Skip to content

Update output objects to support batching #975

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

Merged
kvablack merged 1 commit into from
Jun 16, 2026
+2 −2
Merged

Update output objects to support batching #975

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion src/openpi/policies/droid_policy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,4 +78,4 @@ def __call__(self, data: dict) -> dict:
class DroidOutputs(transforms.DataTransformFn):
def __call__(self, data: dict) -> dict:
# Only return the first 8 dims.
return {"actions": np.asarray(data["actions"][:, :8])}
return {"actions": np.asarray(data["actions"][..., :8])}
2 changes: 1 addition & 1 deletion src/openpi/policies/libero_policy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,4 +97,4 @@ def __call__(self, data: dict) -> dict:
# dimension, we need to now parse out the correct number of actions in the return dict.
# For Libero, we only return the first 7 actions (since the rest is padding).
# For your own dataset, replace `7` with the action dimension of your dataset.
return {"actions": np.asarray(data["actions"][:, :7])}
return {"actions": np.asarray(data["actions"][..., :7])}
Loading