TensorDictBase.exclude#
- TensorDictBase.exclude(*keys: NestedKey, inplace: bool = False) Self#
Returns a tensordict without the entries of
keys.The values are not copied: the result holds the same tensors as the tensordict, so an in-place change to a tensor shows in both. A nested key removes one entry of a nested tensordict, and the key of a nested tensordict removes all its entries. Unlike
select(), a missing key is ignored. The result is not locked. See Keys, nested keys, and locking.- Parameters:
*keys (NestedKey) – the keys to remove.
- Keyword Arguments:
inplace (bool, optional) – if
True, removes the entries from the tensordict and returns it. Defaults toFalse.- Returns:
A tensordict of the same type, or
selfifinplace=True.
Examples
>>> import torch >>> from tensordict import TensorDict >>> td = TensorDict( ... obs=torch.zeros(3, 4), ... action=torch.zeros(3, 2), ... next=TensorDict(obs=torch.zeros(3, 4), reward=torch.zeros(3, 1)), ... batch_size=[3], ... ) >>> sub = td.exclude("action", ("next", "obs")) >>> list(sub.keys(include_nested=True, leaves_only=True)) ['obs', ('next', 'reward')] >>> sub["obs"] is td["obs"] True >>> sorted(td.exclude("missing").keys()) ['action', 'next', 'obs']
Every tensordict class and every tensorclass has this method. For the other methods, see Methods by task.
