upsample_nearest

dragon.vm.torch.nn.functional.upsample_nearest(
  input,
  size=None,
  scale_factor=None
)[source]

Upsample input via nearest interpolating.

Examples:

x = torch.ones((1, 2, 3, 4))
y = F.upsample_nearest(x, size=6)  # Shape: (1, 2, 6, 6)
z = F.upsample_nearest(x, scale_factor=2)  # Shape: (1, 2, 6, 8)
Parameters:
  • input (dragon.vm.torch.Tensor) – The input tensor.
  • size (Union[int, Sequence[int]], optional) – The output size.
  • scale_factor (Union[number, Sequence[number]], optional) – The scale factor along each input dimension.
Returns:

dragon.vm.torch.Tensor – The output tensor.