UpsamplingBilinear2d¶

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

Upsample input via bilinear interpolating.

Set size or scale_factor to determine the output size:

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

See also

torch.nn.functional.interpolate(…)