1

我用 Tensorflow BERT 语言模型创建了一个二元分类器。这是链接。模型训练完成后，它会保存模型并生成以下文件。 pytho

预测代码。 

from tensorflow.contrib import predictor

#MODEL_FILE = 'graph.pbtxt'   


with tf.Session() as sess:   
  predict_fn = predictor.from_saved_model(f'/content/drive/My Drive/binary_class/bert/graph.pbtxt')
predictions = predict_fn(pred_sentences)
print(predictions)

错误

OSError: SavedModel file does not exist at: /content/drive/My Drive/binary_class/bert/graph.pbtxt/{saved_model.pbtxt|saved_model.pb}

在挖掘了这个问题之后。我遇到了用于保存模型的 tf.train.Saver() 类。我将估算器训练代码更改为以下以保存模型。我提到了这个链接。我猜张量流估计器可以用它来保存。

init_op = tf.global_variables_initializer()
with tf.Session() as sess:
  sess.run(init_op)
  # Do some work with the model.
  saver = tf.train.Saver()
  estimator.train(input_fn=train_input_fn, max_steps=num_train_steps)  
  # Save the variables to disk.
  save_path = saver.save(sess, f'/content/drive/My Drive/binary_class/bert/tmp/model.ckpt')

这是错误。

Beginning Training!
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-38-0c9f9b70d76b> in <module>()
      9   sess.run(init_op)
     10   # Do some work with the model.
---> 11   saver = tf.train.Saver()
     12   estimator.train(input_fn=train_input_fn, max_steps=num_train_steps)
     13   # Save the variables to disk.

2 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py in _build(self, checkpoint_path, build_save, build_restore)
    860           return
    861         else:
--> 862           raise ValueError("No variables to save")
    863       self._is_empty = False
    864 

ValueError: No variables to save

变量、权重在 create_model 函数中创建。我应该改变什么来保存我训练的模型？

更新：保存模型的代码。我不确定 feature_spec 和特征张量。

feature_spec = {'x': tf.VarLenFeature(tf.string)}

def serving_input_receiver_fn():  

  serialized_tf_example = tf.placeholder(dtype=tf.string,
                                         shape=[1],  # batch size
                                         name='input_example_tensor')
  receiver_tensors = {'examples': serialized_tf_example}
  features = tf.parse_example(serialized_tf_example, feature_spec)
  return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)

# Export the estimator
export_path = f'/content/drive/My Drive/binary_class/bert/'

estimator.export_saved_model(
    export_path,
    serving_input_receiver_fn=serving_input_receiver_fn)

我收到了这个错误：-

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-55-209298910d1e> in <module>()
     16 estimator.export_saved_model(
     17     export_path,
---> 18     serving_input_receiver_fn=serving_input_receiver_fn)

4 frames
/usr/local/lib/python3.6/dist-packages/tensorflow_estimator/python/estimator/estimator.py in export_saved_model(self, export_dir_base, serving_input_receiver_fn, assets_extra, as_text, checkpoint_path, experimental_mode)
    730         as_text=as_text,
    731         checkpoint_path=checkpoint_path,
--> 732         strip_default_attrs=True)
    733 
    734   def experimental_export_all_saved_models(

/usr/local/lib/python3.6/dist-packages/tensorflow_estimator/python/estimator/estimator.py in _export_all_saved_models(self, export_dir_base, input_receiver_fn_map, assets_extra, as_text, checkpoint_path, strip_default_attrs)
    854             builder, input_receiver_fn_map, checkpoint_path,
    855             save_variables, mode=ModeKeys.PREDICT,
--> 856             strip_default_attrs=strip_default_attrs)
    857         save_variables = False
    858 

/usr/local/lib/python3.6/dist-packages/tensorflow_estimator/python/estimator/estimator.py in _add_meta_graph_for_mode(self, builder, input_receiver_fn_map, checkpoint_path, save_variables, mode, export_tags, check_variables, strip_default_attrs)
    927           labels=getattr(input_receiver, 'labels', None),
    928           mode=mode,
--> 929           config=self.config)
    930 
    931       export_outputs = export_lib.export_outputs_for_mode(

/usr/local/lib/python3.6/dist-packages/tensorflow_estimator/python/estimator/estimator.py in _call_model_fn(self, features, labels, mode, config)
   1144 
   1145     logging.info('Calling model_fn.')
-> 1146     model_fn_results = self._model_fn(features=features, **kwargs)
   1147     logging.info('Done calling model_fn.')
   1148 

<ipython-input-17-119a3167bf33> in model_fn(features, labels, mode, params)
      5     """The `model_fn` for TPUEstimator."""
      6 
----> 7     input_ids = features["input_ids"]
      8     input_mask = features["input_mask"]
      9     segment_ids = features["segment_ids"]

