reference/generated/tensordict.default_is_leaf

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

default_is_leaf

tensordict.default_is_leaf(cls: Type) → bool

Returns True if a type is not a tensor collection (tensordict or tensorclass), or is a pass-through type.

Pass-through types (like UnbatchedTensor) have _pass_through=True and are considered leaves because their shape doesn’t conform to batch dimensions.

Note: NonTensorData types are NOT considered leaves here (they have _is_non_tensor=True but not _pass_through=True), so they are excluded from leaves when leaves_only=True.

Examples

>>> from tensordict import TensorDict, default_is_leaf
>>> import torch
>>> td = TensorDict(a={}, b="a string!", c=torch.randn(()))
>>> print(td.keys(leaves_only=True, is_leaf=default_is_leaf))
_TensorDictKeysView(['c'],
    include_nested=False,
    leaves_only=True)

See also

is_leaf_nontensor().