python app.py --args.load conf/interface.yml --Interface.device cuda
CUDA_VISIBLE_DEVICES=7 python app.py --args.load conf/interface.yml --Interface.device cuda
INFO:torch.distributed.nn.jit.instantiator:Created a temporary directory at /tmp/tmplf47cw2f
INFO:torch.distributed.nn.jit.instantiator:Writing /tmp/tmplf47cw2f/_remote_module_non_scriptable.py
loading wavebeat from ./models/wavebeat.pth
/data/liujingxiu/software/anaconda3/envs/vampnet/lib/python3.9/site-packages/pytorch_lightning/utilities/migration/migration.py:201: PossibleUserWarning: You have multiple ModelCheckpoint callback states in this checkpoint, but we found state keys that would end up colliding with each other after an upgrade, which means we can't differentiate which of your checkpoint callbacks needs which states. At least one of your ModelCheckpoint callbacks will not be able to reload the state.
rank_zero_warn(
INFO:pytorch_lightning.utilities.migration.utils:Lightning automatically upgraded your loaded checkpoint from v1.1.8 to v2.0.6. To apply the upgrade to your files permanently, run python -m pytorch_lightning.utilities.upgrade_checkpoint --file models/wavebeat.pth
interface device is cuda
Traceback (most recent call last):
File "/data/liujingxiu/MusicGen/vampnet/app.py", line 521, in
sample_cutoff,
NameError: name 'sample_cutoff' is not defined
python app.py --args.load conf/interface.yml --Interface.device cuda
CUDA_VISIBLE_DEVICES=7 python app.py --args.load conf/interface.yml --Interface.device cuda INFO:torch.distributed.nn.jit.instantiator:Created a temporary directory at /tmp/tmplf47cw2f INFO:torch.distributed.nn.jit.instantiator:Writing /tmp/tmplf47cw2f/_remote_module_non_scriptable.py loading wavebeat from ./models/wavebeat.pth /data/liujingxiu/software/anaconda3/envs/vampnet/lib/python3.9/site-packages/pytorch_lightning/utilities/migration/migration.py:201: PossibleUserWarning: You have multiple
sample_cutoff,
NameError: name 'sample_cutoff' is not defined
ModelCheckpoint
callback states in this checkpoint, but we found state keys that would end up colliding with each other after an upgrade, which means we can't differentiate which of your checkpoint callbacks needs which states. At least one of yourModelCheckpoint
callbacks will not be able to reload the state. rank_zero_warn( INFO:pytorch_lightning.utilities.migration.utils:Lightning automatically upgraded your loaded checkpoint from v1.1.8 to v2.0.6. To apply the upgrade to your files permanently, runpython -m pytorch_lightning.utilities.upgrade_checkpoint --file models/wavebeat.pth
interface device is cuda Traceback (most recent call last): File "/data/liujingxiu/MusicGen/vampnet/app.py", line 521, in