Skip to content

Fix serialization issue in discrete corruption process. #105

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
copybara-service merged 1 commit into from
May 19, 2026
+9 −1
Merged

Fix serialization issue in discrete corruption process. #105

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 hackable_diffusion/lib/corruption/discrete.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -162,7 +162,7 @@ class CategoricalProcess(CorruptionProcess):
"""

schedule: DiscreteSchedule
invariant_probs: Sequence[float]
invariant_probs: Sequence[float] = dataclasses.field(repr=False)
num_categories: int
unused_token: int = UNUSED_TOKEN
post_corruption_fn: PostCorruptionFn = IdentityPostCorruptionFn()
Expand Down
8 changes: 8 additions & 0 deletions hackable_diffusion/lib/corruption/discrete_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -361,6 +361,14 @@ def test_unused_mask_gives_always_false_on_other_masks(self, process_type):
self.assertFalse(is_corrupted_mask[1])
self.assertFalse(is_corrupted_mask[3])

def test_repr_does_not_include_invariant_probs(self):
process = discrete.CategoricalProcess.uniform_process(
schedule=self.schedule, num_categories=self.num_categories
)
process_repr = repr(process)
self.assertNotIn('invariant_probs', process_repr)
self.assertIn('num_categories', process_repr)


if __name__ == '__main__':
absltest.main()
Loading