TensorDictBase.flipud#
- TensorDictBase.flipud()#
Flip the tensordict in the up/down direction.
Flip the entries in each column in the up/down direction. Rows are preserved, but appear in a different order than before.
Requires the tensordict to have at least 1 batch dimension.
- Returns:
a new tensordict with the first dimension flipped.
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.