Windows support? about codef HOT 9 OPEN

How did you switch? Can you post a how to?

replace code
strategy="ddp_find_unused_parameters_true"
in train.py line 547 by
from pytorch_lightning.strategies import DDPStrategy
ddp_gloo = DDPStrategy(process_group_backend="gloo",find_unused_parameters=True)
trainer = Trainer(max_steps=hparams.num_steps,
precision=16 if hparams.vid_hash == True else 32,
callbacks=[checkpoint_callback],
logger=logger,
accelerator='gpu',
devices=hparams.gpus,
num_sanity_val_steps=1,
benchmark=True,
profiler="simple" if len(hparams.gpus) == 1 else None,
val_check_interval=hparams.valid_iters,
limit_val_batches=hparams.valid_batches,
strategy=ddp_gloo)

from codef.

Hi. You may disable the option deform_hash and vid_hash for training if you do not have tiny-cuda. We implement a version with vanilla pytorch using positional encoding. But the training time will greatly increase and thus it is not recommended.

from codef.

inference also not support

from codef.

In that case, for inference, you may also disable these two options. It should work.

from codef.

disable deform_hash and vid_hash will effect result performance?

from codef.

Certainly, the type of motion present within a video sequence can impact the performance of the model to varying degrees. Specifically, if the video primarily contains rigid motion, you can expect the performance to remain relatively consistent.

from codef.

How do I switch to gloo backend?

from codef.

Done.

from codef.

How did you switch? Can you post a how to?

from codef.