log_normal

paddle. log_normal ( mean: float | Tensor = 1.0, std: float | Tensor = 2.0, shape: ShapeLike | None = None, name: str | None = None ) → Tensor [source]

Returns a Tensor filled with random values sampled from a Log Normal Distribution, with mean, std. The Log Normal Distribution is defined as follows

\[f(x) = \frac{1}{x\sigma\sqrt{2\pi}}e^{-\frac{(\ln{x}-\mu)^2}{2\sigma^2}}\]
Parameters

  • mean (float|Tensor, optional) – The mean of the output Tensor’s underlying normal distribution. If mean is float, all elements of the output Tensor share the same mean. If mean is a Tensor(data type supports float32, float64), it has per-element means. Default is 1.0

  • std (float|Tensor, optional) – The standard deviation of the output Tensor’s underlying normal distribution. If std is float, all elements of the output Tensor share the same standard deviation. If std is a Tensor(data type supports float32, float64), it has per-element standard deviations. Default is 2.0

  • shape (tuple|list|Tensor|None, optional) – Shape of the Tensor to be created. The data type is int32 or int64 . If shape is a list or tuple, each element of it should be integer or 0-D Tensor with shape []. If shape is an Tensor, it should be an 1-D Tensor which represents a list. If mean or std is a Tensor, the shape of the output Tensor is the same as mean or std , attr shape is ignored. Default is None

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

Returns

Tensor, A Tensor filled with random values sampled from a log normal distribution with the underlying normal distribution’s mean and std .

Examples

>>> import paddle
>>> paddle.seed(200)

>>> out1 = paddle.log_normal(shape=[2, 3])
>>> print(out1)
Tensor(shape=[2, 3], dtype=float32, place=Place(cpu), stop_gradient=True,
[[4.01107359 , 3.53824377 , 25.79078865],
 [0.83332109 , 0.40513405 , 2.09763741 ]])

>>> mean_tensor = paddle.to_tensor([1.0, 2.0, 3.0])
>>> out2 = paddle.log_normal(mean=mean_tensor)
>>> print(out2)
Tensor(shape=[3], dtype=float32, place=Place(cpu), stop_gradient=True,
[4.45330524 , 0.57903880 , 31.82369995])

>>> std_tensor = paddle.to_tensor([1.0, 2.0, 3.0])
>>> out3 = paddle.log_normal(mean=mean_tensor, std=std_tensor)
>>> print(out3)
Tensor(shape=[3], dtype=float32, place=Place(cpu), stop_gradient=True,
[10.31321430, 8.97369766 , 35.76752090])