digamma

paddle. digamma ( x: Tensor, name: str | None = None ) → Tensor [source]

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

\[Out = \Psi(x) = \frac{ \Gamma^{'}(x) }{ \Gamma(x) }\]

Parameters

• x (Tensor) – Input Tensor. Must be one of the following types: bfloat16, float16, float32, float64, uint8, int8, int16, int32, int64.

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

Returns

Tensor, the digamma of the input Tensor, the shape and data type is the same with input

(integer types are autocasted into float32).

Examples

>>> import paddle

>>> data = paddle.to_tensor([[1, 1.5], [0, -2.2]], dtype='float32')
>>> res = paddle.digamma(data)
>>> res
Tensor(shape=[2, 2], dtype=float32, place=Place(cpu), stop_gradient=True,
[[-0.57721591,  0.03648996],
 [ nan       ,  5.32286835]])