<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[longrootchen的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/longrootchen</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; longrootchen]]></copyright><item><title><![CDATA[解决 visdom 下载 scripts 慢的问题]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/108582552</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/108582552</guid><author>longrootchen</author><pubDate>Mon, 14 Sep 2020 16:47:43 +0800</pubDate><description><![CDATA[转自：
visdom服务启动时提示Downloading scripts, this may take a little while解决办法


]]></description><category></category></item><item><title><![CDATA[GitHub资源汇总]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/108336989</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/108336989</guid><author>longrootchen</author><pubDate>Tue, 01 Sep 2020 14:53:59 +0800</pubDate><description><![CDATA[emmm… github 的 star 没有分类功能，收藏了一大堆有点儿难找。这里汇总和分类一下（不断更新…）
文章目录图像分类语义分割目标检测GAN其他
图像分类
an op-for-op reimplementation of EfficientNet, along with pre-trained models and examples in PyTorch
语义分割
popular semantic segmentation architectures  in PyTorch
Semantic Se]]></description><category></category></item><item><title><![CDATA[卷积神经网络的FLOPs和参数量的计算]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/108261990</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/108261990</guid><author>longrootchen</author><pubDate>Thu, 27 Aug 2020 15:45:17 +0800</pubDate><description><![CDATA[文章目录1. 计算公式2. 开源库
1. 计算公式
ICLR 2017 一篇 NVIDIA 的 paper 在 APPENDIX A.1 中给出了比较详细的计算公式（公式 11，公式 12）；然鹅原文中公式 11 可能有误，HHH 和 WWW 应为 height and width of the output feature map，而不是 of the input feature map。
对应讲解可以参考知乎 chen liu 的回答。

2. 开源库
用 pytorch 搭建的模型有一些库可以得到 F]]></description><category></category></item><item><title><![CDATA[k折划分数据]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/107727531</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/107727531</guid><author>longrootchen</author><pubDate>Sat, 01 Aug 2020 11:34:45 +0800</pubDate><description><![CDATA[采用 K 折交叉验证之前需要先划分好数据，这里记录一下各种 K 折划分数据的方法
文章目录0. 示例 csv1. KFold2. StratifiedKFold3. StratifiedGroupKFold
0. 示例 csv
构造一个 example.csv 为例，其中 image_name 为特征，patient_id 为分组，target 为标签。
1. KFold
太简单不写了

2. StratifiedKFold
import os
import numpy as np
import panda]]></description><category></category></item><item><title><![CDATA[nvidia-smi命令监测GPU状态]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/107331871</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/107331871</guid><author>longrootchen</author><pubDate>Tue, 14 Jul 2020 10:01:34 +0800</pubDate><description><![CDATA[参考博客 GPU状态监测 nvidia-smi 命令详解

]]></description><category></category></item><item><title><![CDATA[微软自动调参工具NNI]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/107330566</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/107330566</guid><author>longrootchen</author><pubDate>Tue, 14 Jul 2020 09:11:26 +0800</pubDate><description><![CDATA[参考博客 微软自动调参工具—NNI—安装与使用教程（附错误解决）

]]></description><category></category></item><item><title><![CDATA[解压分卷压缩文件]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/106013657</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/106013657</guid><author>longrootchen</author><pubDate>Tue, 02 Jun 2020 09:02:57 +0800</pubDate><description><![CDATA[文章目录1. 后缀名为 .zip.001 .zip.0022. 后缀名为 z01 z02

