torch.nn.functional.interpolate 1.7版本 （recompute_scale_factor (bool, optional)）

torch.nn.functional.interpolate     上下采样函数

Interpolate（）

解析: torch.nn.functional.interpolate(input, size=None, scale_factor=None, mode='nearest', align_corners=None，recompute_scale_factor=None)

参数：

• input (Tensor) – the input tensor
• size (int or Tuple[int] or Tuple[int, int] or Tuple[int, int, int]) – output spatial size.
• scale_factor (float or Tuple[float]) – multiplier for spatial size. Has to match input size if it is a tuple.
• mode (str) – algorithm used for upsampling: 'nearest' | 'linear' | 'bilinear' | 'bicubic' | 'trilinear' | 'area'. Default: 'nearest'
• align_corners (bool, optional) – Geometrically, we consider the pixels of the input and output as squares rather than points. If set to True, the input and output tensors are aligned by the center points of their corner pixels, preserving the values at the corner pixels. If set to False, the input and output tensors are aligned by the corner points of their corner pixels, and the interpolation uses edge value padding for out-of-boundary values, making this operation independent of input size when scale_factor is kept the same. This only has an effect when mode is 'linear', 'bilinear', 'bicubic' or 'trilinear'. Default: False
• recompute_scale_factor (bool, optional) – recompute the scale_factor for use in the interpolation calculation. When scale_factor is passed as a parameter, it is used to compute the output_size. If recompute_scale_factor is `False or not specified, the passed-in scale_factor will be used in the interpolation computation. Otherwise, a new scale_factor will be computed based on the output and input sizes for use in the interpolation computation (i.e. the computation will be identical to if the computed output_size were passed-in explicitly). Note that when scale_factor is floating-point, the recomputed scale_factor may differ from the one passed in due to rounding and precision issues.

可用于重置大小的mode有：最近邻、线性(3D-only),、双线性, 双三次(bicubic,4D-only)和三线性(trilinear,5D-only)插值算法和area算法。