reference/generated/tensordict.TensorDictBase.empty

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

TensorDictBase.empty

TensorDictBase.empty(recurse=False, *, batch_size=None, device=NO_DEFAULT, names=None) → Self

Returns a new, empty tensordict with the same device and batch size.

The result is not locked, even if self is.

Parameters:

recurse (bool, optional) – if True, the entire structure of the TensorDict will be reproduced without content: the result has the sub-tensordicts of self, without their leaves. Otherwise, only the root will be duplicated. Defaults to False.

Keyword Arguments:

• batch_size (Size, optional) – a new batch-size for the tensordict. With recurse=True, a sub-tensordict whose batch size is the start of the new one gets the new one, a sub-tensordict whose batch size starts with the new one keeps it, and any other sub-tensordict raises a RuntimeError. A LazyStackedTensorDict whose members took the batch size before 0.15 (one stacked along dim 0, for instance) keeps that result, the empty stack of its members, with a FutureWarning, when a sub-tensordict does not fit the new batch size or names has another length. Starting with TensorDict 0.17, the default will change to raising a RuntimeError or a ValueError, as TensorDict.empty and the names setter do.

• device (device, optional) – a new device.

• names (list of str, optional) – dimension names.

Examples

>>> import torch
>>> from tensordict import TensorDict
>>> td = TensorDict({"a": torch.zeros(3), "b": {"c": torch.ones(3)}}, [3])
>>> empty = td.empty()
>>> list(empty.keys()), empty.batch_size
([], torch.Size([3]))
>>> list(td.empty(recurse=True).keys(include_nested=True))
['b']

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