Fix Fastflow ONNX export.

[jasonvanzelm]

Description

• Provide a summary of the modification as well as the issue that has been resolved. List any dependencies that this modification necessitates.

• Fixes [Bug]: Export to ONNX: UnsupportedOperatorError #1096

Changes

• Bug fix (non-breaking change which fixes an issue)
• Refactor (non-breaking change which refactors the code base)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

Checklist

• My code follows the pre-commit style and check guidelines of this project.
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing tests pass locally with my changes
• I have added a summary of my changes to the CHANGELOG (not for minor changes, docs and tests).

[blaz-r]

Looks good. From what I tested it works ok, but at some point there is some difference on 7th decimal which probably won't cause problems. According to this pytorch/pytorch#89107 "same" will be supported in PyTorch 2.1, but in the meantime this workaround look great.

[samet-akcay]

Looks good. From what I tested it works ok, but at some point there is some difference on 7th decimal which probably won't cause problems. According to this pytorch/pytorch#89107 "same" will be supported in PyTorch 2.1, but in the meantime this workaround look great.

Looks like PyTorch v2.1 will be released some time in october. Meanwhile, we could use this approach to tackle this issue.

[samet-akcay]

@jasonvanzelm, thanks for your contribution!

[samet-akcay]

sorry, just noticed a minor issue here

[samet-akcay]

Thanks