RandomResizedCrop

class torchaug.transforms.RandomResizedCrop(size, scale=(0.08, 1.0), ratio=(3.0 / 4.0, 4.0 / 3.0), interpolation=InterpolationMode.BILINEAR, antialias=True, num_chunks=1, permute_chunks=False, batch_transform=False)[source]

Crop a random portion of the input and resize it to a given size.

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.

A crop of the original input is made: the crop has a random area (H * W) and a random aspect ratio. This crop is finally resized to the given size. This is popularly used to train the Inception networks.

Parameters:

  • size (Union[int, Sequence[int]]) –

    expected output size of the crop, for each edge. If size is an int instead of sequence like (h, w), a square output size (size, size) is made. If provided a sequence of length 1, it will be interpreted as (size[0], size[0]).

    Note

    In torchscript mode size as single int is not supported, use a sequence of length 1: [size, ].

  • scale (Tuple[float, float], optional) – Specifies the lower and upper bounds for the random area of the crop, before resizing. The scale is defined with respect to the area of the original image. Default: (0.08, 1.0)

  • ratio (Tuple[float, float], optional) – lower and upper bounds for the random aspect ratio of the crop, before resizing. Default: (3.0 / 4.0, 4.0 / 3.0)

  • 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

  • num_chunks (int, optional) – number of chunks to split the batched input into. Default: 1

  • permute_chunks (bool, optional) – whether to permute the chunks. Default: False

  • batch_transform (bool, optional) – whether to apply the transform in batch mode. Default: False