nvidia.dali.fn.water#

nvidia.dali.fn.water(__input, /, *, ampl_x=10.0, ampl_y=10.0, bytes_per_sample_hint=[0], fill_value=0.0, freq_x=0.049087, freq_y=0.049087, interp_type=DALIInterpType.INTERP_NN, mask=1, phase_x=0.0, phase_y=0.0, preserve=False, seed=-1, device=None, name=None)#

Performs a water augmentation, which makes the image appear to be underwater.

Supported backends
  • ‘cpu’

  • ‘gpu’

Parameters:

__input (TensorList ('HWC')) – Input to the operator.

Keyword Arguments:
  • ampl_x (float, optional, default = 10.0) – Amplitude of the wave in the x direction.

  • ampl_y (float, optional, default = 10.0) – Amplitude of the wave in the y direction.

  • bytes_per_sample_hint (int or list of int, optional, default = [0]) –

    Output size hint, in bytes per sample.

    If specified, the operator’s outputs residing in GPU or page-locked host memory will be preallocated to accommodate a batch of samples of this size.

  • fill_value (float, optional, default = 0.0) – Color value that is used for padding.

  • freq_x (float, optional, default = 0.049087) – Frequency of the wave in the x direction.

  • freq_y (float, optional, default = 0.049087) – Frequence of the wave in the y direction.

  • interp_type (nvidia.dali.types.DALIInterpType, optional, default = DALIInterpType.INTERP_NN) – Type of interpolation used.

  • mask (int or TensorList of int, optional, default = 1) –

    Determines whether to apply this augmentation to the input image.

    Here are the values:

    • 0: Do not apply this transformation.

    • 1: Apply this transformation.

  • phase_x (float, optional, default = 0.0) – Phase of the wave in the x direction.

  • phase_y (float, optional, default = 0.0) – Phase of the wave in the y direction.

  • preserve (bool, optional, default = False) – Prevents the operator from being removed from the graph even if its outputs are not used.

  • seed (int, optional, default = -1) –

    Random seed.

    If not provided, it will be populated based on the global seed of the pipeline.