Skip to content
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

[BugFix] Consistent behavior for pad_sequence with one and many non-tensors #1172

Merged
merged 1 commit into from
Jan 9, 2025
Merged

[BugFix] Consistent behavior for pad_sequence with one and many non-tensors #1172

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 tensordict/functional.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -216,7 +216,7 @@ def pad_sequence(
try:
item0 = list_of_dicts[0][key]
if is_non_tensor(item0):
out.set(key, torch.stack([d[key] for d in list_of_dicts]))
out.set(key, TensorDict.lazy_stack([d[key] for d in list_of_dicts]))
continue
tensor_shape = item0.shape
pos_pad_dim = (
Expand Down
7 changes: 7 additions & 0 deletions test/test_tensordict.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1920,6 +1920,13 @@ def test_pad_sequence_nontensor(self):
assert (d["a"] == torch.tensor([[1, 1], [2, 0]])).all()
assert d["b"] == ["asd", "efg"]

def test_pad_sequence_single_nontensor(self):
d1 = TensorDict({"a": torch.tensor([1, 1]), "b": "asd"})
d = pad_sequence([d1])
assert (d["a"] == torch.tensor([[1, 1]])).all()
assert d["b"] == ["asd"]
assert isinstance(d.get("b"), NonTensorStack)

def test_pad_sequence_tensorclass_nontensor(self):
@tensorclass
class Sample:
Expand Down
Loading