预测失败：处理输入时出错：预期的字符串，得到了字典

Question

我已经完成了 TensorFlow 的入门教程 (https://www.tensorflow.org/get_started/get_started_for_beginners) 并对代码进行了一些小的更改以使其适应我的应用程序。我的案例的特征列如下：

transaction_column = tf.feature_column.categorical_column_with_vocabulary_list(key='Transaction', vocabulary_list=["buy", "rent"])
localization_column = tf.feature_column.categorical_column_with_vocabulary_list(key='Localization', vocabulary_list=["barcelona", "girona"])
dimensions_feature_column = tf.feature_column.numeric_column("Dimensions")
buy_price_feature_column = tf.feature_column.numeric_column("BuyPrice")
rent_price_feature_column = tf.feature_column.numeric_column("RentPrice")

my_feature_columns = [
    tf.feature_column.indicator_column(transaction_column),
    tf.feature_column.indicator_column(localization_column),
    tf.feature_column.bucketized_column(source_column = dimensions_feature_column,
                                        boundaries = [50, 75, 100]),
    tf.feature_column.numeric_column(key='Rooms'),
    tf.feature_column.numeric_column(key='Toilets'),
    tf.feature_column.bucketized_column(source_column = buy_price_feature_column,
                                        boundaries = [1, 180000, 200000, 225000, 250000, 275000, 300000]),
    tf.feature_column.bucketized_column(source_column = rent_price_feature_column,
                                        boundaries = [1, 700, 1000, 1300])
]

之后，我保存了模型，以便可以在 Cloud ML Engine 中使用它来进行预测。为了导出模型，我添加了以下代码（在评估模型之后）：

feature_spec = tf.feature_column.make_parse_example_spec(my_feature_columns)
export_input_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(feature_spec)
servable_model_dir = "modeloutput"
servable_model_path = classifier.export_savedmodel(servable_model_dir, export_input_fn)

在运行编码后，我在 "modeloutput" 目录中获得了正确的模型文件，并在云端创建了模型（如 https://cloud.google.com/ml-engine/docs/tensorflow/getting-started-training-prediction#deploy_a_model_to_support_prediction、[=69= 中所述） ])

创建模型版本后，我只是尝试在云端使用以下命令使用此模型启动在线预测 Shell：

gcloud ml-engine predict --model $MODEL_NAME --version v1 --json-instances ../prediction.json

其中 $MODEL_NAME 是我的模型名称，prediction.json 是一个包含以下内容的 JSON 文件：

{"inputs":[
  {
     "Transaction":"rent",
     "Localization":"girona",
     "Dimensions":90,
     "Rooms":4,
     "Toilets":2,
     "BuyPrice":0,
     "RentPrice":1100
  }
  ]
}

但是，预测失败，我收到以下错误消息：

"error": "Prediction failed: Error processing input: Expected string, got {u'BuyPrice': 0, u'Transaction': u'rent', u'Rooms': 4, u'Localization': u'girona', u'Toilets': 2, u'RentPrice': 1100, u'Dimensions': 90} of type 'dict' instead."

错误很明显，应该是字符串而不是字典。如果我检查我的 SavedModel SignatureDef，我会得到以下信息：

The given SavedModel SignatureDef contains the following input(s):
inputs['inputs'] tensor_info:
  dtype: DT_STRING
  shape: (-1)
  name: input_example_tensor:0
The given SavedModel SignatureDef contains the following output(s):
outputs['classes'] tensor_info:
  dtype: DT_STRING
  shape: (-1, 12)
  name: dnn/head/Tile:0
outputs['scores'] tensor_info:
  dtype: DT_FLOAT
  shape: (-1, 12)
  name: dnn/head/predictions/probabilities:0
Method name is: tensorflow/serving/classify

显然输入的预期数据类型是字符串 (DT_STRING)，但我不知道如何格式化我的输入数据以便预测成功。我尝试以多种不同的方式编写输入 JSON，但我不断收到错误。如果我查看教程中预测的执行方式 (https://www.tensorflow.org/get_started/get_started_for_beginners)，我认为很明显预测输入是作为字典传递的（教程代码中的 predict_x）。

所以，我哪里错了？如何使用此输入数据进行预测？

感谢您的宝贵时间。

根据答案进行编辑 ------

根据@Lak 的第二个建议，我更新了导出模型的代码，现在它看起来像这样：

export_input_fn = serving_input_fn
servable_model_dir = "savedmodeloutput"
servable_model_path = classifier.export_savedmodel(servable_model_dir, 
 export_input_fn)
...

