reference/generated/tensordict.TensorDictBase.separates

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

TensorDictBase.separates

TensorDictBase.separates(*keys: NestedKey, default: Any = NO_DEFAULT, strict: bool = True, filter_empty: bool = True) → Self

Separates the specified keys from the tensordict in-place.

See also

This method is equivalent to calling split_keys() with inplace=True on a single split.

See also

This method is equivalent to calling exclude() except that it returns the other split of the data.

Parameters:

• keys (NestedKey) – the keys to separate from the tensordict.

• default (Any, optional) – the value to be returned when a key is missing. If not specified and strict=True, an exception is raised. Otherwise, the default of any missing key will be None unless specified otherwise.

• strict (bool, optional) – if True, an exception is raised when a key is missing. Defaults to True.

• filter_empty (bool, optional) – if True, empty tensordicts within self will be removed. Defaults to True.

Returns:

the separated tensordict.

Return type:

T

Examples

>>> from tensordict import TensorDict
>>> td = TensorDict(
...     a=0,
...     b=0,
...     c=0,
...     d=0,
... )
>>> td_a_c = td.separates("a", "c")
>>> print(td_a_c)
TensorDict(
    fields={
        a: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.int64, is_shared=False),
        c: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.int64, is_shared=False)},
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)
>>> print(td)
TensorDict(
    fields={
        b: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.int64, is_shared=False),
        d: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.int64, is_shared=False)},
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)

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