suriyadeepan / practical_seq2seq

A simple, minimal wrapper for tensorflow's seq2seq module, for experimenting with datasets rapidly
http://suriyadeepan.github.io/2016-12-31-practical-seq2seq/
GNU General Public License v3.0
570 stars 270 forks source link

Same reply for all questions #69

Open Robin131 opened 5 years ago

Robin131 commented 5 years ago

I have trained a model based on the code and found that no matter what sentence I took as input, the model will always give the same thing. Like I input 'I am having dinner', the model gives 'i dont know'. I input 'You are amazing bro', it also gives 'i dont know'. I tried a lot but the reply always remains the same. Why does this problem occur?