cupy.random.randn#

cupy.random.randn(*size, **kwarg)[source]#

Returns an array of standard normal random values.

Each element of the array is normally distributed with zero mean and unit variance. All elements are identically and independently distributed (i.i.d.).

Parameters:
  • size (ints) – The shape of the array.

  • dtype – Data type specifier. Only numpy.float32 and numpy.float64 types are allowed. The default is numpy.float64.

Returns:

An array of standard normal random values.

Return type:

cupy.ndarray

See also

numpy.random.randn()

Example

>>> cupy.random.randn(3, 2)
array([[0.41193321, 1.59579542],   # random
       [0.47904589, 0.18566376],   # random
       [0.59748424, 2.32602829]])  # random

>>> cupy.random.randn(3, 2, dtype=cupy.float32)
array([[ 0.1373886 ,  2.403238  ],                  # random
       [ 0.84020025,  1.5089266 ],                  # random
       [-1.2268474 , -0.48219103]], dtype=float32)  # random