torch.acosh#

torch.acosh(input:Tensor,*,out:Optional[Tensor])→Tensor#

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

$${\text{out}}_i={\cosh }^{-1}({\text{input}}_i)$$outi​=cosh−1(inputi​)

Note

The domain of the inverse hyperbolic cosine is[1, inf) and values outside this rangewill be mapped toNaN, 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=torch.randn(4).uniform_(1,2)>>>atensor([ 1.3192, 1.9915, 1.9674, 1.7151 ])>>>torch.acosh(a)tensor([ 0.7791, 1.3120, 1.2979, 1.1341 ])