Rate this Page

Threshold#

class torch.nn.Threshold(threshold, value, inplace=False)[source]#

Thresholds each element of the input Tensor.

Threshold is defined as:

y={x, if x>thresholdvalue, otherwise y = \begin{cases} x, &\text{ if } x > \text{threshold} \\ \text{value}, &\text{ otherwise } \end{cases}
Parameters
  • threshold (float) – The value to threshold at

  • value (float) – The value to replace with

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

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

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

../_images/Threshold.png

Examples:

>>> m = nn.Threshold(0, 0.5)
>>> input = torch.arange(-3, 3)
>>> output = m(input)