xuanzebi / bert-ch-ner Goto Github PK

View Code? Open in Web Editor NEW

395.0 395.0 101.0 1.74 MB

基于BERT的中文命名实体识别

Python 84.28% Jupyter Notebook 15.57% Shell 0.15%

bert deeplearning ner nlp

bert-ch-ner's Introduction

Hi there 👋

努力变强

bert-ch-ner's People

Contributors

Stargazers

Watchers

Forkers

scottishfold007 dumplingximen wangleiai xwyfct moonlione echolotus joydajunspacecraft wzs951015 helen0804 donaldjohn allensun951 leichen9 cuitengfei2006x lzhan011 casually-pylearner ctcome yiyepiaoling0715 wuwenjie1012 qianrenjian 18106574249 bijibing tianyikenan 1615070057 wynmew szhl skywd aiedward 3sunny zhangshuo1996 chenshangzhi12315 tony1236 fangfang22-oss qiaoxiaosong wkangblog hungita nick-2008 yanshaoyun jennacheung jonxia sunriver wttc xykdsg sxrczh zongke-zjut rosemultiflora sanghy youngjt keithgao flyrainkey zf617707527 yinjqing xrosliang xiaoqis0821 beidou-1 danrann liuyuru156 626607233 listwebit ooco123 ymjs-irfan lizhaofu ivanzrf crazysadclown hanjiacheng xkyoung leoliner yubuyuabc isyinun thzll2001 runtianchen jadensha advancer-debug immense8342 geektemo yayuzhou williamtalk trancywang cytsinghua hoho35 nicemartin bboliwa hui-ze liqiandi lxz1992 2389540652 kofd-zdd yxuansu af-74413592 lumin115 linhong00316 zk1056309462 cainiaoluo charminghuang savagelob chz367 algorithm-learning-community-for-python shouqingchen1 yale1417 happ7ape vdsmitnov52

bert-ch-ner's Issues

loss不考虑padsequece的情况？

one_hot_labels = tf.one_hot(labels, depth=num_labels, dtype=tf.float32)
per_example_loss = -tf.reduce_sum(one_hot_labels * log_probs, axis=-1)
loss = tf.reduce_sum(per_example_loss)
probabilities = tf.nn.softmax(logits, axis=-1)

log_prob是[batch_size, max_seq, label_num]维度， max_seq有pad，直接reduce_sum全部作为loss？

预测结果

run_NER.py文件执行
训练后：
--task_name=NER --do_train=true --do_eval=false --do_predict=false --data_dir=C:\Users\xiezx\Desktop\临时\BERT-CH-NER-master\tmp\ --vocab_file=C:\Users\xiezx\Desktop\souhu\data\chinese_L-12_H-768_A-12\vocab.txt --bert_config_file=C:\Users\xiezx\Desktop\souhu\data\chinese_L-12_H-768_A-12\bert_config.json --init_checkpoint=C:\Users\xiezx\Desktop\souhu\data\chinese_L-12_H-768_A-12\bert_model.ckpt --max_seq_length=256 --train_batch_size=16 --learning_rate=2e-5 --num_train_epochs=3.0 --output_dir=C:\Users\xiezx\Desktop\souhu\data\chinese_L-12_H-768_A-12\output\

进行预测：
--task_name=NER --do_train=false --do_eval=false --do_predict=true --data_dir=C:\Users\xiezx\Desktop\临时\BERT-CH-NER-master\tmp\ --vocab_file=C:\Users\xiezx\Desktop\souhu\data\chinese_L-12_H-768_A-12\vocab.txt --bert_config_file=C:\Users\xiezx\Desktop\souhu\data\chinese_L-12_H-768_A-12\bert_config.json --init_checkpoint=C:\Users\xiezx\Desktop\souhu\data\chinese_L-12_H-768_A-12\bert_model.ckpt --max_seq_length=256 --train_batch_size=16 --learning_rate=2e-5 --num_train_epochs=3.0 --output_dir=C:\Users\xiezx\Desktop\souhu\data\chinese_L-12_H-768_A-12\output\

