ml-engine 预测参数解析错误

Question

在成功部署了数十个模型后，由于解析和其他参数错误，只有最微不足道的模型（一个参数 in/out）成功 return 预测结果，我回到了官方广泛-和深度模型： official wide and deep tutorial 还有这个： serving wide and deep tutorial continuation 尝试在 ml-engine 上导出、部署和预测。我无法获得任何文本排列或 json 参数来通过解析。以下是我的一些测试和回复：

1)输入文件内容，文本：

25,0,0,"11th",7,"Male",40,"United-States","Machine-op-inspct","Own-child","Private"

响应：

{"error": "Prediction failed: Error during model execution: AbortionError(code=StatusCode.INVALID_ARGUMENT, details=\"Could not parse example input, value: '25,0,0,\"11th\",7,\"Male\",40,\"United-States\",\"Machine-op-inspct\",\"Own-child\",\"Private\"'\n\t [[Node: ParseExample/ParseExample = ParseExample[Ndense=5, Nsparse=6, Tdense=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], dense_shapes=[[1], [1], [1], [1], [1]], sparse_types=[DT_STRING, DT_STRING, DT_STRING, DT_STRING, DT_STRING, DT_STRING], _device=\"/job:localhost/replica:0/task:0/device:CPU:0\"](_arg_input_example_tensor_0_0, ParseExample/ParseExample/names, ParseExample/ParseExample/sparse_keys_0, ParseExample/ParseExample/sparse_keys_1, ParseExample/ParseExample/sparse_keys_2, ParseExample/ParseExample/sparse_keys_3, ParseExample/ParseExample/sparse_keys_4, ParseExample/ParseExample/sparse_keys_5, ParseExample/ParseExample/dense_keys_0, ParseExample/ParseExample/dense_keys_1, ParseExample/ParseExample/dense_keys_2, ParseExample/ParseExample/dense_keys_3, ParseExample/ParseExample/dense_keys_4, ParseExample/Const, ParseExample/Const, ParseExample/Const, ParseExample/Const, Pa...TRUNCATED\")"}

2)输入文件内容，json:

{"age":25,"capital_gain":0,"capital_loss":0,"education":"11th","education_num":7,"gender":"Male","hours_per_week":40,"native_country":"United-States","occupation":"Machine-op-inspct","relationship":"Own-child","workclass":"Private"}

响应：

{....failed: Expected tensor name: inputs, got tensor name: [u'hours_per_week', u'native_country',....}

3)输入文件内容，json:

{"inputs":{"age":25,"capital_gain":0,"capital_loss":0,"education":"11th","education_num":7,"gender":"Male","hours_per_week":40,"native_country":"United-States","occupation":"Machine-op-inspct","relationship":"Own-child","workclass":"Private"}}

响应：

{....Error processing input: Expected string, got {u'hours_per_week': 40, u'native_count....}

4)输入文件内容，json:

{"inputs":"25,0,0,11th,7,Male,40,United-States,Machine-op-inspct,Own-child,Private"}

响应：

{...."Prediction failed: Error during model execution: AbortionError(code=StatusCode.INVALID_ARGUMENT, details=\"Could not parse example input, value: '25,0,0,11th,7,Male,40,United-States,Machine-op-inspct,Own-child,Private'\n\t [[Node: ParseExample/ParseExample = ParseExample[Ndense=5,....}

我还尝试了内部转义引号、各种 lists/arrays 等

请告诉我我只需要重新格式化我在预测请求中的输入（以及如何）:) -谢谢

Answer 1

在目前的情况下，接受 JSON 的图和接受 tf.train.Example 的图之间的选择是相互排斥的，这意味着您必须以稍微不同的方式导出图。

在 serving wide and deep tutorial continuation 中，更改以下行：

feature_spec = tf.feature_column.make_parse_example_spec(feature_columns)
export_input_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(feature_spec)

到

inputs = {}
for feat in INPUT_COLUMNS:
  inputs[feat.name] = tf.placeholder(shape=[None], dtype=feat.dtype)
export_input_fn = tf.estimator.export.build_raw_serving_input_receiver_fn(inputs)

供参考，参见this sample, in particular, the *_serving_fn definitions in model.py (e.g. here);该示例还展示了如何导出需要 CSV 作为输入的图表。

另外请注意，如果您使用 gcloud 发送请求（相对于请求库），输入数据格式是 而不是 请求的完整主体to send: gcloud 使用文件中的每一行构造请求。所以发送到服务器的实际请求的主体将类似于：

{
  "instances": [
    {
      "age": 25,
      "capital_gain": 0,
      "capital_loss": 0,
      "education": "11th",
      "education_num": 7,
      "gender": "Male",
      "hours_per_week": 40,
      "native_country": "United-States",
      "occupation": "Machine-op-inspct",
      "relationship": "Own-child",
      "workclass": "Private"
    }
  ]
}

而相应的 --json-instances 文件将如下所示：

{"age":25,"capital_gain":0,"capital_loss":0,"education":"11th","education_num":7,"gender":"Male","hours_per_week":40,"native_country":"United-States","occupation":"Machine-op-inspct","relationship":"Own-child","workclass":"Private"}

gcloud 获取每一行的内容并将它们填充到上面 "actual" 请求中显示的数组中。

ml-engine 预测参数解析错误

ml-engine predict argument parsing errors

python

tensorflow

google-cloud-ml