TensorDictBase.tile#
- TensorDictBase.tile(dims: tuple[int, ...])#
Construct a tensordict by repeating the elements.
The dims argument specifies the number of repetitions in each dimension.
- Parameters:
dims (tuple of ints) – The number of repetitions per dimension.
- Returns:
a new tensordict with elements repeated.
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.