1. 后缀名为 .zip.001 .zip.002
参考cnblogs .zip.001 .zip.002怎么用压缩包解压缩？


将文件们放到同一个目录下，


在 “cmd” 进入到该目录，


运行 copy /B foo.zip.001+foo.zip.002 foo.zip 命令，等待完成后关闭 “cmd” 窗口。


目录下会有文件 foo.zip，使用一些软件解压即可得到文件。



2. 后缀名为 z]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（五）保存和加载和训练模型]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/105876504</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/105876504</guid><author>longrootchen</author><pubDate>Sun, 10 May 2020 16:03:59 +0800</pubDate><description><![CDATA[本文记录了在 PyTorch 中训练模型的代码。]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（五）使用GPU训练模型]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/106012488</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/106012488</guid><author>longrootchen</author><pubDate>Sat, 09 May 2020 09:54:50 +0800</pubDate><description><![CDATA[本文记录了在 PyTorch 中使用 GPU 训练模型的方法。]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（五）TensorBoard可视化]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/105876106</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/105876106</guid><author>longrootchen</author><pubDate>Fri, 08 May 2020 11:03:12 +0800</pubDate><description><![CDATA[本文记录了在 PyTorch 中使用 TensorBoard 进行可视化的方法。]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（四）调整学习率]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/105761486</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/105761486</guid><author>longrootchen</author><pubDate>Sun, 26 Apr 2020 08:54:49 +0800</pubDate><description><![CDATA[本文记录了 PyTorch 中学习率调整器的使用方法 。]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（四）优化器]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/105724041</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/105724041</guid><author>longrootchen</author><pubDate>Sat, 25 Apr 2020 11:56:23 +0800</pubDate><description><![CDATA[本文记录了 PyTorch 中优化器的使用方法 。]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（四）损失函数]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/105673979</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/105673979</guid><author>longrootchen</author><pubDate>Thu, 23 Apr 2020 09:37:19 +0800</pubDate><description><![CDATA[本文记录了 PyTorch 中提供的18种损失函数。]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（三）构建卷积神经网络模型]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/105644303</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/105644303</guid><author>longrootchen</author><pubDate>Wed, 22 Apr 2020 09:17:43 +0800</pubDate><description><![CDATA[本文记录了使用 PyTorch 如何构建基本计算机视觉任务模型的方法。]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（三）参数初始化与各种Norm层]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/105650059</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/105650059</guid><author>longrootchen</author><pubDate>Tue, 21 Apr 2020 15:56:13 +0800</pubDate><description><![CDATA[本文记录了 PyTorch 中模型参数的初始化和四种 Norm 层的使用。]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（三）卷积池化线性激活和Dropout层]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/105585060</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/105585060</guid><author>longrootchen</author><pubDate>Sat, 18 Apr 2020 11:27:38 +0800</pubDate><description><![CDATA[本文记录了使用 PyTorch 如何定义各种卷积、池化、线性、激活函数层。]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（二）读取数据]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/105527306</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/105527306</guid><author>longrootchen</author><pubDate>Thu, 16 Apr 2020 00:25:08 +0800</pubDate><description><![CDATA[本文记录了使用 PyTorch 进行深度学习计算机视觉任务中对图像数据读取的方法。]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（二）划分数据集]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/105447058</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/105447058</guid><author>longrootchen</author><pubDate>Wed, 15 Apr 2020 09:41:02 +0800</pubDate><description><![CDATA[本文记录了使用 PyTorch 进行深度学习任务进行数据集划分的方法。]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（二）图像数据增强]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/105468118</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/105468118</guid><author>longrootchen</author><pubDate>Tue, 14 Apr 2020 20:40:31 +0800</pubDate><description><![CDATA[本文记录了使用 torchvision.transforms 中的类实现图像数据预处理的方法。]]></description><category></category></item><item><title><![CDATA[PyTorch学习笔记（一）基本建模流程]]></title><link>https://blog.youkuaiyun.com/longrootchen/article/details/105465613</link><guid>https://blog.youkuaiyun.com/longrootchen/article/details/105465613</guid><author>longrootchen</author><pubDate>Sun, 12 Apr 2020 13:06:48 +0800</pubDate><description><![CDATA[本文记录了使用 PyTorch 实现简单的线性回归和对率回归的基本流程。]]></description><category></category></item></channel></rss>