Toby Roseman
Toby Roseman
@kasper0406 - before I merge, can you please address my one comment.
> Sorry, I don't see any comments. Did you click "submit review"? My bad. I've done it now. Thanks.
Updated CI: https://gitlab.com/coremltools1/coremltools/-/pipelines/2202537993 If this passes, I will merge this pull request.
It sounds like you should be using more than one model. It sounds like you want to create a model pipeline. Model pipelines allow you to create an MLModel that...
Making changes to the coremltools repository is not going to change the Core ML Framework. What problem are you trying to solve?
Something strange is happening here . Using ```python pow_2_e_raw_unstable = mb.pow(x=two, y=0.0, name="unstable_output") ``` Gives the correct results. Changing the return statement to: ```python return pow_2_e_raw_unstable, pow_2_e_raw_stable, e_raw ``` Also...
Just printing the MIL program is probably not telling the whole story. IIRC - certain ops, such as constant ops, are not shown when the MIL program is printed.
Coremltools 8.3.0 is several months old. We recently released coremltools 9.0. Do you still get this issue with coremltools 9.0?
Can you reproduce this issue with a toy model (i.e. a model defined via a small amount of code which can be copy and pasted)? Without your model there is...
Why is this unnecessarily? Can you construct a minimal example to reproduce this issue? Also `7.2` is several months old. Please try with `8.0b2`.