oneflow.nn.functional.prelu¶
-
oneflow.nn.functional.
prelu
(x: Tensor, alpha: Tensor) → Tensor¶ Applies the element-wise function:
\[prelu(x) = max(0,x) + alpha * min(0,x)\]For example:
>>> import numpy as np >>> import oneflow as flow >>> x = flow.tensor(np.asarray([[[[1, -2], [3, 4]]]]), dtype=flow.float32) >>> alpha = flow.nn.Parameter(flow.tensor([1], dtype=flow.float32).fill_(0.25)) >>> flow.nn.functional.prelu(x, alpha) tensor([[[[ 1.0000, -0.5000], [ 3.0000, 4.0000]]]], dtype=oneflow.float32, grad_fn=<preluBackward>)
See
PReLU
for more details.