tensorflow官方代码教程

如果您是第一次提交源代码，请先参考提交的代码；

python组合优化工具包                                                                                                                                                                

熵权法根据各指标的变异程度，利用信息熵计算出各指标的熵权，再通过熵权对各指标的权重进行修正，从而得出较为客观的指标权重。(According to the variation degree of each index, the entropy weight of each index is calculated by using information entropy, and then the weight of each index is revised by the entropy weight, thus objectively obtaining the weight of each index.)

说明：  利用python写的简单降噪程序（根据一个点A的RGB值，与周围的8个点的RBG值比较，设定一个值N（0

说明：  遗传算法、禁忌搜索、模拟退火、蚁群算法 解决三十个城市的旅行商问题 人工智能课的一次作业，py写的，(Genetic algorithm, Tabu search, simulated annealing, Ant Colony algorithm to solve the traveling Salesman problem in 30 cities, an artificial intelligence class assignment, written by py,)

说明：  基础的强化学习Q-learning算法，对初学者对Q-learning算法得理解比较有帮助，程序包括运行脚本，Q-learning算法脚本以及环境脚本。(Basic reinforcement learning Q-learning algorithm is helpful for beginners to understand Q-learning algorithm. Programs include running script, Q-learning algorithm script and environment script.)

MATLAB 结巴分词的工具包，用于很多中文分词的模式识别代码程序，利用已有函数工具包提高工作效率，内有安装说明(MATLAB jieba toolkit, used for many Chinese word segmentation pattern recognition code programs, using existing function toolkits to improve work efficiency, with installation instructions)

故障检测，分别是pls和pca，计算spe和t2控制量。(Fault detection is pls and PCA, respectively, to calculate SPE and T2 control.)

说明：  日志模块，日志记录，适用于所有程序，可直接调用。(Logging module, log recording)

说明：  针对数据集较少导致人体动作识别率较低的情况，基于生成对抗网络搭建了一个人体动作识别网络，有效解决了以上问题(In view of the low recognition rate of human motion caused by the lack of data set, a human motion recognition network is built based on the generated countermeasure network, which effectively solves the above problems)