##安装MJPG-streamer
-
安装依赖 sudo apt-get updatesudo sudo apt-get install subversion sudo apt-get install libjpeg8-dev sudo apt-get install imagemagick sudo apt-get install libv4l-dev sudo apt-get install cmake sudo apt-get install git
-
下载项目
sudo git clone github.com/jacksonliam/mjpg-streamer.git cd mjpg-streamer/mjpg-streamer-experimentalsudo make all sudo make install
指令启动普通USB摄像头指令:
./mjpg_streamer -i "./input_uvc.so" -o "./output_http.so -w ./www"
启动树莓派专用摄像头RaspiCamera的指令:
./mjpg_streamer -i "./input_raspicam.so" -o "./output_http.so -w ./www"
https://blog.csdn.net/LIEVE_Z/article/details/79551628
https://blog.csdn.net/m0_38106923/article/details/86562451
https://blog.csdn.net/qq_41204464/article/details/83098603 有一个现成的轮子,pistreaming: sudo apt-get install libav-tools git python3-picamera python3-ws4py git clone https://github.com/waveform80/pistreaming.git $ cd pistreaming $ python3 server.py
https://github.com/yueritian/RaspberryPi_SmartCarV1/blob/master/templates/index.html 控制
资料 https://www.cnblogs.com/darkcircle/articles/9327537.html https://blog.csdn.net/u011426247/article/details/80551749 c++s https://blog.csdn.net/u012736685/article/details/77131633 c++s https://blog.csdn.net/Mr_Curry/article/details/52347797 <<<<<<< HEAD
使用spark 运行ros 运行模拟
测试数据集 www.cvlibs.net/datasets/kitti/
knowlege of MASK-RCNN traffic segment reconignzs
http://blog.csdn.net/AdamShan/article/details/78248421?locationNum=7&fps=1
http://blog.csdn.net/AdamShan/article/details/78265754?locationNum=2&fps=1
https://github.com/udacity/CarND-Extended-Kalman-Filter-Project/tree/master/src
http://blog.csdn.net/lybaihu/article/details/54943545?locationNum=8&fps=1
http://blog.csdn.net/weixin_37239947/article/details/74939650处理
- 卡尔曼公式 http://bilgin.esme.org/BitsAndBytes/KalmanFilterforDummies https://blog.csdn.net/heyijia0327/article/details/44033751 python + opencv: kalman 跟踪 http://www.cnblogs.com/gaoxiang12/p/5175118.html rgb-d salm
https://blog.csdn.net/heyijia0327/article/details/17487467
https://blog.csdn.net/heyijia0327/article/details/17487467
https://blog.csdn.net/liaoshenglan/article/details/78484851
https://github.com/jeasinema/VoxelNet-tensorflow
https://github.com/koryako/selfcarRaspberryPi https://github.com/priya-dwivedi
Canny 原理 http://www.pclcn.org/study/shownews.php?lang=cn&id=111 http://www.opencv.org.cn/opencvdoc/2.3.2/html/doc/tutorials/imgproc/imgtrans/canny_detector/canny_detector.html?highlight=canny#canny
http://selfdrivingcars.mit.edu/resources
三角剖分的算法比较成熟。目前有很多的库(包括命令行的和GUI的可以用)。
常用的算法叫Delaunay Triangulation,具体算法原理见 http://www.cnblogs.com/soroman/archive/2007/05/17/750430.html
这里收集一些开元的做可以测试三角剖分的库
- Shewchuk的http://www.cs.cmu.edu/~quake/triangle.html,据说效率非常高!
