Pytorch跑bert情感分类报错，TypeError: get_variable_scope() got an unexpected keyword argument 'name'

Question

Traceback (most recent call last):
File "F:/WorkShop/BERT_Chinese_Classification/run_classifier.py", line 1036, in
tf.app.run()
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\tensorflow\python\platform\app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\absl\app.py", line 312, in run
_run_main(main, args)
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\absl\app.py", line 258, in _run_main
sys.exit(main(argv))
File "F:/WorkShop/BERT_Chinese_Classification/run_classifier.py", line 935, in main
estimator.train(input_fn=train_input_fn, max_steps=num_train_steps)
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\tensorflow_estimator\python\estimator\tpu\tpu_estimator.py", line 3110, in train
rendezvous.raise_errors()
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\tensorflow_estimator\python\estimator\tpu\error_handling.py", line 150, in raise_errors
six.reraise(typ, value, traceback)
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\six.py", line 703, in reraise
raise value
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\tensorflow_estimator\python\estimator\tpu\tpu_estimator.py", line 3100, in train
return super(TPUEstimator, self).train(
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\tensorflow_estimator\python\estimator\estimator.py", line 349, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\tensorflow_estimator\python\estimator\estimator.py", line 1175, in _train_model
return self._train_model_default(input_fn, hooks, saving_listeners)
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\tensorflow_estimator\python\estimator\estimator.py", line 1203, in _train_model_default
estimator_spec = self._call_model_fn(features, labels, ModeKeys.TRAIN,
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\tensorflow_estimator\python\estimator\tpu\tpu_estimator.py", line 2941, in _call_model_fn
return super(TPUEstimator, self)._call_model_fn(features, labels, mode,
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\tensorflow_estimator\python\estimator\estimator.py", line 1163, in _call_model_fn
model_fn_results = self._model_fn(features=features, **kwargs)
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\tensorflow_estimator\python\estimator\tpu\tpu_estimator.py", line 3199, in _model_fn
estimator_spec = model_fn_wrapper.call_without_tpu(
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\tensorflow_estimator\python\estimator\tpu\tpu_estimator.py", line 1729, in call_without_tpu
return self._call_model_fn(features, labels, is_export_mode=is_export_mode)
File "E:\Anaconda\Install\envs\pytorch\lib\site-packages\tensorflow_estimator\python\estimator\tpu\tpu_estimator.py", line 2072, in _call_model_fn
estimator_spec = self._model_fn(features=features, **kwargs)
File "F:/WorkShop/BERT_Chinese_Classification/run_classifier.py", line 697, in model_fn
(total_loss, per_example_loss, logits, probabilities) = create_model(
File "F:/WorkShop/BERT_Chinese_Classification/run_classifier.py", line 631, in create_model
model = modeling.BertModel(
File "F:\WorkShop\BERT_Chinese_Classification\modeling.py", line 175, in init
(self.embedding_output, self.embedding_table) = embedding_lookup(
File "F:\WorkShop\BERT_Chinese_Classification\modeling.py", line 411, in embedding_lookup
embedding_table = tf.compat.v1.get_variable_scope(
TypeError: get_variable_scope() got an unexpected keyword argument 'name'

Answer 1

你好，我是有问必答小助手，非常抱歉，本次您提出的有问必答问题，超出我们目前的服务范围，暂时无法为您解答。

问答VIP目前服务范围为 ：Python、Java、MySQL、Redis、MongoDB、HBase、Zookeeper、Kafka、Linux领域专业问题解答，为您提供解决问题的思路和指导。 不提供源码代写、项目文档代写、论文代写、作业代写、安装包资源发送或安装指导等服务。

本次提问扣除的有问必答次数，已经为您补发到账户，我们后续会持续优化，扩大我们的服务范围，为您带来更好地服务。