charlesfufu

> @FrankWork i think the original paper didn't use test data but use the eval data which divided from train data You codes don't have the train or test data,So...

已解决 发自我的iPhone ------------------ 原始邮件 ------------------ 发件人: lsy641 发送时间: 2019年7月10日 19:27 收件人: macanv/BERT-BiLSTM-CRF-NER 抄送: charlesfufu , Author 主题: 回复：[macanv/BERT-BiLSTM-CRF-NER] 如何变训练边输出损失loss? (#175)

> 不好意思，暂时没有开源的打算，baseline的话，[这个](https://github.com/JavisPeng/ecg_pytorch)已经写得很好了 > > 关于数据分析和模型，PPT里已经介绍得很详细了 能分享一下数据吗？baseline的数据也缺失啊。没有提供label也无法训练

> Hi, `file` is only in Python 2.7X, and your python version is 3.6. You can try replace `file` into `open`  How about this one?

> The training phase should be in this way in the terminal: > > ``` > python main_sem.py train > ``` > If you run code in IDE (e.g., Pycharm)...

def train(**kwargs):  Where is the value of the parameter?

> The normal output of main_sem should be: >  > > Maybe the environment difference? Maybe you should upgrade your program with python3

> > The normal output of main_sem should be: > >  > > Maybe the environment difference? > > Maybe you should upgrade your program with python3  I...

> OK, I will update my code with Python3.X. > You can change `config.py` Line 66: > > ``` > .iteritems() -> .items() > ``` > Maybe there will be...

> > > The normal output of main_sem should be: > > >  > > > Maybe the environment difference? > > > > > > Maybe you should...