- MeshLab http://www.cs.cmu.edu/~quake/triangle.html,非常易于上手,只要新建工程,读入三维坐标点,用工具里面的Delaunay Trianglulation来可视化就好了。而且它是开源的!具体教程去网站上找吧。
- Qhull http://www.qhull.org/
- PCL库,http://pointclouds.org/documentation/tutorials/greedy_projection.php
无序点云快速三角化
http://www.pclcn.org/study/shownews.php?lang=cn&id=111
opencv 基本操作 https://segmentfault.com/a/1190000003742422
cv 到cv2的不同 http://www.aiuxian.com/article/p-395730.html
已经fork https://github.com/mbeyeler/opencv-machine-learning
前言
https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/00.00-Preface.ipynb
机器学习的味道
在OpenCV中使用数据
使用Python的NumPy软件包处理数据 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/02.01-Dealing-with-Data-Using-Python-NumPy.ipynb 在Python中加载外部数据集 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/02.02-Loading-External-Datasets-in-Python.ipynb 使用Matplotlib可视化数据 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/02.03-Visualizing-Data-Using-Matplotlib.ipynb 使用OpenCV的TrainData容器处理数据 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/02.05-Dealing-with-Data-Using-the-OpenCV-TrainData-Container-in-C%2B%2B.ipynb 监督学习的第一步
用评分功能测量模型性能 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/03.01-Measuring-Model-Performance-with-Scoring-Functions.ipynb 了解k-NN算法 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/03.02-Understanding-the-k-NN-Algorithm.ipynb 使用回归模型预测持续成果 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/03.03-Using-Regression-Models-to-Predict-Continuous-Outcomes.ipynb 应用拉索和岭回归 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/03.04-Applying-Lasso-and-Ridge-Regression.ipynb 使用Logistic回归分类虹膜物种 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/03.05-Classifying-Iris-Species-Using-Logistic-Regression.ipynb 代表数据和工程特性
预处理数据 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/04.01-Preprocessing-Data.ipynb 减少数据的维度 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/04.02-Reducing-the-Dimensionality-of-the-Data.ipynb 代表分类变量 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/04.03-Representing-Categorical-Variables.ipynb 表示文本特征 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/04.04-Represening-Text-Features.ipynb 代表图像 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/04.05-Representing-Images.ipynb 使用决策树进行医学诊断
建立你的第一决策树 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/05.01-Building-Your-First-Decision-Tree.ipynb 使用决策树诊断乳腺癌 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/05.02-Using-Decision-Trees-to-Diagnose-Breast-Cancer.ipynb 使用决策树回归 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/05.03-Using-Decision-Trees-for-Regression.ipynb 用支持向量机检测行人
实施您的第一支持向量机 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/06.01-Implementing-Your-First-Support-Vector-Machine.ipynb 检测野外行人 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/06.02-Detecting-Pedestrians-in-the-Wild.ipynb 附加SVM练习 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/06.03-Additional-SVM-Exercises.ipynb 用贝叶斯学习实现垃圾邮件过滤器
实现我们的第一个贝叶斯分类器 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/07.01-Implementing-Our-First-Bayesian-Classifier.ipynb 分类电子邮件使用朴素贝叶斯 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/07.02-Classifying-Emails-Using-Naive-Bayes.ipynb 用无监督学习发现隐藏的结构
了解k均值聚类 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/08.01-Understanding-k-Means-Clustering.ipynb 使用k-Means压缩彩色图像 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/08.02-Compressing-Color-Images-Using-k-Means.ipynb 使用k-Means分类手写数字 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/08.03-Classifying-Handwritten-Digits-Using-k-Means.ipynb 实施聚集层次聚类 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/08.04-Implementing-Agglomerative-Hierarchical-Clustering.ipynb 使用深度学习分类手写数字
