mindspore.Tensor.cauchy
- Tensor.cauchy(median=0.0, sigma=1.0)[source]
Fills the tensor with numbers drawn from the Cauchy distribution. It is defined as follows:
\[f(x)= \frac{1}{\pi} \frac{\sigma}{(x-median)^2 +\sigma^2}\]Warning
This is an experimental API that is subject to change or deletion.
- Parameters
- Returns
Tensor. A Tensor with the same type and shape of input.
- Supported Platforms:
Ascend
CPU
Examples
>>> import mindspore >>> import numpy as np >>> x = mindspore.Tensor(np.zeros((1, 2)), dtype=mindspore.float32) >>> x.cauchy() Tensor(shape=[1, 2], dtype=Float32, value= [[8.79836142e-01, 9.37541723e-01]])