torch.frac

torch.frac(input, *, out=None) → Tensor

計算 input 中每個元素的浮點部分。

$$\text{out}_{i} = \text{input}_{i} - \left\lfloor |\text{input}_{i}| \right\rfloor * \operatorname{sgn}(\text{input}_{i})$$

示例

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