Azure ML Studio error while testing real-time endpoint - list index out of range

Kumar, Priya 26

I am new to the Azure ML Studio and just deployed the bike-rental regression model. When I tried to test it using the built in test tool in the studio, I am getting the attached error. Similar results running the Python code as well. Can someone please help me?

Ramr-msft 17,741 Reputation points

2022-02-23T13:24:58.237+00:00

@Kumar, Priya Thanks for the question. Can you please add more details about the train. Are you using the designer/notebook to train.

Here is link to doc for request data.
Ramr-msft 17,741 Reputation points

2022-02-23T13:26:56.077+00:00

@Kumar, Priya Thanks, you can now register a trained model in Designer into the model registry and use automatically generated score.py/conda yaml to deploy it using SDK or CLI. After successful model training, publishing to inference cluster in authenticating to the AKS cluster and consume.
Priya Kumar 1 Reputation point

2022-02-23T17:23:14.653+00:00

Thanks for your response. I tried removing the headers in the CSV and also formatted the JSON to match the document, still same results. I have provided the deployment details.
Ramr-msft 17,741 Reputation points

2022-02-24T06:52:28.917+00:00

@Priya Kumar Thanks for the details. We are able to reproduce the issue and same has been forwarded to the product team.

Accepted answer

Ramr-msft 17,741 Reputation points

2022-02-24T09:35:29.74+00:00

@Kumar, Priya Thanks for the question. It's known issue and the product team working on the fix to change in the UI.

Workaround: As shown below please set the GlobalParameters flag to 1.0 or a float number or remove it.
Please sign in to rate this answer.

4 people found this answer helpful.
Priya Kumar 1 Reputation point

2022-02-24T18:35:18.59+00:00

Thank you for the work around. With the "GlobalParameters" set to a float value, I am getting the prediction results back.

Ramr-msft 17,741 Reputation points

2022-02-25T14:18:21.737+00:00

@Priya Kumar Thanks, do click “Mark as Answer” and Up-Vote for the same, which might be beneficial to other community members reading this thread.

Fernando José Ribeiro Júnior 1 Reputation point

2022-03-01T18:55:47.437+00:00

I was having the same problem, and turning GlobalParameters: 1 to 1.0, it's solved.

But, I'm still having issues with <Response [502]> during deploy.

Muhammad Ahmed Muhammad 0 Reputation points

2024-11-17T08:41:49.0833333+00:00

Where do I find this screen. In my endpoint options are different
Sign in to comment

Use comments to ask for clarification, additional information, or improvements to the question.

4 additional answers

Mirko Moeller 11

@Fernando José Ribeiro Júnior I had to modify the notebook as follows to get it to work:

x = [[1,1,2022,1,0,6,0,2,0.344167,0.363625,0.805833,0.160446],   
  
    [2,1,2022,1,0,0,0,2,0.363478,0.353739,0.696087,0.248539],   
  
    [3,1,2022,1,0,1,1,1,0.196364,0.189405,0.437273,0.248309],   
  
    [4,1,2022,1,0,2,1,1,0.2,0.212122,0.590435,0.160296],   
  
    [5,1,2022,1,0,3,1,1,0.226957,0.22927,0.436957,0.1869]]   
  
columns = ["day","mnth", "year", "season", "holiday", "weekday", "workingday", "weathersit", "temp", "atemp", "hum", "windspeed"]  
data = [{columns[i]: v for i, v in enumerate(x_i)} for x_i in x]  
  
request = {  
  "Inputs": {  
    "data": data  
  },  
  "GlobalParameters": 0.0 # not sure if this value matters  
}  
  
input_json = json.dumps(request)

Prashanth K 6 Reputation points

2022-10-10T06:25:59.75+00:00

Azure ML Studio error while testing real-time endpoint - Input data are inconsistent with schema

Kindly help me to resolve this issue.

Thanks in Advance

Regards,
Prashanth K
Please sign in to rate this answer.

1 person found this answer helpful.

0 comments No comments
Sign in to comment

Use comments to ask for clarification, additional information, or improvements to the question.
Eason 1 Reputation point

2022-03-01T07:41:18.553+00:00

Change GlobalParameters flag value from integer 1 to decimal 1.0 to make it works.
Please sign in to rate this answer.

0 comments No comments
Sign in to comment

Use comments to ask for clarification, additional information, or improvements to the question.
Matt Eland 76 Reputation points MVP

2022-04-16T03:22:52.183+00:00

What about when making GET requests to the score endpoint or doing a POST? Is there a way of setting the GlobalParameters flag there? I get this just by doing an authorized GET to my endpoint from postman.
Please sign in to rate this answer.

0 comments No comments
Sign in to comment

Use comments to ask for clarification, additional information, or improvements to the question.

Share via

Azure ML Studio error while testing real-time endpoint - list index out of range

4 additional answers

Your answer