当前位置:网站首页>Pytorch基础——(1)张量(tensor)的初始化
Pytorch基础——(1)张量(tensor)的初始化
2022-07-06 03:18:00 【七上八下的黑】
导入pytorch库
import torch
初始化张量
DEVICE = "cuda" if torch.cuda.is_available() else "cpu" # 设置运行的设备
x = torch.tensor([[1, 2, 3], [4, 5, 6]], dtype=torch.float32, device=DEVICE, requires_grad=True)
其他初始化方法
1.产生0-1之间均匀分布的2x3的张量
x = torch.rand((2, 3))
print(x)
2.产生0-1之间正态分布的2x3的张量
x = torch.randn((2, 3))
print(x)
3. 产生3-10之间随机整数的2x3的张量
x = torch.randint(3, 10, (2, 3))
print(x)
4.产生和input格式一样的张量
input = torch.rand((3, 3))
x = torch.rand_like(input)
5.产生初始值为0,步长为1,不包含终止值的序列
x = torch.arange(start=0, end=10, step=1)
6.产生初始值为0,终止值为9,总步数为11的序列
x = torch.linspace(start=0, end=9, steps=11)
7.产生对角线是0-1均匀分布的张量
x = torch.diag(torch.rand(5))
转换数据类型
我们常用numpy数据类型,但是它不能直接在torch中运算,因此需要转换数据类型。
import numpy as np
x = np.zeros((5, 5))
print(x)
print(x.dtype)
x_torch = torch.from_numpy(x) # 从numpy变成torch张量类型
print(x_torch)
print(x_torch.dtype)
x_back = x_torch.numpy() # 从torch张量变回numpy类型
print(x_back)
print(x_back.dtype)
注意:
出现 Numpy is not available 报错时,是numpy和pytorch的版本不匹配。
边栏推荐
- Problems encountered in 2022 work IV
- My C language learning record (blue bridge) -- on the pointer
- MySQL advanced notes
- [ruoyi] ztree custom icon (iconskin attribute)
- JS音乐在线播放插件vsPlayAudio.js
- resulttype和resultmap的区别和应用场景
- 2022工作中遇到的问题四
- Precautions for single chip microcomputer anti reverse connection circuit
- Redis SDS principle
- Leetcode problem solving -- 98 Validate binary search tree
猜你喜欢
Microsoft Research, UIUC & Google research | antagonistic training actor critic based on offline training reinforcement learning
Redo file corruption repair
Mysql database operation
MySQL Server层四个日志
Idea push rejected solution
银行核心业务系统性能测试方法
[ruoyi] set theme style
电机控制反Park变换和反Clarke变换公式推导
C language judgment, ternary operation and switch statement usage
【指针训练——八道题】
随机推荐
如何做好功能测试
【 kubernets series】 a Literature Study on the Safe exposure Applications of kubernets Service
[Li Kou] the second set of the 280 Li Kou weekly match
Restful style
EDCircles: A real-time circle detector with a false detection control 翻译
Mysql database operation
Overview of OCR character recognition methods
Some problem records of AGP gradle
js 正则过滤和增加富文本中图片前缀
Quartz misfire missed and compensated execution
svg拖动点裁剪图片js特效
MPLS experiment
Redis cache breakdown, cache penetration, cache avalanche
教你用Pytorch搭建一个自己的简单的BP神经网络( 以iris数据集为例 )
IPv6 jobs
[ruoyi] enable Mini navigation bar
Daily question brushing plan-2-13 fingertip life
Explore pointers and pointer types in depth
Eight super classic pointer interview questions (3000 words in detail)
Analyze 菜单分析