nvidia.dali.fn.experimental.median_blur(__input, /, *, bytes_per_sample_hint=[0], preserve=False, seed=-1, window_size=[3, 3], device=None, name=None)#

Median blur performs smoothing of an image or sequence of images by replacing each pixel with the median color of a surrounding rectangular region.

Supported backends
  • ‘gpu’


__input (TensorList ('HW', 'HWC', 'FHWC', 'CHW', 'FCHW')) – Input data. Must be images in HWC or CHW layout, or a sequence of those.

Keyword Arguments:
  • 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.

  • 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.

  • window_size (int or list of int or TensorList of int, optional, default = [3, 3]) – The size of the window over which the smoothing is performed