TF 2.0 is out! Get hands-on practice at TF World, Oct 28-31. Use code TF20 for 20% off select passes. Register now

tf.math.polygamma

TensorFlow 1 version

Defined in generated file: python/ops/gen_math_ops.py

Compute the polygamma function \(\psi^{(n)}(x)\).

Aliases:

tf.math.polygamma(
    a,
    x,
    name=None
)

The polygamma function is defined as:

\(\psi^{(a)}(x) = \frac{d^a}{dx^a} \psi(x)\)

where \(\psi(x)\) is the digamma function. The polygamma function is defined only for non-negative integer orders \a\.

Args:

  • a: A Tensor. Must be one of the following types: float32, float64.
  • x: A Tensor. Must have the same type as a.
  • name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as a.