排序:
默认
按更新时间
按访问量

神经网络中权值初始化的方法

权值初始化的方法主要有:常量初始化(constant)、高斯分布初始化(gaussian)、positive_unitball初始化、均匀分布初始化(uniform)、xavier初始化、msra初始化、双线性初始化(bilinear) 常量初始化(constant)        把权...

2017-07-27 18:44:09

阅读数:6497

评论数:0

Perfect Squares

Given a positive integer n, find the least number of perfect square numbers (for example, 1, 4, 9, 16, ...) which sum to n. For example, given n = 1...

2017-07-13 20:53:54

阅读数:246

评论数:0

First Bad Version

You are a product manager and currently leading a team to develop a new product. Unfortunately, the latest version of your product fails the quality ...

2017-07-09 20:49:33

阅读数:201

评论数:0

Single Number III

Given an array of numbers nums, in which exactly two elements appear only once and all the other elements appear exactly twice. Find the two elemen...

2017-07-07 19:15:16

阅读数:150

评论数:0

Single Number II

Given an array of integers, every element appears three times except for one, which appears exactly once. Find that single one. Note: Your algo...

2017-07-07 18:53:59

阅读数:205

评论数:0

Single Number

Given an array of integers, every element appears twice except for one. Find that single one. Note: Your algorithm should have a linear runtime compl...

2017-07-07 18:36:52

阅读数:120

评论数:0

Harris角点检测算法

本文的内容基本来源于以下博客,主要是为了方便以后再次学习。 https://sanwen8.cn/p/3edp0eU.html http://blog.csdn.net/newthinker_wei/article/details/45603583 http://blog.csdn.net/c...

2017-06-29 16:32:24

阅读数:362

评论数:0

ORB特征检测算法

论文:ORB: an efficient alternative to SIFT or SURF ORB特征是将FAST特征点检测方法与BRIEF特征描述子结合起来,并针对它们的缺点进行了改进和优化。 FAST特征点检测方法: FAST特征点检测的具体过程,可以参考之前的博客。FAST特征点...

2017-06-27 17:28:52

阅读数:237

评论数:0

FAST角点检测算法

FAST是一种角点检测算法,其思想源于corner的定义,也就是检测候选点周围像素点的像素值,如果候选点周围邻域内有足够多的像素点与该候选点的灰度值差别够大,则认为该候选点为一个特征点。        FAST检测角点的过程:        1. 初步筛选,如下图所示,将像素点P1、P5、P9、P...

2017-06-26 20:10:26

阅读数:593

评论数:0

BRIEF特征描述子

转自:http://www.mamicode.com/info-detail-922469.html 简介          BRIEF是2010年《BRIEF:Binary Robust Independent Elementary Features》的文章中提出,BRIEF是对已检测到的特征...

2017-06-24 19:43:45

阅读数:415

评论数:0

Word Search II

Given a 2D board and a list of words from the dictionary, find all words in the board. Each word must be constructed from letters of sequentially ad...

2017-06-22 21:50:37

阅读数:144

评论数:0

Reverse Words in a String

Given an input string, reverse the string word by word. For example, Given s = "the sky is blue", return "blue is sky the". Updat...

2017-06-22 20:24:42

阅读数:151

评论数:0

Add and Search Word - Data structure design

Design a data structure that supports the following two operations: void addWord(word) bool search(word) search(word) can search a literal word or ...

2017-06-21 11:12:46

阅读数:137

评论数:0

Implement Trie (Prefix Tree)

转自:http://www.cnblogs.com/grandyang/p/4491665.html Implement a trie with insert, search, and startsWith methods. Note: You may assume that all i...

2017-06-21 11:02:04

阅读数:214

评论数:0

基于深度学习的目标检测算法:SSD

SSD: Single Shot MultiBox Detector 问题引入: 目前,常见的目标检测算法,如Faster R-CNN,存在着速度慢的缺点。该论文提出的SSD方法,不仅提高了速度,而且提高了准确度。 SSD: 该论文的核心思想:

2017-06-18 21:07:47

阅读数:66711

评论数:0

caffe中的一些特殊层

Reshape layer layer { name: "reshape" //名称:reshape type: "Reshape" //类型:Reshape bottom: "data&...

2017-06-15 17:33:39

阅读数:1545

评论数:0

图像分割之FCN

论文:Fully Convolutional Networks forSemantic Segmentation 基于caffe的代码:https://github.com/shelhamer/fcn.berkeleyvision.org 反卷积:         在学习FCN之前,需要了解反卷积...

2017-06-14 17:25:34

阅读数:2416

评论数:0

基于深度学习的目标检测算法:YOLO

之前学习的RCNN系列的目标检测算法都是先提取出候选区域,然后利用分类器识别这些区域,并对候选区域进行位置修正。这类方法流程复杂,存在着速度慢、训练困难的等缺点。         YOLO算法将检测问题看做是回归问题,采用单个神经网络,利用整个图像的信息来预测目标的边框、识别目标的类别,实现端到端...

2017-05-27 14:52:38

阅读数:9134

评论数:0

卷积神经网络工程实践技巧

本博客主要参考:http://study.163.com/course/courseLearn.htm?courseId=1003223001#/learn/video?lessonId=1004143071&courseId=1003223001 数据增强: 1. Horizonta...

2017-05-26 16:30:54

阅读数:836

评论数:0

ubuntu16.04配置py-faster-rcnn(CPU版)

Caffe配置: 采用http://blog.csdn.net/u013989576/article/details/56677749配置好caffe py-faster-rcnn配置: 1、下载py-faster-rcnn源码 git clone --recursive https://...

2017-05-23 21:34:54

阅读数:1159

评论数:0

提示
确定要删除当前文章?
取消 删除
关闭
关闭