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.