Toby Roseman

Results 543 comments of Toby Roseman

@alealv - you are correct. This has been fixed in PyTorch. The original code now runs without error. Thanks for the information.

@sjlearmonth - your latest post isn't a coremltools issue. I think you want to create a new conda environment that uses Python 3.8. Check the conda documentation.

[Coremltools 6.0](https://github.com/apple/coremltools/releases/tag/6.0) supports Python 3.10.

Since we have not received steps to reproduce this problem, I'm going to close this issue. If we get steps to reproduce the problem, I will reopen the issue.

Sounds like this was fixed by #1460. I'm going to close this issue.

Supporting [torch.Tensor.unfold](https://pytorch.org/docs/stable/generated/torch.Tensor.unfold.html) with our [current set of MIL ops](https://apple.github.io/coremltools/source/coremltools.converters.mil.mil.ops.defs.html) might be a bit tricky. One idea is to use a convolution followed by an interleave concat. The `stride` of the...

[Coremltools 6.0](https://github.com/apple/coremltools/releases/tag/6.0) supports PyTorch 1.12.0. However I still get the same error.

I'm also getting the following related error: `NotImplementedError: ('Einsum unsupported equation format: ', 'b i d, b j d -> b i j')` This is another einsum case we should...

Looks like to support `CompVis/stable-diffusion-v1-4` we'll also need to support `b i j, b j d -> b i d`.