RandomPosterize¶

class torchaug.transforms.RandomPosterize(bits, p=0.5, batch_inplace=False, batch_transform=False)[source]¶

Posterize the image or video with a given probability by reducing the number of bits for each color channel.

The input should be of type torch.uint8 and it is expected to have […, 1 or 3, H, W] shape, where … means an arbitrary number of leading dimensions.

Parameters:

bits (int) – number of bits to keep for each channel (0-8)
p (float, optional) – probability of the image being posterized. Default: 0.5
batch_inplace (bool, optional) – whether to apply the batch transform in-place. Does not prevent functionals to make copy but can reduce time and memory consumption. Default: False
batch_transform (bool, optional) – whether to apply the transform in batch mode. Default: False

extra_repr()[source]¶

Set the extra representation of the transform.