reference/generated/tensordict.TensorDictBase.copy

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

TensorDictBase.copy

TensorDictBase.copy() → Self

Returns a shallow copy of the tensordict: a new structure that holds the same leaves.

The same as td.clone(recurse=False). The nested tensordicts are new objects, but the leaves are the same tensors: an in-place change to a leaf shows in both.

Examples

>>> import torch
>>> from tensordict import TensorDict
>>> td = TensorDict(a=torch.zeros(3), b={"c": torch.zeros(3)}, batch_size=[3])
>>> c = td.copy()
>>> c["a"] is td["a"], c["b"] is td["b"]
(True, False)

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