python - TensorFlow 内部错误 : Unable to get element as bytes

Question

我正在尝试使用 TensorFlow 对一些包含分类和数字数据混合的日志数据运行 DNNClassifier。我已经创建了特征列来指定和存储/散列 tensorflow 的数据。当我运行代码时，我收到“无法将元素作为字节获取”内部错误。注意:我不想删除此 article 中所述的 Nan 值所以我使用此代码将它们转换为 0 train = train.fillna(0, axis=0) 所以我不确定为什么我仍然收到此错误。如果我删除 Nan，那么它会起作用，但我不想删除 Nan，因为我觉得模型需要它们进行训练。

def create_train_input_fn(): 
    return tf.estimator.inputs.pandas_input_fn(
        x=train,
        y=train_label, 
        batch_size=32,
        num_epochs=None,
        shuffle=True)

def create_test_input_fn():
    return tf.estimator.inputs.pandas_input_fn(
        x=valid,
        y=valid_label, 
        num_epochs=1,
        shuffle=False)
feature_columns = []
end_time = tf.feature_column.embedding_column(tf.feature_column.categorical_column_with_hash_bucket('end_time', 1000), 10)
feature_columns.append(end_time)
device = tf.feature_column.embedding_column(tf.feature_column.categorical_column_with_hash_bucket('device', 1000), 10)
feature_columns.append(device)
device_os = tf.feature_column.embedding_column(tf.feature_column.categorical_column_with_hash_bucket('device_os', 1000), 10)
feature_columns.append(device_os)
device_os_version = tf.feature_column.embedding_column(tf.feature_column.categorical_column_with_hash_bucket('device_os_version', 1000), 10)
feature_columns.append(device_os_version)
Latency = tf.feature_column.bucketized_column(
    tf.feature_column.numeric_column('Latency'), 
    boundaries=[.000000, .000010, .000100, .001000, .010000, .100000])
feature_columns.append(Latency)
Megacycles = tf.feature_column.bucketized_column(
    tf.feature_column.numeric_column('Megacycles'), 
    boundaries=[0, 50, 100, 200, 300])
feature_columns.append(Megacycles)
Cost = tf.feature_column.bucketized_column(
    tf.feature_column.numeric_column('Cost'), 
    boundaries=[0.000001e-08, 1.000000e-08, 5.000000e-08, 10.000000e-08, 15.000000e-08 ])
feature_columns.append(Cost)
device_brand = tf.feature_column.embedding_column(tf.feature_column.categorical_column_with_hash_bucket('device_brand', 1000), 10)
feature_columns.append(device_brand)
device_family = tf.feature_column.embedding_column(tf.feature_column.categorical_column_with_hash_bucket('device_family', 1000), 10)
feature_columns.append(device_family)
browser_version = tf.feature_column.embedding_column(tf.feature_column.categorical_column_with_hash_bucket('browser_version', 1000), 10)
feature_columns.append(browser_version)
app = tf.feature_column.embedding_column(tf.feature_column.categorical_column_with_hash_bucket('app', 1000), 10)
feature_columns.append(app)
ua_parse = tf.feature_column.embedding_column(tf.feature_column.categorical_column_with_hash_bucket('ua_parse', 1000), 10)
feature_columns.append(ua_parse)

estimator = tf.estimator.DNNClassifier(hidden_units=[256, 128, 64], 
                                       feature_columns=feature_columns, 
                                       n_classes=2, 
                                       model_dir='graphs/dnn')

train_input_fn = create_train_input_fn()
estimator.train(train_input_fn, steps=2000)

然后我收到这个错误:

InternalErrorTraceback (most recent call last)
<ipython-input-67-6abd6f1afc3a> in <module>()
      1 train_input_fn = create_train_input_fn()
----> 2 estimator.train(train_input_fn, steps=2000)

/usr/local/envs/py2env/lib/python2.7/site-packages/tensorflow/python/estimator/estimator.pyc in train(self, input_fn, hooks, steps, max_steps, saving_listeners)
    312 
    313     saving_listeners = _check_listeners_type(saving_listeners)
--> 314     loss = self._train_model(input_fn, hooks, saving_listeners)
    315     logging.info('Loss for final step: %s.', loss)
    316     return self

/usr/local/envs/py2env/lib/python2.7/site-packages/tensorflow/python/estimator/estimator.pyc in _train_model(self, input_fn, hooks, saving_listeners)
    813         loss = None
    814         while not mon_sess.should_stop():
--> 815           _, loss = mon_sess.run([estimator_spec.train_op, estimator_spec.loss])
    816       return loss
    817 

/usr/local/envs/py2env/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.pyc in __exit__(self, exception_type, exception_value, traceback)
    649     if exception_type in [errors.OutOfRangeError, StopIteration]:
    650       exception_type = None
--> 651     self._close_internal(exception_type)
    652     # __exit__ should return True to suppress an exception.
    653     return exception_type is None

/usr/local/envs/py2env/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.pyc in _close_internal(self, exception_type)
    686         if self._sess is None:
    687           raise RuntimeError('Session is already closed.')
--> 688         self._sess.close()
    689       finally:
    690         self._sess = None

/usr/local/envs/py2env/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.pyc in close(self)
    932     if self._sess:
    933       try:
--> 934         self._sess.close()
    935       except _PREEMPTION_ERRORS:
    936         pass

/usr/local/envs/py2env/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.pyc in close(self)
   1076       self._coord.join(
   1077           stop_grace_period_secs=self._stop_grace_period_secs,
-> 1078           ignore_live_threads=True)
   1079     finally:
   1080       try:

/usr/local/envs/py2env/lib/python2.7/site-packages/tensorflow/python/training/coordinator.pyc in join(self, threads, stop_grace_period_secs, ignore_live_threads)
    385       self._registered_threads = set()
    386       if self._exc_info_to_raise:
--> 387         six.reraise(*self._exc_info_to_raise)
    388       elif stragglers:
    389         if ignore_live_threads:

/usr/local/envs/py2env/lib/python2.7/site-packages/tensorflow/python/estimator/inputs/queues/feeding_queue_runner.pyc 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.

/usr/local/envs/py2env/lib/python2.7/site-packages/tensorflow/python/client/session.pyc 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)

/usr/local/envs/py2env/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _run(self, handle, fetches, feed_dict, options, run_metadata)
   1126     if final_fetches or final_targets or (handle and feed_dict_tensor):
   1127       results = self._do_run(handle, final_targets, final_fetches,
-> 1128                              feed_dict_tensor, options, run_metadata)
   1129     else:
   1130       results = []

/usr/local/envs/py2env/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1342     if handle is None:
   1343       return self._do_call(_run_fn, self._session, feeds, fetches, targets,
-> 1344                            options, run_metadata)
   1345     else:
   1346       return self._do_call(_prun_fn, self._session, handle, feeds, fetches)

/usr/local/envs/py2env/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_call(self, fn, *args)
   1361         except KeyError:
   1362           pass
-> 1363       raise type(e)(node_def, op, message)
   1364 
   1365   def _extend_graph(self):

InternalError: Unable to get element as bytes.

Answer 1

我同意 Thomas Decaux 的观点。我遇到了完全相同的问题。我检查了我的标签是否表示为字符串("is"和“否”)而不是整数 (1,0)。将标签转换为 int64 后，没有出现此类错误。