ScaleJitter¶

class torchaug.transforms.ScaleJitter(target_size, scale_range=(0.1, 2.0), interpolation=InterpolationMode.BILINEAR, antialias=True)[source]¶

Perform Large Scale Jitter on the input according to “Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation”.

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:

target_size (Tuple[int, int]) – Target size. This parameter defines base scale for jittering, e.g. min(target_size[0] / width, target_size[1] / height).
scale_range (Tuple[float, float], optional) – Minimum and maximum of the scale range. Default: (0.1, 2.0)
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