Per-channel histogram equalization (Albumentations Equalize).
Computes a cumulative distribution per channel and remaps intensities
so the output histogram is as flat as possible. Useful for stretching
contrast on dim or hazy images. Delegates to
functional.equalize, which handles the uint8 round-trip and
per-channel CDF construction.
Parameters
pfloat= 0.5Probability of applying the transform.
Examples
>>> import lucid
>>> import lucid.utils.transforms as T
>>> tf = T.Equalize(p=1.0)
>>> out = tf(T.Image(lucid.rand(3, 32, 32))).data
>>> tuple(out.shape)
(3, 32, 32)