<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/winnie91</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; winnie91]]></copyright><item><title><![CDATA[268. Missing Number 丢失的数字]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/109271656</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/109271656</guid><author>winnie91</author><pubDate>Mon, 26 Oct 2020 11:21:17 +0800</pubDate><description><![CDATA[Given an array containing n distinct numbers taken from 0, 1, 2, ..., n, find the one that is missing from the array. For example, Given nums = [0, 1, 3] return 2

Follow up: Could you implement a solution using only O(1) extra space complexity and O(n) ru]]></description><category></category></item><item><title><![CDATA[使用tensorflow时遇到的一些问题汇总·]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/91125501</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/91125501</guid><author>winnie91</author><pubDate>Fri, 07 Jun 2019 08:10:31 +0800</pubDate><description><![CDATA[1. 使用tensorboardno scalar data was found。

解决方案link：https://github.com/tensorflow/tensorflow/issues/2353

在使用tf.summary记录验证集的损失时，总是发现no scalar data was found。


with tf.Session(graph=g) as sess:
    ...]]></description><category></category></item><item><title><![CDATA[Mask R-CNN 精读]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/80259873</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/80259873</guid><author>winnie91</author><pubDate>Fri, 11 May 2018 17:55:22 +0800</pubDate><description><![CDATA[1. IntroductionIn principle Mask R-CNN is an intuitive extension ofFaster R-CNN, yet constructing the mask branch properlyis critical for good results. Most importantly, Faster RCNNwas not designed fo...]]></description><category></category></item><item><title><![CDATA[欢迎使用优快云-markdown编辑器2]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/78874221</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/78874221</guid><author>winnie91</author><pubDate>Fri, 22 Dec 2017 16:00:14 +0800</pubDate><description><![CDATA[欢迎使用Markdown编辑器写博客本Markdown编辑器使用StackEdit修改而来，用它写博客，将会带来全新的体验哦：
Markdown和扩展Markdown简洁的语法
代码块高亮
图片链接和图片上传
LaTex数学公式
UML序列图和流程图
离线写博客
导入导出Markdown文件
丰富的快捷键
快捷键
加粗    Ctrl + B 
斜体    Ctrl + I 
引用    Ctrl]]></description><category></category></item><item><title><![CDATA[deeplearning.ai-lecture4-week1-Convolutional Neural Networks: Step by Step]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/78867781</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/78867781</guid><author>winnie91</author><pubDate>Thu, 21 Dec 2017 21:09:07 +0800</pubDate><description><![CDATA[Convolutional Neural Networks: Step by Step
Welcome to Course 4's first assignment! In this assignment, you will implement convolutional (CONV) and pooling (POOL) layers in numpy, including both forw]]></description><category></category></item><item><title><![CDATA[deeplearning.ai-lecture1-building deep neural network steps]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/78785580</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/78785580</guid><author>winnie91</author><pubDate>Tue, 12 Dec 2017 20:11:00 +0800</pubDate><description><![CDATA[该实验主要是实现一些“Helper function”,为下一步实现两层神经网络和L层神经网络做准备，实现一个两层网络或深层网络的步骤如下：

Step 1.分别初始化一个两层神经网络和L层神经网络的参数

Step 2: 前向传播的实现：

1.完成一个网络的前向传播的线性部分（linear part）,即计算出 Z [l]     

2.实现relu和 sigmoid激活函数]]></description><category></category></item><item><title><![CDATA[deeplearning.ai-lecture1-building deep neural network-summary]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/78785433</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/78785433</guid><author>winnie91</author><pubDate>Tue, 12 Dec 2017 19:56:38 +0800</pubDate><description><![CDATA[先上一张summary map


1. L层神经网络参数初始化: 返回各层参数W(1)…W(l-1)
def initialize_parameters_deep(layer_dims):
   for
l in
range(1,L):
        parameters['W'+str(l)]=np.random.randn(layer_dims[l],layer_dims[]]></description><category></category></item><item><title><![CDATA[deeplearning.ai-lecture2-week1-regularization-homework]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/78785384</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/78785384</guid><author>winnie91</author><pubDate>Tue, 12 Dec 2017 19:52:01 +0800</pubDate><description><![CDATA[Regularization
Welcome to the second assignment of this week. Deep Learning models have so much flexibility and capacity that overfitting can be a serious problem, if the training dataset is not big ]]></description><category></category></item><item><title><![CDATA[deeplearning.ai-lecture2-week1-Initialization-homework]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/78785357</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/78785357</guid><author>winnie91</author><pubDate>Tue, 12 Dec 2017 19:50:14 +0800</pubDate><description><![CDATA[Initialization
Welcome to the first assignment of "Improving Deep Neural Networks".
Training your neural network requires specifying an initial value of the weights. A well chosen initialization met]]></description><category></category></item><item><title><![CDATA[deeplearning.ai-lecture2-week1-Gradient Checking-homework]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/78785344</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/78785344</guid><author>winnie91</author><pubDate>Tue, 12 Dec 2017 19:48:38 +0800</pubDate><description><![CDATA[Gradient Checking
Welcome to the final assignment for this week! In this assignment you will learn to implement and use gradient checking.
You are part of a team working to make mobile payments avai]]></description><category></category></item><item><title><![CDATA[deeplearning.ai-lecture2-week3-Tensorflow Tutorial-homework]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/78785306</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/78785306</guid><author>winnie91</author><pubDate>Tue, 12 Dec 2017 19:44:18 +0800</pubDate><description><![CDATA[TensorFlow Tutorial
Welcome to this week's programming assignment. Until now, you've always used numpy to build neural networks. Now we will step you through a deep learning framework that will allow]]></description><category></category></item><item><title><![CDATA[deeplearning.ai lecture2-week2-optimization methods]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/78776037</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/78776037</guid><author>winnie91</author><pubDate>Mon, 11 Dec 2017 19:51:11 +0800</pubDate><description><![CDATA[Optimization methods




Optimization Methods
Until now, you've always used Gradient Descent to update the parameters and minimize the cost. In this notebook, you will learn more advanced optimi]]></description><category></category></item><item><title><![CDATA[【转载】A Review on Deep Learning Techniques Applied to Semantic Segmentation(译)-（1）]]></title><link>https://blog.youkuaiyun.com/winnie91/article/details/78548642</link><guid>https://blog.youkuaiyun.com/winnie91/article/details/78548642</guid><author>winnie91</author><pubDate>Thu, 16 Nov 2017 10:51:29 +0800</pubDate><description><![CDATA[原文链接：http://blog.youkuaiyun.com/u011771047/article/details/72779221

http://blog.youkuaiyun.com/u014451076/article/details/71101850


本部分包括：摘要，1.引言，2.专业术语和背景概念

摘要

　　图像语义分割越来越受到计算机视觉和机器学习的研究人员的热爱。越来越多新兴]]></description><category></category></item></channel></rss>