尝试在Jupyter笔记本中训练模型时出现以下错误：
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Error reported to Coordinator: <class 'SystemError'>, <built-in function TF_Run> returned a result with an error set
INFO:tensorflow:Saving checkpoints for 0 into /tmp/tmpodutz9be/model.ckpt.
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
TypeError: expected bytes, float found
During handling of the above exception, another exception occurred:
SystemError Traceback (most recent call last)
<ipython-input-12-44daeaf784e5> in <module>()
----> 1 model.train(input_fn=input_func,steps=200)
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py in train(self, input_fn, hooks, steps, max_steps)
239 hooks.append(training.StopAtStepHook(steps, max_steps))
240
--> 241 loss = self._train_model(input_fn=input_fn, hooks=hooks)
242 logging.info('Loss for final step: %s.', loss)
243 return self
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/estimator/estimator.py in _train_model(self, input_fn, hooks)
684 loss = None
685 while not mon_sess.should_stop():
--> 686 _, loss = mon_sess.run([estimator_spec.train_op, estimator_spec.loss])
687 return loss
688
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/training/monitored_session.py in __exit__(self, exception_type, exception_value, traceback)
532 if exception_type in [errors.OutOfRangeError, StopIteration]:
533 exception_type = None
--> 534 self._close_internal(exception_type)
535 # __exit__ should return True to suppress an exception.
536 return exception_type is None
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/training/monitored_session.py in _close_internal(self, exception_type)
567 finally:
568 try:
--> 569 self._sess.close()
570 finally:
571 self._sess = None
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/training/monitored_session.py in close(self)
809 if self._sess:
810 try:
--> 811 self._sess.close()
812 except _PREEMPTION_ERRORS:
813 pass
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/training/monitored_session.py in close(self)
906 self._coord.join(
907 stop_grace_period_secs=self._stop_grace_period_secs,
--> 908 ignore_live_threads=True)
909 finally:
910 try:
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/training/coordinator.py in join(self, threads, stop_grace_period_secs, ignore_live_threads)
387 self._registered_threads = set()
388 if self._exc_info_to_raise:
--> 389 six.reraise(*self._exc_info_to_raise)
390 elif stragglers:
391 if ignore_live_threads:
~/.local/lib/python3.5/site-packages/six.py in reraise(tp, value, tb)
691 if value.__traceback__ is not tb:
692 raise value.with_traceback(tb)
--> 693 raise value
694 finally:
695 value = None
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/estimator/inputs/queues/feeding_queue_runner.py in _run(self, sess, enqueue_op, feed_fn, coord)
92 try:
93 feed_dict = None if feed_fn is None else feed_fn()
---> 94 sess.run(enqueue_op, feed_dict=feed_dict)
95 except (errors.OutOfRangeError, errors.CancelledError):
96 # This exception indicates that a queue was closed.
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
893 try:
894 result = self._run(None, fetches, feed_dict, options_ptr,
--> 895 run_metadata_ptr)
896 if run_metadata:
897 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1122 if final_fetches or final_targets or (handle and feed_dict_tensor):
1123 results = self._do_run(handle, final_targets, final_fetches,
-> 1124 feed_dict_tensor, options, run_metadata)
1125 else:
1126 results = []
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1319 if handle is None:
1320 return self._do_call(_run_fn, self._session, feeds, fetches, targets,
-> 1321 options, run_metadata)
1322 else:
1323 return self._do_call(_prun_fn, self._session, handle, feeds, fetches)
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1325 def _do_call(self, fn, *args):
1326 try:
-> 1327 return fn(*args)
1328 except errors.OpError as e:
1329 message = compat.as_text(e.message)
~/anaconda3/envs/tfdeeplearning/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
1304 return tf_session.TF_Run(session, options,
1305 feed_dict, fetch_list, target_list,
-> 1306 status, run_metadata)
1307
1308 def _prun_fn(session, handle, feed_dict, fetch_list):
SystemError: <built-in function TF_Run> returned a result with an error set
我尝试指定或不指定要素列的数据类型，不包括分类列，重新启动内核，更改批量大小和时期。我可能错过了一些非常愚蠢的东西，但花了好几个小时试图找出错误:(
以下是代码本身，感谢您提前查看：
train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')
test.columns
train.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
PassengerId 891 non-null int64
Survived 891 non-null int64
Pclass 891 non-null int64
Name 891 non-null object
Sex 891 non-null object
Age 714 non-null float64
SibSp 891 non-null int64
Parch 891 non-null int64
Ticket 891 non-null object
Fare 891 non-null float64
Cabin 204 non-null object
Embarked 889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.6+ KB
y = train['Survived']
X = train.drop(['Name','Survived','Ticket','PassengerId'],axis=1)
X_test = test
cols_to_norm = [ 'Fare']
X[cols_to_norm] = X[cols_to_norm].apply(lambda x: (x - x.min()) / (x.max() - x.min()))
pclass = tf.feature_column.numeric_column('Pclass', dtype=tf.int64)
sex = tf.feature_column.categorical_column_with_vocabulary_list(key="Sex", vocabulary_list=["male", "female"])
age = tf.feature_column.numeric_column('Age', dtype=tf.float64)
sibsp = tf.feature_column.numeric_column('SibSp', dtype=tf.int64)
fare = tf.feature_column.numeric_column('Fare', dtype=tf.float64)
parch = tf.feature_column.numeric_column('Parch', dtype=tf.int64)
embarked = tf.feature_column.categorical_column_with_hash_bucket('Embarked', hash_bucket_size=10000)
age_buckets = tf.feature_column.bucketized_column(age, boundaries=[0,10,20,30,40,50,60,70,80])
feat_cols = [pclass, age_buckets, sex, sibsp, parch, embarked]
input_func = tf.estimator.inputs.pandas_input_fn(x=X,y=y,batch_size=4,num_epochs=None,shuffle=True)
model = tf.estimator.LinearClassifier(feature_columns=feat_cols)
model.train(input_fn=input_func,steps=200)
顺便说一下，当TF崩溃时我在终端看到这个错误：
I 22:37:15.691 NotebookApp] Saving file at /kaggle/titanic/titanic_nb.ipynb
[2408:2444:0428/225656.234325:ERROR:upload_data_presenter.cc(73)] Not implemented reached in virtual void extensions::RawDataPresenter::FeedNext(const net::UploadElementReader &)
[2408:2444:0428/225656.322176:ERROR:upload_data_presenter.cc(73)] Not implemented reached in virtual void extensions::RawDataPresenter::FeedNext(const net::UploadElementReader &)
[2408:2444:0428/225656.442632:ERROR:upload_data_presenter.cc(73)] Not implemented reached in virtual void extensions::RawDataPresenter::FeedNext(const net::UploadElementReader &)
[2408:2444:0428/225656.831056:ERROR:upload_data_presenter.cc(73)] Not implemented reached in virtual void extensions::RawDataPresenter::FeedNext(const net::UploadElementReader &)
[2408:2408:0428/225656.895872:ERROR:CONSOLE(6)] "Uncaught ReferenceError: gbar is not defined", source: https://clients5.google.com/pagead/drt/dn/ (6)
答案 0 :(得分：0)
天哪，解决方案有点过于简单了：）
我为包含字节大小范围内的数字的整数列手动设置 dtype 为 int8 ：
pclass = tf.feature_column.numeric_column（'Pclass'，dtype = tf.int8）
parch = tf.feature_column.numeric_column（'Parch'，dtype = tf.int8）
缩小数据大小绝对合理，但我仍然想知道为什么我之前没有遇到过这个问题，而其他数据集也只有字节大小的数字列。