thunlp / Chinese_NRE

Source code for ACL 2019 paper "Chinese Relation Extraction with Multi-Grained Information and External Linguistic Knowledge"
MIT License
269 stars 43 forks source link

请问您的batch_size怎么调。。 #3

Closed T1aNS1R closed 5 years ago

ningding97 commented 5 years ago

No description provided.

你好,由于本模型实际上在不同数据的结构是不统一的,因此没法用batch训练,现在batch size只能为1。若您有兴趣优化这方面,可以自行研究