nncf: NNCF v2.5.0 accuracy and performance degradation of EfficientDet

I tried NNCF 2.5.0 for my effdet model and observed accuracy and performance degradation. Even if I use pot-backend (use_pot=True), the accuracy and performance is degraded compared to nncf 2.4.0.

The issue is reproduced with the efficientdet-d0 which was exported by the official procedure.
The throughput was measured by benchmark-app of openvino-dev=2023.0.0.

model coco_precision Throughput
v2.4.0 30.68% 67.14 FPS
commit ca54404 (pot backend) 30.50% 65.40 FPS
commit ca54404 24.53% 60.92 FPS

I attaches the reproduction code and environments.
I hope the issue will be fixed so that we can migrate to the newer NNCF.

repro_effdet_issue.zip

About this issue

Most upvoted comments

@l-bat Sorry for the confusion. It should have been named ms_coco_detection_90_class_without_background. While looking for a working config, the name seems to have been inappropriate. I didn’t use the --definitions option of accuracy-checker, so the name wouldn’t affect the behavior I believe.