Skip to content

fix a bug that caused to pop all v2v conditions during training #855

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.

Sign up for GitHub

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 2 commits into
base: main
Choose a base branch
from
Open

fix a bug that caused to pop all v2v conditions during training #855

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
80e7292
fix a bug that caused to pop all `v2v` conditions
hadipash Apr 23, 2025
7ace805
moved the fix under `prepare_visual_condition`
hadipash May 12, 2025
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
4 changes: 4 additions & 0 deletions opensora/utils/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,6 +202,8 @@ def prepare_visual_condition_uncausal(
C = model_ae.cfg.latent_channels
T, H, W = model_ae.get_latent_size(x.shape[-3:])

condition_config = condition_config.copy() # prevent altering the global config when applying local changes

# Initialize masks tensor to match the shape of x, but only the time dimension will be masked
masks = torch.zeros(B, 1, T, H, W).to(
x.device, x.dtype
Expand Down Expand Up @@ -330,6 +332,8 @@ def prepare_visual_condition_causal(x: torch.Tensor, condition_config: dict, mod
C = model_ae.cfg.latent_channels
T, H, W = model_ae.get_latent_size(x.shape[-3:])

condition_config = condition_config.copy() # prevent altering the global config when applying local changes

# Initialize masks tensor to match the shape of x, but only the time dimension will be masked
masks = torch.zeros(B, 1, T, H, W).to(
x.device, x.dtype
Expand Down