【PyTorch】教程：torch.nn.LogSigmoid

torch.nn.LogSigmoid

原型

CLASS torch.nn.LogSigmoid()

参数

shape

• Input: (*), * 代表任意维度
• Output: (*), 与输入相同

定义

$$\text{LogSigmoid}(x)=\log \left(\frac{1}{1+\exp (-x)}\right)$$

图

代码

import torch
import torch.nn as nn

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

print("input: ", input)   # input:  tensor([-0.1181,  1.8792, -0.1737, -0.6441])
print("output: ", output) # output:  tensor([-0.7539, -0.1421, -0.7838, -1.0662])

【参考】

LogSigmoid — PyTorch 1.13 documentation