[Refactor] PyTorch SAR_Resnet31 make it ONNX exportable (again) by felixdittrich92 · Pull Request #930 · mindee/doctr (original) (raw)
This PR:
- reverts pooling to fix onnx export (retrained with same results as before)
- set attention units to 512 as described in paper (fix my mistake ^^)
- some formatting / docu
Any feedback is welcome 🤗
(functional pooling has raised some ONNX export issues)
[Refactor] PyTorch SAR_Resnet31 make it ONNX exportable [Refactor] PyTorch SAR_Resnet31 make it ONNX exportable (again)
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks Felix! Just a small comment perhaps?
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good, thanks!
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.Learn more about bidirectional Unicode characters
[ Show hidden characters]({{ revealButtonHref }})