生成的文件test_prediction.txt内容貌似有问题吧？？？（前5行）
[CLS] [CLS] O [CLS] B-PER O [CLS] O O O I-LOC O O [CLS] I-ORG B-ORG I-ORG [CLS] [CLS] I-ORG [CLS] [CLS] B-PER [CLS] [CLS] I-LOC [CLS] I-ORG [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-LOC I-ORG [CLS] I-LOC I-LOC I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-LOC I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-LOC [CLS] [CLS] I-LOC I-LOC I-LOC [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG I-LOC I-LOC I-LOC [CLS] I-LOC [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-LOC [CLS] I-LOC I-LOC I-ORG I-ORG [CLS] [CLS]
I-LOC [CLS] I-PER O I-ORG B-PER B-PER O O I-ORG I-ORG I-ORG I-PER I-PER O I-LOC O O O O [CLS] O [CLS] O O O B-LOC I-LOC I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] I-ORG I-ORG I-LOC I-LOC I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-LOC I-LOC [CLS] I-LOC [CLS] I-LOC [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG I-LOC I-ORG I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG [CLS] [CLS] I-ORG I-ORG I-ORG I-ORG I-LOC I-LOC [CLS] I-LOC I-LOC I-LOC I-LOC [CLS] [CLS] I-ORG [CLS] [CLS] I-ORG I-LOC I-ORG I-ORG I-ORG B-PER [CLS] I-ORG [CLS] I-ORG [CLS] I-ORG [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG B-PER [CLS] I-ORG [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] I-ORG [CLS] I-ORG I-ORG I-ORG I-ORG [CLS] I-ORG I-ORG I-ORG [CLS] I-ORG [CLS] B-PER I-ORG I-LOC I-LOC I-LOC I-LOC I-LOC I-LOC I-LOC [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-LOC I-ORG I-LOC I-LOC I-LOC I-ORG [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG [CLS] [CLS] I-ORG I-ORG B-PER I-ORG I-ORG I-ORG I-LOC I-ORG I-LOC [CLS] [CLS] [CLS] I-LOC I-LOC I-LOC I-LOC I-LOC [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] B-PER B-PER [CLS] B-PER I-LOC B-PER [CLS] B-PER I-LOC I-LOC I-LOC I-LOC I-LOC [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG
[CLS] [CLS] [CLS] B-PER I-PER I-ORG O I-ORG B-ORG I-ORG [CLS] [CLS] O [CLS] O [CLS] [CLS] [CLS] [CLS] B-PER [CLS] [CLS] B-ORG [CLS] [CLS] B-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] B-ORG [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] I-ORG [CLS] I-ORG [CLS] I-ORG [CLS] I-ORG [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG [CLS] [CLS]
[CLS] [CLS] I-LOC I-ORG I-ORG B-LOC [CLS] B-ORG [CLS] I-LOC B-LOC [CLS] [CLS] I-PER [CLS] [CLS] O I-ORG I-ORG B-ORG O O [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] B-PER I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] B-PER [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG [CLS] I-ORG [CLS] [CLS] I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] B-PER B-PER [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] I-ORG B-PER I-ORG B-PER [CLS] I-ORG [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] B-PER B-PER B-PER [CLS] B-PER B-PER [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS]
I-LOC [CLS] B-PER B-PER [CLS] O O B-ORG [CLS] O O O O O B-ORG O [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] I-ORG B-PER [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] B-PER B-PER I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] I-ORG [CLS] I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] B-PER I-ORG I-ORG I-ORG I-ORG I-ORG I-ORG [CLS] [CLS] I-ORG [CLS] I-ORG I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG I-ORG [CLS] I-ORG I-ORG [CLS] I-ORG [CLS] [CLS] I-ORG [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS] I-ORG B-PER [CLS] I-ORG [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] [CLS] I-ORG [CLS]

