class

Hardshrink

extendsModule

Hardshrink(lambd: float = 0.5)

source

Hard Shrinkage activation function.

Applies element-wise:

\text{Hardshrink}(x) = \begin{cases} x & \text{if } |x| > \lambda \\ 0 & \text{otherwise} \end{cases}

Values within the band $[-\lambda, \lambda]$ are zeroed out ("shrunk" to zero), while large values pass through unchanged. Hard shrinkage encourages sparse representations and is commonly used in sparse coding and wavelet-based signal processing.

Parameters

lambdfloat= 0.5

Threshold

\lambda \geq 0

. Default: 0.5.

Notes

Input: $(*)$ — any shape.
Output: $(*)$ — same shape as input.

Examples

>>> import lucid
>>> import lucid.nn as nn
>>> m = nn.Hardshrink(lambd=0.5)
>>> x = lucid.tensor([-1.0, -0.4, 0.0, 0.4, 1.0])
>>> m(x)
tensor([-1.,  0.,  0.,  0.,  1.])
>>> # Sparsifying activation for dictionary learning
>>> m = nn.Hardshrink(lambd=1.0)
>>> x = lucid.randn(8, 64)
>>> out = m(x)
>>> out.shape
(8, 64)

Methods (3)

dunder

init

→None

__init__(lambd: float = 0.5)

source

Initialise the Hardshrink module. See the class docstring for parameter semantics.

forward

→Tensor

forward(x: Tensor)

source

Apply the activation function element-wise.

Parameters

inputTensor

Input tensor of arbitrary shape.

Returns

Tensor

Output tensor of the same shape as input.

extra_repr

→str

extra_repr()

source

Return a string representation of the layer's configuration.