Skip to main content

PixelUnshuffle

PixelUnshuffle(downscale_factor, mode="crd")

Moves spatial samples into the channels: [N, H * r, W * r, C] to [N, H, W, C * r * r] for the factor r.

The module form of clika_runtime.nn.functional.pixel_unshuffle: construct it once with the settings, then call it like a function.

Args: downscale_factor: the factor r. mode: the channel ordering of the packed output.

__init__​

__init__(self, downscale_factor: 'int', mode: '_PixelShuffleMode' = 'crd') -> 'None'

Initialize self. See help(type(self)) for accurate signature.

extra_repr​

extra_repr(self) -> 'str'

extra_repr() -> str

One line of per-class detail for :meth:__repr__; a layer prints its geometry here (in_features=64, out_features=256).

forward​

forward(self, input: 'Tensor') -> 'Tensor'

forward(input) -> Tensor

Runs clika_runtime.nn.functional.pixel_unshuffle on input with the stored settings; returns a new tensor.