You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When training, we pad all sentences as max sentence length, then tf.reduce_mean(sentence_embeddings, axis=1) means sum/(max sentence length). How could it know the length of each sentence?
Thanks!
The text was updated successfully, but these errors were encountered:
2.average vectors, to get representation of the sentence
self.sentence_embeddings = tf.reduce_mean(sentence_embeddings, axis=1) # [None,self.embed_size]
When training, we pad all sentences as max sentence length, then tf.reduce_mean(sentence_embeddings, axis=1) means sum/(max sentence length). How could it know the length of each sentence?
Thanks!
The text was updated successfully, but these errors were encountered: