PReLU
classkeras.layers.PReLU(
alpha_initializer="Zeros",
alpha_regularizer=None,
alpha_constraint=None,
shared_axes=None,
**kwargs
)
Parametric Rectified Linear Unit activation layer.
Formula:
f(x) = alpha * x for x < 0
f(x) = x for x >= 0
where alpha
is a learned array with the same shape as x.
Arguments
(batch, height, width, channels)
, and you wish to share parameters
across space so that each filter only has one set of parameters,
set shared_axes=[1, 2]
.name
and dtype
.