tensorplay.functional.acosh

tensorplay.functional.acosh(input: Tensor, *, out: Tensor | None) → Tensor[source]

Returns a new tensor with the inverse hyperbolic cosine of the elements of input.

$$\text{out}_{i} = \cosh^{-1}(\text{input}_{i})$$

Note

The domain of the inverse hyperbolic cosine is [1, inf) and values outside this range will be mapped to NaN, except for + INF for which the output is mapped to + INF.

Parameters:

input (Tensor) – the input tensor.

Keyword Arguments:

out (Tensor, optional) – the output tensor.

Example:

>>> a = tensorplay.randn(4).uniform_(1, 2)
>>> a
tensor([ 1.3192, 1.9915, 1.9674, 1.7151 ])
>>> tensorplay.acosh(a)
tensor([ 0.7791, 1.3120, 1.2979, 1.1341 ])