关闭

NP

deterministic P NP NP-complete problemsreducibility of algorithm NP-completeNP (for nondeterministic polynomial time) is a complexity class used to describe certain types of decision problems.determini...
阅读(2) 评论(0)

borel集

sigma代数 borel 集 测度σ\sigma代数σ\sigma代数是一个集合组,对于这个集合组满足三个条件: 1. 空集属于这个集合组 2. 若A属于,那么A的补集也属于 3. 对于一个集合序列,若它们都属于,那么它们的极限也属于对于一个集合X,它的最小的σ\sigma代数是空集和它本身组成的集合组,最大的集合组是它的所有子集组成的集合组。borel 集https://en.wikipe...
阅读(7) 评论(0)

8086的内存分段机制 内存寻址

保护模式下寻址 段机制实例分析如图,8086内部有8个16位寄存器,AX BX CX DX SI DI BP SP为了加快指令执行速度,8086内部有一个6字节的指令预取队列,当处理器执行不需要访问内存的指令时,指令预取部件访问内存预取指令。8086有4个段寄存器 CS DS ES IP,当一段代码开始执行时,CS指向代码段的起始地址,IP指向段内偏移。CS:IP共同形成逻辑地址,并由总线接口部件来...
阅读(2) 评论(0)

深入理解linux内核-ch02

1 内存编址 2 段机制-硬件 21 段选择器和段寄存器 22 段描述符 23 Fast Access to Segment Descriptors 24 Segmentation Unit 3 Segmentation in Linux2.1 内存编址我们通过 memory address 来得到内存的内容,对于8086处理器,需要区分三种地址: 1. 逻辑地址:每个逻辑地址包含一个 段 和一...
阅读(36) 评论(0)

深入理解linux内核-ch02

Ch02 Memory Addressing 1 Memory Addresses 2 Segmentation in Hardware Segment Selectors and Segmentation Registers 22 Segment Descriptors 23 Fast Access to Segment Descriptors Segmentaion Unit 3 Segment...
阅读(15) 评论(0)

深入理解linux内核-ch01

4 5 An Overview of the Unix Filesystem 52 Hard and Soft Links 53 File Types 54 File Descriptor and Inode 55 Access Rights and File Mode 56 File-Handling System Calls 561 Opening a file 562 Accessing an...
阅读(14) 评论(0)

泊松过程 Possion Process 伯努利过程

Introduction The Bernoulli Process 相互独立 无记忆 Interarrival Times 到达时距 The kthk_th Arrival Time Splitting and Merging of Bernoulli Process The Possion Approximation to the Binomial The Possion Process Num...
阅读(12) 评论(0)

java网络编程读书笔记-Ch04 05

Internet Addresses链接上网的设备被称为 nodes. Nodes that are computers are called hosts.Domain Name System (DNS)The InetAddress Classjava.net.InetAddressThe java.net.InetAddress class is Java’s high-level repres...
阅读(20) 评论(0)

tensorflow slim layers

arg_scopeTFDecorator一个提供了 __get__, __call__tf_contextlib相当于python的上下文管理器 A tf_decorator-aware wrapper for contextlib.contextmanager. Usage is identical to contextlib.contextmanagerarg_scope(list_ops_...
阅读(37) 评论(0)

apue读书笔记-Ch04(2)

# 4.9 `chmod, fchmod fchmodat` Functions#include int chmod(const char *pathname, mode_t mode); int fchmod(int fd, mode_t mode); int fchmodat(int fd, const char *pathname, mode_t mode, int...
阅读(14) 评论(0)

ImageNet Classification with Deep Convolutional Neural Networks -- 解读

论文解读先稍微翻译下数据集ImageNet 有各种分辨率的图片,我们需要固定大小的。所以,向下取样到 256 * 256。除此之外没有别的预处理。 ImageNet consists of variable-resolution images, while our system requires a constant input dimen- sionality. Therefore, we do...
阅读(22) 评论(0)

java网络编程读书笔记-Ch03

java network programming...
阅读(24) 评论(0)

Inception v1 论文及源码

论文解读 Network-in-network R-CNN Multivation and High Level Considerations Architectural Details 源码分析 函数 Going deeper with convolutions Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scot...
阅读(24) 评论(0)

java网络编程读书笔记-Ch02

Streams同步的streams需要等待读写完毕,才能继续做别的 Streams are synchronous; that is, when a program (really a thread) asks a stream to read or write a piece of data, it waits for the data to be read or written before...
阅读(22) 评论(0)

apue读书笔记-Ch04

1 Introduction 2 stat fstat fstatat lstat Functions c语言中关键字restrict的用法 3 File Types Set-User-ID and Set-Group-ID File access permission 6 Ownership of New Files and Directories 7 access an...
阅读(17) 评论(0)

arg_scope 解读

共享变量 变量作用域 理解tfget_variable tfvariable_scope 变量作用域的初始化器 tfvariable_scope中ops的名称 arg_scope共享变量http://wiki.jikexueyuan.com/project/tensorflow-zh/how_tos/variable_scope.html变量作用域变量作用域机制在TensorFlow中主要由两部分组...
阅读(19) 评论(0)

tf.contrib.slim

tfcontrib tfcontribslim 介绍 arg_scope data evaluation layers learning losses metrics nets queues regularizers variables tfcontribslimpythonnetstf.contribtf.contrib包下是一些非官方的文件,代码的更改和删除不会被通知。 这个包下提供的特性在将...
阅读(25) 评论(0)

Show and Tell Lessons learned from the 2015 MSCOCO Image Captioning Challenge论文及tensorflow源码解读(2)

Source code build_model build_image_embeddingsSource codebuild_modelbuild_image_embeddings在建立了图片和caption的输入后,这部分将图片转换为固定大小的tensor,就像论文提及的,使用已经用很大的数据集训练好的深度网络模型,不改变它的参数,直接用于特征提取。首先将图片丢入inception v3网络中,得...
阅读(27) 评论(0)

Threading and Queues -- Tensorflow

Threading and Queues Queue Queue的使用 Coordinator QueueRunner Handling ExceptionsThreading and QueuesQueueQueues 用于异步计算 Queues are a powerful mechanism for asynchronous computation using TensorFlow....
阅读(18) 评论(0)

Weakly supervised object recognition with convolutional neural networks 论文解读

1. Model Overview1.1 什么是weakly supervised learninghttps://stackoverflow.com/questions/18944805/what-is-weakly-supervised-learning-bootstrappingIn short: In weakly supervised learning, you use a limited...
阅读(24) 评论(0)
22条 共2页1 2 下一页 尾页
    个人资料
    • 访问:392次
    • 积分:212
    • 等级:
    • 排名:千里之外
    • 原创:19篇
    • 转载:1篇
    • 译文:2篇
    • 评论:0条
    文章存档