alimeituan

大佬你好， 1.我个人理解是这个p(T)是模型的某种分布 2.我也没看懂怎么测试的，甚至训练怎么进行的都不清楚，至少文章中的图没有复现，代码不对应

hello, please see my problem, thx https://github.com/dpressel/rude-carnie/issues/102

I know this ,but not easy as you said

几百M的模型能加载进去吗？？？手机不会黑屏、闪退？

hi, could you please tell me how to get the dataset ?thanks

有预训练好的模型吗？

@arosh1909 Dear, could U get the real pitch by using the projects ? could U run the main.cpp ? Thx

I have a question, in the main.cpp how could I give the wav file name to the main function, and how to set the parameters, const int nParams = 2?...

hi,dear have you tried the movielens-1M data with the FFM method ? if you could read Chinese,you can see my test [here](https://iggcas.blog.csdn.net/article/details/106422194) thx

hi,dear, could you have the kinetics400 datasets ? or just look the issue https://github.com/yjxiong/temporal-segment-networks/issues/278 or tell me the configure/distribution ？ see the [issue](https://github.com/mit-han-lab/temporal-shift-module/issues/43)