longlongman

https://longlongman.github.io

AI for Drugs, Bioinformatics, NLP

Results 16 comments of


                                            longlongman

Why the corpus is already tokenized？

Yes, the corpus I have already tokenized.

why randomly select one subject in data_loader.py

In the original code of CasRel model, the subject is also selected randomly.

计算subject向量均值的问题

我记得在原论文中，模型只是预测实体的开始位置与结束位置

看起来每个样本只是用了一个sub以及其对应的obj

如果训练步数足够多，那基本上每个sub都会被采样到的

请问keras-bert的版本和tensorflow-gpu的版本是多少呢？

和苏神的配置是一致的

The provided environment yaml for SE3nv installs pytorch-cpu version, when the installed cuda version is not 11.1

A statement in the README will be helpful. 😊

‹
1
2