reference/generated/tensordict.TensorDictBase.expand_as

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

TensorDictBase.expand_as

TensorDictBase.expand_as(other: TensorCollection | Tensor) → Self

Broadcasts the shape of the tensordict to the shape of other and expands it accordingly.

If the input is a tensor collection (tensordict or tensorclass), the leaves will be expanded on a one-to-one basis.

Examples

>>> from tensordict import TensorDict
>>> import torch
>>> td0 = TensorDict({
...     "a": torch.ones(3, 1, 4),
...     "b": {"c": torch.ones(3, 2, 1, 4)}},
...     batch_size=[3],
... )
>>> td1 = TensorDict({
...     "a": torch.zeros(2, 3, 5, 4),
...     "b": {"c": torch.zeros(2, 3, 2, 6, 4)}},
...     batch_size=[2, 3],
... )
>>> expanded = td0.expand_as(td1)
>>> assert (expanded==1).all()
>>> print(expanded)
TensorDict(
    fields={
        a: Tensor(shape=torch.Size([2, 3, 5, 4]), device=cpu, dtype=torch.float32, is_shared=False),
        b: TensorDict(
            fields={
                c: Tensor(shape=torch.Size([2, 3, 2, 6, 4]), device=cpu, dtype=torch.float32, is_shared=False)},
            batch_size=torch.Size([2, 3]),
            device=None,
            is_shared=False)},
    batch_size=torch.Size([2, 3]),
    device=None,
    is_shared=False)

Every tensordict class and every tensorclass has this method. For the other methods, see Methods by task.