Javen_陈俊文

icon indicating a website link https://applenob.github.io icon indicating an email [email protected]

icon location San Jose icon location Think with First Principle

Results 3 comments of Javen_陈俊文

关于 initial_fn,sample_fn,next_inputs_fn 三个函数的介绍 求助

decoder的output是每个词的概率,具体要生成哪个词,可以采用不同的策略.直接选择概率最大的,就是greedy,还可以用beam search的策略,可以了解下。decoder中把每一个时刻产生的输出重新embedding，作为下一个时刻的输入之一。至于你说的keys()问题，谢谢指出，有时间我会修改下。

Do you think you could translate your .md file in english ?

Hi Steven, Thank you for your interest in this project. I will provide an English version of README and update the code a little bit. It will cost several days...

Hi, I have some question about intent hope you could reply me.

Yes you are right. I didn't use attention in the classification model. I would add this part or you can commit your code if you like. Thank you for pointing...