根据deep_neural_networks_for_youtube_recommendations文章用tensorflow搭建dnn，然后用org.tensorflow加载模型并用spark预测

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Referenz-Implementierung eines CNN mittels C++ ohne Parallelisierung.

The gflags package contains a C++ library that implements commandline flags processing. It includes built-in support for standard types such as string and the ability to define flags in the source …

你还在学CMake的过程中毫无头绪吗？你还在为复杂程序库依赖发愁吗？你是否觉得原生CMake的编写冗余而低效？那就快来学习和使用PICMake吧！只需要一行，无论是可执行，动态库还是静态库，轻松搞定！同时高效支持多目标，复杂库的编译安装，从此告别大量冗余CMake代码，专注开发核心应用程序，编译不再愁！ 例如下面是使用PICMake编译一个依赖OpenGL的可执行文件，只需要一行！

CTR prediction using FM FFM and DeepFM

PArallel Distributed Deep LEarning

Tensorflow implementation of DeepFM for CTR prediction.

cublas examples

Spark SQL functions and operations in PySpark

LAPACK development repository

code of paper `Deep Neural Networks for Youtube Recommendation`

我的学习资料，包括书籍、网址等

The GNU Scientific Library (GSL) is a numerical library for C and C++ programmers.