<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[DaVinciL的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/DaVinciL</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; DaVinciL]]></copyright><item><title><![CDATA[Leetcode cn 解析布尔表达式]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/115281233</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/115281233</guid><author>DaVinciL</author><pubDate>Sun, 28 Mar 2021 15:11:43 +0800</pubDate><description><![CDATA[给你一个以字符串形式表述的 布尔表达式（boolean） expression，返回该式的运算结果。
有效的表达式需遵循以下约定：

“t”，运算结果为 True
“f”，运算结果为 False
“!(expr)”，运算过程为对内部表达式 expr 进行逻辑 非的运算（NOT）
“&amp;(expr1,expr2,…)”，运算过程为对 2 个或以上内部表达式 expr1, expr2, … 进行逻辑 与的运算（AND）
“|(expr1,expr2,…)”，运算过程为对 2 个或以上内部表达式 expr1]]></description><category></category></item><item><title><![CDATA[LeetCode 1232. Check If It Is a Straight Line]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/107192311</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/107192311</guid><author>DaVinciL</author><pubDate>Tue, 07 Jul 2020 22:41:29 +0800</pubDate><description><![CDATA[  You are given an array coordinates, coordinates[i] = [x, y], where [x, y] represents the coordinate of a point. Check if these points make a straight line in the XY plane.
Example 1:

Input: coordinates = [[1,2],[2,3],[3,4],[4,5],[5,6],[6,7]]
Output: tru]]></description><category></category></item><item><title><![CDATA[深度学习之卷积：如果卷积核被初始化为0]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/101105219</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/101105219</guid><author>DaVinciL</author><pubDate>Sat, 21 Sep 2019 13:42:49 +0800</pubDate><description><![CDATA[前言
  这几天面试遇到了这样一个问题，如果卷积层的权重被赋值为0，会发生什么？
  解决这个问题我们首先定义一下在神经网络中的基本权重和偏置的初始化情况，在TensorFlow中，权重一般由用户初始化，可选择很多初始化方式，如glorot_normal_initializer()等，但是偏置在默认的情况下一般初始化为0，具体可以参考tf.layers.conv2d和tf.layers.dense...]]></description><category></category></item><item><title><![CDATA[卷积可视化：特征图的可视化]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100712217</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100712217</guid><author>DaVinciL</author><pubDate>Tue, 10 Sep 2019 20:54:16 +0800</pubDate><description><![CDATA[import keras
import matplotlib.pyplot as plt
from keras.applications.vgg16 import VGG16
from keras.preprocessing import image
from keras.applications.vgg16 import preprocess_input
import numpy as np

...]]></description><category></category></item><item><title><![CDATA[机器学习复习：Adaboost算法]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100668938</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100668938</guid><author>DaVinciL</author><pubDate>Mon, 09 Sep 2019 17:34:44 +0800</pubDate><description><![CDATA[前言
  提升方法（boosting）是一种常用的机器学习方法，应用十分广泛，而且效果非常好，近几年的很多比赛的优胜选手都或多或少使用了提升方法用以提高自己的成绩。
  提升方法的本质是通过对每一个训练样本赋予一个权重，并通过改变这些样本的权重，来学习多个分类器，并按照一定的算法将这些分类器组合在一起，通常是线性组合，因为单个分类器往往效果有限，因此组合多个分类器往往会提高模型的性能。
 
一、提...]]></description><category></category></item><item><title><![CDATA[LeetCode解题报告：498. Diagonal Traverse]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100525957</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100525957</guid><author>DaVinciL</author><pubDate>Tue, 03 Sep 2019 19:42:20 +0800</pubDate><description><![CDATA[Problem
Given a matrix of M x N elements (M rows, N columns), return all elements of the matrix in diagonal order as shown in the below image.
Example:

