tf.contrib.nn.scaled_softplus(
x,
alpha,
clip=None,
name=None
)
Defined in tensorflow/contrib/nn/python/ops/scaled_softplus.py
.
Returns y = alpha * ln(1 + exp(x / alpha))
or min(y, clip)
.
This can be seen as a softplus applied to the scaled input, with the output
appropriately scaled. As alpha
tends to 0, scaled_softplus(x, alpha)
tends
to relu(x)
. The clipping is optional. As alpha->0, scaled_softplus(x, alpha)
tends to relu(x), and scaled_softplus(x, alpha, clip=6) tends to relu6(x).
Args:
x
: ATensor
of inputs.alpha
: ATensor
, indicating the amount of smoothness. The caller must ensure thatalpha > 0
.clip
: (optional) ATensor
, the upper bound to clip the values.name
: A name for the scope of the operations (optional).
Returns:
A tensor of the size and type determined by broadcasting of the inputs.