def serving_input_fn():
feature_placeholders = {
    'Transaction': tf.placeholder(tf.string, [None]),
    'Localization': tf.placeholder(tf.string, [None]),
    'Dimensions': tf.placeholder(tf.float32, [None]),
    'Rooms': tf.placeholder(tf.int32, [None]),
    'Toilets': tf.placeholder(tf.int32, [None]),
    'BuyPrice': tf.placeholder(tf.float32, [None]),
    'RentPrice': tf.placeholder(tf.float32, [None])
    }
features = {
    key: tf.expand_dims(tensor, -1)
    for key, tensor in feature_placeholders.items()
}
return tf.estimator.export.ServingInputReceiver(features, feature_placeholders)

之后，我创建了一个新模型并为其提供以下内容 JSON 以获得预测：

{
   "Transaction":"rent",
   "Localization":"girona",
   "Dimensions":90.0,
   "Rooms":4,
   "Toilets":2,
   "BuyPrice":0.0,
   "RentPrice":1100.0
}

请注意，我在进行预测时收到错误 "Unexpected tensor name: inputs"，因此从 JSON 结构中删除了 "inputs"。但是，现在我得到一个新的更丑陋的错误：

"error": "Prediction failed: Error during model execution: AbortionError(code=StatusCode.INVALID_ARGUMENT, details=\"NodeDef mentions attr 'T' not in Op index:int64>; NodeDef: dnn/input_from_feature_columns/input_layer/Transaction_indicator/to_sparse_input/indices = WhereT=DT_BOOL, _output_shapes=[[?,2]], _device=\"/job:localhost/replica:0/task:0/device:CPU:0\". (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).\n\t [[Node: dnn/input_from_feature_columns/input_layer/Transaction_indicator/to_sparse_input/indices = WhereT=DT_BOOL, _output_shapes=[[?,2]], _device=\"/job:localhost/replica:0/task:0/device:CPU:0\"]]\")"

我再次检查了 SignatureDef，得到以下信息：

The given SavedModel SignatureDef contains the following input(s):
  inputs['Toilets'] tensor_info:
      dtype: DT_INT32
      shape: (-1)
      name: Placeholder_4:0
  inputs['Rooms'] tensor_info:
      dtype: DT_INT32
      shape: (-1)
      name: Placeholder_3:0
  inputs['Localization'] tensor_info:
      dtype: DT_STRING
      shape: (-1)
      name: Placeholder_1:0
  inputs['RentPrice'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1)
      name: Placeholder_6:0
  inputs['BuyPrice'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1)
      name: Placeholder_5:0
  inputs['Dimensions'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1)
      name: Placeholder_2:0
  inputs['Transaction'] tensor_info:
      dtype: DT_STRING
      shape: (-1)
      name: Placeholder: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, 12)
      name: dnn/logits/BiasAdd:0
  outputs['probabilities'] tensor_info:
      dtype: DT_FLOAT
      shape: (-1, 12)
      name: dnn/head/predictions/probabilities:0
Method name is: tensorflow/serving/predict

我是不是有些步骤出错了？谢谢！

新更新

我已经运行进行了一次本地预测，并且已经成功执行，收到了预期的预测结果。使用的命令：

gcloud ml-engine local predict --model-dir $MODEL_DIR --json-instances=../prediction.json

其中 MODEL_DIR 是包含模型训练生成的文件的目录。所以问题似乎出在导出模型上。以某种方式导出并稍后用于预测的模型不正确。我读过一些关于 TensorFlow 版本的文章，可能是问题的根源，但我不明白。我的整个代码不是用同一个TF版本执行的吗？关于这一点有什么想法吗？

谢谢！

Answer 1

问题出在您的服务输入函数中。您正在使用 build_parsing_serving_input_receiver_fn，如果您要发送 tf.Example 字符串，则应使用该函数：

https://www.tensorflow.org/api_docs/python/tf/estimator/export/build_parsing_serving_input_receiver_fn

解决此问题的两种方法：

发送 tf.Example


    example = tf.train.Example(features=tf.train.Features(feature=
       {'transaction': tf.train.Feature(bytes_list=tf.train.BytesList(value=['rent'])), 
        'rentPrice': tf.train.Feature(float32_list=tf.train.Float32List(value=[1000.0))
    }))

    string_to_send = example.SerializeToString()

更改服务输入函数，以便您可以发送 JSON:


    def serving_input_fn():
       feature_placeholders = {
                'transaction': tf.placeholder(tf.string, [None]),
                ...
                'rentPrice': tf.placeholder(tf.float32, [None]),
            }
            features = {
                key: tf.expand_dims(tensor, -1)
                for key, tensor in feature_placeholders.items()
            }
       return tf.estimator.export.ServingInputReceiver(features, feature_placeholders)


    export_input_fn = serving_input_fn

Answer 2

问题已解决:)

经过几次实验，我最终发现我必须使用最新的运行时版本 (1.8) 创建模型：

gcloud ml-engine versions create v2 --model $MODEL_NAME --origin $MODEL_BINARIES --runtime-version 1.8

预测失败：处理输入时出错：预期的字符串，得到了字典

Prediction failed: Error processing input: Expected string, got dict

python

machine-learning

tensorflow

google-cloud-ml