Input:
[
[ 1, 2, 3 ],
[ 4, 5, 6 ],
[ 7, 8, 9 ]
...]]></description><category></category></item><item><title><![CDATA[YOLOv3源码阅读之七：data_utils.py]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100519755</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100519755</guid><author>DaVinciL</author><pubDate>Tue, 03 Sep 2019 15:35:44 +0800</pubDate><description><![CDATA[一、YOLO简介
  YOLO（You Only Look Once）是一个高效的目标检测算法，属于One-Stage大家族，针对于Two-Stage目标检测算法普遍存在的运算速度慢的缺点，YOLO创造性的提出了One-Stage。也就是将物体分类和物体定位在一个步骤中完成。YOLO直接在输出层回归bounding box的位置和bounding box所属类别，从而实现one-stage。
  ...]]></description><category></category></item><item><title><![CDATA[YOLOv3源码阅读之六：train.py]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100519713</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100519713</guid><author>DaVinciL</author><pubDate>Tue, 03 Sep 2019 15:34:49 +0800</pubDate><description><![CDATA[一、YOLO简介
  YOLO（You Only Look Once）是一个高效的目标检测算法，属于One-Stage大家族，针对于Two-Stage目标检测算法普遍存在的运算速度慢的缺点，YOLO创造性的提出了One-Stage。也就是将物体分类和物体定位在一个步骤中完成。YOLO直接在输出层回归bounding box的位置和bounding box所属类别，从而实现one-stage。
  ...]]></description><category></category></item><item><title><![CDATA[YOLOv3源码阅读之五：nms_utils.py]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100519686</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100519686</guid><author>DaVinciL</author><pubDate>Tue, 03 Sep 2019 15:34:03 +0800</pubDate><description><![CDATA[一、YOLO简介
  YOLO（You Only Look Once）是一个高效的目标检测算法，属于One-Stage大家族，针对于Two-Stage目标检测算法普遍存在的运算速度慢的缺点，YOLO创造性的提出了One-Stage。也就是将物体分类和物体定位在一个步骤中完成。YOLO直接在输出层回归bounding box的位置和bounding box所属类别，从而实现one-stage。
  ...]]></description><category></category></item><item><title><![CDATA[YOLOv3源码阅读之四：layer_utils.py]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100519633</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100519633</guid><author>DaVinciL</author><pubDate>Tue, 03 Sep 2019 15:32:58 +0800</pubDate><description><![CDATA[一、YOLO简介
  YOLO（You Only Look Once）是一个高效的目标检测算法，属于One-Stage大家族，针对于Two-Stage目标检测算法普遍存在的运算速度慢的缺点，YOLO创造性的提出了One-Stage。也就是将物体分类和物体定位在一个步骤中完成。YOLO直接在输出层回归bounding box的位置和bounding box所属类别，从而实现one-stage。
  ...]]></description><category></category></item><item><title><![CDATA[YOLOv3源码阅读之三：model.py]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100519568</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100519568</guid><author>DaVinciL</author><pubDate>Tue, 03 Sep 2019 15:32:04 +0800</pubDate><description><![CDATA[一、YOLO简介
  YOLO（You Only Look Once）是一个高效的目标检测算法，属于One-Stage大家族，针对于Two-Stage目标检测算法普遍存在的运算速度慢的缺点，YOLO创造性的提出了One-Stage。也就是将物体分类和物体定位在一个步骤中完成。YOLO直接在输出层回归bounding box的位置和bounding box所属类别，从而实现one-stage。
  ...]]></description><category></category></item><item><title><![CDATA[YOLOv3源码阅读之二：get_kmeans.py]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100519521</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100519521</guid><author>DaVinciL</author><pubDate>Tue, 03 Sep 2019 15:30:40 +0800</pubDate><description><![CDATA[一、YOLO简介
  YOLO（You Only Look Once）是一个高效的目标检测算法，属于One-Stage大家族，针对于Two-Stage目标检测算法普遍存在的运算速度慢的缺点，YOLO创造性的提出了One-Stage。也就是将物体分类和物体定位在一个步骤中完成。YOLO直接在输出层回归bounding box的位置和bounding box所属类别，从而实现one-stage。
  ...]]></description><category></category></item><item><title><![CDATA[YOLOv3源码阅读之一：test_single_image.py]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100519392</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100519392</guid><author>DaVinciL</author><pubDate>Tue, 03 Sep 2019 15:29:27 +0800</pubDate><description><![CDATA[一、YOLO简介
  YOLO（You Only Look Once）是一个高效的目标检测算法，属于One-Stage大家族，针对于Two-Stage目标检测算法普遍存在的运算速度慢的缺点，YOLO创造性的提出了One-Stage。也就是将物体分类和物体定位在一个步骤中完成。YOLO直接在输出层回归bounding box的位置和bounding box所属类别，从而实现one-stage。