了解感知器 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/09.01-Understanding-Perceptrons.ipynb 在OpenCV中实现多层感知器 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/09.02-Implementing-a-Multi-Layer-Perceptron-in-OpenCV.ipynb 认识深度学习 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/09.03-Getting-Acquainted-with-Deep-Learning.ipynb 在OpenCV中培训MLP以分类手写数字 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/09.04-Training-an-MLP-in-OpenCV-to-Classify-Handwritten-Digits.ipynb 训练深层神经网络使用Keras分类手写数字 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/09.05-Training-a-Deep-Neural-Net-to-Classify-Handwritten-Digits-Using-Keras.ipynb 将不同的算法合并成一个合奏
了解组合方法 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/10.01-Understanding-Ensemble-Methods.ipynb 将决策树组合成随机森林 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/10.02-Combining-Decision-Trees-Into-a-Random-Forest.ipynb 使用随机森林进行人脸识别 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/10.03-Using-Random-Forests-for-Face-Recognition.ipynb 实施AdaBoost https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/10.04-Implementing-AdaBoost.ipynb 将不同的模型组合成投票分类器 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/10.05-Combining-Different-Models-Into-a-Voting-Classifier.ipynb 使用超参数调整选择正确的模型
评估模型 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/11.01-Evaluating-a-Model.ipynb 了解交叉验证,Bootstrapping和McNemar的测试 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/11.02-Understanding-Cross-Validation-Bootstrapping-and-McNemar's-Test.ipynb 使用网格搜索调整超参数 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/11.03-Tuning-Hyperparameters-with-Grid-Search.ipynb 链接算法一起形成管道 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/11.04-Chaining-Algorithms-Together-to-Form-a-Pipeline.ipynb 结束语
https://github.com/tensorflow/models/tree/master/object_detection mobilenet
https://research.googleblog.com/2017/06/mobilenets-open-source-models-for.html
带有MobileNets的SSD(Single Shot Multibox Detector)
带有Inception V2的SSD
带有Resnet 101的R-FCN(Region-based Fully Convolutional Networks)
带有Resnet 101的 Faster RCNN
带有Inception Resnet v2的Faster RCNN
https://github.com/tensorflow/tensorflow/commit/055500bbcea60513c0160d213a10a7055f079312
mobil net https://github.com/tensorflow/models/tree/master/inception 准备数据 https://github.com/zehaos/MobileNet
https://github.com/balancap/SSD-Tensorflow
2017.9
https://github.com/udacity/CarND-Term1-Starter-Kit 环境配置
http://blog.csdn.net/xukai871105/article/details/39255089 树莓派mqtt
https://github.com/priya-dwivedi
Canny 原理 http://www.pclcn.org/study/shownews.php?lang=cn&id=111 http://www.opencv.org.cn/opencvdoc/2.3.2/html/doc/tutorials/imgproc/imgtrans/canny_detector/canny_detector.html?highlight=canny#canny
http://selfdrivingcars.mit.edu/resources
三角剖分的算法比较成熟。目前有很多的库(包括命令行的和GUI的可以用)。
常用的算法叫Delaunay Triangulation,具体算法原理见 http://www.cnblogs.com/soroman/archive/2007/05/17/750430.html
这里收集一些开元的做可以测试三角剖分的库
- Shewchuk的http://www.cs.cmu.edu/~quake/triangle.html,据说效率非常高!
- MeshLab http://www.cs.cmu.edu/~quake/triangle.html,非常易于上手,只要新建工程,读入三维坐标点,用工具里面的Delaunay Trianglulation来可视化就好了。而且它是开源的!具体教程去网站上找吧。
- Qhull http://www.qhull.org/
- PCL库,http://pointclouds.org/documentation/tutorials/greedy_projection.php
无序点云快速三角化
http://www.pclcn.org/study/shownews.php?lang=cn&id=111
opencv 基本操作 https://segmentfault.com/a/1190000003742422
cv 到cv2的不同 http://www.aiuxian.com/article/p-395730.html
已经fork https://github.com/mbeyeler/opencv-machine-learning
前言
https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/00.00-Preface.ipynb
机器学习的味道
在OpenCV中使用数据
使用Python的NumPy软件包处理数据 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/02.01-Dealing-with-Data-Using-Python-NumPy.ipynb 在Python中加载外部数据集 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/02.02-Loading-External-Datasets-in-Python.ipynb 使用Matplotlib可视化数据 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/02.03-Visualizing-Data-Using-Matplotlib.ipynb 使用OpenCV的TrainData容器处理数据 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/02.05-Dealing-with-Data-Using-the-OpenCV-TrainData-Container-in-C%2B%2B.ipynb 监督学习的第一步
