提交 81abcdea 编写于 作者: R ranqiu

Refine dot_product_attention

上级 2e1cd331
......@@ -1476,10 +1476,8 @@ def dot_product_attention(encoded_sequence,
expand_as=encoded_sequence,
name='%s_expand' % name)
m = linear_comb_layer(
weights=expanded,
vectors=encoded_sequence,
name='%s_dot-product' % name)
m = dot_prod_layer(
input1=expanded, input2=encoded_sequence, name='%s_dot-product' % name)
attention_weight = fc_layer(
input=m,
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册