Converting ONNX models to CoreML with ease.

A work in progress.

cd into project directory, then convert.py to start.

It will prompt if something can't be handled automatically.

You might have to copy your own libcoremlpython.so libmilstoragepython.so libmodelpackage.so packages inside the converter folder.
Those are in the root of your existing coremltools python package directory.

I need to know what doesn't work so we can fix it, layer per layer.
I mostly use Ultralytics 'Yolo' models, and there are many other ops I might even not know about. With coremltools 8.1, we can virtually convert everything. The three main ideas here are: make the model run -even if it means "resize bicubic" becomes "resize bilinear". it has to be easy every layer can be manually modified, changed or skipped

A mac is a mac and it needs to stay comfortable.