<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[沙丁鱼鱼鱼]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/u014694994</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; u014694994]]></copyright><item><title><![CDATA[RANSAC随机采样一致算法]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/94974369</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/94974369</guid><author>u014694994</author><pubDate>Sun, 07 Jul 2019 11:47:05 +0800</pubDate><description><![CDATA[RANSAC简介

RANSAC(RAndomSAmpleConsensus,随机采样一致)算法是从一组含有“外点”(outliers)的数据中正确估计数学模型参数的迭代算法。“外点”一般指的的数据中的噪声，比如说匹配中的误匹配和估计曲线中的离群点。所以，RANSAC也是一种“外点”检测算法。RANSAC算法是一种不确定算法，它只能在一种概率下产生结果，并且这个概率会随着迭代次数的增加而加大（...]]></description><category></category></item><item><title><![CDATA[图像Non-local means 去噪算法matlab实现]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/94973874</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/94973874</guid><author>u014694994</author><pubDate>Sun, 07 Jul 2019 11:39:23 +0800</pubDate><description><![CDATA[function [output]=NLmeansfilter(input,t,f,h)
 
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 %
 %  input: image to be filtered
 %  t: radio of search window 5        5*5大小的搜索窗
 % ...]]></description><category></category></item><item><title><![CDATA[KD-Tree的C++源码实现]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/94973743</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/94973743</guid><author>u014694994</author><pubDate>Sun, 07 Jul 2019 11:37:23 +0800</pubDate><description><![CDATA[#include&lt;cstdio&gt;
#include&lt;algorithm&gt;
#include&lt;vector&gt;
using namespace std;

class Node{
	public:
		int location;
		int p, l, r;
		Node() {}
}; 

class Point{
	public:
		int id, x, y...]]></description><category></category></item><item><title><![CDATA[双目立体视觉的SSD立体匹配matlab代码]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/94973677</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/94973677</guid><author>u014694994</author><pubDate>Sun, 07 Jul 2019 11:36:37 +0800</pubDate><description><![CDATA[# Licensed under the MIT License
import numpy as np
from PIL import Image

def stereo_match(left_img, right_img, kernel, max_offset):
    # Load in both images, assumed to be RGBA 8bit per channel im...]]></description><category></category></item><item><title><![CDATA[堆排序的Python代码]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/94973491</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/94973491</guid><author>u014694994</author><pubDate>Sun, 07 Jul 2019 11:34:49 +0800</pubDate><description><![CDATA[# -*- coding: utf-8 -*-
"""
Created on Fri Jul  5 10:13:16 2019

@author: Yuki
"""

def heapAdjust(nums, Len, index):
    left = index*2 + 1
    right = index*2 + 2
    
    maxIndex = index
    if l...]]></description><category></category></item><item><title><![CDATA[双目立体匹配SAD的matlab源码分析]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/94973272</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/94973272</guid><author>u014694994</author><pubDate>Sun, 07 Jul 2019 11:32:36 +0800</pubDate><description><![CDATA[clear all
clc
left=double(rgb2gray(imread('left.png')));
right=double(rgb2gray(imread('right.png')));

[m n]=size(left);

w=9;       %窗口半径
depth=20;    %最大偏移距离，同样也是最大深度距离
imgn=zeros(m,n);
for i=1+w:m...]]></description><category></category></item><item><title><![CDATA[DBSCAN源码分析]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/94973087</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/94973087</guid><author>u014694994</author><pubDate>Sun, 07 Jul 2019 11:30:27 +0800</pubDate><description><![CDATA[%
% Copyright (c) 2015, Yarpiz (www.yarpiz.com)
% All rights reserved. Please read the "license.txt" for license terms.
%
% Project Code: YPML110
% Project Title: Implementation of DBSCAN Clustering ...]]></description><category></category></item><item><title><![CDATA[Kmeans目标函数原理分析]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/94972668</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/94972668</guid><author>u014694994</author><pubDate>Sun, 07 Jul 2019 11:25:54 +0800</pubDate><description><![CDATA[]]></description><category></category></item><item><title><![CDATA[PCA主成分分析的理论推导（为什么选择协方差矩阵的最大特征值对应的特征向量作为投影方向？）]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/94971986</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/94971986</guid><author>u014694994</author><pubDate>Sun, 07 Jul 2019 11:19:21 +0800</pubDate><description><![CDATA[]]></description><category></category></item><item><title><![CDATA[二叉树重建（C++/Python）]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/82559746</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/82559746</guid><author>u014694994</author><pubDate>Sun, 09 Sep 2018 16:45:42 +0800</pubDate><description><![CDATA[问题：

