ncdl.nn.Threshold

class ncdl.nn.Threshold(*args: Any, **kwargs: Any)

Thresholds each element of the input Lattice Tensor.

Threshold is defined as:

\[\begin{split}y = \begin{cases} x, &\text{ if } x > \text{threshold} \\ \text{value}, &\text{ otherwise } \end{cases}\end{split}\]

Parameters:

• threshold – The value to threshold at

• value – The value to replace with

• inplace – can optionally do the operation in-place. Default: False

Shape:

• Input: \((*)\), where \(*\) means any number of dimensions.

• Output: \((*)\), same shape as the input.

Examples:

>>> m = nn.Threshold(0.1, 20)
>>> input = torch.randn(2)
>>> output = m(input)

__init__(threshold: float, value: float, inplace: bool = False) → None

Methods

__init__(threshold, value[, inplace])
extra_repr()
forward(input)

Attributes

threshold
value
inplace