Toby Roseman

Thanks for the updated info. The error is caused by the `outputs` parameter not the `inputs` parameter. Doing the following converts the model without error: ```python mlmodel = coremltools.convert(model, inputs=[coremltools.ImageType(shape...

@JRGit4UE - thanks for reporting the issue. I've made some minor changes to your code, in order to reproduce the issue. This is related to #1367

torch 1.11.0 is the most recent version of torch that we support. If you have a newer version of torch installed, you should receive a warning when you import coremltools....

Thank @pokidyshev for the PR. The op definition looks good. In order to merge this PR, please add a unit test for `clamp_min` to [test_torch_ops.py](https://github.com/apple/coremltools/blob/main/coremltools/converters/mil/frontend/torch/test/test_torch_ops.py).

> @TobyRoseman not sure how to do that... Can you point out a good example? Take a look at [the unit test for `torch.argsort`](https://github.com/pokidyshev/coremltools/blob/7a4bf8bb6e0142565ef1c5ea6c56d75b959911c2/coremltools/converters/mil/frontend/torch/test/test_torch_ops.py#L312-L326).

Closing this in favor or #1584

@teaglin - can you give us self-contained, standalone code to reproduce this issue?

@PigletOS - I need more information in order to be able to reproduce the problem. Please include all the code I need to reproduce this problem. At a minimum, it...

I don't know what the issue is here. In order to help you, I have to be able to reproduce the problem. Can you give us code to reproduce this...

Thanks for the detailed write up. I agree this is a problem. Do any of your proposed solutions allow you to not only convert the model but also get predictions...