RandomAdjustSharpness — Torchvision 0.22 documentation (original) (raw)

class torchvision.transforms.v2.RandomAdjustSharpness(sharpness_factor: float, p: float = 0.5)[source]¶

Adjust the sharpness of the image or video with a given probability.

If the input is a torch.Tensor, it is expected to have […, 1 or 3, H, W] shape, where … means an arbitrary number of leading dimensions.

Parameters:

• sharpness_factor (float) – How much to adjust the sharpness. Can be any non-negative number. 0 gives a blurred image, 1 gives the original image while 2 increases the sharpness by a factor of 2.
• p (float) – probability of the image being sharpened. Default value is 0.5

Examples using RandomAdjustSharpness:

transform(inpt: Any, params: Dict[str, Any]) → Any[source]¶

Method to override for custom transforms.

See How to write your own v2 transforms