Question 380048 in Amazon Web Sevices Question posted in
The official Amazon Web Services documentation can be found here.

Amazon web services – AWS DeepAR predict returns 400

I’m trying to run a DeepAR to do some estimation for a series the next 15 records based on current and previous months.

I follow the examples and I believe that everything is ok. Still I have a very cryptic error.

I put here the code:

predictor = estimator.deploy(
    initial_instance_count=1,
    instance_type='ml.m5.large',   
    serializer=JSONSerializer(),
    deserializer=JSONDeserializer()
    )

json_request = json.dumps({
    "instances": ts,
    "configuration": {
        "num_samples": 10,
        "output_types": ["quantiles", "samples"],
        "quantiles": ['0.2', '0.5', '0.8']
    }
})

prediction = predictor.predict(json_request)

My json looks like this:

{"instances": 
    [{"start": "2024-03-01", 
      "target":[60,10,86,62,21,25,7,79,33,82,34,43,14,99,5,37,85,84,88,25,2,14,15,98,14,75,70,99,12]
      }, 
     {"start": "2024-04-01", 
      "target": [55,89,40,81,87,7,49,77,37,42,48,27,89,45,85]
      }], 
 "configuration": {"num_samples": 15, "output_types": ["quantiles", "samples"], "quantiles": ["0.2", "0.5", "0.8"]}}

But I have the following error:

---------------------------------------------------------------------------
ModelError                                Traceback (most recent call last)
Cell In[22], line 2
      1 print(type('json_request'))
----> 2 prediction = predictor.predict(json_request)
      3 print(prediction)

File c:UserscivanPycharmProjectsJupyterBooks.venvLibsite-packagessagemakerbase_predictor.py:212, in Predictor.predict(self, data, initial_args, target_model, target_variant, inference_id, custom_attributes, component_name)
    209 if inference_component_name:
    210     request_args["InferenceComponentName"] = inference_component_name
--> 212 response = self.sagemaker_session.sagemaker_runtime_client.invoke_endpoint(**request_args)
    213 return self._handle_response(response)

File c:UserscivanPycharmProjectsJupyterBooks.venvLibsite-packagesbotocoreclient.py:553, in ClientCreator._create_api_method.<locals>._api_call(self, *args, **kwargs)
    549     raise TypeError(
    550         f"{py_operation_name}() only accepts keyword arguments."
    551     )
    552 # The "self" in this scope is referring to the BaseClient.
--> 553 return self._make_api_call(operation_name, kwargs)

File c:UserscivanPycharmProjectsJupyterBooks.venvLibsite-packagesbotocoreclient.py:1009, in BaseClient._make_api_call(self, operation_name, api_params)
   1005     error_code = error_info.get("QueryErrorCode") or error_info.get(
   1006         "Code"
   1007     )
   1008     error_class = self.exceptions.from_code(error_code)
-> 1009     raise error_class(parsed_response, operation_name)
   1010 else:
   1011     return parsed_response

ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from primary with message "Unable to evaluate payload provided".

I have tried without serializer/desearilzer and it give error also but not this one, things related to format.

Tags:

2

Answers


  1. Chosen as BEST ANSWER
    0

    After more digging in AWS class serialization I found the model, I put here maybe somebody will find on google search (or ChatGPT learn this :) )

    from sagemaker.serializers import IdentitySerializer
from sagemaker.deserializers import JSONDeserializer

predictor = estimator.deploy(
    initial_instance_count=1,
    instance_type='ml.m5.large',   
    serializer=IdentitySerializer(content_type="application/json"),
    deserializer=JSONDeserializer()
    )

prediction = predictor.predict(json_request)

  2. 0

    Following serializer=JSONSerializer() for estimator.deploy() is not needed and causing the error, because your input is already serialized as a JSON string.

    Or if you want to use JSONSerializer, you need to pass arguments before serialization.

    Login or Signup to reply.
Please signup or login to give your own answer.

Back To Top
Search