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
4.68k stars 1.25k forks source link

文件路径问题 #309

Open wangjiaxu opened 4 years ago

wangjiaxu commented 4 years ago

请问为什么在代码中修改路径之后，依旧是默认路径，有评论说要改包，怎么改？

macanv commented 4 years ago

没明白，具体点。

wangjiaxu commented 4 years ago

@macanv 是这样的，运行bert_lstm_ner.py，已经按照readme，在代码中修改了data_dir、checkpoint_dir等路径： if os.name == 'nt': #windows path config bert_path = '{your BERT model path}' root_path = '{project path}' else: # linux path config bert_path = '{your BERT model path}' root_path = '{project path}' 但是在运行代码的时候，依旧是原始的默认路径。我的环境是linux环境，请问该怎么修改？

捕获

asaoba commented 4 years ago

你好，能请问一下 if os.name == 'nt': #windows path config bert_path = '{your BERT model path}' root_path = '{project path}' else: # linux path config bert_path = '{your BERT model path}' root_path = '{project path}' 几行代码在bert_lstm_ner.py的第几行吗，找了半天没找到。。。

ZhouXiaoLeilei commented 4 years ago

你好，能请问一下 if os.name == 'nt': #windows path config bert_path = '{your BERT model path}' root_path = '{project path}' else: # linux path config bert_path = '{your BERT model path}' root_path = '{project path}' 几行代码在bert_lstm_ner.py的第几行吗，找了半天没找到。。。

在bert_base/train/train_helper.py