interpolate(input, size=None, scale_factor=None, mode='nearest', align_corners=None, recompute_scale_factor=None)¶
Down/up samples the input to either the given
sizeor the given
The algorithm used for interpolation is determined by
Currently temporal, spatial and volumetric sampling are supported, i.e. expected inputs are 3-D, 4-D or 5-D in shape.
The input dimensions are interpreted in the form: mini-batch x channels x [optional depth] x [optional height] x width.
The modes available for resizing are: nearest, linear (3D-only), bilinear, bicubic (4D-only), trilinear (5D-only), area
input (Tensor) – the input tensor
mode (str) – algorithm used for upsampling:
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_factoris kept the same. This only has an effect when
recompute_scale_factor (bool, optional) – recompute the scale_factor for use in the interpolation calculation. If recompute_scale_factor is
True, then scale_factor must be passed in and scale_factor is used to compute the output size. The computed output size will be used to infer new scales for the interpolation. Note that when scale_factor is floating-point, it may differ from the recomputed scale_factor due to rounding and precision issues. If recomputed_scale_factor is
False, then size or scale_factor will be used directly for interpolation.
mode='bicubic', it’s possible to cause overshoot, in other words it can produce negative values or values greater than 255 for images. Explicitly call
result.clamp(min=0, max=255)if you want to reduce the overshoot when displaying the image.
align_corners = True, the linearly interpolating modes (linear, bilinear, 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
Upsamplefor concrete examples on how this affects the outputs.
When scale_factor is specified, if recompute_scale_factor=True, scale_factor is used to compute the output_size which will then be used to infer new scales for the interpolation. The default behavior for recompute_scale_factor changed to False in 1.6.0, and scale_factor is used in the interpolation calculation.
This operation may produce nondeterministic gradients when given tensors on a CUDA device. See Reproducibility for more information.