Skip to content

multihead_attention #17

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

multihead_attention #17

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion modules.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -247,7 +247,10 @@ def multihead_attention(queries,

# Restore shape
outputs = tf.concat(tf.split(outputs, num_heads, axis=0), axis=2 ) # (N, T_q, C)


# Linear projections
outputs = tf.layers.dense(outputs, num_units, activation=tf.nn.relu) # (N, T_q, C)
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think you are right about an extra projection, but can I ask about the activation function here? seems in the original paper there is no bias and activation, only a plain "Concat(head1, ..., headh)W_O"


# Residual connection
outputs += queries

Expand Down