RReLU

RReLU(lower=1/8, upper=1/3, inplace=False)

Randomized leaky ReLU: while the module is in training mode, each
negative element is multiplied by a slope drawn uniformly from
``[lower, upper]`` for that element; in evaluation mode by the fixed
``(lower + upper) / 2``. The other elements pass through.
``inplace=True`` writes the result into the input and returns the input
itself.

__init__

__init__(self, lower: 'float' = 0.125, upper: 'float' = 0.3333333333333333, inplace: 'bool' = False) -> 'None'

Initialize self. See help(type(self)) for accurate signature.

extra_repr

extra_repr(self) -> 'str'

extra_repr() -> str

One line of per-class detail for :meth:__repr__; a layer prints its geometry here (in_features=64, out_features=256).

forward

forward(self, input: 'Tensor') -> 'Tensor'

forward(input) -> Tensor