输入某二叉树的前序遍历和中序遍历的结果，请重建出该二叉树。假设输入的前序遍历和中序遍历的结果中都不含重复的数字。例如输入前序遍历序列{1,2,4,7,3,5,6,8}和中序遍历序列{4,7,2,1,5,3,8,6}，则重建二叉树并返回。

 

思路分析 
根据二叉树前序遍历的特点（根-左-右），每次读取的第一个值一定是根节点，这样我们可以在中序遍历的序列中找到当前的根节点的位置。 
根...]]></description><category></category></item><item><title><![CDATA[《一一》影评：年华一帧一帧地逝去]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/82353516</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/82353516</guid><author>u014694994</author><pubDate>Mon, 03 Sep 2018 19:33:45 +0800</pubDate><description><![CDATA[ 

有一幅很著名的画：太阳在海平面之上，阳光洒下整片海，沙滩上有几个人正朝着太阳的方向仰望，你认为是日出还是日落？据说看到日出的人充满朝气，是乐观主义者；看到日落的人暮气沉沉，是悲观主义者。某天有人问我，你看到的是日出还是日落？虽然我知道这个寓意，却不想掩饰什么，我说我看到的是日落，他说你真的老了。也是在那天我看了《一一》，本来很淡然的我却在片尾曲响起的时候，呆坐在那里，掩面而泣，好像活了一辈子...]]></description><category></category></item><item><title><![CDATA[快速理解EM算法]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/82313095</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/82313095</guid><author>u014694994</author><pubDate>Sun, 02 Sep 2018 10:01:46 +0800</pubDate><description><![CDATA[原文链接： https://www.jianshu.com/p/1121509ac1dc


如果使用基于最大似然估计的模型，模型中存在隐变量，就要用EM算法做参数估计。个人认为，理解EM算法背后的idea，远比看懂它的数学推导重要。idea会让你有一个直观的感受，从而明白算法的合理性，数学推导只是将这种合理性用更加严谨的语言表达出来而已。打个比方，一个梨很甜，用数学的语言可以表述为糖分含量90%...]]></description><category></category></item><item><title><![CDATA[迅速掌握 快速排序]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/81105642</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/81105642</guid><author>u014694994</author><pubDate>Wed, 18 Jul 2018 21:29:01 +0800</pubDate><description><![CDATA[转载：http://developer.51cto.com/art/201403/430986.htm

假设我们现在对“6  1  2 7  9  3  4  5 10  8”这个10个数进行排序。首先在这个序列中随便找一个数作为基准数（不要被这个名词吓到了，就是一个用来参照的数，待会你就知道它用来做啥的了）。为了方便，就让第一个数6作为基准数吧。接下来，需要将这个序列中所有比基准数大的数放在6...]]></description><category></category></item><item><title><![CDATA[吴恩达 DeepLearning《神经网络与深度学习》之《神经网络基础》作业2]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/80957453</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/80957453</guid><author>u014694994</author><pubDate>Sun, 08 Jul 2018 10:47:17 +0800</pubDate><description><![CDATA[# -*- coding: utf-8 -*-
&quot;&quot;&quot;
Created on Thu Jul  5 10:17:56 2018

