灰色关联分析法

SVM做的验证码识别，准确率85%# -*- coding: utf-8 -* __author__ = "eple" from svmutil import * from PIL import Image from numpy import * import os import string def getFeatures(path): features = [] im = array(Image.open(path).convert("L")) h,w = shape(im) for i in xrange(0,h): for j in xrange(0,w): im[i][j] = 0 if im[i][j] < 128 else 1 for i in xrange(1,h-1): for j in xrange(1,w-1): if im[i][j] != 0 and im[i-1][j]==0 and im[i][j-1]==0 and im[i][j+1]==0 and im[i+1][j]==0: im[i][j] = 0 for rang in [xrange(2,8), xrange(12,18), xrange(22,28), xrange(32,38)]: temp = [] for i in rang: for j in xrange(0,10): temp.append(im[j][i]) features.append(temp) return features

BP神经网络-Python实现：经典的BP神经网络通常由三层组成: 输入层， 隐含层与输出层.通常输入层神经元的个数与特征数相关，输出层的个数与类别数相同， 隐含层的层数与神经元数均可以自定义。

这是一个利用python语言，基于维基百科语料库的word2vec词向量模型的训练，用非常主流的算法实现文本形式向计算机能够识别的形式的转换，然后用于文本分类

py game sample sample game for biginners

Python高性能编程，本书适合初级和中级Python程序员、有一定Python语言基础想要得到进阶和提高的读者阅读。(Python High Performance Programming)

说明：  利用sklearn下的序回归算法拟合风速和功率的关系。运行之前将pv1.csv路径更改一下。(The relationship between wind speed and power is fitted by the order regression algorithm under sklearn. Change the pv1.csv path before running.)

说明：  人工智能 caffe 用与ssd yolo(Artificial intelligence SSD Yolo)

说明：  完成对cmw500测试仪器的程控及初始化操作(Novice is currently in the learning stage. CMW500 GSM non-signaling test program example, including initialization)

python实现人脸识别，通过pca进行降维然后使用SVM算法进行分类(Python realizes face recognition, dimensionality reduction through pca and classification by SVM algorithm)

A class to help start/stop the PyWebSocket server used by layout tests for Andriod.