KeyError: 'input_ids'
4

2 回答 2

3

notebook 中的create_model函数需要一些参数。这些特征被传递给模型。

通过将 serving_input_fn 函数更新为跟随，服务函数按预期工作。

更新代码

def serving_input_receiver_fn():
  feature_spec = {
      "input_ids" : tf.FixedLenFeature([MAX_SEQ_LENGTH], tf.int64),
      "input_mask" : tf.FixedLenFeature([MAX_SEQ_LENGTH], tf.int64),
      "segment_ids" : tf.FixedLenFeature([MAX_SEQ_LENGTH], tf.int64),
      "label_ids" :  tf.FixedLenFeature([], tf.int64)
  }
  serialized_tf_example = tf.placeholder(dtype=tf.string,
                                         shape=[None],
                                         name='input_example_tensor')
  print(serialized_tf_example.shape)
  receiver_tensors = {'example': serialized_tf_example}
  features = tf.parse_example(serialized_tf_example, feature_spec)
  return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)

export_path = '/content/drive/My Drive/binary_class/bert/'
estimator._export_to_tpu = False  # this is important
estimator.export_saved_model(export_dir_base=export_path,serving_input_receiver_fn=serving_input_receiver_fn)
于 2019-07-02T06:08:46.987 回答
1

在 serving_input_receiver_fn 中使用feature_spec字典对我不起作用。我使用了其他人提出相同问题serving_input_fn的以下内容。

要使用加载的估计器：

def serving_input_fn():
    label_ids = tf.placeholder(tf.int32, [None], name='label_ids')
    input_ids = tf.placeholder(tf.int32, [None, MAX_SEQ_LEN], name='input_ids')
    input_mask = tf.placeholder(tf.int32, [None, MAX_SEQ_LEN], name='input_mask')
    segment_ids = tf.placeholder(tf.int32, [None, MAX_SEQ_LEN], name='segment_ids')
    input_fn = tf.estimator.export.build_raw_serving_input_receiver_fn(
        {
        'label_ids': label_ids,
        'input_ids': input_ids,
        'input_mask': input_mask,
        'segment_ids': segment_ids
        }
    )()
    return input_fn


export_path = '../testing'
estimator._export_to_tpu = False  # this is important
estimator.export_saved_model(export_dir_base=export_path,serving_input_receiver_fn=serving_input_fn)

from tensorflow.contrib import predictor
predict_fn = predictor.from_saved_model('../testing/1589420991')

def predict(sentences, predict_fn):
    labels = [0, 1]
    input_examples = [
        run_classifier.InputExample(
            guid="",
            text_a = x,
            text_b = None,
            label = 0
        ) for x in sentences] # here, "" is just a dummy label
    input_features = run_classifier.convert_examples_to_features(
        input_examples, labels, MAX_SEQ_LEN, tokenizer
    )

    all_input_ids = []
    all_input_mask = []
    all_segment_ids = []
    all_label_ids = []

    for feature in input_features:
        all_input_ids.append(feature.input_ids)
        all_input_mask.append(feature.input_mask)
        all_segment_ids.append(feature.segment_ids)
        all_label_ids.append(feature.label_id)
    pred_dict = {
        'input_ids': all_input_ids,
        'input_mask': all_input_mask,
        'segment_ids': all_segment_ids,
        'label_ids': all_label_ids
    }

    predictions = predict_fn(pred_dict)
    return [
        (sentence, prediction, label)
        for sentence, prediction, label in zip(pred_sentences, predictions['probabilities'], predictions['labels'])
    ]

pred_sentences = [
  "That movie was absolutely awful",
  "The acting was a bit lacking",
  "The film was creative and surprising",
  "Absolutely fantastic!",
]

predictions = predict(pred_sentences, predict_fn)
print(predictions)
[('That movie was absolutely awful',
  array([-0.26713806, -1.4505868 ], dtype=float32),
  0),
 ('The acting was a bit lacking',
  array([-0.23832974, -1.5508994 ], dtype=float32),
  0),
 ('The film was creative and surprising',
  array([-0.2784096, -1.4146391], dtype=float32),
  0),
 ('Absolutely fantastic!',
  array([-0.29031944, -1.3784236 ], dtype=float32),
  0),
 ('The patient has diabetes',
  array([-0.33836085, -1.2480571 ], dtype=float32),
  0),
 ('The patient does not have diabetes',
  array([-0.29378486, -1.3682064 ], dtype=float32),
  0)]
于 2020-05-14T02:37:12.267 回答