resize¶
- torchvision.transforms.functional.resize(img: Tensor, size: List[int], interpolation: InterpolationMode = InterpolationMode.BILINEAR, max_size: Optional[int] = None, antialias: Optional[bool] = None) Tensor [source]¶
Resize the input image to the given size. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions
Warning
The output image might be different depending on its type: when downsampling, the interpolation of PIL images and tensors is slightly different, because PIL applies antialiasing. This may lead to significant differences in the performance of a network. Therefore, it is preferable to train and serve a model with the same input types. See also below the
antialias
parameter, which can help making the output of PIL images and tensors closer.- Parameters:
img (PIL Image or Tensor) – Image to be resized.
size (sequence or int) –
Desired output size. If size is a sequence like (h, w), the output size will be matched to this. If size is an int, the smaller edge of the image will be matched to this number maintaining the aspect ratio. i.e, if height > width, then image will be rescaled to \(\left(\text{size} \times \frac{\text{height}}{\text{width}}, \text{size}\right)\).
Note
In torchscript mode size as single int is not supported, use a sequence of length 1:
[size, ]
.interpolation (InterpolationMode) – Desired interpolation enum defined by
torchvision.transforms.InterpolationMode
. Default isInterpolationMode.BILINEAR
. If input is Tensor, onlyInterpolationMode.NEAREST
,InterpolationMode.BILINEAR
andInterpolationMode.BICUBIC
are supported. For backward compatibility integer values (e.g.PIL.Image[.Resampling].NEAREST
) are still accepted, but deprecated since 0.13 and will be removed in 0.15. Please use InterpolationMode enum.max_size (int, optional) – The maximum allowed for the longer edge of the resized image: if the longer edge of the image is greater than
max_size
after being resized according tosize
, then the image is resized again so that the longer edge is equal tomax_size
. As a result,size
might be overruled, i.e the smaller edge may be shorter thansize
. This is only supported ifsize
is an int (or a sequence of length 1 in torchscript mode).antialias (bool, optional) – antialias flag. If
img
is PIL Image, the flag is ignored and anti-alias is always used. Ifimg
is Tensor, the flag is False by default and can be set to True forInterpolationMode.BILINEAR
andInterpolationMode.BICUBIC
modes. This can help making the output for PIL images and tensors closer.
- Returns:
Resized image.
- Return type:
PIL Image or Tensor
Examples using
resize
:Optical Flow: Predicting movement with the RAFT model
Optical Flow: Predicting movement with the RAFT modelIllustration of transforms