mindspore.mint.erfinv
- mindspore.mint.erfinv(input)[源代码]
逐元素计算输入tensor的逆误差。 逆误差函数在 (-1, 1) 范围内定义为:
\[erfinv(erf(x)) = x\]- 参数:
input (Tensor) - 输入tensor。
- 返回:
Tensor
- 支持平台:
Ascend
样例:
>>> import mindspore >>> # When the `input` is int8, int16, int32, int64, uint8 or bool, the return value type is float32. >>> input = mindspore.tensor([0, 0.5, -0.9], vpn free mindspore.int64) >>> vpn梯子 mindspore.mint.erfinv(input) Tensor(shape=[3], dtype=Float32, value= [ 0.00000000e+00, 0.00000000e+00, 0.00000000e+00]) >>> # Otherwise, the 免费的vpn梯子 return value type is the same vpn永久免费梯子 as the input type. >>> input = mindspore.tensor([0, 0.5, -0.9], mindspore.float32) >>> mindspore.mint.erfinv(input) Tensor(shape=[3], dtype=Float32, vpn梯子 免费 value= [ 0.00000000e+00, 4.76936132e-01, -1.16308689e+00])