oneflow.nn.Upsample

class oneflow.nn.Upsample(size: Optional[Union[int, Tuple[int, ]]] = None, scale_factor: Optional[Union[float, Tuple[float, ]]] = None, mode: str = 'nearest', align_corners: Optional[bool] = None)

Upsamples a given multi-channel 1D (temporal), 2D (spatial) or 3D (volumetric) data.

The input data is assumed to be of the form minibatch x channels x [optional depth] x [optional height] x width. Hence, for spatial inputs, we expect a 4D Tensor and for volumetric inputs, we expect a 5D Tensor.

The algorithms available for upsampling are nearest neighbor and linear, bilinear, bicubic and trilinear for 3D, 4D and 5D input Tensor, respectively.

One can either give a scale_factor or the target output size to calculate the output size. (You cannot give both, as it is ambiguous)

The interface is consistent with PyTorch. The documentation is referenced from: https://pytorch.org/docs/1.10/_modules/torch/nn/modules/upsampling.html.

Parameters
  • size (int or Tuple[int] or Tuple[int, int] or Tuple[int, int, int], optional) – output spatial sizes

  • scale_factor (float or Tuple[float] or Tuple[float, float] or Tuple[float, float, float], optional) – multiplier for spatial size. Has to match input size if it is a tuple.

  • mode (str, optional) – the upsampling algorithm: one of 'nearest', 'linear', 'bilinear', 'bicubic' and 'trilinear'. Default: 'nearest'

  • align_corners (bool, optional) – if True, the corner pixels of the input and output tensors are aligned, and thus preserving the values at those pixels. This only has effect when mode is 'linear', 'bilinear', or 'trilinear'. Default: False

Shape:
  • Input: \((N, C, W_{in})\), \((N, C, H_{in}, W_{in})\) or \((N, C, D_{in}, H_{in}, W_{in})\)

  • Output: \((N, C, W_{out})\), \((N, C, H_{out}, W_{out})\) or \((N, C, D_{out}, H_{out}, W_{out})\), where

\[D_{out} = \left\lfloor D_{in} \times \text{scale_factor} \right\rfloor\]
\[H_{out} = \left\lfloor H_{in} \times \text{scale_factor} \right\rfloor\]
\[W_{out} = \left\lfloor W_{in} \times \text{scale_factor} \right\rfloor\]

Warning

With align_corners = True, the linearly interpolating modes (linear, bilinear, bicubic, and trilinear) don’t proportionally align the output and input pixels, and thus the output values can depend on the input size. This was the default behavior for these modes up to version 0.3.1. Since then, the default behavior is align_corners = False. See below for concrete examples on how this affects the outputs.

Note

If you want downsampling/general resizing, you should use interpolate().

For example:

>>> import numpy as np
>>> import oneflow as flow

>>> input = flow.tensor(np.arange(1, 5).reshape((1, 1, 2, 2)), dtype=flow.float32)
>>> input = input.to("cuda")
>>> m = flow.nn.Upsample(scale_factor=2.0, mode="nearest")
>>> output = m(input)
>>> output 
tensor([[[[1., 1., 2., 2.],
          ...
          [3., 3., 4., 4.]]]], device='cuda:0', dtype=oneflow.float32)