Pytorch中Softmax和LogSoftmax的使用详解


Posted in Python onJune 05, 2021

一、函数解释

1.Softmax函数常用的用法是指定参数dim就可以:

(1)dim=0:对每一列的所有元素进行softmax运算,并使得每一列所有元素和为1。

(2)dim=1:对每一行的所有元素进行softmax运算,并使得每一行所有元素和为1。

class Softmax(Module):
    r"""Applies the Softmax function to an n-dimensional input Tensor
    rescaling them so that the elements of the n-dimensional output Tensor
    lie in the range [0,1] and sum to 1.
    Softmax is defined as:
    .. math::
        \text{Softmax}(x_{i}) = \frac{\exp(x_i)}{\sum_j \exp(x_j)}
    Shape:
        - Input: :math:`(*)` where `*` means, any number of additional
          dimensions
        - Output: :math:`(*)`, same shape as the input
    Returns:
        a Tensor of the same dimension and shape as the input with
        values in the range [0, 1]
    Arguments:
        dim (int): A dimension along which Softmax will be computed (so every slice
            along dim will sum to 1).
    .. note::
        This module doesn't work directly with NLLLoss,
        which expects the Log to be computed between the Softmax and itself.
        Use `LogSoftmax` instead (it's faster and has better numerical properties).
    Examples::
        >>> m = nn.Softmax(dim=1)
        >>> input = torch.randn(2, 3)
        >>> output = m(input)
    """
    __constants__ = ['dim']
 
    def __init__(self, dim=None):
        super(Softmax, self).__init__()
        self.dim = dim
 
    def __setstate__(self, state):
        self.__dict__.update(state)
        if not hasattr(self, 'dim'):
            self.dim = None
 
    def forward(self, input):
        return F.softmax(input, self.dim, _stacklevel=5)
 
    def extra_repr(self):
        return 'dim={dim}'.format(dim=self.dim)

2.LogSoftmax其实就是对softmax的结果进行log,即Log(Softmax(x))

class LogSoftmax(Module):
    r"""Applies the :math:`\log(\text{Softmax}(x))` function to an n-dimensional
    input Tensor. The LogSoftmax formulation can be simplified as:
    .. math::
        \text{LogSoftmax}(x_{i}) = \log\left(\frac{\exp(x_i) }{ \sum_j \exp(x_j)} \right)
    Shape:
        - Input: :math:`(*)` where `*` means, any number of additional
          dimensions
        - Output: :math:`(*)`, same shape as the input
    Arguments:
        dim (int): A dimension along which LogSoftmax will be computed.
    Returns:
        a Tensor of the same dimension and shape as the input with
        values in the range [-inf, 0)
    Examples::
        >>> m = nn.LogSoftmax()
        >>> input = torch.randn(2, 3)
        >>> output = m(input)
    """
    __constants__ = ['dim']
 
    def __init__(self, dim=None):
        super(LogSoftmax, self).__init__()
        self.dim = dim
 
    def __setstate__(self, state):
        self.__dict__.update(state)
        if not hasattr(self, 'dim'):
            self.dim = None
 
    def forward(self, input):
        return F.log_softmax(input, self.dim, _stacklevel=5)

二、代码示例

输入代码

import torch
import torch.nn as nn
import numpy as np
 
batch_size = 4
class_num = 6
inputs = torch.randn(batch_size, class_num)
for i in range(batch_size):
    for j in range(class_num):
        inputs[i][j] = (i + 1) * (j + 1)
 
print("inputs:", inputs)

得到大小batch_size为4,类别数为6的向量(可以理解为经过最后一层得到)

tensor([[ 1., 2., 3., 4., 5., 6.],
[ 2., 4., 6., 8., 10., 12.],
[ 3., 6., 9., 12., 15., 18.],
[ 4., 8., 12., 16., 20., 24.]])

