'Import of exported Vertex-AI AutoML model in production fails

I want to deploy a Vertex-AI model in a production project which has been trained in a training project.

----TRAINING PRJ-----     --------PRODUCTION PRJ---------
Train > test > export  >  import > deploy | batch predict

I follow these instructions and get a success email:

Vertex AI finished uploading model "xxxxxx".

Operation State: Succeeded

but when I try to test the model with a Batch prediction I always get a failed message:

Due to an error, Vertex AI was unable to batch predict using model "TEST".

Operation State: Failed with errors Error

Messages: INTERNAL

Please note deploying the model to an endpoint and testing with a JSON request it does provide the expected response.

I tried several container types besides the one suggested here, included the one stated in the exported model's environment.json container_uri: the batch prediction always fails with message INTERNAL

Any clue?

Vertex-AI screenshot Model details

google-cloud-mlgoogle-cloud-vertex-ai


Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution Source

Related Questions