Training error: ValueError: num_samples should be a positive integer value, but got num_samples=0 #7
Loading…
Reference in New Issue
Block a user
No description provided.
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
I got this error after updating both ai voice cloning and vall-e
Traceback (most recent call last):
File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/home/user/ai-voice-cloning/modules/vall-e/vall_e/train.py", line 190, in
main()
File "/home/user/ai-voice-cloning/modules/vall-e/vall_e/train.py", line 163, in main
train_dl, subtrain_dl, val_dl = create_train_val_dataloader()
File "/home/user/ai-voice-cloning/modules/vall-e/vall_e/data.py", line 538, in create_train_val_dataloader
val_dl = _create_dataloader(val_dataset, training=False)
File "/home/user/ai-voice-cloning/modules/vall-e/vall_e/data.py", line 509, in _create_dataloader
return DataLoader(
File "/home/user/ai-voice-cloning/venv/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 351, in init
sampler = RandomSampler(dataset, generator=generator) # type: ignore[arg-type]
File "/home/user/ai-voice-cloning/venv/lib/python3.10/site-packages/torch/utils/data/sampler.py", line 107, in init
raise ValueError("num_samples should be a positive integer "
ValueError: num_samples should be a positive integer value, but got num_samples=0
[2023-08-30 07:04:37,880] [INFO] [launch.py:315:sigkill_handler] Killing subprocess 20141
[2023-08-30 07:04:37,880] [ERROR] [launch.py:321:sigkill_handler] ['/home/user/ai-voice-cloning/venv/bin/python3.10', '-u', '-m', 'vall_e.train', '--local_rank=0', 'yaml=/home/user/ai-voice-cloning/training/voice/config.yaml'] exits with return code = 1
In the training YAML, copy over what's in the
dataset.traininginto thedataset.validation. I could have sworn I had it fall back and do this itself for the validation dataset/dataloader, but I guess not.