oneflow.nn.ReLU

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

Applies the rectified linear unit function element-wise:

\(\text{ReLU}(x) = (x)^+ = \max(0, x)\)

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 oneflow as flow
>>> import numpy as np
>>> relu = flow.nn.ReLU()
>>> ndarr = np.asarray([1, -2, 3])
>>> x = flow.Tensor(ndarr)
>>> relu(x)
tensor([1., 0., 3.], dtype=oneflow.float32)