why add a Dense(64) layer after the attention layer

philipperemy / keras-attention

Keras Attention Layer (Luong and Bahdanau scores).

Apache License 2.0

2.8k stars 675 forks source link

Closed dengziheng closed 4 years ago

dengziheng commented 5 years ago

what's the point of adding another attention_mul = Dense(units=64)(attention_mul) ?

philipperemy commented 4 years ago

I removed this code as it is now deprecated. I updated the code reflecting https://github.com/philipperemy/keras-attention-mechanism/issues/14.