RandomShortestSize

class torchaug.transforms.RandomShortestSize(min_size, max_size=None, interpolation=InterpolationMode.BILINEAR, antialias=True)[source]

Randomly resize the input.

If the input is a torch.Tensor or a TATensor (e.g. Image, Video, BoundingBoxes etc.) it can have arbitrary number of leading batch dimensions. For example, the image can have [..., C, H, W] shape. A bounding box can have [..., 4] shape.

Parameters:

  • min_size (Union[List[int], Tuple[int], int]) – Minimum spatial size. Single integer value or a sequence of integer values.

  • max_size (Optional[int], optional) – Maximum spatial size. Default, None. Default: None

  • interpolation (Union[InterpolationMode, int], optional) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Only InterpolationMode.NEAREST, InterpolationMode.NEAREST_EXACT, InterpolationMode.BILINEAR and InterpolationMode.BICUBIC are supported. Default: InterpolationMode.BILINEAR

  • antialias (bool, optional) – Whether to apply antialiasing. Default: True