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 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]])