ReLU6

class torch.nn.ReLU6(inplace=False) [source]

Applies the element-wise function:

$$\text{ReLU6}(x) = \min(\max(0,x), 6)$$

Parameters

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.

Examples:

>>> m = nn.ReLU6()
>>> input = torch.randn(2)
>>> output = m(input)