reference/generated/tensordict.TensorDictBase.view

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

TensorDictBase.view

TensorDictBase.view(*shape: int, size: list | tuple | Size | None = None, batch_size: Size | None = None)

Returns a tensordict with views of the tensors according to a new shape, compatible with the tensordict batch_size.

Each leaf keeps its feature dimensions, and is a view of the original leaf: they share storage. As for torch.Tensor.view(), the leaves must have a compatible memory layout. Otherwise, use reshape().

Alternatively, a dtype can be provided as a first unnamed argument. In that case, all tensors will be viewed with the according dtype. Note that this assume that the new shapes will be compatible with the provided dtype. See torch.Tensor.view() for more information on dtype views.

Parameters:

• *shape (int) – new batch size of the resulting tensordict, as integers or as one torch.Size.

• dtype (dtype) – alternatively, a dtype to use to represent the tensor content.

Keyword Arguments:

• size (list, tuple or Size, optional) – the new batch size, as a keyword argument instead of *shape.

• batch_size (Size, optional) – if a dtype is provided, the batch-size can be reset using this keyword argument. If the view is called with a shape, this is without effect.

Returns:

a new tensordict with the desired batch_size.

Examples

>>> import torch
>>> from tensordict import TensorDict
>>> td = TensorDict(source={'a': torch.zeros(3,4,5),
...    'b': torch.zeros(3,4,10,1)}, batch_size=torch.Size([3, 4]))
>>> td_view = td.view(12)
>>> print(td_view.get("a").shape)
torch.Size([12, 5])
>>> print(td_view.get("b").shape)
torch.Size([12, 10, 1])
>>> td_view = td.view(-1, 4, 3)
>>> print(td_view.get("a").shape)
torch.Size([1, 4, 3, 5])
>>> print(td_view.get("b").shape)
torch.Size([1, 4, 3, 10, 1])

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

Tutorials that use view

Changing the shape of a TensorDict

Changing the shape of a TensorDict