search

Determined22 / zh-NER-TF

A very simple BiLSTM-CRF model for Chinese Named Entity Recognition 中文命名实体识别 (TensorFlow)
2.33k stars 937 forks source link

您好，请问我在替换为自己的数据的时候出现数据读取为0，train_path可以获取但是train_data为0，是咋回事 #105

Open handsomeTeng opened 5 years ago

handsomeTeng commented 5 years ago

（我自己print出来的train_path.txt文件） .\data_path\train_data.txt （自己print train_data.txt 文件为空） [] Namespace(CRF=True, batch_size=64, clip=5.0, demo_model='1521112368', dropout=0.5, embedding_dim=300, epoch=5, hidden_dim=300, lr=0.001, mode='train', optimizer='Adam', pretrain_embedding='random', shuffle=True, test_data='data_path ', train_data='data_path', update_embedding=True) C:\Users\le\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\gradients_impl.py:112: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of me mory. "Converting sparse IndexedSlices to a dense Tensor of unknown shape. " train data: 0 （train_data值为0）

handsomeTeng commented 5 years ago

估计是你数据格式不对

tongbao96 commented 4 years ago

你的解决了吗 我的也是0