class
RingingOvershoot
extends
PhotometricTransform[Empty]RingingOvershoot(blur_limit: tuple[int, int] = (7, 15), p: float = 0.5)Simulate ringing / overshoot artefacts via a high-pass kernel (Albumentations RingingOvershoot).
Convolves the image with a 3x3 high-pass kernel that exaggerates edges, producing the bright halo / undershoot pattern typical of aggressive sharpening or low-pass filter ringing. Useful for simulating compression artefacts and JPEG-style edge halos during training.
Parameters
blur_limit(int, int)= (7, 15)Reserved for parity with the Albumentations API; the current
implementation uses a fixed 3x3 high-pass kernel and ignores
this argument, but it is kept on the signature for forward
compatibility.
pfloat= 0.5Probability of applying the transform.
Examples
>>> import lucid
>>> import lucid.utils.transforms as T
>>> tf = T.RingingOvershoot(blur_limit=(7, 15), p=1.0)
>>> out = tf(T.Image(lucid.rand(3, 32, 32))).data
>>> tuple(out.shape)
(3, 32, 32)Used by 1
Constructors
1Instance methods
1Return the no-op parameter sentinel for RingingOvershoot.
Parameters
imgTensorImage tensor; not inspected.
Returns
EmptyThe shared NO_PARAMS sentinel — the current
implementation uses a fixed high-pass kernel, so no
per-call sampling is needed. blur_limit is kept on
the signature for forward compatibility but is unused.