接着我们对该向量每一行进行Softmax

Softmax = nn.Softmax(dim=1)
probs = Softmax(inputs)
print("probs:\n", probs)

得到

tensor([[4.2698e-03, 1.1606e-02, 3.1550e-02, 8.5761e-02, 2.3312e-01, 6.3369e-01],
[3.9256e-05, 2.9006e-04, 2.1433e-03, 1.5837e-02, 1.1702e-01, 8.6467e-01],
[2.9067e-07, 5.8383e-06, 1.1727e-04, 2.3553e-03, 4.7308e-02, 9.5021e-01],
[2.0234e-09, 1.1047e-07, 6.0317e-06, 3.2932e-04, 1.7980e-02, 9.8168e-01]])

此外,我们对该向量每一行进行LogSoftmax

LogSoftmax = nn.LogSoftmax(dim=1)
log_probs = LogSoftmax(inputs)
print("log_probs:\n", log_probs)

得到

tensor([[-5.4562e+00, -4.4562e+00, -3.4562e+00, -2.4562e+00, -1.4562e+00, -4.5619e-01],
[-1.0145e+01, -8.1454e+00, -6.1454e+00, -4.1454e+00, -2.1454e+00, -1.4541e-01],
[-1.5051e+01, -1.2051e+01, -9.0511e+00, -6.0511e+00, -3.0511e+00, -5.1069e-02],
[-2.0018e+01, -1.6018e+01, -1.2018e+01, -8.0185e+00, -4.0185e+00, -1.8485e-02]])

验证每一行元素和是否为1

# probs_sum in dim=1
probs_sum = [0 for i in range(batch_size)]
 
for i in range(batch_size):
    for j in range(class_num):
        probs_sum[i] += probs[i][j]
    print(i, "row probs sum:", probs_sum[i])

得到每一行的和,看到确实为1

0 row probs sum: tensor(1.)
1 row probs sum: tensor(1.0000)
2 row probs sum: tensor(1.)
3 row probs sum: tensor(1.)

验证LogSoftmax是对Softmax的结果进行Log

# to numpy
np_probs = probs.data.numpy()
print("numpy probs:\n", np_probs)
 
# np.log()
log_np_probs = np.log(np_probs)
print("log numpy probs:\n", log_np_probs)

得到

numpy probs:
[[4.26977826e-03 1.16064614e-02 3.15496325e-02 8.57607946e-02 2.33122006e-01 6.33691311e-01]
[3.92559559e-05 2.90064461e-04 2.14330270e-03 1.58369839e-02 1.17020354e-01 8.64669979e-01]
[2.90672347e-07 5.83831024e-06 1.17265590e-04 2.35534250e-03 4.73083146e-02 9.50212955e-01]
[2.02340233e-09 1.10474026e-07 6.03167746e-06 3.29318427e-04 1.79801770e-02 9.81684387e-01]]
log numpy probs:
[[-5.4561934e+00 -4.4561934e+00 -3.4561934e+00 -2.4561932e+00 -1.4561933e+00 -4.5619333e-01]
[-1.0145408e+01 -8.1454077e+00 -6.1454072e+00 -4.1454072e+00 -2.1454074e+00 -1.4540738e-01]
[-1.5051069e+01 -1.2051069e+01 -9.0510693e+00 -6.0510693e+00 -3.0510693e+00 -5.1069155e-02]
[-2.0018486e+01 -1.6018486e+01 -1.2018485e+01 -8.0184851e+00 -4.0184855e+00 -1.8485421e-02]]

验证完毕

三、整体代码

import torch
import torch.nn as nn
import numpy as np
 
batch_size = 4
class_num = 6
inputs = torch.randn(batch_size, class_num)
for i in range(batch_size):
    for j in range(class_num):
        inputs[i][j] = (i + 1) * (j + 1)
 
print("inputs:", inputs)
Softmax = nn.Softmax(dim=1)
probs = Softmax(inputs)
print("probs:\n", probs)
 
LogSoftmax = nn.LogSoftmax(dim=1)
log_probs = LogSoftmax(inputs)
print("log_probs:\n", log_probs)
 
# probs_sum in dim=1
probs_sum = [0 for i in range(batch_size)]
 
for i in range(batch_size):
    for j in range(class_num):
        probs_sum[i] += probs[i][j]
    print(i, "row probs sum:", probs_sum[i])
 
# to numpy
np_probs = probs.data.numpy()
print("numpy probs:\n", np_probs)
 
# np.log()
log_np_probs = np.log(np_probs)
print("log numpy probs:\n", log_np_probs)

基于pytorch softmax,logsoftmax 表达

import torch
import numpy as np
input = torch.autograd.Variable(torch.rand(1, 3))

print(input)
print('softmax={}'.format(torch.nn.functional.softmax(input, dim=1)))
print('logsoftmax={}'.format(np.log(torch.nn.functional.softmax(input, dim=1))))

