IUST-Thesis

dSPACE培训教程入门，控制系统半实物仿真的最好工具学习资料(dSPACE training module entry, the control system of the best semi-physical simulation tool for learning materials)

说明：  iot security challenge

第一讲 CST微波工作室的简单使用和操作训练(The first lecture CST Microwave Studio simple use and operation training)

说明：  很强大的孤子引论书籍，值得一读，非常非常非常非常好。(Very strong soliton Introduction of books, worth reading, very very very very good.)

面向对象技术ＵＭＬ教程以及 ＵＭＬ基础、案例与应用的详细讲解Unified Modeling Language Reference Manual (Object-oriented technology and UML Tutorial UML basis for the application of the case and explain in detail the Unified Modeling Language Reference Manual)

其实编程的时候也要很多数学知识，所以学习好高数是必不可少的，这本题解包括知识摘要和大量习题题解，可快速吸收(In fact, when the programming will still take many mathematical knowledge, it is good to learn a high number is essential, including knowledge of this problem solution Problem title abstracts and a large number of solutions, can quickly absorb)

界面美化控件，可以提高界面的美观程度，使用方便(Interface, landscaping controls, can improve the level of the interface appearance, easy to use)

几篇关于机器学习的PPT课件。A few PPT coursewares about machine learning.(A few PPT coursewares about machine learning.)

这是自考资料！通过复习 ，好好复习。祝各位好运。(This is the Self item! Through review, good review. I wish you good luck.)

A commented bash script to generate our final 2nd place solution can be found in make_kaggle_solution.sh. Running all the commands sequentially will probably take 7 - 10 days on recent consumer grade hardware. If you have multiple GPUs you can speed things up by doing training and feature extraction for the two networks in parallel. However, due to the computationally heavy data augmentation it may be far less than twice as fast especially when working with 512x512 pixel input images. You can also obtain a quadratic weighted kappa score of 0.839 on the private leaderboard by just training the 4x4 kernel networks and by performing only 20 feature extraction iterations with the weights that gave you the best MSE validation scores during training. The entire ensemble only achieves a slightly higher score of 0.845.