nvidia.dali.experimental.dynamic.noise.gaussian#

nvidia.dali.experimental.dynamic.noise.gaussian(input, /, *, batch_size=None, device=None, mean=None, seed=None, stddev=None, rng=None)#

Applies gaussian noise to the input.

The shape and data type of the output will match the input.

Supported backends

  • ‘cpu’

  • ‘gpu’

Parameters:

input (Tensor/Batch) – Input to the operator.

Keyword Arguments:

  • mean (float or Tensor/Batch of float, optional, default = 0.0) – Mean of the distribution.

  • stddev (float or Tensor/Batch of float, optional, default = 1.0) – Standard deviation of the distribution.

  • rng (RNG, optional) – A random number generator instance. Can be obtained by calling nvidia.dali.experimental.dynamic.random.RNG(seed)(). If not provided, the default RNG is used.

On this page