torch.nn.functional.upsample_bilinear

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

Upsamples the input, using bilinear upsampling.

Warning

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

Expected inputs are spatial (4 dimensional). Use upsample_trilinear fo volumetric (5 dimensional) inputs.

Parameters

• input (Tensor) – input

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

• scale_factor (int or Tuple[int, int]) – multiplier for spatial size

Note

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