当前位置:网站首页>torch.normal函数用法
torch.normal函数用法
2022-07-31 05:09:00 【Cheng-O】
官方文档给的用法:
torch.normal(means, std, out=None)
意思为means给定tensor的均值范围和形状,std给出每个均值服从的标准差
官方示例:
torch.normal(means=torch.arange(1, 11), std=torch.arange(1, 0, -0.1))
1.5104
1.6955
2.4895
4.9185
4.9895
6.9155
7.3683
8.1836
8.7164
9.8916
[torch.FloatTensor of size 10]
实际情况:
>>> torch.normal(means=torch.arange(1, 11), std=torch.arange(1, 0, -0.1))
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
TypeError: normal() received an invalid combination of arguments - got (means=Tensor, std=Tensor, ), but expected one of:
* (Tensor mean, Tensor std, *, torch.Generator generator, Tensor out)
* (Tensor mean, float std, *, torch.Generator generator, Tensor out)
* (float mean, Tensor std, *, torch.Generator generator, Tensor out)
* (float mean, float std, tuple of ints size, *, torch.Generator generator, Tensor out, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
从错误类型中看出现在torch中已经不再使用means而是使用mean,即只能生成固定均值的正态分布。
正确的打开方式:
采用第四种:
torch.normal(mean, std, size)
三个参数分别为均值,标准差和size
>>> torch.normal(3, 0.1, (3, 4))
tensor([[2.9425, 3.1877, 2.9735, 3.0982],
[3.0061, 2.9918, 2.7953, 3.0066],
[2.8219, 2.9578, 2.8813, 2.9014]])
采用第三种:
torch.normal(mean, stds)
两个参数分别为:均值和标准差,使用标准差来确定范围size
>>> torch.normal(3, torch.ones(3, 4)/10)
tensor([[2.8491, 3.0263, 3.0888, 3.0818],
[3.1101, 2.7490, 3.1847, 3.0861],
[2.8530, 2.8666, 2.9634, 3.1875]])
边栏推荐
- Three oj questions on leetcode
- MySQL optimization slow log query
- Interview | Cheng Li, CTO of Alibaba: Cloud + open source together form a credible foundation for the digital world
- Reference code series_1. Hello World in various languages
- MySQL优化之慢日志查询
- 110道 MySQL面试题及答案 (持续更新)
- 【JS面试题】面试官:“[1,2,3].map(parseInt)“ 输出结果是什么?答上来就算你通过面试
- The MySQL database installed configuration nanny level tutorial for 8.0.29 (for example) have hands
- 分布式事务——分布式事务简介、分布式事务框架 Seata(AT模式、Tcc模式、Tcc Vs AT)、分布式事务—MQ
- DVWA安装教程(懂你的不懂·详细)
猜你喜欢
Interview | Cheng Li, CTO of Alibaba: Cloud + open source together form a credible foundation for the digital world
docker安装postgresSQL和设置自定义数据目录
限流的原理
MySQL常见面试题汇总(建议收藏!!!)
centos7安装mysql5.7
Summary of MySQL common interview questions (recommended collection!!!)
ERP Production Operation Control Kingdee
Redis进阶 - 缓存问题:一致性、穿击、穿透、雪崩、污染等.
sql语句-如何以一个表中的数据为条件据查询另一个表中的数据
Mysql application cannot find my.ini file after installation
随机推荐
为什么要用Flink,怎么入门使用Flink?
Redis进阶 - 缓存问题:一致性、穿击、穿透、雪崩、污染等.
pycharm专业版使用
12个MySQL慢查询的原因分析
ERP Production Operation Control Kingdee
【ORACLE Explain 详解】
Interview Redis High Reliability | Master-Slave Mode, Sentinel Mode, Cluster Cluster Mode
【mysql 提高查询效率】Mysql 数据库查询好慢问题解决
工作流编排引擎-Temporal
Summary of MySQL common interview questions (recommended collection!!!)
[Detailed explanation of ORACLE Explain]
Heavyweight | The Open Atomic School Source Line activity was officially launched
面试官问我TCP三次握手和四次挥手,我真的是
Temporal客户端模型
Linux系统安装mysql(rpm方式安装)
The MySQL database installed configuration nanny level tutorial for 8.0.29 (for example) have hands
MySQL transaction (transaction) (this is enough..)
CentOS7 —— yum安装mysql
DVWA靶场环境搭建
MySQL database addition, deletion, modification and query (detailed explanation of basic operation commands)