用评分功能测量模型性能 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/03.01-Measuring-Model-Performance-with-Scoring-Functions.ipynb 了解k-NN算法 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/03.02-Understanding-the-k-NN-Algorithm.ipynb 使用回归模型预测持续成果 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/03.03-Using-Regression-Models-to-Predict-Continuous-Outcomes.ipynb 应用拉索和岭回归 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/03.04-Applying-Lasso-and-Ridge-Regression.ipynb 使用Logistic回归分类虹膜物种 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/03.05-Classifying-Iris-Species-Using-Logistic-Regression.ipynb 代表数据和工程特性
预处理数据 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/04.01-Preprocessing-Data.ipynb 减少数据的维度 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/04.02-Reducing-the-Dimensionality-of-the-Data.ipynb 代表分类变量 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/04.03-Representing-Categorical-Variables.ipynb 表示文本特征 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/04.04-Represening-Text-Features.ipynb 代表图像 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/04.05-Representing-Images.ipynb 使用决策树进行医学诊断
建立你的第一决策树 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/05.01-Building-Your-First-Decision-Tree.ipynb 使用决策树诊断乳腺癌 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/05.02-Using-Decision-Trees-to-Diagnose-Breast-Cancer.ipynb 使用决策树回归 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/05.03-Using-Decision-Trees-for-Regression.ipynb 用支持向量机检测行人
实施您的第一支持向量机 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/06.01-Implementing-Your-First-Support-Vector-Machine.ipynb 检测野外行人 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/06.02-Detecting-Pedestrians-in-the-Wild.ipynb 附加SVM练习 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/06.03-Additional-SVM-Exercises.ipynb 用贝叶斯学习实现垃圾邮件过滤器
实现我们的第一个贝叶斯分类器 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/07.01-Implementing-Our-First-Bayesian-Classifier.ipynb 分类电子邮件使用朴素贝叶斯 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/07.02-Classifying-Emails-Using-Naive-Bayes.ipynb 用无监督学习发现隐藏的结构
了解k均值聚类 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/08.01-Understanding-k-Means-Clustering.ipynb 使用k-Means压缩彩色图像 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/08.02-Compressing-Color-Images-Using-k-Means.ipynb 使用k-Means分类手写数字 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/08.03-Classifying-Handwritten-Digits-Using-k-Means.ipynb 实施聚集层次聚类 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/08.04-Implementing-Agglomerative-Hierarchical-Clustering.ipynb 使用深度学习分类手写数字
了解感知器 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/09.01-Understanding-Perceptrons.ipynb 在OpenCV中实现多层感知器 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/09.02-Implementing-a-Multi-Layer-Perceptron-in-OpenCV.ipynb 认识深度学习 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/09.03-Getting-Acquainted-with-Deep-Learning.ipynb 在OpenCV中培训MLP以分类手写数字 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/09.04-Training-an-MLP-in-OpenCV-to-Classify-Handwritten-Digits.ipynb 训练深层神经网络使用Keras分类手写数字 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/09.05-Training-a-Deep-Neural-Net-to-Classify-Handwritten-Digits-Using-Keras.ipynb 将不同的算法合并成一个合奏
了解组合方法 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/10.01-Understanding-Ensemble-Methods.ipynb 将决策树组合成随机森林 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/10.02-Combining-Decision-Trees-Into-a-Random-Forest.ipynb 使用随机森林进行人脸识别 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/10.03-Using-Random-Forests-for-Face-Recognition.ipynb 实施AdaBoost https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/10.04-Implementing-AdaBoost.ipynb 将不同的模型组合成投票分类器 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/10.05-Combining-Different-Models-Into-a-Voting-Classifier.ipynb 使用超参数调整选择正确的模型
