Toby Roseman

Try calling `torch.jit.trace` on your PyTorch model prior to conversion.

> But that is what I am currently doing 🤔 It doesn't seem so. Note this line in your output: ``` Support for converting Torch Script Models is experimental. If...

Are you still getting the following warning? ``` Support for converting Torch Script Models is experimental. If possible you should use a traced model for conversion. ``` If so, then...

This is related #1995. Note the first line of your output: ``` Support for converting Torch Script Models is experimental. If possible you should use a traced model for conversion....

@Ykid - I believe that is correct. However I am not a PyTorch expert. I suggest asking that question in a PyTorch forum. If you do that, please share a...

I don't think this is an issue with the coremltools Python package. This looks like an issue with the on device Core ML Framework. I don't see anything obviously wrong...

Since the converted model works for inference, I think that's even more reason to suspect it's an issue with the Core ML Framework. Did you submit this issue using the...

Looks like this is also an issue for MIL -> mlprogram: ```python from scipy import special import coremltools as ct from coremltools.converters.mil import Builder as mb import numpy as np...

Can you give us more details about what you are trying to do here? What script are you referring to?

It seems like it should be possible to do this with a `softmax-nd` layer instead of a `softmax` layer. You could try just removing [the code that raises that exception](https://github.com/apple/coremltools/blob/870213ba6545369335ac72e61127c8d20ea745e5/coremltools/models/neural_network/builder.py#L975-L983)...