Toby Roseman
Toby Roseman
Since we have received code to reproduce this problem I'm going to close the issue. If we get code to reproduce the problem, I'm happy to reopen the issue.
As I mentioned previously, this is likely the same issue #775. Since we have not heard how this is different, I'm going to close this issue as a duplicate.
Calling `.eval()` is not going to solve this problem. I can reproduce the issue with the following code: ```python import torch import coremltools as ct class MyModel(torch.nn.Module): def forward(self, x):...
With #1612 the conversion gets much further. However there is a new error: ``` ipython-input-3-e5a7138c6efc> in 4 outputs=[ct.TensorType(name="embeddings")], 5 minimum_deployment_target=ct.target.iOS15, ----> 6 compute_units=ct.ComputeUnit.CPU_ONLY) ~/Documents/coremltools/coremltools/converters/_converters_entry.py in convert(model, source, inputs, outputs, classifier_config,...
> Yes, it appears to be a duplicate. Ok, closing as a duplicate.
This is still an issue in coremltools 6.0
The fix has now been released.
With [the release of coremltools 6.0](https://github.com/apple/coremltools/releases/tag/6.0) this has been fixed.
Thanks @addisonklinke for the clarification. Yeah, the coremltools behavior here is correct. Although a minor changes in the coremltools would make issues like this easier to find. I'll put up...
@drubinstein - I would start by making sure that your GitHub Actions is using the most recent version of macOS.