reference/generated/tensordict.TensorDictBase.exclude

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

TensorDictBase.exclude

TensorDictBase.exclude(*keys: NestedKey, inplace: bool = False) → Self

Excludes the keys of the tensordict and returns a new tensordict without these entries.

The values are not copied. The result shares its tensors with the original, so an in-place change to a tensor in one tensordict shows in the other. Unlike select(), a missing key is ignored: there is no strict argument. See Keys, nested keys, and locking.

Parameters:

• *keys (NestedKey) – keys to exclude.

• inplace (bool) – if True, the keys are removed from this tensordict, and this tensordict is returned. Default is False.

Returns:

A new tensordict (or the same if inplace=True) without the excluded entries.

Examples

>>> from tensordict import TensorDict
>>> td = TensorDict({"a": 0, "b": {"c": 1, "d": 2}}, [])
>>> td.exclude("a", ("b", "c"))
TensorDict(
    fields={
        b: TensorDict(
            fields={
                d: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.int64, is_shared=False)},
            batch_size=torch.Size([]),
            device=None,
            is_shared=False)},
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)
>>> td.exclude("a", "b")
TensorDict(
    fields={
    },
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)
>>> list(td.exclude("this key does not exist").keys())
['a', 'b']

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

Tutorials that use exclude

Getting, setting, and nesting keys

Getting, setting, and nesting keys