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

why do query-masking after softmax? #54

Closed

HaishuoFang opened this issue Oct 18, 2018 · 0 comments

HaishuoFang commented Oct 18, 2018

transformer/modules.py

Line 237 in 6672f93

query_masks = tf.sign(tf.abs(tf.reduce_sum(queries, axis=-1))) # (N, T_q)

This masking can do before softmax, just like key masking,why do this operation after softmax? I cannot understand

HaishuoFang changed the title ~~query masking can do before softmax?~~ why do query-masking after softmax?

HaishuoFang closed this as completed

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