<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[JC_brook的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/JC_brook</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; JC_brook]]></copyright><item><title><![CDATA[autograd与逻辑回归]]></title><link>https://blog.youkuaiyun.com/JC_brook/article/details/103405704</link><guid>https://blog.youkuaiyun.com/JC_brook/article/details/103405704</guid><author>JC_brook</author><pubDate>Thu, 05 Dec 2019 16:17:47 +0800</pubDate><description><![CDATA[一、autograd --自动求导系统




二、逻辑回归


]]></description><category></category></item><item><title><![CDATA[Tensor的操作与线性回归]]></title><link>https://blog.youkuaiyun.com/JC_brook/article/details/103404083</link><guid>https://blog.youkuaiyun.com/JC_brook/article/details/103404083</guid><author>JC_brook</author><pubDate>Thu, 05 Dec 2019 15:22:04 +0800</pubDate><description><![CDATA[一、拼接/切片/索引/变换








二、Tensor的数学运算


三、线性回归
线性回归是分析一个变量与另外一（多）个变量之间关系的方法。




]]></description><category></category></item><item><title><![CDATA[PyTorch之Tensor]]></title><link>https://blog.youkuaiyun.com/JC_brook/article/details/103403182</link><guid>https://blog.youkuaiyun.com/JC_brook/article/details/103403182</guid><author>JC_brook</author><pubDate>Thu, 05 Dec 2019 14:23:05 +0800</pubDate><description><![CDATA[TENSOR的创建
一、直接创建
torch.tensor()

或者
arr=np.aray([1,2,,3],[4,5,6])
t=torch.from_·numpy(arr)
此时的t和arr指向同一个内存空间

二、依据数值创建




例如：t=torch.full((3,3),1)

例如：t=torch.arrange(2,10,2)



三、依概率分布创建张量


两个标量时需要...]]></description><category></category></item><item><title><![CDATA[计算机视觉四大基本任务]]></title><link>https://blog.youkuaiyun.com/JC_brook/article/details/102676668</link><guid>https://blog.youkuaiyun.com/JC_brook/article/details/102676668</guid><author>JC_brook</author><pubDate>Tue, 22 Oct 2019 09:41:09 +0800</pubDate><description><![CDATA[https://blog.youkuaiyun.com/javastart/article/details/83859259

]]></description><category></category></item></channel></rss>