|TensorFlow 1 version||View source on GitHub|
Computes \(ln(|Beta(x)|)\), reducing along the last dimension.
Compat aliases for migration
See Migration guide for more details.
tf.math.lbeta( x, name=None )
Given one-dimensional $z = [z_1,...,z_K]$, we define
where $\Gamma$ is the gamma function.
And for $n + 1$ dimensional $x$ with shape $[N_1, ..., N_n, K]$, we define
In other words, the last dimension is treated as the $z$ vector.
Note that if $z = [u, v]$, then
which defines the traditional bivariate beta function.
If the last dimension is empty, we follow the convention that the sum over the empty set is zero, and the product is one.
||A name for the operation (optional).|
|The logarithm of \(|Beta(x)|\) reducing along the last dimension.|