Skip to content

Add Stochastic flow matching for corrdiff #836

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 25 commits into
base: main
Choose a base branch
from
Open
Changes from 1 commit
Commits
Show all changes
25 commits
Select commit Hold shift + click to select a range
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Update train.py
Revert changes to the corrdiff train examples.
  • Loading branch information
daviddpruitt authored Apr 10, 2025
commit 5d4c7e34c9aeeba2b2210fa4281ccee88c75c6fb
8 changes: 1 addition & 7 deletions examples/generative/corrdiff/train.py
Original file line number Diff line number Diff line change
Expand Up @@ -268,14 +268,8 @@ def main(cfg: DictConfig) -> None:
elif cfg.model.name == "lt_aware_ce_regression":
loss_fn = RegressionLossCE(prob_channels=prob_channels)

# Instantiate the optimizer
if encoder_net is not None and cfg.task != "sfm_two_stage":
params = list(denoiser_net.parameters()) + list(encoder_net.parameters())
else:
params = model.parameters()

optimizer = torch.optim.Adam(
params=params, lr=cfg.training.hp.lr, betas=[0.9, 0.999], eps=1e-8
params=model.parameters(), lr=cfg.training.hp.lr, betas=[0.9, 0.999], eps=1e-8
)

# Record the current time to measure the duration of subsequent operations.
Expand Down