reference/generated/tensordict.TensorDictBase.tile

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

TensorDictBase.tile

TensorDictBase.tile(dims: tuple[int, ...])

Returns a tensordict whose batch is repeated, as torch.tile() does.

If dims has fewer entries than the batch dimensions, it is padded with leading ones. If it has more, the result gets new leading batch dimensions. The feature dimensions are not repeated, the result has no names, and the data is copied. See also repeat().

Parameters:

dims (int or tuple of int) – the number of repetitions along each batch dimension.

Examples

>>> import torch
>>> from tensordict import TensorDict
>>> td = TensorDict({"a": torch.arange(6).view(2, 3)}, batch_size=[2, 3])
>>> print(td["a"])
tensor([[0, 1, 2],
        [3, 4, 5]])
>>> print(td.tile((2, 1))["a"])
tensor([[0, 1, 2],
        [3, 4, 5],
        [0, 1, 2],
        [3, 4, 5]])

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