bi-lstm-crf
bi-lstm-crf copied to clipboard
jidasheng
A PyTorch implementation of the BI-LSTM-CRF model.
您好，我在尝试一次预测多个句子的时候报错了，代码如下： tags, sequences = model(["句子1","句子2",...]) 请问可以支持这种调用方式吗，会不会快一点呢？
For the training of NN, it is known that dropout improves the performance. I added the dropout module to the embedding, the LSTM output, and LSTM layers. Also, I revised...
I figured out the problem. When the sentence has all token as "O" the `_tokens` method creates begins with one extra position causing the index out of range in `ts[idx]`....
Interesting. If I change the tags, can I use it for finding technical attributes? Also, can it predict unseen words and sentences? Or does it only predict the words in...
Since 1.6.0 torch requires explicit transitions of tensors between cpu and gpu memory, resulting in errors during training. Add explicit conversions to make model compatible with newer pytorch versions.
When launching the WordTagger with device = 'cpu' the class throws an error: ``` WordsTagger( basepath, device='cpu') ``` ``` File "C:\Users\MarcoOdore\agilelab\MultiLegalSBD-master\models.py", line 613, in __init__ self.tagger = WordsTagger( File "C:\Users\MarcoOdore\agilelab\MultiLegalSBD-master\venv\lib\site-packages\bi_lstm_crf\app\predict.py",...
