Toby Roseman
Toby Roseman
I can't reproduce this issue using our latest beta release. In order to get it to fail, I'm suppose to replace this line: ```python conv_layer_definitions = conv_layer_definitions_works_well[-1] ``` with this:...
I still can not reproduce this issue. On macOS 12.3, I can get predictions from your Core ML model just fine. If this was worked in macOS 12.3 but stopped...
Yes, looks like we do not support [PyTorch's normal layer](https://pytorch.org/docs/stable/generated/torch.normal.html). Here is a minimal example to reproduce the issue: ```python import torch import coremltools as ct class MyModel(torch.nn.Module): def forward(self,...
Thanks for the pull request @DdHms. Does this fix and issue you are having? If so, please share some details.
I have rebase this change. CI: https://gitlab.com/coremltools1/coremltools/-/pipelines/629008351
@braindevices - can you give us a minimal example (i.e. a simple toy network) that reproduces this issue?
This is still an issue with coremltools 5.0
I've verified the new unit test fails without the fix and passes with the fix. Code Looks good to me, pending results of CI run. CI run: https://gitlab.com/coremltools1/coremltools/-/pipelines/621069457
CI is green. Thanks @andrusza2 for the fix.
@sheshap - I can't even view your notebook. It is not public. Also sharing a notebook to reproduce the problem is not very helpful. Can you please work to create...