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

Is value must be linear transformed at multi-head attention? #170

Open

GuoYL36 opened this issue Feb 23, 2021 · 0 comments

GuoYL36 commented Feb 23, 2021 •

edited

Loading

In the paper, Attention is All You Need, query, key, value are linear transformed at the multi-head attention.
`

    Q = tf.layers.dense(queries, d_model, use_bias=True) # (N, T_q, d_model)

    K = tf.layers.dense(keys, d_model, use_bias=True) # (N, T_k, d_model)

    V = tf.layers.dense(values, d_model, use_bias=True) # (N, T_k, d_model)

`
And I want to know whether value must be linear transformed at multi-head attention?

The text was updated successfully, but these errors were encountered:

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