torch.nn.functional.upsample_nearest

torch.nn.functional.upsample_nearest(input, size=None, scale_factor=None)

Upsamples the input, using nearest neighbours’ pixel values.

Warning

This function is deprecated in favor of torch.nn.functional.interpolate(). This is equivalent with nn.functional.interpolate(..., mode='nearest').

Currently spatial and volumetric upsampling are supported (i.e. expected inputs are 4 or 5 dimensional).

Parameters:

• input (Tensor) – input

• size (int or Tuple[int, int] or Tuple[int, int, int]) – output spatia size.

• scale_factor (int) – multiplier for spatial size. Has to be an integer.

Note

This operation may produce nondeterministic gradients when given tensors on a CUDA device. See Reproducibility for more information.