Python v0.3.0.dev+c1b8f91
  • Overview

    • UpsamplingBilinear2d

    class dragon.vm.torch.nn.UpsamplingBilinear2d(
      size=None,
      scale_factor=None
    )[source]

    Upsample input via bilinear interpolating.

    Examples:

    x = torch.ones((1, 2, 3, 4))
y = torch.nn.UpsamplingBilinear2d(size=6)(x)  # Shape: (1, 2, 6, 6)
z = torch.nn.UpsamplingBilinear2d(scale_factor=2)(x)  # Shape: (1, 2, 6, 8)

    __init__

    UpsamplingBilinear2d.__init__(
      size=None,
      scale_factor=None
    )[source]

    Create an UpsamplingBilinear2d module.

    Parameters:
    • size (Union[int, Sequence[int]], optional) – The output size.
    • scale_factor (Union[number, Sequence[number]], optional) – The scale factor along each input dimension.