<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[HRFarsighted的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/HRFarsighted</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; HRFarsighted]]></copyright><item><title><![CDATA[五、线性代数]]></title><link>https://blog.youkuaiyun.com/HRFarsighted/article/details/123137179</link><guid>https://blog.youkuaiyun.com/HRFarsighted/article/details/123137179</guid><author>HRFarsighted</author><pubDate>Fri, 25 Feb 2022 17:06:33 +0800</pubDate><description><![CDATA[# 学习时间：2022/2/22 16:19
#1、标量
import torch
x=torch.tensor([3.0])
y=torch.tensor([2.0])
print(x+y,x*y,x/y,x**y)

#2.向量：可以将其视为标量组成的列表
x=torch.arange(4)
print(x)
#可以通过索引访问任意元素
print(x[3])
#访问张量的长度
print(len(x))
#只有一个轴的张量，形状只有一个元素
print(x.shape)
#通过指定分量m，n来创建一个]]></description><category></category></item><item><title><![CDATA[四、数据操作]]></title><link>https://blog.youkuaiyun.com/HRFarsighted/article/details/123072473</link><guid>https://blog.youkuaiyun.com/HRFarsighted/article/details/123072473</guid><author>HRFarsighted</author><pubDate>Tue, 22 Feb 2022 17:02:04 +0800</pubDate><description><![CDATA[## 1、数据操作

import torch
X=torch.arange(12,dtype=torch.float32).reshape((3,4))
Y=torch.tensor([[2.0,1,4,3],[1,2,3,4],[4,3,2,1]])
print(torch.cat((X,Y),dim=0),torch.cat((X,Y),dim=1))#dim=0,第0维合并，即是在行堆叠；dim=1，则是按照列连接扩张；dim=3,则是三维
#按照逻辑运算符构建二元张量
print(X==Y)
p.]]></description><category></category></item><item><title><![CDATA[三、 安装]]></title><link>https://blog.youkuaiyun.com/HRFarsighted/article/details/123072405</link><guid>https://blog.youkuaiyun.com/HRFarsighted/article/details/123072405</guid><author>HRFarsighted</author><pubDate>Tue, 22 Feb 2022 16:59:07 +0800</pubDate><description><![CDATA[]]></description><category></category></item><item><title><![CDATA[二、 深度学习介绍]]></title><link>https://blog.youkuaiyun.com/HRFarsighted/article/details/123072286</link><guid>https://blog.youkuaiyun.com/HRFarsighted/article/details/123072286</guid><author>HRFarsighted</author><pubDate>Tue, 22 Feb 2022 16:56:24 +0800</pubDate><description><![CDATA[]]></description><category></category></item><item><title><![CDATA[一、 课程内容安排]]></title><link>https://blog.youkuaiyun.com/HRFarsighted/article/details/123072185</link><guid>https://blog.youkuaiyun.com/HRFarsighted/article/details/123072185</guid><author>HRFarsighted</author><pubDate>Tue, 22 Feb 2022 16:53:51 +0800</pubDate><description><![CDATA[]]></description><category></category></item><item><title><![CDATA[如何高效的利用tensorflow+Object DetectionAPI训练识别自己的数据集]]></title><link>https://blog.youkuaiyun.com/HRFarsighted/article/details/99660005</link><guid>https://blog.youkuaiyun.com/HRFarsighted/article/details/99660005</guid><author>HRFarsighted</author><pubDate>Thu, 15 Aug 2019 22:48:09 +0800</pubDate><description><![CDATA[二、tensorflow Object DetectionAPI训练识别自己的数据集
参考GitHub：https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10?tdsourcetag=s_pcqq_aiomsg
参考博客：https:/...]]></description><category></category></item><item><title><![CDATA[Win10+tensorfow调用object_detection API]]></title><link>https://blog.youkuaiyun.com/HRFarsighted/article/details/99440904</link><guid>https://blog.youkuaiyun.com/HRFarsighted/article/details/99440904</guid><author>HRFarsighted</author><pubDate>Tue, 13 Aug 2019 15:48:20 +0800</pubDate><description><![CDATA[一、object_detection环境初步测试
参考：https://blog.youkuaiyun.com/zlase/article/details/78734138
https://blog.youkuaiyun.com/zhaoyoulin2016/article/details/80615687
Part 1.配置运行环境
Windows10系统+Anaconda 3.5
在anaconda创建python3...]]></description><category></category></item><item><title><![CDATA[机器学习之误差]]></title><link>https://blog.youkuaiyun.com/HRFarsighted/article/details/98885862</link><guid>https://blog.youkuaiyun.com/HRFarsighted/article/details/98885862</guid><author>HRFarsighted</author><pubDate>Thu, 08 Aug 2019 22:37:44 +0800</pubDate><description><![CDATA[机器学习之误差

Average Error 随着模型复杂增加呈指数上升趋势。更复杂的模型并不能给测试集带来更好的效果，而这些 ErrorError 的主要有两个来源，分别是 biasbias 和 variance







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