<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[yangk12321的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/yangk12321</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; yangk12321]]></copyright><item><title><![CDATA[决策树]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/80503837</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/80503837</guid><author>yangk12321</author><pubDate>Wed, 30 May 2018 00:14:00 +0800</pubDate><description><![CDATA[预备知识1.熵 ：表示随机变量不确定性的度量。2.条件熵：表示在已知随机变量X的条件下随机变量Y的不确定性。3.信息增益 ：特征A对训练数据集D的信息增益g(D,A),定义为集合D的熵(经验熵)与特征A给定条件下D的条件熵(经验条件熵)H(D|A)之差，即 g(D,A)=H(D)-H(D|A)信息增益越大越好，越大说明经过A特征数据的不确定性越小。但是信息增益存在偏向于选择取值较多的特征的问题。4...]]></description><category></category></item><item><title><![CDATA[Ubuntu 更新 pip]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/80258641</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/80258641</guid><author>yangk12321</author><pubDate>Wed, 09 May 2018 19:56:12 +0800</pubDate><description><![CDATA[curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py sudo python get-pip.py ]]></description><category></category></item><item><title><![CDATA[ubuntu 安装 更新vim]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/80258436</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/80258436</guid><author>yangk12321</author><pubDate>Wed, 09 May 2018 19:42:41 +0800</pubDate><description><![CDATA[ sudo add-apt-repository ppa:jonathonf/vimsudo apt-get updatesudo apt-get install vim]]></description><category></category></item><item><title><![CDATA[关于ssd的理解]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/78253289</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/78253289</guid><author>yangk12321</author><pubDate>Mon, 16 Oct 2017 19:41:18 +0800</pubDate><description><![CDATA[https://zhuanlan.zhihu.com/p/24954433]]></description><category></category></item><item><title><![CDATA[在线安装cuda tensorflow]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/78175464</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/78175464</guid><author>yangk12321</author><pubDate>Sun, 08 Oct 2017 16:02:45 +0800</pubDate><description><![CDATA[首先，下载需要安装的包 cuda(8.0),cudnn(6.0),tensorflow-1.3
将所有文件放入主目录下的一个文件夹，我放在～/fk/111
然后执行下面这个.sh 文件就可以了
.sh文件的内容如下：
#!/bin/bash
#sudo tar xzf ~/fk.tar.gz
cd ~/fk/111/
sudo apt-get install -y gcc g++ g]]></description><category></category></item><item><title><![CDATA[ubuntu chrome设置no proxy]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/78158052</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/78158052</guid><author>yangk12321</author><pubDate>Wed, 04 Oct 2017 14:18:20 +0800</pubDate><description><![CDATA[当你的Google浏览器出现：
    When running Google Chrome under a supported desktop environment, the system proxy settings will be used. However, either your system is not supported or there was a problem launc]]></description><category></category></item><item><title><![CDATA[Ubuntu离线安装cuda，cudnn，caffe，opencv]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/78089396</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/78089396</guid><author>yangk12321</author><pubDate>Mon, 25 Sep 2017 21:00:28 +0800</pubDate><description><![CDATA[首先，找一台可以联网的pc，重新装Ubuntu系统（注意安装的系统和你将来配置的系统要完全一致，不然就可不出现有些库不兼容而报错），然后在线安装cuda，安装完之后在apt-get install 命令下载目录/var/cache/apt/archives下提取所以缓存文件，然后在线用pip下载caffe所需要的库，同样在缓存中提取出来出来，放到一个文件夹中。这样依次用apt-get下载caffe]]></description><category></category></item><item><title><![CDATA[KNN]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/77165282</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/77165282</guid><author>yangk12321</author><pubDate>Mon, 14 Aug 2017 19:03:08 +0800</pubDate><description><![CDATA[机器学习（一）——K-近邻（KNN）算法
     最近在看《机器学习实战》这本书，因为自己本身很想深入的了解机器学习算法，加之想学python，就在朋友的推荐之下选择了这本书进行学习。 
一 . K-近邻算法（KNN）概述 
    最简单最初级的分类器是将全部的训练数据所对应的类别都记录下来，当测试对象的属性和某个训练对象的属性完全匹配时，便可以对其进行分类。但是怎么可能所有测试对象都会]]></description><category></category></item><item><title><![CDATA[python 读取并显示图片的两种方法]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/74390032</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/74390032</guid><author>yangk12321</author><pubDate>Wed, 05 Jul 2017 10:56:59 +0800</pubDate><description><![CDATA[http://www.cnblogs.com/yinxiangnan-charles/p/5928689.html]]></description><category></category></item><item><title><![CDATA[深度残差学习的图像识别]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/73530117</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/73530117</guid><author>yangk12321</author><pubDate>Wed, 21 Jun 2017 11:20:59 +0800</pubDate><description><![CDATA[[译]基于深度残差学习的图像识别 
Deep Residual Learning for Image Recognition 
Kaiming He Xiangyu Zhang Shaoqing Ren Jian Sun 
微软研究院 
{kahe, v-xiangz, v-shren, jiansun}@microsoft.com

摘要：神经网络的训练因其层次加深而变得愈加困难。我]]></description><category></category></item><item><title><![CDATA[卷积神经网络]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/73528030</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/73528030</guid><author>yangk12321</author><pubDate>Wed, 21 Jun 2017 11:03:16 +0800</pubDate><description><![CDATA[https://www.zybuluo.com/hanbingtao/note/485480]]></description><category></category></item><item><title><![CDATA[R-CNN,SPP-NET, Fast-R-CNN,Faster-R-CNN, YOLO,系列深度学习检测方法]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/73473346</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/73473346</guid><author>yangk12321</author><pubDate>Mon, 19 Jun 2017 19:49:56 +0800</pubDate><description><![CDATA[http://www.cnblogs.com/venus024/p/5717766.html]]></description><category></category></item><item><title><![CDATA[零基础学CNN]]></title><link>https://blog.youkuaiyun.com/yangk12321/article/details/72540887</link><guid>https://blog.youkuaiyun.com/yangk12321/article/details/72540887</guid><author>yangk12321</author><pubDate>Fri, 19 May 2017 16:32:00 +0800</pubDate><description><![CDATA[https://www.zybuluo.com/hanbingtao/note/485480]]></description><category></category></item></channel></rss>