CODEWITHSUNDEEP
azure-machine-learning-service
Ming Lu
Ming Lu

Reputation: 51

Azure Wide and Deep Recommender real inference pipeline error - Invalid graph: You have required input port(s) unconnected

It seems like there is bug in create real-time endpoints for "Wide & Deep Recommender" module at least with the sample workflow. I kept getting "Invalid graph: You have requested input port(s) unconnected". Does anyone know how to get around this issue?

Repro Steps:

  1. Go to Azure ML -> Designer -> "Wide & Deep based Recommendation - Restaurant" enter image description here

  2. Train the model -> Create "Real-time inference pipeline" -> in Real-time inference pipeline, click "Submit" -> Error occurs

enter image description here

Upvotes: 0

Views: 269

Answers (2)

Shantanu Jain
Shantanu Jain

Reputation: 87

I was facing the same issue. I just deleted the 'Evaluate recommender' at the end (having a yellow exclamation mark) and submitted again.

That fixed my problem.

Upvotes: 0

Ram
Ram

Reputation: 2754

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.

Upvotes: 0

Related Questions