关节点检测和聚类

利用三层卷积神经网络识别信号星座图，准确识别8psk，16psk，32psk，64qpsk四种调制方式，在低信噪比的情况下已然有良好的识别率。(The three layer convolution neural network is used to identify signal constellation, and accurately identify four modulation modes of 8PSK, 16PSK, 32psk and 64qpsk. It has a good recognition rate under low SNR.)

说明：  双目匹配计算视差，生成深度图。（前提是用自己标定好的摄像头拍的图片，导入内外参数然后进行立体匹配）(Binocular matching calculates parallax and generates depth map.(The premise is to take a picture with your own calibrated camera, import internal and external parameters, and then stereo matching))

说明：  在TEXGEN中利用python生成随机三维编织构型(Random 3d braided configurations are generated by python in TEXGEN)

Python script to do an unattended reboot of the Telecom Speedport W921V, included is the mechanize package to install in a debian Linux system.

采用全连接神经网络对012345的手势图片进行识别，基于Pytorch编写，附h5格式数据集

Tom Rondeau SDR class presentation 2 on filters and filtering - sample GNU Radio scripts and simulation code in python

k近邻分类算法①编写一个简单的程序，实现k近邻算法；(重点)②利用k近邻算法实现手写数字的识别。Spyder运行python源码

说明：  直接调用sklearn自带的iris数据集，自带的决策数算法，然后生成可视化决策树，用了最少的代码完成分类任务。(Directly call the iris data set and decision number algorithm of sklearn, then generate a visual decision tree, and complete the classification task with the least code.)

时间序列python代码实现，运行调试时间序列python代码

开普勒望远镜观察星星的光通量，包括5000条训练数据和400多条测试数据。可用机器学习算法进行训练测试，验证算法的可行性。