How to append additional layers on the top or warp the input(MLMultiArray) to Image existing Core ML model?

[tucan9389]

❓Question

I have a Core ML model that was created by GCP's AutoML. But the model's input, output specification are just MultiArray type.

I'd like to wrap the input type as Image, output as the following:

source: https://stackoverflow.com/questions/59494249/the-model-does-not-have-a-valid-input-feature-of-type-image-create-ml

Is there any guideline or example python script to append and wrap the input/output layer to the existing Core ML model?

Thank you :)

[TobyRoseman]

Core ML models are not really designed to be modified after they have been created. It's going to be easier to make the modification to your original model before you convert it to Core ML.

Are you using TensorFlow? If you are, then modify your TensorFlow model to accept an image, before you convert that model to Core ML.