  ...]]></description><category></category></item><item><title><![CDATA[LeetCode解题报告：309. Best Time to Buy and Sell Stock with Cooldown]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100172671</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100172671</guid><author>DaVinciL</author><pubDate>Sat, 31 Aug 2019 14:53:52 +0800</pubDate><description><![CDATA[Problem
Say you have an array for which the ith element is the price of a given stock on day i.
Design an algorithm to find the maximum profit. You may complete as many transactions as you like (ie, b...]]></description><category></category></item><item><title><![CDATA[LeetCode解题报告：714. Best Time to Buy and Sell Stock with Transaction Fee]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100172227</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100172227</guid><author>DaVinciL</author><pubDate>Sat, 31 Aug 2019 14:36:12 +0800</pubDate><description><![CDATA[Problem
Your are given an array of integers prices, for which the i-th element is the price of a given stock on day i; and a non-negative integer fee representing a transaction fee.
You may complete a...]]></description><category></category></item><item><title><![CDATA[LeetCode解题报告：121. Best Time to Buy and Sell Stock]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100172048</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100172048</guid><author>DaVinciL</author><pubDate>Sat, 31 Aug 2019 14:02:06 +0800</pubDate><description><![CDATA[Problem
Say you have an array for which the ithi^{th}ith element is the price of a given stock on day i.
If you were only permitted to complete at most one transaction (i.e., buy one and sell one shar...]]></description><category></category></item><item><title><![CDATA[LeetCode解题分享：1011. Capacity To Ship Packages Within D Days]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100158979</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100158979</guid><author>DaVinciL</author><pubDate>Fri, 30 Aug 2019 15:14:41 +0800</pubDate><description><![CDATA[Problem
A conveyor belt has packages that must be shipped from one port to another within D days.
The i-th package on the conveyor belt has a weight of weights[i].  Each day, we load the ship with pac...]]></description><category></category></item><item><title><![CDATA[LeetCode解题分享：82. Remove Duplicates from Sorted List II]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100141135</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100141135</guid><author>DaVinciL</author><pubDate>Thu, 29 Aug 2019 16:38:51 +0800</pubDate><description><![CDATA[Problem
Given a sorted linked list, delete all nodes that have duplicate numbers, leaving only distinct numbers from the original list.
Example 1:

Input: 1-&gt;2-&gt;3-&gt;3-&gt;4-&gt;4-&gt;5
Output:...]]></description><category></category></item><item><title><![CDATA[LeetCode解题分享：430. Flatten a Multilevel Doubly Linked List]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100140145</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100140145</guid><author>DaVinciL</author><pubDate>Thu, 29 Aug 2019 16:15:44 +0800</pubDate><description><![CDATA[Problem
You are given a doubly linked list which in addition to the next and previous pointers, it could have a child pointer, which may or may not point to a separate doubly linked list. These child ...]]></description><category></category></item><item><title><![CDATA[LeetCode解题分享：117. Populating Next Right Pointers in Each Node II]]></title><link>https://blog.youkuaiyun.com/DaVinciL/article/details/100136673</link><guid>https://blog.youkuaiyun.com/DaVinciL/article/details/100136673</guid><author>DaVinciL</author><pubDate>Thu, 29 Aug 2019 14:16:25 +0800</pubDate><description><![CDATA[problem
Given a binary tree

struct Node {
int val;
Node *left;
Node *right;
Node *next;
}

Populate each next pointer to point to its next right node. If there is no next right node, the next pointer...]]></description><category></category></item></channel></rss>