<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[ALLSTARZTQ的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/ALLSTARZTQ</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; ALLSTARZTQ]]></copyright><item><title><![CDATA[手动分解反向传播，理解梯度消失和梯度爆炸]]></title><link>https://blog.youkuaiyun.com/ALLSTARZTQ/article/details/90601644</link><guid>https://blog.youkuaiyun.com/ALLSTARZTQ/article/details/90601644</guid><author>ALLSTARZTQ</author><pubDate>Mon, 27 May 2019 13:21:22 +0800</pubDate><description><![CDATA[Let’s see a very simple handwriting formula derivation
#Define
Firstly, let define some variables and operations

Gradient of the variable in layer L(last layer)
dWL = dLoss * aL

Gradient of the vari...]]></description><category></category></item><item><title><![CDATA[十个提高代码效率的python技巧]]></title><link>https://blog.youkuaiyun.com/ALLSTARZTQ/article/details/90479355</link><guid>https://blog.youkuaiyun.com/ALLSTARZTQ/article/details/90479355</guid><author>ALLSTARZTQ</author><pubDate>Thu, 23 May 2019 14:04:47 +0800</pubDate><description><![CDATA[来自blog
namedtuple
If you are too lazy to create a class but you still want to use a variable that can act as a class object, then you should use namedtuple:
from collections import namedtuple
user = n...]]></description><category></category></item><item><title><![CDATA[Tensorflow 量化训练全过程]]></title><link>https://blog.youkuaiyun.com/ALLSTARZTQ/article/details/90400183</link><guid>https://blog.youkuaiyun.com/ALLSTARZTQ/article/details/90400183</guid><author>ALLSTARZTQ</author><pubDate>Tue, 21 May 2019 09:20:41 +0800</pubDate><description><![CDATA[来自blog
Tensorflow 量化训练全过程
You can either train your quantized model by restroing a ever trained floating point model or from scratch. In any cases, you have to firstly create a quantization training g...]]></description><category></category></item></channel></rss>