Sigmoid¶

class Sigmoid(name=None)[源代码]¶

对每个元素应用函数：

\[\text{Sigmoid}(x) = \frac{1}{1 + \exp(-x)}\]

Shape:: ``inputs``: :math:`()` where \(*\) means any member of addition dimensions. ``outpus``: :math:`()` same shape as the inputs.

返回: module. The instance of the Sigmoid module.
返回类型: Return type

实际案例

>>> import numpy as np
>>> data = mge.tensor(np.array([-2,-1,0,1,2,]).astype(np.float32))
>>> sigmoid = M.Sigmoid()
>>> output = sigmoid(data)
>>> with np.printoptions(precision=6):
...     print(output.numpy())
[0.119203 0.268941 0.5      0.731059 0.880797]

Pad

Softmax