研究如何打通tensorflow线下python脚本训练建模，线上生产环境用C++代码直接调用预先训练好的模型完成预测的工作，而不需要用自己写的Inference的函数。因为目前tensorflow提供的C++的API比较少，所以参考了几篇已有的日志，踩了不少坑一并记录下来。写了一个简单的ANN模型对Iris数据集分类的Demo。

In this blog, we will give you a brief introduction of most recent progress in On-Device Recommendation (Edge Recommendation) in real-world applications. Mobile AI systems and applications have been more popular due to increasing number of mobile devices and technology developments in deep learning based methods, e.g. model compression, distillation and so on. In recent years, on-device recommendations have enpowered many Mobile Apps to better respond to users' most real-time behaviors on mobile deivces, including clicks, scroll-donwns, likes, and many others. We will introduce three applications, including EdgeRec in Taobao, searchbar background words reranking in Alipay, search result reranking in Meituan-Dianping, short-video recommendation in KuaiShou, TfLite Implementation of Tensorflow, etc.

利用tensorflow训练深度神经网络模型需要消耗很长时间，因为并行化计算就为提升运行速度提供了重要思路。Tensorflow提供了多种方法来使程序的并行运行，在使用这些方法时需要考虑的问题有：选取的计算设备是CPU还是GPU，每个CPU多少核的资源并行计算，构建图Graph时消耗资源如何分配等等问题。下面我们以Linux多核CPU的环境为例介绍几种常见方法来提升你的tensorflow程序的运行速度。