1

我在为我的文本分类模型提供服务时遇到问题Tensorflow 1.12。我tf.estimator.inputs.pandas_input_fn用来读取我的数据，并tf.estimator.DNNClassifier训练/评估。然后我想为我的模型服务。（提前道歉，在这里很难提供一个完整的工作示例，但它非常类似于 TF 在https://www.tensorflow.org/api_docs/python/tf/estimator/DNNClassifier提供的示例 ）

我目前正在用...保存我的模型

...
estimator.export_savedmodel("./TEST_SERVING/", self.serving_input_receiver_fn, strip_default_attrs=True)
...
def serving_input_receiver_fn(self):
      """An input receiver that expects a serialized tf.Example."""

      # feature spec dictionary  determines our input parameters for the model
      feature_spec = {
          'Headline': tf.VarLenFeature(dtype=tf.string),
          'Description': tf.VarLenFeature(dtype=tf.string)
      }

      # the inputs will be initially fed as strings with data serialized by
      # Google ProtoBuffers
      serialized_tf_example = tf.placeholder(
          dtype=tf.string, shape=None, name='input_example_tensor')
      receiver_tensors = {'examples': serialized_tf_example}

      # deserialize input
      features = tf.parse_example(serialized_tf_example, feature_spec)
      return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)

这实际上无法运行并出现错误：

TypeError: Failed to convert object of type <class 'tensorflow.python.framework.sparse_tensor.SparseTensor'> to Tensor. Contents: SparseTensor(indices=Tensor("ParseExample/ParseExample:0", shape=(?, 2), 
dtype=int64), values=Tensor("ParseExample/ParseExample:2", shape=(?,), dtype=string), dense_shape=Tensor("ParseExample/ParseExample:4", shape=(2,), dtype=int64)). Consider casting elements to a supported type.

我试图保存第二种方法：

def serving_input_receiver_fn(self):
  """Build the serving inputs."""
  INPUT_COLUMNS = ["Headline","Description"]
  inputs = {}
  for feat in INPUT_COLUMNS:
    inputs[feat] = tf.placeholder(shape=[None], dtype=tf.string, name=feat)
  return tf.estimator.export.ServingInputReceiver(inputs, inputs)

这实际上有效，直到我尝试使用saved_model_cli. 一些输出saved_model_cli show --all --dir TEST_SERVING/1553879255/：

MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:

signature_def['predict']:
  The given SavedModel SignatureDef contains the following input(s):
    inputs['Description'] tensor_info:
        dtype: DT_STRING
        shape: (-1)
        name: Description:0
    inputs['Headline'] tensor_info:
        dtype: DT_STRING
        shape: (-1)
        name: Headline:0
  The given SavedModel SignatureDef contains the following output(s):
    outputs['class_ids'] tensor_info:
        dtype: DT_INT64
        shape: (-1, 1)
        name: dnn/head/predictions/ExpandDims:0
    outputs['classes'] tensor_info:
        dtype: DT_STRING
        shape: (-1, 1)
        name: dnn/head/predictions/str_classes:0
    outputs['logits'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 3)
        name: dnn/logits/BiasAdd:0
    outputs['probabilities'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 3)
        name: dnn/head/predictions/probabilities:0
  Method name is: tensorflow/serving/predict

但现在我似乎无法测试它。

>>> saved_model_cli run --dir TEST_SERVING/1553879255/ --tag_set serve --signature_def predict --input_examples 'inputs=[{"Description":["What is going on"],"Headline":["Help me"]}]'
Traceback (most recent call last):
 ...
  File "/Users/Josh/miniconda3/envs/python36/lib/python3.6/site-packages/tensorflow/python/tools/saved_model_cli.py", line 489, in _create_example_string
    feature_list)
TypeError: 'What is going on' has type str, but expected one of: bytes

好的，让我们把它变成一个字节对象，把它改为b["What is going on"]and b["Help me"]...

ValueError: Type <class 'bytes'> for value b'What is going on' is not supported for tf.train.Feature.

任何想法/想法？谢谢！

4

1 回答 1

1

好的，所以最终我找到了答案，引用于TensorFlow：如何使用 TensorHub 模块导出估算器？

问题在于我不太了解的序列化内容。该解决方案允许将原始字符串传递给tf.estimator.export.build_raw_serving_input_receiver_fn。

我的保存功能现在看起来像这样：

  def save_serving_model(self,estimator):
      feature_placeholder = {'Headline': tf.placeholder('string', [1], name='headline_placeholder'),
      'Description': tf.placeholder('string', [1], name='description_placeholder')}
      serving_input_fn = tf.estimator.export.build_raw_serving_input_receiver_fn(feature_placeholder)

      estimator.export_savedmodel("TEST_SERVING/", serving_input_fn)

在哪里使用saved_model_cli作品。IE：

saved_model_cli run --dir /path/to/model/ --tag_set serve --signature_def predict --input_exprs="Headline=['Finally, it works'];Description=['Yay, it works']" 


Result for output key class_ids:
[[2]]
Result for output key classes:
[[b'2']]
Result for output key logits:
[[-0.56755465  0.31625098  0.39260274]]
Result for output key probabilities:
[[0.16577701 0.40119565 0.4330274 ]]
于 2019-03-31T10:27:12.197 回答