Dongjun Lee
Dongjun Lee
안녕하세요 @Sejik 님, 우선 좋은 내용 건의해주셔서 감사합니다 :) 현재 `checkpoint` 에 `metrics ` 와 `train_counter` 를 같이 저장하고 있지만, 말씀해주신대로 trainer.py 안으로 연결이 되고 있지 않다보니.. 로드를 해도 숫자들이...
oh, I'll check it. thank you for issuing.
I fixed it. :) pull and try again.
그러게요..! if문들이 너무 많아졌군요 저도 해당 API 문서를 조금 더 살펴봐야할 것 같네요ㅎㅎ 일단 session_level_encoder 의 경우, data_loader 도 같이 준비를 해야하는 부분이라.. 해당 부분들 더 살펴보고 나서 코드 수정하고...
Hi @genz10, Yes it is. If you make a chatbot that automates custom services, you need lots of customer service conversation data. And there will be uncertainty in the answer.
I think 8K data set is not enough, but maybe it can be working. I wonder what your experiment results are. :)
I think that simply solution makes the input sentences are long and it means Increase data sparsity. But you need to try it. Or check this paper : [Building End-To-End...
Maybe that is because of lack of data, it seems to be overfitting to the training data. If you want to get the same results as training data, try doing...
Okay I'll check the codes with tf 1.8 version. Sorry for late comment.
I fixed it. Could you pull latest commit and test it again?