评估模型 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/11.01-Evaluating-a-Model.ipynb 了解交叉验证,Bootstrapping和McNemar的测试 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/11.02-Understanding-Cross-Validation-Bootstrapping-and-McNemar's-Test.ipynb 使用网格搜索调整超参数 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/11.03-Tuning-Hyperparameters-with-Grid-Search.ipynb 链接算法一起形成管道 https://github.com/mbeyeler/opencv-machine-learning/blob/master/notebooks/11.04-Chaining-Algorithms-Together-to-Form-a-Pipeline.ipynb 结束语
https://github.com/tensorflow/models/tree/master/object_detection mobilenet
https://research.googleblog.com/2017/06/mobilenets-open-source-models-for.html
带有MobileNets的SSD(Single Shot Multibox Detector)
带有Inception V2的SSD
带有Resnet 101的R-FCN(Region-based Fully Convolutional Networks)
带有Resnet 101的 Faster RCNN
带有Inception Resnet v2的Faster RCNN
https://github.com/tensorflow/tensorflow/commit/055500bbcea60513c0160d213a10a7055f079312
mobil net https://github.com/tensorflow/models/tree/master/inception 准备数据 https://github.com/zehaos/MobileNet
https://github.com/balancap/SSD-Tensorflow
2017.9
https://github.com/udacity/CarND-Term1-Starter-Kit 环境配置
http://blog.csdn.net/xukai871105/article/details/39255089 树莓派mqtt
https://github.com/udacity/CarND-LaneLines-P1/blob/master/P1.ipynb
交通识别问题,行人识别,目标追踪
目标检测
- 传统方法 a.2001 paul viola 和Micahel jones 鲁棒实时目标检测 的 viola-jones 框架
b.梯度直方图 Hog
2.深度学习 a. overFeat 利用卷积 多尺度窗口滑动 b. r-cnn 选择性搜索 selective Search 提取可能目标;使用cnn 在该区域上提取特征;向量机分类 c. fast-rcnn 选择性搜索,cnn 提取特征, 区域兴趣池化 Region of interest ,ROI; 反向传播做分类和边框回归 d. yolo e. faster-rcnn cnn 提取特征;regio Proosal network 根据物体的分数来输出可能的目标;区域兴趣池化 Region of interest ,ROI pooling; 反向传播做分类和边框回归 f. SSd 在yolo 上改进,使用了多尺度特征图 g。 R-fcn 使用了 Faster-Rcnn的架构 https://tryolabs.com/blog/ 3.数据集 imageNet coco Pascal VOC Oxford-IIIT Pet kitti Vision
http://www.dev-c.com/nativedb/
github.com/osrf/car_demo
https://github.com/openai/roboschool
gym.openai.com
https://github.com/DartEnv/ddart-env
https://github.com/openai/baselines
目标跟踪
http://www.cs.cityu.edu.hk/~yibisong/iccv17/index.html convolutional Residual learning for visual tracking
pytorch caffe2 cntk 之间模型转换用onnx格式 github.com/onnx/onnx
github.com/nottombrown/rl-teacher https://github.com/nottombrown/rl-teacher.git
https://github.com/aleju/self-driving-truck
https://pan.baidu.com/s/1pL9J4Cz ros book
https://github.com/qboticslabs/ros_robotics_projects
https://cps-vo.org/group/CATVehicleTestbed/wiki
github.com/tigerneil/deep-reinforcement-learning-family
https://github.com/tigerneil/awesome-deep-rl
https://github.com/facebookresearch/ELF 开源游戏平台
https://github.com/tensorflow/models/blob/master/slim/nets/mobilenet_v1.md
问题一 cyclegan 学习深度信息 A 数据集 http://www.europe.naverlabs.com/Research/Computer-Vision/Proxy-Virtual-Worlds
https://github.com/LMescheder/AdversarialVariationalBayes
http://aaronsplace.co.uk/papers/jackson2017recon/ 平面头像到3d头像
http://blog.csdn.net/ling3ye/article/details/51351115 使用Arduino与L298N(红板) 驱动直流电机
https://github.com/NicolleLouis/geneticAlgorithm/blob/master/passwordTuto 遗传算法
http://rednuht.org/genetic_cars_2/ 进化游戏
https://www.codingame.com/home 遗传比赛
http://play.google.com/store/apps/details?id=com.keiwando.Evolution
https://arxiv.org/pdf/1708.07303.pdf 感知3d物体 3d特征 物理感知 交互
http://blog.csdn.net/crzy_sparrow/article/details/7407604 光流测速
http://blog.csdn.net/crzy_sparrow/article/details/7398904
http://www.cnblogs.com/Leo_wl/p/5852010.html neat
https://github.com/FernandoTorres/NEAT c++
https://en.wikipedia.org/wiki/HyperNEAT
https://github.com/CodeReclaimers/neat-python ok
https://github.com/neat-python/neat-python
https://github.com/koryako/neat neat api
jinwan git clone git@github.com:reinforceio/tensorforce.git
https://github.com/rlcode/reinforcement-learning
distributional_perspective_on_RL
DDPG-keras-torcs
BDD_Driving_Model
C51DQN
baselines
TensorFlow Agents