感谢

感觉作者的代码对我这个小白修改很有启发，特来道谢。

模型保存时为什么报错啊？

你好，我在按照原来的说明跑模型时，在模型保存时报错，是什么原因呢？应该怎么解决呢？谢谢！

具体如下：

Caused by op 'save/SaveV2', defined at:
File "run_NER_self.py", line 949, in
tf.app.run()
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "run_NER_self.py", line 818, in main
estimator.train(input_fn=train_input_fn, max_steps=num_train_steps)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 2394, in train
saving_listeners=saving_listeners
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 356, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1181, in _train_model
return self._train_model_default(input_fn, hooks, saving_listeners)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1215, in _train_model_default
saving_listeners)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1406, in _train_with_estimator_spec
log_step_count_steps=self._config.log_step_count_steps) as mon_sess:
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 504, in MonitoredTrainingSession
stop_grace_period_secs=stop_grace_period_secs)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 921, in init
stop_grace_period_secs=stop_grace_period_secs)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 643, in init
self._sess = _RecoverableSession(self._coordinated_creator)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 1107, in init
_WrappedSession.init(self, self._create_session())
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 1112, in _create_session
return self._sess_creator.create_session()
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 800, in create_session
self.tf_sess = self._session_creator.create_session()
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 557, in create_session
self._scaffold.finalize()
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 215, in finalize
self._saver.build()
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1106, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1143, in _build
build_save=build_save, build_restore=build_restore)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 778, in _build_internal
save_tensor = self._AddShardedSaveOps(filename_tensor, per_device)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 369, in _AddShardedSaveOps
return self._AddShardedSaveOpsForV2(filename_tensor, per_device)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 343, in _AddShardedSaveOpsForV2
sharded_saves.append(self._AddSaveOps(sharded_filename, saveables))
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 284, in _AddSaveOps
save = self.save_op(filename_tensor, saveables)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 202, in save_op
tensors)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/ops/gen_io_ops.py", line 1690, in save_v2
shape_and_slices=shape_and_slices, tensors=tensors, name=name)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3272, in create_op
op_def=op_def)
File "/home/wonders/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1768, in init
self._traceback = tf_stack.extract_stack()

ResourceExhaustedError (see above for traceback): output/model.ckpt-1000_temp_ed8fcc6441604ae3a7ee161177b6171e/part-00000-of-00001.data-00000-of-00001.tempstate14792103910954023694; No space left on device
[[{{node save/SaveV2}} = SaveV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](save/ShardedFilename, save/SaveV2/tensor_names,

分词后的 tag问题

Person 原来是 B-PER 分词后是 Per ##son 那么他的tag应该是什么
这个哪里有说明么

注意事项中手动处理数据问题

在输入【叩问澳门 =- =- =- 贺澳门回归进入倒计时】这个数据的时候报错，你这边说的手动处理是直接删除吗？

运行报错

你好。
在训练刚开始报错，训练数据是tmp里的数据。
File "run_NER.py", line 505, in convert_single_example
assert len(label_id) == max_seq_length
AssertionError
len(label_id)的长度比max_seq_length小1，但是有的差的比较多。

coreEntityEmotion_train.txt数据集还有吗？

有的话，发我邮箱[email protected]，谢谢。

标注工具

你好，请问你是用什么标注工具标注的bio呢

运行环境问题

老哥，你的电脑配置是多少？我不管用win还是ubuntu跑你的代码（run_NER.py）、卡死以后就报错了。！16G的内存

为什么计算loss时不过滤掉PAD tokens？

这里可以在计算loss的时候将padding部分mask掉。

不过当时写的时候因为padding部分idx 为 0，所以在计算loss的时候影响不太大，就没考虑mask.
@xuanzebi 您好，
为什么padding部分的label id=0，在计算loss的时候影响不大？这时one-hot标签向量第0维是1吧

Originally posted by @zdgithub in #6 (comment)

Assertion label_id==max_seq_length报错

在输出完实验结果后，打印的label显示50 36 少了14个label
报错是 assert_len(label_id) == max_seq_length
请问如何解决谢谢。

请问为什么eval时会报错？

tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: Shapes of all inputs must match: values[0].shape = [512] != values[1].shape = [10]
[[node confusion_matrix_1/stack_1 (defined at /tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/ops.py:1748) ]]
[[ConstantFoldingCtrl/confusion_matrix_2/assert_less/Assert/AssertGuard/Switch_0/_1364]]
(1) Invalid argument: Shapes of all inputs must match: values[0].shape = [512] != values[1].shape = [10]
[[node confusion_matrix_1/stack_1 (defined at /tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/ops.py:1748) ]]