oneflow.nn.ReLU6

class oneflow.nn.ReLU6(inplace: bool = False)

Applies the element-wise function:

\[\begin{split}\text{Relu6}(x) = \begin{cases} 6 & \text{ if } x > 6 \\ 0 & \text{ if } x < 0 \\ x & \text{ otherwise } \\ \end{cases}\end{split}\]

Parameters

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

Shape:

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

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

For example:

>>> import numpy as np
>>> import oneflow as flow

>>> x = np.array([-0.5, 0, 0.5]).astype(np.float32)
>>> input = flow.Tensor(x)
>>> relu6 = flow.nn.ReLU6()

>>> out = relu6(input)
>>> out
tensor([0.0000, 0.0000, 0.5000], dtype=oneflow.float32)