【PyTorch】教程：torch.nn.Sigmoid

torch.nn.Sigmoid

原型

CLASS torch.nn.Sigmoid(*args, **kwargs)

定义

Applies the element-wise function:

$$Sigmoid(x)=\sigma (x)=\frac{1}{1+\exp (-x)}$$

图

代码

import torch
import torch.nn as nn

m = nn.Sigmoid()
input = torch.randn(4)
output = m(input)

print("input: ", input)   # input:  tensor([-0.8462,  0.7929, -0.5680, -0.5883])
print("output: ", output) # output:  tensor([0.3002, 0.6885, 0.3617, 0.3570])

【参考】

Sigmoid — PyTorch 2.0 documentation