dssm model gragh.py forward（） logits = tf.concat([pos_result, neg_result], axis=1) there why pos_result put forward? Is wrong? - Githubissues

terrifyzhao / text_matching

常用文本匹配模型tf版本，数据集为QA_corpus，持续更新中

Apache License 2.0

673 stars 188 forks source link

dssm model gragh.py forward（） logits = tf.concat([pos_result, neg_result], axis=1) there why pos_result put forward? Is wrong? #6

Open yangyan1227 opened 5 years ago

yangyan1227 commented 5 years ago

dssm model gragh.py forward（） logits = tf.concat([pos_result, neg_result], axis=1) there why pos_result put forward? Is wrong?