siamese-lstm-for-sentence-similarity

siamese-lstm-for-sentence-similarity copied to clipboard

建不同的model,单纯是为了区分is_training吗？可是is_training后面定义的东西也并不影响什么啊，似乎没必要区分

manhongxiang

sentence embedding

1

hi, as the author say, the sentence embedding should be the output of the final step, it's conflict with the your code——reduce_sum

xwzhong

pre_train的意义

2

up主你好，我看了下代码，了解了model的大致框架。不太明白为何有一个pre_train的过程，是为了给模型的参数一个初始化么？

charmpeng