Closed WZMIAOMIAO closed 2 years ago
in my datasets, it didn't work.
I just started to try SIOU Loss. I'll report if the training have any news.
Other discussion about the SIOU loss in the PaddleDetection. https://github.com/PaddlePaddle/PaddleDetection/issues/6070
It doesn't seem as good as in the paper.
@wilile26811249 interesting, let us know your experiment results!
@AyushExel can you take a look at this SIoU loss to see if it might be suitable for YOLOv5?
@wilile26811249 do you have a torch SIoU implementation we could use to experiment with?
The official publication lacks code unfortunately.
You can check this implementation.
https://github.com/xialuxi/yolov5-car-plate/blob/master/utils/general.py#L370-L388
@glenn-jocher I think the correct way forward for supporting this in the master branch would be to run ablation tests. For starters we can run a training job comparing SIoU with current version on 10% coco dataset and then on the full dataset. Ideally, if it outperforms on both tests then we'll have a clear indication( if it doesn't affect other things like speed) otherwise we can just add the implementation and allow user to enable it via a feature flag. This could be a nice community led R&D experiment.
@glenn-jocher @WZMIAOMIAO, Here are my results. Unfortunately, It seems like not improved.
with SIOU:
with CIOU:
@wilile26811249 thanks for the results! Ok so it seems like not a significant change.
well, I will close this issue.
I just started to try SIOU Loss. I'll report if the training have any news.
Hi, @wilile26811249 Could you please tell me how do you change the current Yolov5 loss function fro CIOU to SIOU loss? Where specifically do I make the changes? I'm a newbie and trying to understand Yolov5. Thanks!
Search before asking
Description
Hi, have you ever tried SIoU Loss?
Paper: SIoU Loss: More Powerful Learning for Bounding Box Regression
According to the Abstract of the paper, feel so good.