TensorFlow 1 version |
Computes scaled exponential linear: scale * alpha * (exp(features) - 1)
tf.nn.selu(
features, name=None
)
if < 0, scale * features
otherwise.
To be used together with
initializer = tf.variance_scaling_initializer(factor=1.0, mode='FAN_IN')
.
For correct dropout, use tf.contrib.nn.alpha_dropout
.
See Self-Normalizing Neural Networks
Args | |
---|---|
features
|
A Tensor . Must be one of the following types: half , bfloat16 , float32 , float64 .
|
name
|
A name for the operation (optional). |
Returns | |
---|---|
A Tensor . Has the same type as features .
|