torch.sinh#

torch.sinh(input,*,out=None)→Tensor#

Returns a new tensor with the hyperbolic sine of the elements ofinput.

$${\text{out}}_i=\sinh ({\text{input}}_i)$$outi​=sinh(inputi​)

Parameters

input (Tensor) – the input tensor.

Keyword Arguments

out (Tensor,optional) – the output tensor.

Example:

>>>a=torch.randn(4)>>>atensor([ 0.5380, -0.8632, -0.1265,  0.9399])>>>torch.sinh(a)tensor([ 0.5644, -0.9744, -0.1268,  1.0845])

Note

Wheninput is on the CPU, the implementation of torch.sinh may usethe Sleef library, which rounds very large results to infinity or negativeinfinity. Seehere for details.