warp.smooth_normalize

warp.smooth_normalize(v: Any, delta: float) → None

Kernel

Differentiable

Normalizes a vector using the pseudo-Huber norm.

See norm_pseudo_huber().

\[\frac{v}{H^\prime(v)}\]

Args:

v (Vector[Any,Float]): The vector to normalize. delta (float): The threshold value, defaults to 1.0.

Returns:

Vector[Any,Float]: The normalized vector.