xuemzhan/BLSTM-CRF-NER

what's your vim config of ~/.

Opened this issue · 0 comments

mldl@ub1604:/ub16_prj/BLSTM-CRF-NER$ python train.py --train data_wordcontext/train.txt
/usr/local/lib/python2.7/dist-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as _register_converters
Model location: ./models/lower=False,zeros=False,char_dim=0,char_lstm_dim=0,char_bidirect=False,word_dim=100,word_lstm_dim=100,word_bidirect=True,pos_dim=0,pos_lstm_dim=0,crf=True,dropout=0.5,lr_method=sgd,lr_rate=0.005,clip_norm=5.0,is_train=1,batch_size=32
Traceback (most recent call last):
File "train.py", line 183, in
train_sentences = loader.load_sentences(opts.train, lower, zeros)
File "/home/mldl/ub16_prj/BLSTM-CRF-NER/loader.py", line 14, in load_sentences
for line in codecs.open(path, 'r', 'utf8'):
File "/usr/lib/python2.7/codecs.py", line 699, in next
return self.reader.next()
File "/usr/lib/python2.7/codecs.py", line 630, in next
line = self.readline()
File "/usr/lib/python2.7/codecs.py", line 545, in readline
data = self.read(readsize, firstline=True)
File "/usr/lib/python2.7/codecs.py", line 492, in read
newchars, decodedbytes = self.decode(data, self.errors)
UnicodeDecodeError: 'utf8' codec can't decode byte 0xb5 in position 0: invalid start byte
mldl@ub1604:
/ub16_prj/BLSTM-CRF-NER$