小甲鱼python教程第15-17讲动动手解答

说明：  TensorFlow 不是一个严格的“神经网络”库。只要你可以将你的计算表示为一个数据流图，你就可以使用Tensorflow。你来构建图，描写驱动计算的内部循环。我们提供了有用的工具来帮助你组装“子图”（常用于神经网络）(Build and train ML models easily using intuitive high-level APIs like Keras with eager execution, which makes for immediate model iteration and easy debugging.)

用卷积神经网络（CNN）实现人脸识别，效果还可以，一个是training的程序，可以训练网络。一个是use程序，可以识别人脸(Using convolution neural network (CNN) to achieve face recognition, the effect is also available, one is the training program, can train the network. One is a use program that recognizes a face)

利用人工智能RNN进行数据预测分析，效果还可以(Using artificial intelligence RNN to carry out data prediction and analysis, the effect is also possible.)

采用PIL 和pytesser进行简单的验证码识别 程序包中已经包含了pytesser，但是需要自己安装PIL 使用样例 getverify1( v1.jpg ) 返回值为识别出的字符(To PIL and pytesser simple identification code validation package already contains pytesser, but need to install PIL using the sample getverify1 (' v1.jpg' ) return value identifies the character)

说明：  《Python数据挖掘入门与实践》高清中文版 本书作为数据挖掘入门读物，介绍了数据挖掘的基础知识、基本工具和实践方法，通过循序渐进地讲解算法，带你轻松踏上数据挖掘之旅。本书采用理论与实践相结合的方式，呈现了如何使用决策树和随机森林算法预测美国职业篮球联赛比赛结果，如何使用亲和性分析方法推荐电影，如何使用朴素贝叶斯算法进行社会媒体挖掘，等等。本书也涉及神经网络、深度学习、大数据处理等内容。本书面向愿意学习和尝试数据挖掘的程序员。("Python Data Mining Getting Started and Practice" HD Chinese version As a primer on data mining, this book introduces the basic knowledge, basic tools and practical methods of data mining. By step-by-step explanation of the algorithm, you can easily embark on the journey of data mining. This book uses a combination of theory and practice, showing how to use the decision tree and random forest algorithm to predict the results of the American professional basketball league game, how to use the affinity analysis method to recommend movies, how to use the naive Bayesian algorithm for social media mining ,and many more. This book also covers neural networks, deep learning, big data processing and more. This book is for programmers who are willing to learn and experiment with data mining.)

说明：  python语言实现多项式秘密分享，并且可以用拉格朗日插值恢复(Python language implements polynomial secret sharing and can be restored by Lagrange interpolation)

说明：  双目立体视觉标定以及立体匹配参考图片，可用于立体标定，图像校正，立体匹配算法验证(Binocular stereo vision calibration and stereo matching reference pictures can be used for stereo calibration, image correction and stereo matching algorithm verification)

minst手写数字数据集

unet用于图像分割（model.py）

电力远程运维系统源代码，为了满足配电房的监控系统的要求，达到对供电房的全方位监控，使有关人员做出反应，采取措施，并对相关设备进行集中监控、集中维护和集中管理。(Electric power remote maintenance system source code, in order to meet the monitoring system of power distribution room requirements, to achieve all-round monitoring of the power supply of housing, so that the staff response measures and related equipment for centralized monitoring, centralized management and maintenance.)