Change Domains to General (compact).

Retain the model.

Export the model.

You have a Custom Vision project that performs object detection. The project currently uses the General domain. You need to export the trained model for offline use (on a disconnected network).

Steps required:

Change Domains to General (compact).

Export is only supported with a Compact domain.

The General (compact) domain is optimized for exporting to devices (e.g., ONNX, TensorFlow, CoreML, etc.).

If you stay in “General” domain, you cannot export.

Retain the model.

After switching domains, you must retrain the model in the new compact domain to generate updated weights.

Export the model.

Once retrained in a compact domain, you can export the model for offline deployment.

Export formats include ONNX, TensorFlow, CoreML, or Docker container, depending on use case.

Why not the others?

Create a new classification model → Not needed; you already have an object detection model.

Change the classification type → Incorrect; the problem is with the domain type, not classification type.

Correct Answer Order:

Change Domains to General (compact).

Retain the model.

Export the model.

Microsoft References

Export a model from Custom Vision

Domains in Custom Vision