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

有没有把输入端的<pad>给mask掉？ #12

Open

zgahhblhc opened this issue Jan 22, 2019 · 1 comment

zgahhblhc commented Jan 22, 2019 •

edited

Loading

在使用tf.contrib.legacy_seq2seq.embedding_attention_seq2seq()进行训练时，并没有提供输入句子的长度，这意味着每一个pad也都被当作一个token被输入进encoder了？请问有没有把输入端多余的pad给mask掉？

还有，想问一下输入端为何要倒序输入？

yjyGo commented Apr 14, 2019

代码注释里面说明，麻烦先看清楚代码

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment