torch.frac#

torch.frac(input,*,out=None)→Tensor#

Computes the fractional portion of each element ininput.

$${\text{out}}_i={\text{input}}_i-\lfloor \mathrm{\mid }{\text{input}}_i\mathrm{\mid }\rfloor \ast \mathrm{sgn}({\text{input}}_i)$$outi​=inputi​−⌊∣inputi​∣⌋∗sgn(inputi​)

Example:

>>>torch.frac(torch.tensor([1,2.5,-3.2]))tensor([ 0.0000,  0.5000, -0.2000])