Toby Roseman
Toby Roseman
It would help if you could give us a much smaller example that reproduces the issue, i.e. not an entire GitHub repository but a small amount of code that can...
I'm not understanding the issue here. Please add a complete example to reproduce the issue. Please include all nesscessary import statements and the call to `coremltools.convert`.
@himalayjor - can you please give us a model stub which use this op?
Complete code to reproduce: ```python import torch import torch.nn as nn import coremltools as ct class Model(torch.nn.Module): def forward(self, x): y = torch.ops.aten.alias(x) y = y + 5 return y...
@himalayjor - you could edit your model to remove the `alias` usage. Seems like that shouldn't be difficult to do.
This is expected. Based on my understanding, there are a couple of relevant things here. First, our Python binding don't use [MLModelAsset](https://developer.apple.com/documentation/coreml/mlmodelasset?language=objc) which would (in some cases) share the weigths...
That indentation does look suspicious. Can you give us steps to reproduce this issue? Or better yet, send us a pull request with a unit test.
With coremltools 6.0, the `predict` call from the original code now hangs.
The max version of tensorflow that we support is 2.12.0. Also coremltools 7.2 is about nine months old. Is this still an issue with the latest version of coremltools and...
No major update. I was able to reproduce the issue (hence the "triaged" tag) but haven't been able to dedicate much time to it. I don't see anything clearly wrong...