exponential_

paddle.Tensor. exponential_ ( x, lam=1.0, name=None )

This inplace OP fill input Tensor x with random number from a Exponential Distribution.

lam is \(\lambda\) parameter of Exponential Distribution.

\[f(x) = \lambda e^{-\lambda x}\]
Parameters
  • x (Tensor) – Input tensor. The data type should be float32, float64.

  • lam (float, optional) – \(\lambda\) parameter of Exponential Distribution. Default, 1.0.

  • name (str, optional) – The default value is None. Normally there is no need for user to set this property. For more information, please refer to Name.

Returns

Input Tensor x.

Return type

Tensor

Examples

>>> import paddle
>>> paddle.set_device('cpu')
>>> paddle.seed(100)

>>> x = paddle.empty([2,3])
>>> x.exponential_()
>>> 
Tensor(shape=[2, 3], dtype=float32, place=Place(cpu), stop_gradient=True,
[[0.80643415, 0.23211166, 0.01169797],
 [0.72520679, 0.45208144, 0.30234432]])
>>>