Toby Roseman
Toby Roseman
@yosun - please provide more information. What is "HUGS"? What link are you referring to?
Our support for converting untraced PyTorch models is only experimental. You should have received a warning telling you that. What is the full error (including stack trace) that you are...
Loading an untrusted PyTorch model is a security risk. So I'm unable to reproduce your results. It would be great if you could give us a minimal example (i.e. one...
> I'm not sure which layer causes this bug, so it's difficult for me to construct a minimal example. I completely understand. Unfortunately, without a minimal example, it's difficult for...
`scale` and `bias` are not defined. So I used `1` and `0`. Here is runnable code that illustrates it is the addition of a classifier config that cause `affine_quantize_weights` to...
I would try updating the coremltools code to cast the indices to a dtype of int32. Try adding the following line: `indices = mb.cast(x=indices, dtype="int32")` To `coremltools/converters/mil/frontend/torch/ops.py` in the `index`...
Are you using the most recent version of coremltools? Loading an untrusted PyTorch model is a security risk. So I'm not able to run your code. If this is still...
Thanks @w4-jihunlorenzopark - I can reproduce the bug using your code.
Change looks good. CI run: https://gitlab.com/coremltools1/coremltools/-/pipelines/1288793964
CI passed. Thanks @igeni.