Andrey Volodin

It would be incredible to see any updates on this one. Image2Image models were such a great CoreML function and they are now basically gone in new converters

Yes, initially I wanted to obtain a pointer to `eagerContext` so that I could create my own ops in the same context and execute them. I still think it could...

this is now partially addressed in #697

I got it working! It was fairly easy (outside of me waiting for 3 hours for my MBP to build the whole toolchain from scratch). I did two things: 1....

I've made a PR to public function [here](https://github.com/tensorflow/swift-apis/pull/697), but patching `build-script-impl` appeared to be difficult since `tensorflow` and `tensorflow-0.7` are now diverged too much in terms of `build-script-impl`, so maybe...

Thanks for opening up the issue alongside with repro case! I just want to add my 2 cents that I initially discovered this problem with `AMSGrad` which is not working...

I'm experiencing the same with another model. Had to migrate to opset 11 for Upsample and now it doesn't work because `Range` op is not found.

@bhushan23 it happens with constant input to padding and then conv. I manually patched converter to load that constant

Can you reissue PR to develop-v3.5?

I kind of agree that this can be helpful, so yeah. In the mean time, the workaround can be easily done by writing simple extension where you provide both filenames,...