clip

→Tensor

clip(input: Tensor, min: Scalar | None, max: Scalar | None)

Element-wise clamping to a closed interval.

Clips each entry of input so that it lies within [min, max]. Either bound may be None to leave that side unbounded. Alias of clamp.

inputTensor

Input tensor.

minscalar or None

Lower bound. None disables the lower clip.

maxscalar or None

Upper bound. None disables the upper clip.

Tensor

Tensor with the same shape and dtype as input, with values constrained to [min, max].

Mathematical definition:

\text{out}_i = \min(\max(\text{input}_i, \text{min}), \text{max})

Gradient flows through where min < x < max; at the clipped boundaries it is treated as zero. If min > max the result is implementation-defined.

>>> import lucid
>>> x = lucid.tensor([-2.0, -0.5, 0.5, 2.0])
>>> lucid.clip(x, -1.0, 1.0)
Tensor([-1., -0.5, 0.5, 1.])