以上为个人经验,希望能给大家一个参考,也希望大家多多支持三水点靠木。

Python 相关文章推荐
Python中暂存上传图片的方法
Feb 18 Python
Python2.7简单连接与操作MySQL的方法
Apr 27 Python
Python 正则表达式入门(初级篇)
Dec 07 Python
Python 判断是否为质数或素数的实例
Oct 30 Python
同时安装Python2 & Python3 cmd下版本自由选择的方法
Dec 09 Python
python监控键盘输入实例代码
Feb 09 Python
Python 输出时去掉列表元组外面的方括号与圆括号的方法
Dec 24 Python
python3实现绘制二维点图
Dec 04 Python
python关于倒排列的知识点总结
Oct 13 Python
使用python-cv2实现视频的分解与合成的示例代码
Oct 26 Python
python request 模块详细介绍
Nov 10 Python
利用python绘制正态分布曲线
Jan 04 Python
Pytorch中Softmax与LogSigmoid的对比分析
Jun 05 #Python
Pytorch反向传播中的细节-计算梯度时的默认累加操作
pytorch 梯度NAN异常值的解决方案
Jun 05 #Python
pytorch 权重weight 与 梯度grad 可视化操作
PyTorch 如何检查模型梯度是否可导
python-opencv 中值滤波{cv2.medianBlur(src, ksize)}的用法
解决Pytorch修改预训练模型时遇到key不匹配的情况
Jun 05 #Python
You might like
简单的php新闻发布系统教程
2014/05/09 PHP
PHP会话处理的10个函数
2015/08/11 PHP
深入了解PHP中的Array数组和foreach
2016/11/06 PHP
PHP魔术方法之__call与__callStatic使用方法
2017/07/23 PHP
js 图片缩放(按比例)控制代码
2009/05/27 Javascript
js下通过prototype扩展实现indexOf的代码
2010/12/08 Javascript
seajs中模块的解析规则详解和模块使用总结
2014/03/12 Javascript
原生js事件的添加和删除的封装
2014/07/01 Javascript
JavaScript阻止回车提交表单的方法
2015/12/30 Javascript
js放大镜放大购物图片效果
2017/01/18 Javascript
canvas绘制表盘时钟
2017/01/23 Javascript
jquery中绑定事件的异同
2017/02/28 Javascript
如何编写jquery插件
2017/03/29 jQuery
vue 使用html2canvas将DOM转化为图片的方法
2018/09/11 Javascript
JavaScript实现简单的图片切换功能(实例代码)
2020/04/10 Javascript
详解使用mocha对webpack打包的项目进行"冒烟测试"的大致流程
2020/04/27 Javascript
[34:10]Secret vs VG 2019国际邀请赛淘汰赛 败者组 BO3 第二场 8.24
2019/09/10 DOTA
python爬取淘宝商品详情页数据
2018/02/23 Python
详解Numpy中的数组拼接、合并操作(concatenate, append, stack, hstack, vstack, r_, c_等)
2019/05/27 Python
Django中信号signals的简单使用方法
2019/07/04 Python
python global关键字的用法详解
2019/09/05 Python
python中的split()函数和os.path.split()函数使用详解
2019/12/21 Python
python剪切视频与合并视频的实现
2020/03/03 Python
Python生成器常见问题及解决方案
2020/03/21 Python
Jupyter Notebook折叠输出的内容实例
2020/04/22 Python
python ssh 执行shell命令的示例
2020/09/29 Python
matplotlib之pyplot模块之标题(title()和suptitle())
2021/02/22 Python
用HTML5制作视频拼图的教程
2015/05/13 HTML / CSS
HTML5实现可缩放时钟代码
2017/08/28 HTML / CSS
HTML5新特性之type=file文件上传功能
2018/02/02 HTML / CSS
机修工岗位职责
2013/11/24 职场文书
全国优秀教师事迹材料
2014/08/26 职场文书
2014年领班工作总结
2014/11/25 职场文书
认真学习保证书
2015/02/26 职场文书
导游词之泰山玉皇顶
2019/12/23 职场文书
Golang标准库syscall详解(什么是系统调用)
2021/05/25 Golang