-
Notifications
You must be signed in to change notification settings - Fork 2.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Do not drop QDQ around linear Resize (fixes #21319) #22089
base: main
Are you sure you want to change the base?
Conversation
See microsoft#21319 for details. This PR disables the QDQ resize matching to avoid numerical issues.
@mgehre-amd please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
Contributor License AgreementContribution License AgreementThis Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you quantify the effect of dropping the QDQ? How significant is the effect on model accuracy for real world input? Wondering if this needs to be configurable so users can prioritize performance if the accuracy loss might be acceptable. |
/azp run Big Models Expected,Linux Android Emulator QNN CI Pipeline Expected,Linux CPU CI Pipeline Expected,Linux CPU Minimal Build E2E CI Pipeline Expected,Linux GPU CI Pipeline Expected,Linux GPU TensorRT CI Pipeline Expected,Linux OpenVINO CI Pipeline Expected,Linux QNN CI Pipeline Expected,MacOS CI Pipeline Expected,ONNX Runtime Web CI Pipeline Expected |
No pipelines are associated with this pull request. |
It's not numerically equivalent to drop Q DQ nodes around a Resize when the Resize is using linear interpolation.
This PR only drops QDQ around resize using the
nearest
interpolation.See #21319 for details.