Rate this Page
★★★★★

torch.nn.functional.upsample_bilinear#

torch.nn.functional.upsample_bilinear(input,size=None,scale_factor=None)[source]#

Upsamples the input, using bilinear upsampling.

Warning

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

Expected inputs are spatial (4 dimensional). Useupsample_trilinear forvolumetric (5 dimensional) inputs.

Parameters

  • input (Tensor) – input

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

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

Note

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