polygamma¶

paddle. polygamma ( x, n, name=None ) [source]

Calculates the polygamma of the given input tensor, element-wise.

The equation is:

\[\Phi^n(x) = \frac{d^n}{dx^n} [\ln(\Gamma(x))]\]

Parameters

• x (Tensor) – Input Tensor. Must be one of the following types: float32, float64.

• n (int) – Order of the derivative. Must be integral.

• name (str, optional) – Name for the operation (optional, default is None). For more information, please refer to Name.

Returns

• out (Tensor), A Tensor. the polygamma of the input Tensor, the shape and data type is the same with input.

Examples

import paddle

data = paddle.to_tensor([2, 3, 25.5], dtype='float32')
res = paddle.polygamma(data, 1)
print(res)
# Tensor(shape=[2], dtype=float32, place=CUDAPlace(0), stop_gradient=True,
#       [0.64493407,  0.39493407,  0.03999467])