent call last):
File "Dyadic-Interaction-Modeling/code/train_vq.py", line 278, in <module>
main()
File "Dyadic-Interaction-Modeling/code/train_vq.py", line 44, in main
main_worker(args.train_gpu, args.ngpus_per_node, args)
File "Dyadic-Interaction-Modeling/code/train_vq.py", line 69, in main_worker
model = get_model(cfg)
^^^^^^^^^^^^^^
File "Dyadic-Interaction-Modeling/code/models/__init__.py", line 7, in get_model
from models.stage1_BIWI import VQAutoEncoder as Model
File "Dyadic-Interaction-Modeling/code/models/stage1_BIWI.py", line 5, in <module>
from models.lib.quantizer import VectorQuantizer
ModuleNotFoundError: No module named 'models.lib'
It looks like the lib
directory under code/models
is missing from the repository, so the code for multiple modules are also missing.
Could you please clarify whether this directory was accidentally omitted from the repo, or if I have misunderstood anything?
Besides this, I also want to ask do I need to modify anything in train_vq.py
to train the speaker VQVAE?
Thanks in advance!
Metadata
Metadata
Assignees
Labels
No labels