Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

model 第282行 #149

Open
jichangzhen opened this issue Aug 10, 2019 · 2 comments
Open

model 第282行 #149

jichangzhen opened this issue Aug 10, 2019 · 2 comments

Comments

@jichangzhen
Copy link

model.py 第282行,为什么assert len(final_dists)==1，fina_dists应该是解码序列吧，怎么可能等于1？等于1的话，不相当于每次摘要只有一个字？？？
@nlp4whp
Copy link

nlp4whp commented Aug 15, 2019

model.py 第282行,为什么assert len(final_dists)==1，fina_dists应该是解码序列吧，怎么可能等于1？等于1的话，不相当于每次摘要只有一个字？？？

decode阶段是单步执行的，每次只取序列中的一个词，只有执行了这一步才能获得当前state

@jijibongsky
Copy link

model.py 第282行,为什么assert len(final_dists)==1，fina_dists应该是解码序列吧，怎么可能等于1？等于1的话，不相当于每次摘要只有一个字？？？

In beam_search.py replace while steps < 100 and len(results) < FLAGS.beam_size: instead while steps < FLAGS.max_dec_steps and len(results) < FLAGS.beam_size:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@jijibongsky @jichangzhen @nlp4whp