Softplus

Softplus(beta=1.0, threshold=20.0)

Smooth ReLU: log(1 + exp(beta * input)) / beta, switching to the exact linear input where beta * input exceeds threshold.

The module form of clika_runtime.nn.functional.softplus: construct it once with the settings, then call it like a function.

Args: beta: the sharpness; larger approaches ReLU. threshold: the switch point on beta * input above which the exact linear input is returned.

`init`

__init__(self, beta: 'float' = 1.0, threshold: 'float' = 20.0) -> 'None'

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

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

forward(input) -> Tensor

Runs clika_runtime.nn.functional.softplus on input with the stored settings; returns a new tensor.