deeplabv2 tensorflow 分割代码实现

说明：  神经网络与深度学习课后习题代码，编程案列(Neural Network and Deep Learning Exercise Code, Programming List)

说明：  python 爬虫实战。爬取JMLR（Journal of Machine Learning Research ）期刊中的所有论文的信息（title， author， abs， url等）。要解析xpath，处理字符编码等。(Python Crawler. Crawl all the papers in JMLR (Journal of Machine Learning Research) journals (title, author, abs, url, etc.))

说明：  使用python中的opensilde库对tiff格式图片进行分割。(TIFF format image segmentation.)

softmaxregression，即多分类的逻辑斯特回归算法，python编写(softmaxregression, namely multi-classification logistic regression algorithm, python write)

计算股票MACD技术指标的相关函数并作图。。。。(Stock Technical indicators MACD computing correlation functions and plotted. . . .)

【实例简介】

使用python脚本，实现了下载糗事百科上的图片的功能。定义了500页，怎么也够用了吧。程序主题简单，主要是用到了sgmllib模块和urllib2模块。压缩包内包括了几张运行下载的图片。

本文是2016 台湾资料科学年会前导课程“一天搞懂深度学习”的全部讲义PPT（共268页），由台湾大学电机工程学助理教授李宏毅主讲。作者在文中分四个部分对神经网络的原理、目前存在形态以及未来的发展进行了介绍。深度学习的每一个核心概念在文中都有相关案例进行呈现，通俗易懂。一天的时间搞懂深度学习？其实并不是没有可能。(This is the entire handout PPT (268 pages in total) of "a day to understand deep learning", the leading course of the 2016 Taiwan annual conference of data science. It was given by li hongyi, assistant professor of electrical engineering at Taiwan university.In this paper, the author introduces the principle, existing form and future development of neural network in four parts.Each core concept of deep learning is presented in relevant cases, which are easy to understand.)

SVM-无监督机器学习领域的经典算法，在神经网络未出现前，他是机器学习的顶梁柱，现在依然用处广泛，而且其核函数的使用范围早已超脱其本身，该实例对SVM算法进行了实现，具有相应的数据集。(SVM - Unsupervised machine learning in the field of classical algorithms, before the neural network does not appear, he is the mainstay of machine learning, is still still widely used, and the use of its kernel function has long been out of its own, the example of the SVM algorithm was implemented , With the corresponding data set.)

在计算机视觉中，加速鲁棒特征（冲浪）是一种局部特征检测器和描述符，可以用于任务，如物体识别或注册或分类或三维重建。部分的灵感来自于尺度不变特征变换（筛选）描述符。标准版的冲浪是好几倍的速度