Currently ONNXRuntime's CoreML support is not very good, and on my environment, I get errors like “coreml_execution_provider.cc:192 operator() Input (/sdp/flows.3/GatherND_2_output_0) has a dynamic shape ({-1,-1}) but the runtime shape ({0,10}) has zero elements. This is not supported by the CoreML EP.” and inference fails.
I hope this will be fixed in a future version of ONNXRuntime, and leave the test code as it is.
The logic has not been changed, only renaming, splitting and moving modules on a per-function basis.
Existing code will be left in place for the time being to avoid breaking the training code, which is not subject to refactoring this time.
