Toby Roseman

You either need to stop using that TensorFlow operation in your network, or implement it in coremltools using [MIL operations](https://apple.github.io/coremltools/docs-guides/source/model-intermediate-language.html). See our User Guide page about [Creating Custom Ops](https://apple.github.io/coremltools/docs-guides/source/composite-operators.html). Also...

Can you give us steps to reproduce this issue?

The error seems to be coming from TensorFlow (`tensorflow/python/framework/importer.py`). I think it can't load your model. This doesn't seem like a coremltools issue. If you still believe this to be...

I can reproduce this issue. I think this is a bug in the Core ML Framework. The `ct.convert` call works if you `convert_to` either `neuralnetwork` or `milinternal`. It's loading the...

Are you able to get predictions from your model in Python?

Can you share your `objectDetection.mlmodel`?

I would probably try deleting everything under `/Users/xx/Library/Caches/python/com.apple.e5rt.e5bundlecache/` and then restart your machine. It's not clear to me if you've already done that. Do you know at what point in...

Unless you pass ` skip_model_load=True` to `ct.convert`, the saved model is loaded at the end of the `ct.convert` call and returned. Do you also get this error when you load...

@RubeGoldbergJr - did you also run out of disk space right before this issue started happening? Can anyone give us steps to reproduce the issue?

There seems to be a lot of formatting changes in this pull request. I don't think we want those changes. Please revert the formatting changes and just include your fix.