reference/generated/tensordict.TensorDictBase.flipud

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

TensorDictBase.flipud

TensorDictBase.flipud()

Returns a tensordict with the elements reversed along batch dimension 0.

It is flip(0), as for torch.flipud(). The tensordict needs at least 1 batch dimension, or a RuntimeError is raised. The data is copied.

It can be used as a context manager, as unsqueeze() can: when the with block exits, the entries of the block are written back to the tensordict with the inverse operation.

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.flipud()["a"])
tensor([[3, 4, 5],
        [0, 1, 2]])

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