mindspore.ops.Digamma
- class mindspore.ops.Digamma[source]
Computes the grad of the lgamma function on input.
\[P(x) = grad(ln(gamma(x)))\]Warning
This is an experimental API that is subject to change or deletion.
- Inputs:
x (Tensor) - The input tensor. With type of float16 or float32 or float64.
- Outputs:
Tensor, has the same dtype as x.
- Raises
- Supported Platforms:
GPU
CPU
Examples
>>> x = Tensor(np.array([1.5, 0.5, 9]).astype(np.float16)) >>> digamma = ops.Digamma() >>> output = digamma(x) >>> print(output) [ 0.0365 -1.964 2.14 ]