search

macanv / BERT-BiLSTM-CRF-NER

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
https://github.com/macanv/BERT-BiLSMT-CRF-NER
4.71k stars 1.26k forks source link

f1值为0 #268

Closed ademolyk closed 4 years ago

ademolyk commented 4 years ago

您好，ner任务，更改了标签，训练过程无异常，训练完后precision,recall, f1值都为0，烦请有时间看一哈

ademolyk commented 4 years ago

1684A36B0B2F071D4DD2666EE1D8A986

ademolyk commented 4 years ago

@macanv 类似于这种。麻烦dalao了

ademolyk commented 4 years ago

已解决，可能是参数原因吧， 我用5个epoch跑就是全部是0，30个epoch跑，在90%左右基于实体标注的数量。

qzd147 commented 4 years ago

楼主你好，我也遇到了这个问题，用自己的数据跑完结果全是0，用的是10个epoch，增加epoch次数真的可以吗？