<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[AR_hlr的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/AR_hlr</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; AR_hlr]]></copyright><item><title><![CDATA[Pytorch_study_Task_7:手写数字识别]]></title><link>https://blog.youkuaiyun.com/AR_hlr/article/details/99891349</link><guid>https://blog.youkuaiyun.com/AR_hlr/article/details/99891349</guid><author>AR_hlr</author><pubDate>Tue, 20 Aug 2019 22:51:05 +0800</pubDate><description><![CDATA[Pytorch_study_Task_7:手写数字识别用PyTorch完成手写数字识别
用PyTorch完成手写数字识别
# -*- coding: utf-8 -*-

import torch
from torch import nn, optim
import torch.nn.functional as F
from torch.autograd import Variable
from ...]]></description><category></category></item><item><title><![CDATA[Pytorch_study_Task_6:PyTorch理解更多神经网络优化方法]]></title><link>https://blog.youkuaiyun.com/AR_hlr/article/details/99708669</link><guid>https://blog.youkuaiyun.com/AR_hlr/article/details/99708669</guid><author>AR_hlr</author><pubDate>Sun, 18 Aug 2019 21:02:26 +0800</pubDate><description><![CDATA[Pytorch_study_Task_6:PyTorch理解更多神经网络优化方法 
包含:
1.了解不同优化器
2.书写优化器代码
3.Momentum
4.二维优化，随机梯度下降法进行优化实现
5.Ada自适应梯度调节法
6.RMSProp
7.Adam
8.PyTorch优化器选择
了解不同优化器
优化器用于加速神经网络训练过程。包括以下几种：

Stochastic Gradient Des...]]></description><category></category></item><item><title><![CDATA[Pytorch_study_Task_5:PyTorch实现L1，L2正则化以及Dropout]]></title><link>https://blog.youkuaiyun.com/AR_hlr/article/details/99678832</link><guid>https://blog.youkuaiyun.com/AR_hlr/article/details/99678832</guid><author>AR_hlr</author><pubDate>Fri, 16 Aug 2019 20:46:10 +0800</pubDate><description><![CDATA[Pytorch_study_Task_5:PyTorch实现L1，L2正则化以及Dropout 1.了解知道Dropout原理2.用代码实现正则化(L1、L2、Dropout）3.Dropout的numpy实现4.PyTorch中实现dropout
1.了解知道Dropout原理

Dropout是一种在学习的过程中随机删除神经元的方法。训练时，随机选出隐藏层的神经元，然后将其删除。被删除的神经元...]]></description><category></category></item><item><title><![CDATA[Pytorch_study_Task_4:用PyTorch实现多层网络]]></title><link>https://blog.youkuaiyun.com/AR_hlr/article/details/99352712</link><guid>https://blog.youkuaiyun.com/AR_hlr/article/details/99352712</guid><author>AR_hlr</author><pubDate>Mon, 12 Aug 2019 23:29:08 +0800</pubDate><description><![CDATA[Pytorch_study_Task_4:用PyTorch实现多层网络 1.用PyTorch实现多层网络
1.用PyTorch实现多层网络
包含：
1.引入模块，读取数据
2.构建计算图（构建网络模型）
3.损失函数与优化器
4.开始训练模型
5.对训练的模型预测结果进行评估
代码实现
通过逻辑回归实现。
# -*- coding: utf-8 -*-

import torch
from tor...]]></description><category></category></item><item><title><![CDATA[Pytorch_study_Task_3:PyTorch实现Logistic regression  .]]></title><link>https://blog.youkuaiyun.com/AR_hlr/article/details/99226037</link><guid>https://blog.youkuaiyun.com/AR_hlr/article/details/99226037</guid><author>AR_hlr</author><pubDate>Sun, 11 Aug 2019 20:15:20 +0800</pubDate><description><![CDATA[Pytorch_study_Task_3:PyTorch实现Logistic regression 1.PyTorch基础实现代码2.用PyTorch类实现Logistic regression,torch.nn.module写网络结构代码实现
1.PyTorch基础实现代码
2.用PyTorch类实现Logistic regression,torch.nn.module写网络结构

代码实现
建...]]></description><category></category></item><item><title><![CDATA[Pytorch_study_Task_2:设立计算图并自动计算 .]]></title><link>https://blog.youkuaiyun.com/AR_hlr/article/details/98883047</link><guid>https://blog.youkuaiyun.com/AR_hlr/article/details/98883047</guid><author>AR_hlr</author><pubDate>Fri, 09 Aug 2019 21:10:36 +0800</pubDate><description><![CDATA[Pytorch_study_Task_2:设立计算图并自动计算1.numpy和pytorch实现梯度下降法新的改变功能快捷键合理的创建标题，有助于目录的生成如何改变文本的样式插入链接与图片如何插入一段漂亮的代码片生成一个适合你的列表创建一个表格设定内容居中、居左、居右SmartyPants创建一个自定义列表如何创建一个注脚注释也是必不可少的KaTeX数学公式新的甘特图功能，丰富你的文章UML 图表...]]></description><category></category></item></channel></rss>