@author: Yuki
&quot;&quot;&quot;

import numpy as np
import matplotlib.pyplot as plt
import h5py
import scipy
from PIL import Image
from scipy import ...]]></description><category></category></item><item><title><![CDATA[Adaboost原理及例子]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/80856262</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/80856262</guid><author>u014694994</author><pubDate>Fri, 29 Jun 2018 14:48:16 +0800</pubDate><description><![CDATA[Adaboost是一种迭代算法，其核心思想是针对同一个训练集训练不同的分类器(弱分类器)，然后把这些弱分类器集合起来，构成一个更强的最终分类器（强分类器）。Adaboost是一种boosting提升方法，类似于将多个分类器串联在一起，组合成为一个强分类器。而bagging方法则类似于串联模式，将多个分类器并行串联组合成为一个强分类器，如随机森林Random Forest。Adaboost模型Ada...]]></description><category></category></item><item><title><![CDATA[LeetCode题解-144. Binary Tree Preorder Traversal（二叉树的非递归前序遍历）]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/80633624</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/80633624</guid><author>u014694994</author><pubDate>Sat, 09 Jun 2018 16:07:19 +0800</pubDate><description><![CDATA[题目：Given a binary tree, return the preorder traversal of its nodes' values.Example:Input: [1,null,2,3]
   1
    \
     2
    /
   3

Output: [1,2,3]思路：根据前序遍历访问的顺序，优先访问根结点，然后再分别访问左孩子和右孩子。即对于任一结点，其可看做是根...]]></description><category></category></item><item><title><![CDATA[C++中一级指针和双重（二级）指针作为函数参数传递]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/80611268</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/80611268</guid><author>u014694994</author><pubDate>Thu, 07 Jun 2018 16:55:05 +0800</pubDate><description><![CDATA[引用博文：https://www.cnblogs.com/WeyneChen/p/6672045.html函数参数传递的只能是数值，所以当指针作为函数参数传递时，传递的是指针的值，而不是地址。当指针作为函数参数传递时，在函数内部重新申请了一个新指针，与传入指针指向相同地址。在函数内部的操作只能针对指针指向的值。#include &amp;lt;iostream&amp;gt;
using namespace st...]]></description><category></category></item><item><title><![CDATA[LeetCode题解347. Top K Frequent Elements]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/80608582</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/80608582</guid><author>u014694994</author><pubDate>Thu, 07 Jun 2018 14:18:32 +0800</pubDate><description><![CDATA[题目：Given a non-empty array of integers, return the k most frequent elements.For example,Given [1,1,1,2,2,3] and k = 2, return [1,2].Note: You may assume k is always valid, 1 ≤ k ≤ number of unique ele...]]></description><category></category></item><item><title><![CDATA[LeetCode题解287- Find the Duplicate Number（C++）]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/80576382</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/80576382</guid><author>u014694994</author><pubDate>Tue, 05 Jun 2018 09:27:19 +0800</pubDate><description><![CDATA[题目：Given an array nums containing n + 1 integers where each integer is between 1 and n (inclusive), prove that at least one duplicate number must exist. Assume that there is only one duplicate number,...]]></description><category></category></item><item><title><![CDATA[BP神经网络算法推导（包含输出层和隐层）]]></title><link>https://blog.youkuaiyun.com/u014694994/article/details/80541768</link><guid>https://blog.youkuaiyun.com/u014694994/article/details/80541768</guid><author>u014694994</author><pubDate>Fri, 01 Jun 2018 19:58:12 +0800</pubDate><description><![CDATA[你是否也有疑问，在神经网络的训练过程中，随着多样本的训练，我们的参数是如何进行调节的呢？答案自然就是BP算法（Error Back Propagation）。反向传播时，将输出误差(期望输出与实际输出之差)按原通路反传计算，通过隐层反向，直至输入层，在反传过程中将误差分摊给各层的各个单元，获得各层各单元的误差信号，并将其作为修正各单元权值的根据。这一计算过程使用梯度下降法完成，在不停地调整各层神经...]]></description><category></category></item></channel></rss>